Datasets:

ianiket23

/

podcast_llama_chat_format-5k

like 0

<s>[INST] also. He was convinced of uh yes, [/INST] he was absolutely </s><s>[INST] based on what exactly by linguistic like human based linguistic canal. She [/INST] she he whatever, you know, Kayla was ended up being like a modification of his sister's name. The real guy's sister's name was so good at building the back story all these guys and and it's funny like these guys are part of a hacking crew. They social engineer the ship out of each other just to build if one of them ever gets caught, they'll convince the everybody else that you know, they're a Brazilian uh you know, I sp owner or something like that and that's how I'm so powerful. </s><s>[INST] Well yeah, that's social engineering aspect. Is part of living a life of cybercrime or cyber security and the offensive or defensive. So a B unit can also just attention of a tangent first. [/INST] That's my favorite tangent. </s><s>[INST] Okay. Um is it possible for me to have a podcast conversation with somebody who hasn't been caught yet and because they have the conversation they still won't be caught. And is that a good idea meaning is there a safe way from criminal to talk to me on a podcast. [/INST] I would think so </s><s>[INST] I [/INST] would think that that that someone could I mean, someone who has been living a double life for, for long enough where you think they're not a criminal? Um, no, </s><s>[INST] no, no. They would have to admit that they they would say I am a V unit, [/INST] so you would want to have a conversation with the unit? </s><s>[INST] Yes. [/INST] Is </s><s>[INST] there a way I'm just speaking from an FBI perspective, technically speaking, because I I let me explain my motivation. I think I would like to be able to talk to people from all walks of life and understanding criminals. Understanding their mind, I think is very important and I think there's fundamentally something different between a criminal who is still active versus one that's been caught the mind just from observing. It changes completely once you're caught, you know, you have a big shift in your understanding of the world. Um, I mean that I do have a question about the ethics of having such conversations, but first, technically, uh is that, is it possible [/INST] if I was technically advising you? I would say, first off, don't advertise it, don't the fewer people that you're going to tell that you're having this conversation with the better. Um, and yeah, you could do it in person. Are you doing? It </s><s>[INST] would be amazing. Yeah, but their their face would not be shown. [/INST] Face would not be Yeah, I mean, you couldn't publish the show for a while, They'd have to put a lot of trust in you that you are not going to, you're going to have to alter those tapes. I say tapes because it's old school, you know. Exactly. I'm sure a lot of people just said that like ship this old guy just tape </s><s>[INST] VHS was the 1800s I think. [/INST] Um But yeah, yeah, you could do it. They have to have complete faith and trust in you that you destroy the originals after you've altered it. What </s><s>[INST] about if they don't have faith, is there a way for them to obtain security? Um so, uh like for me to go through some kind of process where I meet them somewhere where, I [/INST] mean, you're not going to do it without a bag over your head. I don't know if that's the life you want to </s><s>[INST] live. I'm fine with a bag over my head that's gonna get taken out of context. But I just, I think it's a worthy effort. It's a worthy, it's worthy to go through the hardship of that to understand the mind of somebody. I think fundamentally, conversations are a different thing than the operation of law enforcement. Understanding the mind of a criminal, I think is really important. [/INST] I don't know if you're going to have the honest conversation that you're looking for. I mean, it may sound honest, but it may not be the truth I found most times when I was talking to criminals, it's lies mixed with half truths. Uh, and you you kinda it's if they're good, they can keep that story going for long enough. If they're not, you know, you kind of see the relief in them. When you finally break that wall down, </s>

<s>[INST] in that same way the idea that the U. S. Government or any government could be doing mass surveillance on its citizens is um is one that was a wake up call because you could imagine the ways in which that could um be like you could abuse the power of that to control the citizenry for political reasons and purposes. [/INST] Absolutely. You know, you could abuse it. I think during part of the Snowden League saw the two N. S. A. Guys were uh, modern, like their girlfriends and there's rules in place for that. Those people should be punished for abusing that. But how else are we going to hear about? You know, terrorists that are in the country talking about birthday cakes. Uh, and you know, that was a case where that, that was the trip word that, that, you know, we're gonna go bomb new york city's subway. </s><s>[INST] It's complicated, but it just feels like there should be some balance of transparency. There should be a check on that [/INST] power because </s><s>[INST] like, you know, in the name of the war on terror, you can sort of sacrifice that there is a trade opportunity, security and freedom, but it just feels like there's a giant slippery slope on the sacrificing of freedom in the name of security, [/INST] I hear you. And, </s><s>[INST] and you [/INST] know, we we live in a world where, well, I live in a world where I had to tell you exactly when I arrested someone, I had read a 50 page document of how I arrested you, uh, and all the probable cause I have against you and all that. Well, you know, bad guys are reading that they're reading how I caught you and they're changing the way they're doing things, they're changing their M. O. Um you know, they're doing it to be more secure if, you know, we tell people how we're monitoring, you know, how what we're surveilling we're going to lose that. I mean the terrorists are just going to go a different way and I'm not trying to again I'm not big government, I'm not trying to say that, you know, it's cool that that we're monitoring the U. S. Government's monitoring everything, you know, big text monitoring everything that they're just monetizing it versus uh possibly using it against you. </s><s>[INST] But there's a balance in those 50 pages. They have a lot of value um if they make your job harder but they prevent you from abusing the power of the job. There's a balance. That's a tricky balance. So the chat logs in Iceland give you evidence of the heroin and all the large scale czar level uh drug trading. What else did it give you in terms of the how to catch [/INST] gave us infrastructure. So the onion name was actually running on a server in France. So if you like, and it only community through a back channel of VPN um to connect to the Iceland server. Um there was a Bitcoin like kind of vault server that was also in Iceland. And I think that was so that the admin couldn't get into the Bitcoins the other admins that were hired to work on the site so you could get into the site but you couldn't touch the money, only ross had access to that. And then you know another another big mistake on ross's part is he had the backups for everything at a data center in philadelphia don't put your infrastructure, the United </s><s>[INST] States. [/INST] I mean again let's not make a playbook but you know </s><s>[INST] I I think the people of competence would know already. [/INST] I agree </s><s>[INST] but it's interesting that he wasn't competent enough to make so he was incompetent in certain ways. Yeah [/INST] I don't I don't think he was a mastermind of setting up and an infrastructure that would protect his his his online business because you know keeping chat logs, keeping a diary, putting infrastructure where it shouldn't be um bad decisions. </s><s>[INST] How did you figure out that he's in san Francisco? [/INST] So we had that part with Jared that he was on the west coast and then was he was a partner um in uh he was a DHS agent um worked for HSI homeland security investigations in Chicago. Uh He started his Silk Road investigation because he was working at O'hare and a weird package came in um come to find out, he traced it back to Silk Road. So he started working at a Silk Road investigation long before I started my case and he made his way up undercover all the way to be an admin on Silk Road. Um So he was talking to ross on a jabber server, the private jabber server, Private chat communication server. And we noticed that ross is um time zone on. That jabber server was set to the west coast. So we we had pacific time on there. So we had a region one 24th of the world was covered of where we thought he might be. </s><s>[INST] And from there, how do you get to san Francisco? [/INST] There was another guy an I. R. S. Agent that was part of the team and he used a powerful tool um to find his clue. Um He used the world of google. Uh he simply just went back and googled around for Silk Road at the time was coming up and found some posts on like some help forums that this guy was starting in onion website and wanted some Cryptocurrency help. And if you could help him please reach out to ross dot at gmail dot com. Um In my world, that's that's a clue. So </s><s>[INST] okay, so that that's as simple as that. [/INST] And the name he used on that post was Frosty. </s><s>[INST] Yeah, so you have to connect Frosty and other uses and Frosty and here's a gmail. And the gmail has the name the [/INST] gmail posted. That, that I need help under the name Frosty on this forum. </s>

<s>[INST] So I I feel pretty um you know, I'm pretty short on adjectives when I describe stuff adjectives a tricky. In fact, I try to avoid adjectives because I think that's a slippery slope that you just live in the land of adjectives and you never actually make a point. Anyway. I guess you're supposed to use an audio form words to describe the thing that you're describing so that you can understand have to convert the ideas of my brain into ideas in your brain and hence the beauty of human human communication. Anyway I feel pretty good in the thing I like the way it looks like the way it feels you should check it out to right now. You can get a special discount. Just go to mizzen and main dot com and use promo code lex. This show is also brought to you by Inside Tracker a service. I used to track biological data. They have a bunch of plans. Most included blood tests that uh use machine learning algorithms on that blood data, DNA data and fitness tracker data to give you suggestions on what you should do with your [/INST] life. </s><s>[INST] It's signs back recommendations for positive diet and lifestyle changes. It's really exciting to me the kind of stuff you could do with machine learning algorithms on data that comes from the human body. But the first piece of that I think that's essential is to actually be collecting that data from you or give the algorithm enough data about you. They can make such predictions and a lot of that has to be done in a way that's uh privacy preserving and effective in terms of not just low number of samples, single instances of data collection but across the lifespan across many weeks, months years and so on. Anyway. Inside Tracker is one of the company's doing a great job of pushing that kind of idea forward. You can get special savings for a limited time and you go to inside tracker dot com slash lex This episode is also brought to you by eight sleep and its new pod three mattress. They recently launched the next generation. It's always nice when the number go up Anyway. I love the originals. I love that you want even more. [/INST] It's </s>

<s>[INST] Okay, cool. So what, what some, what are some interesting things that came to life from this from this work? Uh, do you like, what are some insights about um, about games where natural language is involved and cooperation? Deep cooperation is involved? Well, [/INST] I think there's a few insights. Um, so first of all the fact that you can't rely purely, or even largely on self play, that you really have to have an understanding of how humans approach the game. Um, I think that that's one of the major conclusions that I'm drawing from this work. Um, and that is I think applicable more broadly to a lot of different games. So we've actually already taken the approaches that we've used in diplomacy and tried them on uh, cooperative card game called Hannah B and we've had a lot of success in that game as well. Um, on the language side, I think the fact that we were able to control the language model um, through this intense approach was very effective. Um, and it allowed us instead of just imitating how humans would communicate, were able to go beyond that and able to um, feed into its superhuman strategies that it can then um, you know, generate messages corresponding to </s><s>[INST] is there something you could say about detecting whether a person or a i is lying or not? The [/INST] bot doesn't explicitly try to calculate whether somebody is lying or not, but what it will do is try to predict what actions they're going to take, given the communications, given the messages that they sent to us. So given our conversation, what do I think you're going to do? And implicitly, there is a calculation about whether you're lying to me in that, you know, if if you're based on your messages, if I think you're going to attack me this turn. Um, even though your messages say that you're not, then, you know, essentially the body is predicting that you're lying, but it doesn't view it as as lying the same way that we would view it as lying, but </s><s>[INST] you could probably reformulate with all the same data and make a classifier lying or not. [/INST] Yeah, I think, I think you could do that um that was not something that we were focused on, but I think that it is possible that, you know, if you came up with some measurements of like what does it mean to tell a lie? Because there's there's a spectrum, right? Like if you're withholding some information, is that a lie? Um if you mostly telling the truth, but you forgot to mention this like one action out of like 10, Is that a lie? Um It's hard to draw the line, but you know, if you're willing to do that and then you could possibly use it to uh this </s><s>[INST] feels like an argument inside a relationship now. What constitutes a lie um depends what you mean by the definition of the word is okay. Um still, it's fascinating because trust and lying is all intermixed into this and it's language models that are becoming more and more sophisticated. It's just a fascinating space to explore. Um what what what what do you see as the future of this work um that is inspired by the breakthrough performance that you're getting here with diplomacy. [/INST] Uh I think there's a few different directions to take this work. Um I I think really what is showing us is the potential that language models have. I mean I think a lot of people didn't think that this kind of result was possible even today despite all the progress that we made in language models. And so it shows us how we can leverage the power of things like self play on top of language models to get um increasingly better performance and um the ceiling is really much higher than what we have right now. </s><s>[INST] Is this transferable somehow to to chatbots for the more general task of dialogue? So because there is a kind of negotiation here a dance between entities that are trying to cooperate and at the same time a little bit adversarial which I think maps somewhat to the general, you know, the entire process of reddit or like internet communication. You're cooperating your adversarial, you're having debates, you're having uh camaraderie, all that kind of stuff. [/INST] I think one of the things that's really useful about diplomacy is that we have a well defined value function. There is a well defined score that the body is trying to optimize and in a in a setting like a general chat bot setting it needs it would need that kind of um objective in order to fully leverage the techniques that we've developed. </s><s>[INST] What about like what we talked about earlier with N. P. C. S. Inside video games like how can it be used to create for elder scrolls, six more compelling um N. P. C. S. That you could talk to instead of instead of committing all kinds of violence with a sword and fighting dragons just sitting in a tavern and drink all day and talk to the chat pot. [/INST] The way that we've approached on diplomacy is you condition the language on an intent. Now that intent and diplomacy is is an action but it doesn't have to be. And you can imagine, you know, you could have N. Pcs in video games or the metaverse or whatever where there's some intent or there's some objective that they're trying to maximize and you can specify what that is. Um and and then the language can correspond to that intent. Now I'm not saying that this is you know happening imminently but um I'm saying that this is like a future application potentially of this direction of research. </s>

<s>[INST] I don't even know how to comprehend either of those numbers frankly. Uh just a smaller side because I am a computer science person. I also find sally or thomas are beautiful. And so you have somebody like Stephen Wolfram who recently has been very excitedly exploring a proposal for a data structure. That could be um the numbers that would make you a little bit happier in terms of scale because they're very, very, very, very tiny. Um do you like this space of exploration of really thinking, letting go of space time, let go of everything and trying to think what kind of data structures could be underneath this whole mess. [/INST] That's right. So if they're thinking about these as outside of space time, then that's what we have to do, that's what our best theories are telling us. You now have to think outside of space time. Of course I should back up and say, we know that Einstein surpassed Newton, right? But that doesn't mean that they're not good work to do Newton. There's all sorts of Newtonian physics that takes us to the moon and so forth, and there's lots of good problems that we want to solve with. Newtonian physics. The same thing will be true of spacetime. Well, still, it's not like we're going to stop using spacetime will continue to do all sorts of good work there, but for for those scientists who are really looking two go deeper to actually find the next, you know, just like what Einstein did to Newton, what what are we gonna do? Einstein, how do we get beyond Einstein and quantum theory to something deeper, then we have to actually let go. And if we're going to do like this to me, to kind of approach, it's critical that it's not automata in spacetime, it's automata prior to space time, from which we're going to show how space time emerges if you're doing automated within spacetime. Well, that might be fun model, but it's not the radical new step that we need. </s><s>[INST] Yeah, so the space time emerges from that whatever system, like you're saying it's it's a dynamical system, do we even have an understanding what dynamical means when we go beyond [/INST] when </s><s>[INST] you start to think about dynamics? That could mean a lot of things. Even causality could mean a lot of things. If if we if we realize that everything is an interface uh like what how much do we really know is an interesting question because you you brought neurons I gotta ask you and another yet another danger. There's a paper remember a while ago looking at called coulda neuroscientists understand a microprocessor and I just enjoyed that thought experiment that they provided. Which is they basically it's a couple of neuroscientists eric Jonas and Conrad according who used the tools of neuroscience to analyze a microprocessor computer, computer chip, [/INST] we're leaving it here, what happens and so forth. And if you go and lesion in the computer, it's very very clear that lesion experiments on computers are not going to give you a lot of insight. </s><s>[INST] And also the measurement devices and the kind of sort of just using the basic approaches of neuroscience collecting the data, trying to intuit about the underlying function of it. And that helps you understand that our scientific exploration of concepts um depending on the field are are maybe in the very very early stages, I wouldn't say it leads us astray perhaps it does sometimes, but it's not a it's not anywhere close to some fundamental mechanism that actually makes the thing work? I don't know if you can sort of comment on that in terms of using neuroscience to understand the human mind and neurons are we really far away potentially from understanding in the way we understand The transistors. Enough to be able to build a computer. So 1 1 um one thing about understanding is you can understand for fun the other one is to understand so you could build things and and that's when you really have to understand [/INST] exactly. In fact what got me into the field that I. M. I. T. Was um work by David Marr on this very topic. So David Marr was professor at MIT but he'd done his PhD in neuroscience studying just the architecture of the brain. But he realized that his his his work it was on the cerebellum. He realized that his work as rigorous as it was left him unsatisfied because he didn't know what the cerebellum was for </s><s>[INST] and [/INST] and why it had that architecture. And so he he went to M. I. T. And he was an ai lab there and and he said he had this three level approach that really grabbed my attention. So I when I was an undergrad at U. C. L. A. I read one of his papers in a in a class and said who is this guy? Because he said you have to have a computational theory what is being computed and why? Mhm. An algorithm? How is it being computed what what are the precise algorithms and then the hardware? How does it get in stand located in the hardware? So to really do Neurosciences argued, we need to have understanding at all those levels. And that really got me I loved the neuroscience but I realized this guy was saying if you can't build it you don't understand it effectively. And so that's why I went to MIT and I had the pleasure of working with David until he died as just a year and a half later. So there was there's been that idea that, you know, with neuroscience we have to have in some sense, a top down model of what what's being computed and why that we would then go after the same thing with the trying to reverse engineer a computing system like your laptop. We really would we really need to understand what the user interface is about and why we have what are the keys on the keyboard for and so forth. You need to know why to really understand why all the circuitry and what what it's for. Now we don't evolution of natural selection does not tell us the deeper question that we're asking the answer to the deeper question which is why what what why what what's this deeper reality and what's it up to and why all it tells us is that whatever reality is, it's not what you see, What you see is just an adaptive fiction. </s>

<s>[INST] What role do humans play in this? So what's the this biological system like a human body is made up of cells? What what role like how do you optimize the human system, the multiple engineers collaborating, figuring out what to focus on what to contribute, which which task to optimize in this neural network, who is in charge of figuring out which task needs more data. What can you can you speak to the hyper parameters the human uh system, [/INST] it really just comes down to extremely good execution from an engineering team, who knows what they're doing, they understand intuitively the philosophical insights underlying the data engine and the process by which the system improves and uh how to again like delegate the strategy of the data collection and how that works and then just making sure it's all extremely well executed and that's where most of the work is, is not even the philosophizing or the research or the ideas of it is just extremely good execution is so hard when you're dealing with data at that </s><s>[INST] scale. So your role in the data engine, executing well on it. It is difficult and extremely important. Is there a priority of like uh like a vision board of saying like we really need to get better at stoplights. Like the prioritization of tasks is that essentially, and that comes from the data [/INST] that comes to um a very large extent to what we are trying to achieve in the product for a map where we're trying to the release, we're trying to get out um in the feedback from the QA team where the system is struggling or not, the things we're trying to improve and </s><s>[INST] the QA team gives some signal some information in aggregate about the performance of the system in various conditions [/INST] and then of course all of us drive it and we can also see it, it's really nice to work with the system that you can also experience yourself and you know, it drives you home. It's </s><s>[INST] is there some insight you can draw from your individual experience that you just can't quite get from an aggregate statistical Yeah, it's so weird. Right? Yes. It's not scientific in a sense because you're just one anecdotal sample. [/INST] Yeah, I think there's a ton of uh it's a source of truth is your interaction with the system and you can see it, you can play with it, you can perturb it, you can get a sense of it, you have an intuition for it. I think numbers just like have a way of numbers and plots and graphs are much harder. Uh, it hides a lot of </s><s>[INST] it's like if you train a language model, what it's a really powerful way is, is by you interacting with [/INST] it and try </s><s>[INST] to build up an intuition. [/INST] Yeah, I think like Ellen also like he always wanted to drive the system himself. He drives a lot and uh, I want to say almost daily. So, uh, he also sees this as a source of truth. You driving the system um, and performing and </s><s>[INST] yeah, so what do you think? Tough questions here? Uh, so Tesla last year removed radar from, from the sensor suite and now just announced there's going to remove ultrasonic sensors relying solely on vision. So camera only does that make the perception problem harder or easier? I [/INST] would almost reframe the question in some way. So the thing is basically you would think that additional sensors </s><s>[INST] by the way, can I just interrupt. I wonder if a language model will ever do that If you prompted? Let me reframe your question. That would be epic. [/INST] That's the wrong </s><s>[INST] problem. Sorry. [/INST] It's like a little bit of a wrong question because basically you would think that these sensors are an asset to you. But if you fully consider the entire product in its entirety. These sensors are actually potentially liability because the sensors aren't free. They don't just appear on your car. You need suddenly you need to have an entire supply chain. You have people procuring it. There can be problems with them. They may need replacement. They are part of the manufacturing process. They can hold back the line in the production, you need to source them to maintain them. You have to have teams that write the firmware, all of the, all of it. And then you also have to incorporate and fuse them into the system in some way. And so it actually like bloats the a lot of it. And I think Ellen is really good at simplify, simplify best part is no part. And he always tries to throw away things that are not essential because he understands the entropy in organizations and an approach And I think in this case the cost is high and you're not potentially seeing it if you're just a computer vision engineer and I'm just trying to improve my network and you know, is it more useful or less useful? How how useful is it? And the thing is once you consider the full cost of a sensor, it actually is potentially a liability and you need to be really sure that it's giving you extremely useful information in this case. We looked at using it or not using it and the delta was not massive. And so it's not useful </s><s>[INST] is it also blow in the data engine like having more sense [/INST] percent </s><s>[INST] and [/INST] these sensors, you know, they can change over time. For example, you can have one type of say radar, you can have other type of radar. They change over time now you suddenly need to worry about it. Now suddenly you have a column in your sequel light telling you, oh, what sensor type was it? And they all have different distributions and then uh, they can, they just, they contribute noise and entropy into everything and they bloat stuff And also organizationally has been really fascinating to me that it can be very distracting. Um, if you, if you, if you only want to get to work is vision, all the resources are on it and you're building out a data engine and you're actually making forward progress because that is the, the sensor with the most bandwidth, the most constraints in the world and you're investing fully into that and you can make that extremely good if you're, you're only a finite amount of sort of spend of focus across different facets of the system. </s>

<s>[INST] So that's that's an incredible book. And some of the same people you mentioned Ed Franken which I guess of expert systems, fame and Minsky of course people know in the I world but they represent the artificial intelligence [/INST] world that do hope and </s><s>[INST] dream that ai is intelligence. Is [/INST] that it was my thinking well you know I see where they're coming from and from suspected. Yeah, you're right. But that's not my perspective. So I thought I had to say it and as I was writing my book, you see, I thought well I don't really know anything about neurophysiology. What am I doing writing this book? So I certainly reading up about neurophysiology and I read and I think I'm trying to find out how it is. The nerve signals could possibly preserve quantum coherence and all I read is that the electrical signals which go along the nerves create a effects through the brain. There's no chance you can isolate it. So this is hopeless. So I come to the end of the book and I'm more or less give up. I just think of something which I didn't believe in this. Maybe this is a way around it. But no. And then you say, I thought, well, maybe this book at least stimulate young people to do science or something. And I got all these letters from old retired people instead is the only people who could have time to read my book. </s><s>[INST] So except [/INST] for Stewart Hammer off. </s><s>[INST] Except for Stuart hamm on Stuart [/INST] Hammer off wrote to me and he said, I think you're missing something you don't know about micro tubules, do you didn't put it quite like that. But that was more or less it. And he said, this is what you really need to consider. So, I thought, my God, yes, that's a much more promising </s><s>[INST] structure. So, I mean, fundamentally you were searching for the source of non computable source of consciousness within the human brain in the biology. And so what are my uh if I may ask, what are micro tubules? [/INST] Well, you see, I was ignorant and what I'd read. I never came across them in in in the books. I looked at perhaps I only read rather superficially, which is true, but I didn't know about micro tubules Stewart. I think one of the things here was impressed him about them. When you see pictures of mitosis that's a cell dividing. And you see all the chromosomes and the chromosomes get they'll get or get lined up and then they get pulled apart. And so as the cell divides the half the chromosomes go, you know how they want to divide into the two parts and they go to different ways. And what is it that's pulling them apart? Well those are these little things called micro tubules. And so he started to get interested in them. And he formed the view when he was his day job. A night job of what we call it is to put people to sleep. Except he doesn't like calling to sleep because it's different general anesthetics in a reversible way. So you want to make sure that they don't experience the pain that would otherwise be something that they feel and consciousness is turned off for a while and it can be turned back on again. So it's crucial that you can turn it off and turn it on. And what do you do when you're doing that? What do general anesthetic gasses do and see he formed the view that it's the micro tubules that they affect. And the details of why he formed that view is not. Well that's clear to me. But there but there's an interesting story he keeps talking about. But I've found this very exciting because I thought these structures these little tubes which inhabit pretty well all cells it's not just neurons apart from red blood cecil red blood cells they inhabit pretty well all the other cells in the body, but they're not all the same kind, you get different kinds of micro tubules and the ones that excited me the most. This is may still not be totally clear, but the ones that excited me most were the ones that the only ones that I knew about at the time, because they were they're very, very symmetrical structures. And I had reason to believe that these very symmetrical structures would be much better at preserving a quantum state quantum coherence, preserving the thing without you just need to preserve certain degrees of freedom without them leaking into the environment once they leak into the environment, your loss. So you got to preserve these quantum states at a level which the state reduction process comes in and that's where I think the non compute ability comes in and it's the measurement process in quantum mechanics. What's going on? </s><s>[INST] So something about the measurement process and what's going on? Something about the structure of the micro tubules. Your intuition says maybe there's something here maybe this kind of structure allows for the the mystery of the [/INST] there was a much better chance. Yes, it just struck me partly, it was the symmetry because there is a feature of symmetry, you can produce, preserve quantum coherence much better with symmetrical structures. There's a good reason for that. And that impressed me a lot. I didn't know the difference between the a lattice and be lighters at that time which could be important. Now that couldn't that's c which isn't talked about much </s>

<s>[INST] And you were deeply involved with that [/INST] at the time. I was very much involved with that. I was like the lead architect, I ended up talking to people who had already developed serious third party libraries that did similar things and sort of taking ideas from them and getting their feedback on my design and eventually we put it in the standard library and after a few years I got distracted. I think the thing the big thing that distracted me was actually type annotations, </s><s>[INST] but [/INST] other people kept it alive and kicking and it's been quite successful actually in the world of python web clients. </s><s>[INST] So initially what are some of the design challenges there in that debate for the pep And what are some things that got rejected? What are some things that got accepted to stand out to you? [/INST] There are a couple of different ways you can handle parallel i O. And this happens sort of at an architectural level in operating systems as well, like Windows prefers to do it one way and UNIX prefers to do it the other way. You sort of you have an object that represents a network endpoint, say connection with a web browser that your client and say you're you're you're waiting for an incoming request. Two fundamental approaches are okay, I'm waiting for an incoming request. I'm doing something else. Come wake me up or of course sort of come tell me when something interesting happened like a packet came in on that network connection. And the other paradigm is we're on a team of a whole bunch of people with maybe a little mind and we can only manage one web connection at a time. So I'm just sitting looking at this this web connection and I'm just blocked until something comes in and then uh I'm already waiting for it, I get I get the data, I process the data and then I go back to the top and say now sort of I'm waiting for the next packet. Those are about the two paradigms. One is a paradigm where there is sort of notionally a threat of control, whether it's an actual operating system, thread or more an abstraction in, we call them tasks, but the task in a or a threat in other contexts is devoted to one thing and it has logic for all the stages, like when it's a web request, like first wait, wait for the first line of the web request parse it because then, you know, if it's a get or a post or put or whatever or an error, uh then wait until you have a bunch of lines until there's a blank line and parts that as heathers and then interpret that and then wait for the rest of the data to come in. If there is any more that you request, expect that sort of standard web stuff. And the other thing is, and there's always endless debate about which approach is more efficient and which approach is more error prone where I just have a whole bunch of stacks in front of me and whenever a packet comes in, I sort of look at the number of the fact that there's some number on the packet and I say, oh that packet goes in this pile and then I can do a little bit and then sort of that pile provides my context. And as soon as I'm done with the processing, I sort of I can forget everything about what's going on because the next packet will come in from some random other client and it's that pile, </s><s>[INST] this pile [/INST] uh and every time a pile is maybe empty or full or whatever the criteria is, I can toss it away or use it for a new space but several traditional third party libraries for asynchronous I o processing in python chose the model of a callback and that's that's the idea where you have a bunch of different stacks of paper in front of you and every time someone gives you a piece gives you a new sheet, you decide which stack it belongs to. And that leads to a certain style of spaghetti code that I find sort of aesthetically not pleasing. And I was sort of never very successful. And I had heard many stories about people who were also sort of complaining about that style of coding. It was very prevalent in javascript at the time, at least because it was like how the javascript event loop basically works. And so I thought well the task based model where each task has a bunch of logic. We had mechanisms in the python language that we could easily reuse for for that. And I thought I want to build a whole library for asynchronous networking i o uh and all the other things that may need to be done a synchronously uh based on that paradigm and so I just chose a paradigm and try to see how far I could get with that. And it turns out that it's pretty good paradigm. So </s><s>[INST] people enjoy that kind of paradigm programming for asynchronous io, relative to callbacks. Okay, beautiful. So how does that all interplay with the infamous guild, the go, the global interpreter lock, maybe can you say what the deal is and how does it dance beautifully with a sen ko [/INST] The global interpreter lock solves the problem that python originally was not written with either asynchronous or or parallelism in mind at all. There was no concurrency in the language, there was no parallelism, there were no threads, only a small number of years into python's initial development, all the new cool operating systems like uh Sun. Os and silicon graphics, I rex and then eventually pas IX and Windows all came with threading libraries that lets you do multiple things in parallel and there is a certain certain sort of principle which is the operating system handles the threads for you and the program can pretend that there are as many cpus as as there are threats in the program uh and those Cpus were completely independently and if you don't have enough Cpus operating system sort of simulates those extra Cpus on the other hand, if you have enough Cpus, you can get a lot of work done by deploying those multiple Cpus, but python wasn't written to to do that. Uh And so as libraries for for multi threading were added to C. But every operating system then there was adding their own version of that. We thought and maybe we were wrong, but at the time we thought, well we quickly want to be able to support these multiple threads Because they seemed at the time in the early 90s when they were new, at least to me, they seemed a cool, interesting programming paradigm. And one of the things that that python at least at the time felt was nice about the language was that we could give a safe version of all kinds of cool new operating system toys to the python programmer. Like, I remember one or two years before threading, I I had spent some time adding networking sockets uh to python and there were very literal translation of the networking sockets that were in the BSD operating system. So UNIX BSD But the nice thing was if you're using sockets from python, then all the things you can do wrong with sockets in C would automatically give you a clear error message instead of just ending up with a malfunctioning hanging program. And so we thought, well we'll do the same thing with threading, but we didn't really want to rewrite the interpreter to be threat safe because that that was was like there would be a very complex re factoring of all the interpreter code and all the runtime code because all the objects were written with the assumption that there's only one thread. And so we said, okay, well we'll take our losses will provide something that looks like threads and as long as you only have a single CPU on your computer, which most computers at the time did uh it feels just like threats because The whole idea of of multiple threats in the Os was that even if your your computer only had one CPU you could still fire up at many threads as you wanted. Well, within reason maybe 10 or 12, not 5000. Uh And so we thought we had conquered the the abstraction of threats pretty well because multi core Cpus were not in, in most python programmers hands anyway. And then of course a couple of more iterations of moore's law and computers getting faster. And at some point, uh the chip designers decided that they couldn't make the Cpus faster, but they could still make them smaller and so they could put multiple Cpus on one chip. And suddenly there was all this pressure about do things in parallel and that's where the the solution we had in python didn't work. And that's that's sort of the moment that the gill became became infamous because the guilt, the guilt was the solution, we used to sort of take this single interpreter and share it between all the different operating system threats that you could create. And so as long as the hardware physically only had one CPU that was all fine. And then as hardware offenders were suddenly telling us all, oh, you got to paralyze everything's got to be paralyzed. People started saying, oh but we can use multiple threads in python and then they discovered, oh, but actually all threats run on a single single core. </s>

<s>[INST] Yeah, I was just, uh, as I often do, rereading Viktor Frankl's man's search for meaning. And he said something, Um, I just I often pull out sort of lines. The mere knowledge that a man was either a camp guard or prisoner tells us almost nothing. Human kindness can be found in all groups, even those which as a whole it would be easy to condemn. So that's speaking to you Feel for those people at the lowest level, implementing the orders, Um, [/INST] of those above right. And also you were yourself What will happen if you were given those same orders, You know, I mean, what would you do? What kind of reaction would you have in a similar situation? And, you know, you don't know </s><s>[INST] I could see myself in in World War Two, fighting for almost any country that I was born in. There's a love of community. There's a love of country that's just, uh, at least to me, it comes naturally. Just love of community and country is one such community, and I could see fighting for that country especially when you're sold the story that you're fighting evil. And I'm sure every single country was told that story effectively. And then, uh, when you're in the military and you have a gun in your hand or you're in the police force and you're ordered, go to this place and commit violence, it's hard to know what you would do. It's a mix of fear. It's a mix of. Maybe you convince yourself, you know, what can one person really do? And over time it's again that slippery slope because you could see all the people who protest who revolt, they're ineffective. So, like if you actually want to practically help somehow you're going to convince yourself that you can't one person can't possibly help, and then you have a family. So you want to make you know you want to protect your family. You tell all these stories, and over time it you naturally convince yourself to dehumanize the other. Yeah, I think about this a lot, Um, mostly because I worry that I would be a good German. [/INST] Yeah, No, no, that's right. That's right. And one of the, you know, one of my tasks as a as a teacher, right? Our students and I have classes on genocide, and I have one now, Uh, and another one, by the way, on Stalin, Um, but the one on on genocide, you know, one of my task is to try to try to get to get the students to understand This is not about weird people who live far away and in time and in place. But it's about them, you know, and that, you know, that's a hard lesson, but it's an important one. You know that that this is in all of us. You know, it's in all of us, and there's nothing, you know, and you just try to gird yourself up, you know, to try to figure out ways that maybe you won't be complicit, um, and that you learn how to stand by your principles. But it's very hard. It's extremely difficult, and you can't. The other interesting thing about it is not predictable. They've done a lot of studies of polls. For example, who during the war saved Jews, you know well, who are the Poles who saved Jews versus those who turned them in? It's completely unpredictable, you know. Sometimes it's the worst anti Semites who protect them because they don't believe they should be killed. Right? Um, and sometimes, you know, it's not predictable. It's not as if the humanists among us, you know, are the ones who, uh, you know, can consistently show up. You know, uh, you know and experience danger, in other words, and are ready to take on danger to defend your fellow human beings? Not necessarily. I mean, sometimes simple people do it, and sometimes they do it for really simple reasons. And sometimes people you would expect to do it, don't you know? And you've got that mix and it's just not predictable. </s><s>[INST] One thing I've learned in this age of social media is it feels like the people with integrity and the ones who would do the right thing are the quiet ones. Uh, in terms of humanists, in terms of activists, there's so many points to be gained, um, of declaring that you would do the right thing. It's a simple, quiet folks, because I've I've seen quite on a small, obviously much smaller scale, just shows of integrity and character when they were sacrificed to be made and it was done quietly, Uh, this sort of the small heroes, Uh, those are your right there. It's surprising, but they're often quiet. That's why I'm distrustful of people who kind of proclaim that they would do the right thing [/INST] right. And there's different kinds of integrity to I mean, I edited a memoir of a polish, uh, you know, underground fighter member of the underground who was in Majdanek in the concentration camp at Majdanek. You know, when he was just an interesting mix of different kinds of integrity. You know, on the one hand, you know, he really bothered him deeply when Jews were killed, were sent to camp, or is that sort of thing? On the other hand, he was something of an anti Semite, you know? And he would, uh you know, sometimes if Jews were his friends, he would help them. And if they weren't sometimes he was really mean to them, you know? And you could in their various levels, You know, a concentration camp is, uh, a terrible social experiment in some ways. Right? Uh, but you learn a lot from how people behave. And what you see is that you know, people behave sometimes extraordinarily well in some situations and extraordinary poorly in others, and that it's mixed and you can't predict it. And it's hard to hard to find consistency. I mean, that's the other thing. It's, you know, No, I think we claim too much consistency for the people we study and the people we think about in the past, you know, they're not consistent anymore than you. We are consistent, right? </s>

<s>[INST] Fascinating to think that COVID-19 is uh as a result of a virus evolving together with like twitter, like figuring out how we can sneak past the defenses of the humans. So it's not bad enough. And then then the misinformation, all that kind of stuff together is operating in such a way that the virus can spread effectively. I wonder, I mean obviously uh virus is not intelligent, but there's a uh there's a rhyme and rhythm to the way this whole evolutionary process works and creates these fascinating things that spread throughout the entire civilization. [/INST] Absolutely. It's um yeah, I'm I'm completely fascinated by this idea of social media in particular how it replicates how it grows. I've been how it how it actually starts interacting with the biology of the virus masks who's going to get vaccinated politics. Like these seem so external to virus biology, but it's become so intertwined and and it's interesting and I actually think we could find out that the virus actually becomes obviously not intentionally, but you know, we could find that choosing people choosing not to our masks, choosing not to counter this virus in a regimented and sort of organized way effectively gives the virus more opportunity to escape. We can look at vaccines, you know, we're about to, we're about to have one of the most aggressive vaccination programs the world has ever seen. But we are unfortunately doing it right at the peak of viral transmission when millions and millions of people are still getting infected. And when we do that, that just gives this virus so many more opportunities. I mean, orders of magnitude more opportunity to mutate around our immune system. If we were to vaccinate everyone when there's not a lot of virus, then there's just not a lot of virus. And so there's not going to be as many, you know, I don't even know how many zeros are at the end of however many viral particles there are in the world right now, you know more than quadrillions, you know, and so if you assume that at any given time somebody might have trillions of virus in them and any given individual, so then you know multiply trillions by millions and you know, you get a lot of viruses out there and if you start applying pressure, ecological pressure to this virus that that when it's not abundant, I had the opportunity for a virus to sneak around immunity, especially when all the vaccines are identical essentially. Um it </s><s>[INST] sticks is one to mutate and then jumps takes [/INST] one in the whole world, you know, and we have to, we have to not forget that this particular virus was one, it was one opportunity and it has spread across the globe and there's no reason that can't happen tomorrow. I knew, you know it's scary. </s><s>[INST] I have a million other questions in this direction, but I'd love to talk about one of the most exciting aspects of your work which is testing or rapid testing. You wrote a great article in time On November 17. This is like a month ago about rapid testing titled How we can stop the spread of COVID-19 by Christmas, let's jot down the fact that this is a month ago. So maybe your timeline would be different, but let's say in a month. So you've talked about this powerful idea for quite awhile. Throughout the COVID-19 pandemic. How do we stop the spread of COVID-19 in a month. [/INST] Well, we uh we use tests like these, you know, So so the only reason the virus continues spreading is because people spread it to each other. This isn't this isn't magic. Um and so there's a few ways to stop the virus from spreading to each other. And that is uh you either can vaccinate everyone and vaccinating everyone is a way to immunologically prevent the virus from growing inside of somebody and therefore spreading. We don't know yet actually if this vaccine, if any of these vaccines are going to prevent onward transmission. So uh so that may or may not serve to be one opportunity. Certainly I think it will decrease transmission. But the other idea that we have at our disposal now, we had it in May, we had it in june july august september october november. And now it's december. We still have it. We still choose not to use it in this country and in much of the world. And thats rapid testing that is giving its empowering people to know that they are infected and giving them the opportunity to not spread it to their loved ones and their friends and neighbors and whoever else. Um We could have done this. We still can today. We could start we have millions of these tests. These tests are simple paper strip tests. They are uh inside of this thing is just a little piece of paper. Um No and I can actually open it up here. There we go. So this this is how we do it right here. We have this little paper strip test. This is enough to let you know if you're infectious With somewhere around the order of 99% sensitivity, 99% specificity. You can know if you have infectious virus in you, If we can get these out to everyone's homes, build these, make 10,000,000, million, 30 million of them a day. We make more bottles of Dasani water every day. We can make these little paper strip tests and if we do that and we get these into people's homes so that they can use them twice a week. Then we can know if we're infectious, you know, is it perfect? Absolutely not. But is it near perfect. Absolutely. You know, and so if we can say, hey, the transmission of this is, you know, for every 100 people that get infected right now, They go on to in fact maybe 130 additional people. And that's exponential growth. 100 becomes 130, a couple days later that 100 30 becomes Another another 100 65 people have now been infected. And you know go over three weeks and 100 people become 500 people infected. Now it doesn't take much to have those 100 people, not in fact 130, but in fact 90 all we have to do is remove say 30 40% of new infections from continuing their spread. And then instead of exponential growth you have exponential decay. So this doesn't need to be perfect. We don't have to go from 100 to 0. We just have to go and have those 100 people infect 90 and those 90 people. In fact, you know, 82 whatever it might be and you do that for a few weeks and boom, you have now gone instead of 100 to 500 you've gone from 100 to 20. It's not very hard. And so the way to do that is to let people know that they're infectious. I mean I were perfect example right now I I this morning I use these tests To make sure that I wasn't infectious. Is it perfect. No, but it reduced my odds 99%. I already was at extremely low odds because I've spent my life quarantining these days. </s>

<s>[INST] it's complicated. I mean actually might is interesting because it's I would say M. I. T. Is different than stanford for example. I think it has a more kind of [/INST] narrow um about an algae in my apartment. Well </s><s>[INST] no, it's interesting because I would argue that there's some aspect of a brand like taliban, Emmett, no relation that has a kind of interact like the brand results in the behavior of the like enforces a kind of behavior and the people and the people feed the brand. And like there's a lot, I think stanford is a good example of something that's more distributed. There's sufficient amount of diversity in like all kinds of like centers and all that kind of stuff that the the brand doesn't become one thing mitt. So engineering, it's, you know, I think that [/INST] the taliban scratching scratching for it because I think it was more like mitt than than you might imagine. But, but isn't taliban, isn't it? Pretty. I don't </s><s>[INST] think there's a diversity. [/INST] So yeah, sorry, so just rephrase so, so people say, oh the Deobandi school and like what is that? I mean, but the taliban are, they're an ethnic movement. They represent a vision of postion power. Right? Punches are people who are quite internally diverse who actually speak multiple dialects of pashto who reside across the frontier of Pakistan in Afghanistan, there are pashtuns who live all over the planet, right? There's a community Moscow California everywhere. Right? So it's a global diaspora of sorts, passengers have a kind of geological imagination. So that lots of passions can tell you the names of their grandparents, great grandparents and so on and that's kind of a, there's a sense of pride in that posture. Language is a kind of a core element of that identity, but it's not universal. So for example, you can meet people who say I am pashtun, but I don't know pashto. So as you, as you claw away at this idea, it's amorphous. It also means different things, different people at different times. So saying the taliban are postion requires lots of qualifiers because lots of passions will say no, no, I have nothing to the taliban, I hate those people. So the taliban tried to mobilize other past tunes with limited success, but their core membership is almost exclusively pashtun and they say no, no, we represent afghans, we represent pious Muslims and so in recent 23 years they've gone further to say no, we have ethnic groups, we have those bags, we have Tajiks, we have Hazaras and in the north of Afghanistan in recent years they did do a bit better drawing in people who were very disaffected because the government and they were able to diversify their ranks somewhat. But if you watched almost 15 and who they've appointed what language they've used, how if present themselves, it's clear that you know, they are pashtun, they are male and they are extremely ideologically cohesive and disciplined, I'd say, right, so I think that a lot of the polish centrism, la block some of that stuff was the way to fight a war. Um they are, they are finally, you know, a guerilla movement, they see themselves as kind of pius Robin Hoods, the rhetoric is very much about taking from the rich, taking the privilege giving to the poor being on the side of the underdog, fighting against evil. And so I mean they're bag, if you like their thing, their, their central theme, their brand is about public morality and so their origin story going back 24 is that they interceded, they broke up a gang of criminals who were trying to write people and so there's a wrenching kind of like, it's not like sexuality and on, on public morality really been the core of like, you know, we're gonna restore order and morality and how that translates into governance is something they've never sorted out. I mean, how do you run a banking system if you're internal priorities are really about, you know, the length of beard and then, and then their path to power and in a kind of abstract sense, I mean a lot of that was very much driven by, um, if you like propagating the problems of martyrdom. And that sounds, I don't mean to say that in a way that to make it sound ridiculous, make it sound like it's um, you know, a moral judgment is simply, I think the fact it's a fact of their appeal that they promised young men who have known nothing else but studying in certain schools if at all, but they've known fighting and they've known they've known victimization and this isn't I'm not asking for like sympathy for them. I think the reality is that a lot of the we know about the kind of foot soldiers is that they they lost families and bombings um in airstrikes in night raids. Yeah I mean orphans have always been a stream um living in in all male society not knowing girls not knowing women. Hearing things from outside about places like Kabul. And so there's always been this kind of urban rural dimension. It's not it's not just that but I think there's a there's a whole imagination that being taliban captures and the whole marginal thing is really it's um yeah I think to any religious person, I mean it's not a it's not a bizarre idea. I mean it animates I mean so many global traditions. You know I think the but you try to tell like an army colonel try to here to have a conversation with you know U. S. Marine about this. I mean someone get it from their own religious backgrounds but I think the it it's an alien idea but I think it is essential to kind of stretch of imagination understand that's that's attractive and now one of the dilemmas going forward is that they've got a pivot from martyrdom and some have been some have told foreign journalists. I mean it's good that we're in charge now we're going to build a proper state, but i i it's kind of boring. Um I want to keep fighting, I want to maybe I'll do it in Pakistan. </s>

<s>[INST] so you're thinking including something bigger than just liberal education, also including science engineering and technology. That should also comment that, you know, I mostly stay out of politics and out of some of these aspects of liberal education, that's kind of been the most controversial and difficult within the university. But there is a kind of ripple effect of fear within that space into science and engineering and technology that I think has uh, has a nature that's difficult to describe. It doesn't have a controversial nature. It just has a nature of fear where you're not, You know, you're not just saying stupid stuff as a young 20 year old, you know, for example, Deep learning, machine learning is really popular in the computer science now as an approach for creating artificial intelligence systems. It's it is controversial in that space to say that anything against machine learning, saying sort of, exploring ideas that saying this is going to lead to a dead end. Um, now that that takes some guts to do as a young 20 year old within uh, within the classroom, to think like that, to raise that question in a machine learning course. It sounds ridiculous because it's like who's going to uh complain about this, but the fear that starts in uh in a course on history or on some course that cover society. The fear ripples and affects those students that are asking big out of the box questions about engineering, about computer science. And there's a lot, you know, there's like linear algebra that's not going to change, but then there's like applied linear algebra, which is machine learning and that's when robots and real system touch human beings. And that's when you have to ask yourself these difficult questions about about humanity, [/INST] even in the engineering and science and technology courses, and these are not separate worlds in two senses, I've just taken delivery of my copy of the book that eric Schmidt and Henry Kissinger have co authored on artificial intelligence. The central question of which is what does this mean for us broadly, but they're not separate worlds, you know, in C. P. Snow's sense of, you know, the chasm between science and arts because on a university campus, everything is contagious from a novel coronavirus to the behaviors that are occurring in the english department. Those behaviors if denunciation becomes a norm, you know, undergraduate denounces professor teaching assistant denounces undergraduate. Those behaviors are contagious and will spread inexorably first to social science and then to the natural sciences. And I think that's that's part of the reason why when this started to happen when we started to get the origins of disinfect dis invitation and cancel culture. It was not just a few conservative professors in the humanities who had to worry. Everybody had to worry because eventually it was going to come even to the most apparently hard stem part of the campus. It's, it's contagious. This is something Nicholas christakis should look at because he's very good at looking at the way in which social networks, like the ones that exist in a university can spread everything. But I think when we look back and ask why did work is um, spread so rapidly and rapidly out of humanity's into other parts of universities. And why did it spread across the country and beyond the United States? To the other english speaking universities, it's because it's a contagion. Uh, and these behaviors are contagious. The president of a university, I won't name said to me that he receives every day at least one denunciation, one call for somebody or rather to be fired for something that they said, that's the crazy kind of totalitarian ism light that now exists in our universities. And of course the people who want to downplay this say, oh well they're only have been 100 and something in dis invitations or oh, there really aren't that many cases. But the point is that the famous events, the events that get the attention are responsible for a general chilling. That as you say, spreads to every part of the university and creates a a very familiar culture in which people are afraid to say what they think. Self censorship. Look at the heterodox Academy data on this grows and grows. So now a majority of students will say, this is clear from the latest heterodox academy surveys, we are scared to say what we think in case we get denounced, in case we get canceled. Well, that's just not the correct atmosphere for a university in a free society. To me, what's really creepy is how many of the behaviors I see on university campuses today are reminiscent of the way that people used to behave in the soviet union or in the soviet bloc or in mao's china, the sort of totalitarian ism light that I think we're contending with here, which manifests itself as denunciations. People informing on superiors, some people using it for career advantage, other people reduced to helpless, desperate apology to try to exonerate themselves. People disappearing metaphorically, if not literally all of this is so reminiscent of the totalitarian regimes that I studied earlier in my career, that it makes me feel sick. And what makes me really feel sick is that the people doing this stuff, the people who write the letters of denunciation are apparently unaware that they're behaving exactly like people in Stalin's soviet union, they don't know that. So they clearly have there's been a massive educational failure if somebody can write an anonymous or non anonymous letter of denunciation and not feel shame. I mean, you should feel morally completely contaminated as you're doing that. But people haven't been taught the realities of totalitarian ism. For all these reasons, I think you need to try at least to create a new institution where those pathologies will be structurally excluded. </s>

<s>[INST] molecule map of what happens to skin [/INST] which has </s><s>[INST] never been done before. So, there what are [/INST] interesting surprises there. </s><s>[INST] So [/INST] one of the things we can </s><s>[INST] see the part of what's [/INST] driving information, we can actually see </s><s>[INST] macrophages and [/INST] other dendritic cells, pieces like cells that are part of the immune system kind of creeping along towards the surface of the </s><s>[INST] skin, which is now we know it's actually [/INST] physically driving the immune system is these cells </s><s>[INST] going and creating this inflammation, [/INST] which is what leads to some of </s><s>[INST] the rashes. But we didn't [/INST] see as much in them as we saw. For example, some of the signatures of scott kelly. So we can see within the crew </s><s>[INST] who's getting more [/INST] of a rash or not or who didn't experience </s><s>[INST] any rash [/INST] and some people had changes in </s><s>[INST] vision. Some people had, [/INST] you know, other G. I. Problems even, you know, even looking at what happens to the gut </s><s>[INST] and looking at the microbiome in [/INST] the gut, other people didn't. So we were able </s><s>[INST] to see it start [/INST] to get a little bit predictive about their </s><s>[INST] medicine right now we're just diagnosing. [/INST] But it'd be good to say uh if you're going into space, </s><s>[INST] here's exactly what you [/INST] need for each bacteria </s><s>[INST] in your body. [/INST] Here's what you can really take to get rid of nausea or other ways </s><s>[INST] we can monitor to keep keep the [/INST] information down. What does it take to prepare for one of these missions? Because you mentioned, some of the </s><s>[INST] folks are not [/INST] necessarily lifelong astronauts, </s><s>[INST] you're talking about [/INST] more and more regular civilians. </s><s>[INST] What's [/INST] what does it take physiologically and psychologically </s><s>[INST] to prepare for these. They have to do a [/INST] lot of the same training that most astronauts do. So a lot of it's on hawthorne at SpaceX headquarters, which if you can </s><s>[INST] never get a chance to do a tour as [/INST] fabulous as you can see. Always john rockets being built and then we're drawing blood over there </s><s>[INST] right next to them. So it's a really [/INST] cool place. But </s><s>[INST] the, the training, they have [/INST] to go through a lot of the ops, a lot of the programming just in </s><s>[INST] case most of the systems are [/INST] automated on the Dragon </s><s>[INST] and other spacecraft, [/INST] but just in case, so I have to go through all </s><s>[INST] the majority of training [/INST] if you want to go to the </s><s>[INST] space station, as [/INST] the actual emissions are including john Schaffner, you have to do training for some of the Russian </s><s>[INST] modules. And if you don't do that training, then [/INST] you're not allowed to go to the Russian </s><s>[INST] part of the space station apparently. [/INST] So right now john schaffner for example, unless he completes this additional training all in Russian, </s><s>[INST] he's not allowed [/INST] to learn enough Russian to be, you know, just so </s><s>[INST] it's not just technical [/INST] enough enough </s><s>[INST] enough enough. [/INST] And uh, so it's a, and </s><s>[INST] if he doesn't learn, he can't [/INST] go to that part of the space station. So interesting things like that. But you'll be, you know, it's not that far like, oh, I can see </s><s>[INST] it right there, I can't float [/INST] over to that, that capsule, </s><s>[INST] but technically [/INST] he can't go. So, you know, </s><s>[INST] is there um, [/INST] chinese </s><s>[INST] components to this, the international space [/INST] station is their collaboration there, </s><s>[INST] sadly. No, they're building [/INST] their own space station. I'm glad they're building a space station actually, eventually there'll </s><s>[INST] Be probably four space [/INST] Stations in orbit by 20, some from the orbital reefs, some from Lockheed Martin </s><s>[INST] of course axiom is, [/INST] is far ahead </s><s>[INST] right now. They're probably gonna be done first. But the [/INST] extraordinary thing </s><s>[INST] is [/INST] uh, there's </s><s>[INST] unfortunately there's no [/INST] collaboration between the, you see that as a negative. That's not the positive </s><s>[INST] kind of competition. It's it's a good [/INST] question. So </s><s>[INST] maybe [/INST] for example when we get different Nasa grants, you apply for a </s><s>[INST] grant, you get to the [/INST] lab, it goes, you know, to </s><s>[INST] go through Cornell the grants [/INST] office. I have to sign as a scientist as the </s><s>[INST] P. I. On the on the mission. Say I promise [/INST] I will move no funds or resources or any </s><s>[INST] staff to anyone in china or work with anyone in china with [/INST] these dollars that you're giving to the </s><s>[INST] lab for this mission. [/INST] And so like every </s><s>[INST] other grand I get from the [/INST] Nasa D. O. D. Or </s><s>[INST] sorry, do you let me go back to [/INST] that every other grant </s><s>[INST] I get from say the NIH or [/INST] the NSF </s><s>[INST] even symptoms D. O. D. You don't have to promise that you won't talk to anybody in china [/INST] about it. But for Nasa alone is </s><s>[INST] congressional mandated [/INST] you have to promise and sign all the paperwork that I can't do </s><s>[INST] anything with anyone in china about this. [/INST] And what if </s><s>[INST] you have said about that is I want [/INST] to at least be able to chat </s><s>[INST] with him about it and know what [/INST] they're up to, but we can't, you know, </s><s>[INST] even go to a conference in China technically with [/INST] Nasa funds about, say, space medicine or </s><s>[INST] engineering a new rocket. [/INST] I can't </s><s>[INST] go, I could go with personal [/INST] funds, but I can't use those funds. </s><s>[INST] Like you should be able to go to a [/INST] conference and in a </s><s>[INST] friendly way, talk shit [/INST] scientists, </s><s>[INST] like we're doing like, like the way scientists do really well, which is [/INST] like a compliment, </s><s>[INST] but it's a backhanded compliment. Like, like [/INST] you're doing a really good </s><s>[INST] job here and [/INST] then you kind of implied that you're doing </s><s>[INST] much better job. That's [/INST] the core of </s><s>[INST] competition. You get jealous and [/INST] then everybody's trying to improve. But that </s><s>[INST] you're ultimately talking, [/INST] you're ultimately collaborating closely. You're competing </s><s>[INST] closely as opposed to in your own silos. Well, let me ask, [/INST] uh, </s><s>[INST] in terms of [/INST] preparing um, for spaceflight, you know, I I tweeted about this and I </s><s>[INST] I joked about it and [/INST] I I talked to you along </s><s>[INST] quite a lot these [/INST] days. What I tweeted </s>

<s>[INST] You know, To me, it's fascinating for being humble. Like the humans cannot possibly be the most amazing thing that such if you look at the entirety of the system that leads small and you paint that cannot possibly be the most amazing thing that process generates. So like if you look at the evolution, what's the equivalent in the cosmological evolution and its selection for technology, the equivalent of the human eye or the human brain universes that are able to do some, like they don't need the damn stars. They, they're able to just do some incredible generation of complexity fast on like much more than if you [/INST] think about it's like most of our universe </s><s>[INST] is pretty freaking boring. There's not much going on. It's a few rocks flying around and there's some like apes that are just like um doing podcasts, something weird on some weird planet. It just seems very inefficient. If you think about like the amazing thing, the human eye, the visual cortex can do the, the brain nervous of everything that makes us more powerful than single cell organisms. Like if there's an equivalent of that for universes there, like the richness of physics that could be uh that could be expressed through a particular set of parameters. Like, I mean that like for me, I'm so from a computer science perspective, huge fan of cellular automata, which is a nice sort of pretty visual way to illustrate how different laws can result in uh drastically different levels of complexity. So like it's like, yeah, okay, so we're all like celebrating, [/INST] look our little cellular tom and is able to generate </s><s>[INST] pretty triangles and squares and therefore we achieve general intelligence. And then there will be like some badass chuck Norris type, like uh universal turing machine type of cellular automata, they're able to generate other cellular automata that does any arbitrary level of computation off the bat it like those have to then exist. And then we're just like this, we're just, we'll be forgotten. Is this story, this is uh, this podcast just entertains a few other apes for for [/INST] a few months. Well, I'm kind of surprised to hear your cynicism. I'm very, I usually think of you as like a one who celebrates humanity in all its forms and things like that and I guess I just, I don't, I see it the way you just described. I mean, Okay, five, we've been here for 13.7 billion years and you're saying, gosh, that's a long time. Let's get on with the show already. Some other universe could have kicked our butt by now, but That's putting a characteristic time. I mean, why is 13.7 billion a long time? I mean, compared to compared to what I guess. So when I look at our universe, I see this extraordinary hierarchy that has developed over that time. So at the beginning it was a chaotic mess of you know, some plasma, nothing interesting going on there. And even for the first stars to form that a lot of really interesting uh evolutionary processes had to occur by evolutionary in that sense. I just mean, um taking place over extended periods of time and structures are forming then. And then it took that first generation of stars in order to produced the medals that uh, that then can more efficiently produce another generation of stars. We're only the third generation of stars. So we might still be pretty quick to the to the game here. So, but I don't think I don't Okay, so then, so then you have these stars that you have solar systems on those solar systems, you have, um, rocky worlds, you have gas giants, like all this complexity and then you start getting life and the, the complexity that's evolved through the evolutionary process in life forms is just, it's not a letdown to me just </s><s>[INST] and there's some of it is like some, some of the planet's is like, I see like different flavors of ice cream there. I see, but there might be water under all kinds of life forms and some volcanoes, all kinds of weird stuff. No, no, I, I don't, I think it's beautiful. I think our life is beautiful and I think it was designed that by, by design the scarcity of the whole thing. I think mortality as terrifying as it is. As fundamental to the whole reason we enjoy everything. No, I think it's beautiful. I just think that all of us, um conscious beings in the grand scheme of basically every scale will be completely forgotten. [/INST] Well that's true. I think everything is transient and that would go back to maybe something more like loud to the Tao Beijing or something where it's like, yes, there is nothing but change, there is nothing but emergence and dissolve and that that's it. But I just in this picture of this hierarchy that's developed, I don't mean to say that now it gets to us and that's the pinnacle. In fact, I think the, at a high level the story I'm trying to tease out in my research is about, Okay, well, so then what's the next level of hierarchy? And if and if it's okay, we're kind of pretty smart. I mean, talking about people like lee small and alan goose max, Take Mark. Okay, we're really smart talking about me. Okay, we're kind of, we can find our way to the grocery store or whatever, but but what's next? You know, I mean, what if, what if there's another level of hierarchy that grows on top of us that is even more profoundly capable? And I mean, we've talked a lot about super conducting sensors. Imagine these uh cognitive systems far more capable than us residing somewhere else in the solar system off of the surface of the earth, where it's much darker, much colder, much more naturally suited to them. And they have these sensors that can detect single photons of light uh, from radio waves out too, all across the spectrum to gamma rays and just see the whole universe. And they just live in space with these massive um collection optics so that they what do they do? They just look out and and experience that that vast array of of what's being developed. </s>

<s>[INST] Yeah, I don't find it super interesting. Well, he also wrote the book, [/INST] The Real Anthony Fauci, is that the name of the book? Did he write that? I don't know, I'm not sure about that. </s><s>[INST] I'm aware of that book, I didn't know he wrote it. I think I need it, but it's been on my reading list to get, I've been trying to get a good, balanced reading list about the COVID pandemic to understand what the hell happened. And anytime I start to try to go into that place, [/INST] it's just, I'm exhausted, exhausted by it. Well, it's interesting to me that you wouldn't wait longer before delving into those books </s><s>[INST] to have maybe a more clear hindsight. But I think this is a pretty good time. You don't think so? Like this is, it depends on your goals. If you're thinking of it as a historical event, yes, you should probably wait longer. But if you're thinking about like understanding what is broken about our system that we responded so poorly, that there was so much division, what is broken about our political system that it didn't unite us, it divided us. Who's to blame? There's probably a lot of different narratives, but I feel like the more you learn about this, the better you can understand. I read, on just Vladimir Putin, I read like five biographies already, maybe more. Just, it helps to really understand the people involved, the organizations involved, I don't know, everything from the scientists to the political leaders. It felt like the blog posts and the tweets didn't quite capture the story. [/INST] They didn't quite, they didn't quite, no, one of the things I read a ton, I don't read any like modern political books. So I don't read the memoirs of elected officials. I don't read any, I just feel like I get enough of it in my job. So my reading list is just other things. It's history, it's narrative nonfiction, economics, et cetera. And that's my bias because I'm so overloaded with a lot of the stuff you're talking about. I haven't read any of Obama's books. I didn't read John Bolton's book or, you know, I don't read any of that stuff, </s><s>[INST] although I'm sure there is value to be gleaned from it. What about the other candidate that, according to the subreddit, and as you mentioned, you've criticized it a little bit, Marianne Williamson, do you think, [/INST] what are the pros and cons of her as a candidate? This is another area where many in my audience really are angry with me. I don't find her candidacy super interesting. I'll tell you the pros and the cons as I see them. I do think that we have elected officials in the U.S., particularly presidents, from a really narrow range of backgrounds. So it's lawyers and sometimes business people, very, very often lawyers. I think we would benefit from a much greater diversity of backgrounds. And I once said, and that would include people from education, people from the science world, people with backgrounds, maybe running nonprofits, et cetera. Now, Marianne Williamson did, I guess, at one point, run some kind of small nonprofit. And some in my audience thought that credential alone would make me fall head over heels in love with the idea of a Marianne candidacy. I've interviewed for her. It's just not for me is the way I like to say it. It's the background of the woo woo type stuff is a bit off-putting to me. I understand that someone with literal Christian Bible beliefs that also I don't like, maybe I'm more willing to accept as most of our presidents, of course, have had those views because they're otherwise more qualified. But some of the things that she says just strike me as, I just don't know. I'll give you an example. When she was on with Russell Brand, she said, there's no such thing as clinical depression. It just means someone in a clinic told you, you have depression. I don't believe that to be the case. I think we have an understanding. There's two types of depression. There's like a genetic predisposition depression. There's like a acute, something's happening in my life. Temporary depression, okay. When she was asked about it recently, she said, I didn't mean it. I was just trying to impress Russell Brand. I don't know if I'm more bothered by the things she first said or by the fact that she wanted to impress Russell Brand. But it's just like, it's just really not for me. And I agree with her on, we need to take the climate more seriously. We need to expand access to hell. I'm with all of that stuff. Now I want to say one other thing about this. Anybody who wants to run should run. I am not suggesting there should be an uncontested primary for Joe Biden. Absolutely. So you think it should be contested? Well, what I mean by contested is, so there's two parts to what we mean by contested. Will the DNC organize debates? And we'll get to that in a second, but should anybody who's on the left get out of the way because Joe Biden is president and he's running for reelection? Absolutely not. The question about should there be debates? I would like there to be debates. The DNC pretty clearly isn't going to organize them. I think if you did them, you would have to say at what polling level do you qualify? And I don't know exactly where you put that number, but I think it would be a great thing to put Joe Biden on a stage with, if you can get what, 6%, 8%? I'm not really sure what the number would be. </s><s>[INST] I'm totally all for that. Why is this set of candidates, at least from my perspective, so weak? [/INST] Do you have an understanding? Do you have an understanding? There's a lot of different answers to this. One aspect of this, which I think is more of a socio-cultural thing, which I've recently read about to some degree, is the job actually turns off the people who would be best at it because of what you need to do to become president. And it includes all but completely abandoning your existing day-to-day life job, which you may depend on, and family to some degree. It's horribly negative, as we already talked about. And at the end of all of that, you either lose and then have to rebuild, and maybe you're not in a position to be able to do that, or you win, and then now you've got four years of being one of the most hated people, no matter how good a job you do. So I think by its nature, it turns off a lot of people that would otherwise be good. I also think that there's a lot of posturing from within the parties about, well, you might be good, but it's not your time yet, so you should wait, and then let's talk about maybe a Senate seat here and there. So it's like a company, essentially, and they're figuring out where they want to place people. I think all of these things make it so we end up with candidates most people aren't super thrilled with. </s>

<s>[INST] And in that [/INST] picture, </s><s>[INST] what would be the role of creativity. But a few people ask about creativity, do you think when you think about intelligence? I mean, certainly the story you told the beginning of your book involved, you know, creating movies and so on, sort of making making money. You know, you can make a lot of money in our modern world with music and movies. So if you are an intelligence system, you may want to get good at that. But that's not necessarily what I mean by creativity. Is it important on that complex goals where the sea is rising for there to be something creative or or am I being very human centric and thinking, creativity is somehow special relative to intelligence? [/INST] Mayan hunches a we should think your creativity simply as an aspect of intelligence. And uh we we have to be very careful with the human vanity we have we have this tendency very often want to say as soon as machines can do something, we try to diminish it and saying oh but that's not like real intelligence, you know because they're not creative or there were or this or that the other thing um if we ask ourselves to write down a definition of what we actually mean by being creative, what we mean by Andrew wiles what he did there for example, don't we often mean that someone takes very unexpected leap. It's not like taking 573 and multiplying it by 224 by just a step of straightforward cookbook like rules. Right? You can maybe make it, you make a connection between two things that people have never thought was connected, surprising or something like that. Huh? I think I think this is an aspect of intelligence and uh this is actually one of the most important aspect of it. Maybe the reason we humans tend to be better at it than traditional computers because it's something that comes more naturally if you're a neural network than if your traditional logic gates based computer machine. You know we physically have all these connections. Mhm. And that did you activate here, activated here, activate here being, you know, a my hunch is that if we ever build a machine, well, you could just give it the task. Hey, hey, uh you say, hey, you know, I just realized that I want to travel around the world instead this month. Can you teach my G. I course for me? And it's like, okay, I'll do it and it does everything that you would have done and improvises and stuff that would, in my mind involve a lot of creativity. </s><s>[INST] Yeah, So it's actually a beautiful way to put it. I think we do try to grab grasp at the, you know, the definition of intelligence is everything. We don't understand how to build. So like so we, as humans try to find things well that we have our machines don't have. And maybe creativity is just one of the things, one of the words we use to describe that, that's a really interesting way to put [/INST] it, and I don't think we need to be that defensive. I don't think anything good comes out of saying, well, where somehow special, you know, it's um contrary wise, there are many examples in history of where trying to pretend that we're somehow superior to all other intelligent beings has led the pretty bad results, right? Nazi Germany? They said that they were somehow superior to other people. Uh today we still do a lot of cruelty to animals by saying that we're so superior somehow. And they can't feel pain, slavery was justified by the same kind of just really weak arguments. And and I don't think if we actually go ahead and build artificial general intelligence can do things better than us. I don't think we should try to found our self worth on some sort of bogus claims of superiority in terms of our intelligence. I think we should instead find our calling and the meaning of life from from the experiences that we have. You know, I can have, I can have very meaningful experiences, even if there are other people who are smarter than me, you know? Okay, when I go to faculty meeting here and I were talking about something that I certainly realize, oh, but he has an old price. He has an old price. He has a surprise. I don't have, what does that make me enjoy life any less? Or I enjoy talking to those people. That's of course not, you know, and contrary wise, I I I feel very honored and privileged to get to interact with with other very intelligent beings that are better than me. A lot of stuff. So I don't think there's any reason why we can't have the same approach with intelligent machines. </s><s>[INST] That's a really interesting. So people don't often think about that. They think about when there's going if there's machines that are more intelligent, you naturally think that that's not going to be um a beneficial type of intelligence, you don't realize it could be, you know, like peers with Nobel prizes that that would be just fun to talk with, and they might be clever about certain topics and uh you can have fun having a few drinks with them, so [/INST] well also, you know, another example, we can all relate to it of why it doesn't have to be a terrible thing to be impressed with the presence of people or even smarter than us all around is when, when you and I were both two years old, I mean, our parents were much more intelligent than us, right? Worked out okay, because their goals were aligned with our goals and that I think is really the number one key issue we have to solve if we value in line of the value alignment problem. Exactly. Because people who see too many Hollywood movies with lousy science fiction, plot lines, they worry about the wrong thing, right? They worry about some machines, certainly turning evil, it's not malice, they wish that is the concern its competence. By definition intelligence makes you makes you very competent if you have a more intelligent goal. Playing, Computer playing is the less intelligent one. And when we define intelligence is the ability to accomplish, go winning right, it's going to be the more intelligent one that wins and if you have human and then you have an A g that's more intelligent than always, and they have different goals, guess who's going to get their way right? So I was just reading about, I was just reading about this uh particular rhinoceros species that was driven extinct just a few years ago, a bummer is looking at this cute picture, mommy rhinoceros with its it's child, you know, why did we humans drive it to extinction? Wasn't because we were evil rhino haters as a whole. It was just because we are goals weren't aligned with those of the rhinoceros, and it didn't work out so well for the rhinoceros because we were more intelligent, right? So I think it's just so important that if we ever do build a G i before we unleash anything, we have to make sure that it's it learns to understand our goals, adopts our goals and it retains those goals. </s>

<s>[INST] A lot of people ask me to add some merch, like a T shirt or a mug. What else can you do? A merchant? It'd be cool to do some super complicated merch. Like like a mini robot or some kind like the butter robot, Maybe a piece of software that you can run. I think that's called the virus that I just try to sell you a virus. [/INST] Um </s><s>[INST] it's a good kind of virus, I swear For a limited time. 9 99. No, you know, as a fan of different podcasts and different shows, I like, I like merch. It's a good way to get um to wear something where you support the people and you're like proud. And it also helps you find the other humans that support the same kind of thing. I don't know. It's pretty cool. As long as the shirt is not too flashy. If it's like subtle clean. Yeah, it's definitely something I'll um do in the future. Just just for fun. Get a free trial and full access to Shopify his entire suite of features when you sign up at Shopify dot com slash lex. That's all lower case. This show is also brought to you by athletic greens and it's uh a G one drink which is an all in one drink to support better health and peak performance I drink. I just drank one actually and that was the second time I drank today. So the first thing I drink every day to break my fast and then I oftentimes drink it again to get even more nutrition when I do any kind of crazy exercise or fasting or all that kind of stuff. So I do a keto diet. I'm currently doing carnivore. I don't think of it as a diet. It's just the thing I'm doing. It's not uh something I'm doing religiously. It's just the thing that makes me feel good. I'm very much a proponent of listening to my body of studying my body, be like a scientist and running a study of end of one. So just trying to understand what makes you feel good and what doesn't make you feel good and doing more of the stuff that makes you feel good. And so carnivore is definitely something that makes me feel good. But it is a little bit of restricting in terms of social life in terms of a little bit of variety. But I'm somebody who likes the boring stuff so I love it. I'm, I'm really happy. [/INST] But </s><s>[INST] of course the little flavor is always fun. Some flavorful food with friends anyway, no matter what I'm doing is good to have like a grounding and great nutrition, which is what athletic greens does for me. They'll give you a one month supply official when you sign up at athletic greens dot com slash lex this episode is also sponsored by fun dries spelled F. U. N D R I S. E. It's a platform that allows you to invest in private real estate. There's all kinds of madness going on right now in the markets. I am barely paying attention. I don't really know what's going on in terms of crypto in terms of the stock market, [/INST] I </s><s>[INST] really try to not pay close attention to the dynamics of the market because it really can pull you in in the way that a sort of any kind of fun gambling game can pull you in. So I tried to think of what the wise long term investment is that doesn't require me to check things every single day that can I can avoid the whole addictive aspect of investing and for that I think still diversification is a really powerful tool so you should really invest in all kinds of things. And fun dries makes it really easy to invest in private real estate. Over 150,000 investors use it check out fun dries. It takes just a few minutes to get started at fun dries dot com slash flex. This episode is brought to you by better help spelled H E L. P. Help. They figure out what you need to match you with a licensed professional therapists and under 48 hours. I'm a huge fan of talk therapy. I just recently had a bunch of conversations about psychiatry, about talk therapy, about calling young about Sigmund Freud and of course they were clinical psychologists or psychiatrists in part they had patients, some patients that had for many years and they've used that personal interaction to develop theories of the human mind and um I think that personal interaction just like in a podcast is such a powerful tool to delve too pull apart the different things that make up this beautiful complex mess that is the mind. Looking into the memory, the recent memory, the deep memory, the trauma that you haven't really dealt with. The things that really bother you. I think talking through it just trying to articulate the thing that bothers you still I think the act of articulation to another human being that is a good listener. It somehow untangles that mess. I'm a big believer in that and so better help is the thing that makes that easy but in any aspect of life you should do that kind of thing. Even if it's just with a close friend, have a deep conversation with or without a microphone. It helps check them out at better help dot com slash lex and save on your first month. This show is also brought to you by Inside Tracker a service. I used to track biological data. They have a bunch of plans, most of which include blood tests. They give you a bunch of kinds of data. So then you take these machine learning algorithms that incorporate the blood data. DNA data, fitness tracker data, all that stuff to give you a picture of what's going on inside inside your body, not some kind of generic average population data about what's supposed to be going on your body. And then somehow from that, inferring general kinds of patterns of lifestyle changes you should be engaging in. No, this is from your own body data driven to tell you what the heck you should do now this is obviously the future. To me, it kind of bothers me that medicine is not based on long term data that comes from your own body. It's kind of absurd. It puts way too much responsibility on the doctor to figure out what the heck is going on inside. You know, of course they've gotten pretty damn good at that kind of thing. But why not make it much, much more powerful? So big supporter of Inside Tracker for pushing forward, that kind of idea of being data driven in recommending lifestyle changes, health changes, all that kind of stuff. Get special savings for a limited time when you go to Inside Tracker dot com slash lex, this is the lex Friedman podcast support it. Please check out our sponsors in the description and now dear friends, here's magnus Carlsen, you're considered by many to be one of the greatest if not the greatest chess players of all time, but you're also one of the best fantasy football ak soccer competitors in the world. Plus recently picking up poker and uh, competing at a world class level. So before chess, let's talk football and greatness, You're a real Madrid fan. So let me ask you the ridiculous big question, who do you think is the greatest football a. K a soccer player of all time? Can you make the case for messi? Can you make the case for Cristiano Ronaldo pele maradona? Does somebody anybody jumped in mind? [/INST] I think it's pretty hard to make a case for anybody else than messi for his for his all around game. And frankly, like my round Madrid fandom sort of predates the Ronaldo era era, the second Ronaldo, not not not the first one. So I always liked Ronaldo, but I always kind of thought that messi was was better and I went to quite a number of Madrid games and they've always been super helpful full to me down there. The only thing is that like they asked me, they were going to do an interview and they were gonna ask me who my favorite player was and um I said somebody else, I think I said isco at that point, I was like, okay, take two. Now you say Ronaldo. So for them it was it was very important, but it wasn't, it wasn't that huge to um to me, so </s><s>[INST] messy over maradona. [/INST] Yeah, but it's, I think just like with just, it's hard to compare eras. Obviously the improvements in football have been like in technique and such have been even greater than they have been in, in, in just, but it's um, it's always um, it's always a weird discussion uh, to have, </s><s>[INST] but just as a fan, what do you think is beautiful about the game? What defines greatness? Is it, you know, with messy one? He's really good at finishing two. Very good at assist. Like three. There's just magic. It's just beautiful to see the play. So it's not just about the finishing, there's some, it's like Martinez Hand of God, there's some creativity on the pitch. Is that important? Or is it very important to get the World Cups and the big championships and that kind of stuff. [/INST] I think the World Cup is pretty, pretty overrated seeing as um, as it's such a small sample size. So uh, it's sort of annoys me always when, you know, titles are always um always appreciated so much. Even though that particular title can be, can be a lot of, a lot of luck or at least some at least some luck. Um So I do appreciate um, statistics a bit and all the statistics. Say that mess is the best finisher of all time, which I think helps a lot. Um and then there's the intangibles as well. The </s><s>[INST] flip side of that is the small sample size is what really creates the magic. It's so it's just like the olympics. You, you basically train your whole life for this. You live your whole life for this and it's a rare moment. One mistake and it's all over. That's [/INST] for </s><s>[INST] some reason, a lot of people either break under that pressure or rise up under that pressure. You don't, you don't admire the magic of that. [/INST] No, I I do. I just think that like rising and to the pressure and breaking on the under the pressure is often really oversimplified. Like taken on what's on what's happening. </s><s>[INST] We yeah, we do romanticize the game. Yeah. Well, let me ask you another ridiculous question and another. You're also a fan of basketball. [/INST] Yes. </s><s>[INST] Let me ask the goat question. The, you know, I'm biased because I went to high school in Chicago, you know, Chicago bulls during the Michael, Jordan era. Uh, let me ask the Jordan versus Lebron James question, let's let's continue on this threat of greatness. Which one do you pick or somebody else. So [/INST] I'll give you a completely different answer. Um, depending on my mood and depending who on whom I talked to? I picked one of one of the two and then I tried to argue for </s><s>[INST] the quantum mechanical thing. Well, can you, what again, what what would if you were to argue for either one? Statistically, I think Lebron James is going to surpass Jordan's. [/INST] Yeah, no doubt. </s><s>[INST] And so again, there's a debate between [/INST] unquantifiable greatness. No, that, I mean that's the whole that's the whole debate. </s><s>[INST] Yes. So it's, well, it's quantifiable versus unquantifiable. what's more important and your depending on mood all over the [/INST] place. </s><s>[INST] But what do you lean in general? With these, with these folks? With with with soccer, with anything in life towards the unquantifiable more? [/INST] No, definitely towards the quantifiable. </s><s>[INST] So when you're unsure, lean towards [/INST] the numbers, but </s><s>[INST] see like it's later generations, there's something that's what people say about maradona is, you know, he took arguably somewhat mediocre team to two world Cup. So there's that also uplifting nature of the player to be able to rise up the whole, it is a team sport. [/INST] So are you gonna like, I'm gonna punish um messy for taking a mediocre argentine squad to to the to the final in 2014 and punish him because they lost to a great team very narrowly after they missed. He he set up like a great chance for rain in the first half which he um which he fluffed and then eventually they lost the game. Yeah. </s><s>[INST] They do criticize cristiano Ronaldo messi for being on really strong squads in terms of the club teams and saying, yeah, okay, it's easy when you have like or whoever on your team. It [/INST] would be very interesting just if the league could make a decision. Yeah. </s><s>[INST] Just random random allocation. [/INST] Yeah. </s><s>[INST] Um And just every single game just keep relocating maybe once a season um or every season you get random [/INST] but let's say every every </s><s>[INST] player [/INST] um if let's say they signed a five year contract for a team, like one of them you're gonna get randomly allocated to, to, let's say the bottom half team, </s><s>[INST] I bet you there's gonna be so much corruption around that [/INST] would never happen or work, but I think it's, </s><s>[INST] you never know. [/INST] So </s><s>[INST] on chess, let's zoom out. If you break down your approach to chess when you're at your best. What what do you think um What do you think contributes to that approach? Is that memory recall specific lines and positions? Is it intuition how much of it is intuition how much of it is pure calculation, how much of it is messing with the strategy of the opponent. So the game theory aspect, in terms of what contributes to the highest level of play that um that you do. [/INST] I think the answer differs a little bit now from what it did Eight years ago. For instance, like I've I feel like I've had like two peaks in, in my career in 2014. Uh well 2013, and also in 2019. And in those years, I was very different um in terms of um of my strength strength specifically in 2019, I benefited a lot from opening preparation While in 2013, I mostly tried to avoid my opponent's preparation rather than that being a being a strength. So I'm I'm mentioning that also because it's something something you didn't didn't mention. I think like my intuitive understanding of chess has over those years always been a little bit better than the others even though it has evolved as well. Um Certainly there are there are things that I understand now that I didn't understand back then, but that's not only for me that's for um for others as well. Um I was younger back then, so I played with more energy which meant that I could play better in long drawn out games. Um </s><s>[INST] Which [/INST] was also a necessity for me because I didn't I couldn't couldn't beat people in the in the openings. Um But in terms of calculation that's always been a weird issue for me, like I've always been really really bad at solving exercises and chess, like that's been like a blind spot for me, first of all I found it hard to concentrate on them. Um and to look to look deep enough. </s><s>[INST] So this is like a puzzle opposition made in X. I [/INST] mean one thing is made but find the best move that's generally the exercise like find the best move, find the best line, </s><s>[INST] you just don't connect with it. [/INST] Usually like you have to to look look deep and then when I get these lines during the game I very often find the the right solution even though um even though it's not still um the best part of my game to to calculate very very deeply, </s><s>[INST] but it doesn't feel like calculation you're saying in terms of [/INST] no it does sometimes, but for me it's more like I'm at the board trying to find, trying to find the solution and I understand like the training at home is like trying a little bit too to replicate that. Like you give somebody a half an hour um in a position like in this instance you might have thought for half an hour if you play the game, but I just, I just cannot do it. One thing I know that I am good at though is um calculating short lines because I calculate them them Well I'm good at seeing um little details and I'm also much better than than most at evaluating, which I think is something that sets me sets me apart from from others. </s><s>[INST] So evaluating specific position, if I if I make this move and the position changes in this way, is this the step in the right direction? Like in a big picture way [/INST] Yeah, like you calculate a few moves ahead and then you evaluate because a lot of, a lot of time, a lot of the times you cannot um the branch has become so big that you kind of calculate everything. So you </s><s>[INST] have a fog [/INST] Yeah, so you have to you have to make evaluations based on, you know, based based mostly on the knowledge and intuition and somehow I seem to do that uh pretty well </s><s>[INST] when you say you're good at short lines, what's that, what's what's short, [/INST] That's usually like lines of um 2-4 moves each. </s><s>[INST] Okay so that that's directly applicable to even faster games like blitz chess and so on. [/INST] Yeah blitz as a lot about calculating forest lines. So those you can see pretty clearly that the players who struggle applets who are great at classical are those who rely on deep calculating ability because you simply don't have time for for that and lets you have to calculate quickly and rely a lot on intuition. </s><s>[INST] Can you try to I know it's really difficult. Can you try to talk through what's actually being visualized in your head? Is there is there a visual component? Yeah, [/INST] no I just visualized the board. I mean the board is in is in is in my head </s><s>[INST] two dimensional. [/INST] My interpretation is that it's it is 2,2 dimensional </s><s>[INST] like what color is it brown tinted? Is it black? Is it uh like what's the theme? Is it a big board, small board? Are the, what do the ponds look like or is it more in the space of concepts like uh [/INST] Yeah there are there aren't a lot of colors. It's it's mostly </s><s>[INST] so what is the queen's gambit on the ceiling [/INST] whatever to to imagine. What </s><s>[INST] about when you do the branching, when you have multiple boards and so on what how does that look? [/INST] It's only one at a time. So </s><s>[INST] position and one [/INST] position at a time and then I go back and and that's what when when people play or at least that's what I do when I play blindfold chess against several people then it's just always one word at a time and the rest are stored away somewhere. </s><s>[INST] But how do you store them away? So like you went down one branch you're like all right, that's I got that. I understand that. That's there's some good there, there's some bad there. Now let me go down another branch. Like how do you store away the information just put on a shelf kinda? [/INST] I I try and store it away. Sometimes I have to sort of repeat it because I forget. Um And it does happen frequently in games that um you're thinking for, especially if you're thinking for long let's say a half an hour or even more than that that you play a move and then your opponent place and move. Then you play a move and they play move again and you realize oh I actually calculated that, I just forgot about it. Um So that's obviously what happens when you store the information and you cannot retrieve it </s><s>[INST] When you think about a move for 2030 minutes. Like how do you break that down? What can you describe what like what's the algorithm here that takes 30 minutes to run? [/INST] 30 minutes is uh at least from you. It's usually a waste um 30 minutes usually means that I don't know what to do. I'm trying </s><s>[INST] just running into the wall [/INST] Over, I'm trying to find something that isn't there? I think um 10-15 minutes things and complicated positions can be really, really Helpful. Then you can spend your time pretty um efficiently. Um just it just means that the branches are getting getting wide. There's a there's a lot to um to run through um both in terms of calculation and a lot you have to evaluate as well and then based on based on that 10-15 minutes think you you have a pretty good idea what to What to do. I mean it's it's very rare that I would think for half an hour and I would have a eureka moment during the game. Like if I haven't seen it in 10 minutes, I'm probably not gonna see it at all. You're </s><s>[INST] going to different branches and like after 15 minutes, it's like [/INST] mainly to the middle game because when you get to the end game, it's usually brute force calculation that makes you spend so much time. So middle game is normally, it's it's it's a complicated mix of brute force calculation and and uh and like creativity and and evaluation. So endgame, it's it's it's more, it's easier in that sense? </s><s>[INST] Well you're good at every aspect of chess, but you're also your end game is legendary. It baffles experts. So can you linger on that, then try to explain what the heck is going on there, Like if you look at game six of the previous world Championship, uh the longest game ever played in chess, it was uh I think his queen versus your rook knight and two pawns. There's so many options there, it's such an interesting little little dance and it's kind of not obvious that it wouldn't be a draw. So how do you escape the it not being a draw and you win that match? [/INST] No, I knew um that for most of the time it was a theoretical draw since um chess with seven or less pieces on the board is solved. So you can, like people who are watching online, they can just check it, they can check and they can check a so called table base and they it just gonna spit out win for white win for black or a draw. So and also I knew that I knew that didn't know that position specifically, but I knew that it had to be a draw. So for me it was about staying alert first of all trying to look for the best way to put my pieces. But yeah, those end games are a bit, they're a bit unusual, they don't happen too often. So what I'm usually good at is I'm using my my strength that I also use and in middle games is that I evaluate well and I calculate short variations quite even </s><s>[INST] for the endgame short variations [/INST] matter. Yes, it does matter in some simpler endgames. Yeah, but also like there are these theoretical endgames with very few pieces like rook nights uh and two pawns versus queens. But a lot of end games are simply defined by the queen's being exchanged and there are a lot of other pieces left and then it's usually not brute force, it's usually more of understanding and evaluation and then then I can use my my strengths very well. </s><s>[INST] Why are you so damn good at the end game? Isn't there a lot of moves from when the end game starts to when the endgame finishes and you have a few pieces you have to figure out. It's like a sequence of little games that happens right? Like little pattern like how how does it being able to evaluate a single position lead you to evaluate a long sequence of position that eventually lead to a checkmate. [/INST] Well I think if you evaluate well at the start, you know what plans to go for and then usually the play from there is is often pretty simple, let's say you understand how to arrange your pieces and often also how to arrange your ponds early in the end game then that makes all all the all the difference. And after that is like what we call technique very often that it's technique basically just mean means that the moves are simple and uh these are moves that you know, a lot of players </s><s>[INST] could, could [/INST] make, not only not only the very strongest ones, these are moves that are kind of understood and unknown. </s><s>[INST] So with the evaluation, you just constantly improving a little bit and that just leads to suffocating the position and then eventually to the wind as long as you're doing the evaluation Well, one step at a time [/INST] to some extent also. Yeah, as I said, like if you valued it better and thus accumulated some some small advantages, then you can, you can often make your your your life pretty easy towards the end of the endgame. </s><s>[INST] So you said in 2019 sort of the second phase of why you're so damn good. You you did a lot of opening preparation. What's the goal for you of the opening game of chess is to throw the opponent off from any prepared lines. Is there something you could put into words about why you're so damn good at the openings [/INST] again, these things have changed a lot over time. Back in Kasparov's days for instance, um he very often got huge advantages from the opening as as white can </s><s>[INST] explain why [/INST] there were several reasons for, for that. First of all, he, he worked harder, he was more creative and finding ideas. He was able to look places, others didn't also, he had a very strong team of people who had specific strengths in, in openings that he could use. So </s><s>[INST] they would come up with ideas and he would, he was integrate those ideas into. Yeah. [/INST] And they would also very often come up with them, them himself also at the start, he had some of the first computer engines to, to work for him to, to find his ideas to look deeper, to verify his ideas. He was better at using them than a lot of others. Now, I feel like the playing field is a lot more level. There are both computer engines, neural networks and hybrid engines available to practically anybody. So it's, it's much harder to find ideas now that that actually like give you an advantage with the white pieces. I mean people don't expect to find those ideas anymore. Now it's all about finding ideas that are missed by the engines, either they're missed entirely or their missed at low depth. Uh, and using them to, you know, gain some advantage in the sense that you have more more knowledge and uh, you know, it's also good to know that usually these are not complete bluffs, these are like semi bluff so that you know, that even if your opponent makes all the right moves, you can still make a draw. And also at the start of 2019 neural networks had just started to be a thing in chess and I'm not entirely sure, but there were at least some players in, even in the top events you, you could see did not use them or did not use them in the right way and then you can gain a huge advantage because a lot of positions they were being evaluated differently by the neural networks than traditional chess engines because they simply think about chest in a very, very different way. So short answer is these days it's all about surprising your, your opponent and taking it into position where you have more, more </s><s>[INST] knowledge. So is there some sense in which it's okay to make suboptimal quote unquote moves [/INST] you have to, I mean you have to because the best moves have been analyzed to death mostly. So </s><s>[INST] that's kind of when you say something bluff, that's a kind of sacrifice. You're, you're sacrificing the optimal move, the optimal position so that you can take the opponent. I mean that's a game theoretic, you take the opponent to something they didn't prepare. Well [/INST] yeah, but you could also look at it another way that regardless, like if you turn on whatever engine you turn on, like if you try to analyze either from the starting position or the starting position of some popular opening. Like if you analyze long enough it's always going to end up in a draw. So in that sense you may not be going for like the objective, the trials that are objectively the most difficult to draw against. But you know you are trying to look at least at the less obvious path. </s><s>[INST] How much do you use engines to use Leila stock fish in your preparations? [/INST] My team does personally, I try not to use them too much on on my own because I know that when I play you can obviously cannot have help from from engines and often I feel like often having imperfect or knowledge about a position or some engine knowledge can be a lot worse than than having no knowledge. So I try to look at engines as little as possible. </s><s>[INST] So yeah, so your team uses them for research for generation of ideas but you are relying primarily on your human resources. [/INST] Yeah, for sure. You </s><s>[INST] can evaluate well, you don't leave [/INST] and I can evaluate as a human. I can know what they find unpleasant and, and, and so on and it's very often the case for me to some extent, but a lot for for others that you arrive in a position and your opponent plays a move that you didn't expect and you know, if you didn't expect it, you know that it's probably not a great move since it hasn't been expected by by the engine, but if it's not, if it's not obvious why it's not a good move, it's usually very, very hard to figure it out. And so then looking at the engines doesn't necessarily help because at that point like you're facing a human, you have to sort of think as a human, </s><s>[INST] I was chatting with the demonstrates Abbasi of deepmind a couple of days ago and he asked me to ask you about what you first felt when you saw the play of Alpha Zero, like interesting ideas, any creativity um did you feel fear that the machine is taking over? Did you, were you inspired? And and what, what was going on in your mind and heart? [/INST] Funny thing about them is, is he he doesn't play chess at all? Like, like an Ai he plays in a very, very human way? No, I was hugely inspired when I, I saw the games at first. Um and in terms of man versus machine, I mean that battle was, was kind of lost for humans even before I enter top level chess. Um so that's never been an issue for me. I never, never liked playing as computers much anyway, so, so that's completely fine. But it was amazing to see how they, quote unquote, thought about chess and in such a different way and in a way that you could mistake for creativity, </s><s>[INST] mistake for strong words. Uh is it well to you, how many sacrifices? It's willing to make that like sacrifice pieces and then wait for prolonged periods of time before doing anything with that. Is that is that weird to you, that that's part of chess? [/INST] No, it's one of the things that's hardest to replicate as a human as well, or at least from my playing playing style that usually when I, I sacrifice, I feel like I'm, you know, I don't do it unless I feel like I'm getting something like tangible, uh, in, in return and like </s><s>[INST] a few moves down the line. [/INST] If you move down the line, you can see that you can either retrieve the material or you can put your opponent's king under pressure or have some very like very concrete positional advantage that sort of compensates for it for instance in chest. So bishops and knights are fairly equivalent. Um, we both give them three points, but bishops are a little bit better and especially a bishop pair is a lot better than, than a bishop and a knight. So, or especially two nights depends on the position, but like on average they are so like sacrificing a pawn in order to get, get a bishop pair. That's one of the most common sacrifices in. </s><s>[INST] Yeah, [/INST] I mean it depends on the situation, but generally that's fine. And there are a lot of openings that are based on that, that you sacrifice a pawn for the bishop pair and then eventually it's some sort of positional equality. Um, so that's fine. But the way alpha zero would, would sacrifice a night or sometimes £2.03 ponds </s><s>[INST] and you can [/INST] see that it's looking for some sort of positional domination, but it's, It's hard to understand and it's um, it was really fascinating to see. Um, yeah, in 2019 I was sacrificing a lot of lot of ponds especially and it was, it was a great joy. Unfortunately, it's not so easy to continue to do that. People, people have found a more solid opening lines since that don't allow me to, to do that as often. I'm still trying both to get those positions and still trying to, to learn the art of, of sacrificing pieces. </s><s>[INST] So demos also made a comment that was interesting to my new chess brain, which is one of the reasons that chess is fun is because of the quote creative tension between the bishop and the knight. So you're talking about this interesting um, difference between the two pieces that there's some kind of, how would you convert that? I mean that's like a poetic statement about chess. I think he said that. Why is chess been played for such a long time? Why is it so fun to play at every level that if you can reduce it to one thing is it's the bishop and the, and the night some kind of weird dynamics that they create in chess. Is there any truth to that? [/INST] It sounds very good. I haven't tried a lot of other games, but I tried to play a little bit of soggy and for my new brain um, comparing it to chess. What annoyed me about that game is how much the pieces suck basically you have one rook and you have one bishop that move like in chess and the rest of the pieces are really not very powerful. So I think that's one of the attractions of chest like how powerful especially the queen which </s><s>[INST] interesting [/INST] I kind of think makes it makes a lot of fun. </s><s>[INST] You you think power is more fun than like variety [/INST] you know there is a variety of but </s><s>[INST] not much more so than like like [/INST] so </s><s>[INST] like night I mean they all move in different ways. They're all like weird. There's just all these weird patterns and positions that can emerge. The difference in the pieces create all kinds of interesting dynamics I guess is what I'm trying to say. [/INST] Yeah and I guess it is quite fascinating that all those years ago they created the knight and the bishop without probably realizing that they would be almost equally equally strong with such different qualities. </s><s>[INST] That's crazy that this you know that like when you design computer games it's like an art form, it's a science and an art to balance it. You know, you talk about starcraft and all those games like so that you can have competitive play at the highest level with all those different units and in the case of chess it's different pieces and they somehow designed the game that was super competitive but there's probably some kind of natural selection that the chest just wouldn't last if it was designed poorly. [/INST] Yeah and I think the rules have changed over time a little little bit But I would be I mean speaking of games and all that, I'm also interested to play other other games like just 960 or Fischer random as they call it like that. You have 960 maps instead of one. </s><s>[INST] Yeah. So for people who don't know Fischer Random Chess Chess. 960s. [/INST] Yeah, that basically just means that the quants are in the same way and the major pieces are distributed randomly on the on the last rank, only that there have to be obviously bishops of opposite color and the king has to be in between the rocks so that you can cancel both ways. You </s><s>[INST] can still castle and you [/INST] can still castle, but it makes it interesting. So you still have it still castles in the same way. So let's say the king is like, </s><s>[INST] yeah, what happens in that case? [/INST] Yeah, let's say the king is in the corner. Um so to, to castle this side, you have, you have to clear a whole lot of pieces. </s><s>[INST] No, [/INST] the king would go here and the rook would go there. Um and that's happened in my games as well. Like I forgot about Castling and I've been like attacking a king over here and then all of a </s><s>[INST] sudden escapes [/INST] to the other side. I think um I think Fischer chess is, is good that it it's the maps will generally </s><s>[INST] be [/INST] worse than regular chest. Like I think the starting position is as close to ideal for creating a competitive game as possible. But they will still be like interesting and diverse enough that you can play very, very interesting games. </s><s>[INST] So when you say maps, there's 960 different options and like what fraction of that creates interesting games at the highest level. This is something that a lot of people are curious about because when you challenge a great chess player like yourself to uh, to look at a random starting position that feels like it pushes you to play pure chess versus memorizing live [/INST] for sure for sure. But that's that's the whole idea. Yeah, that's what you want and how </s><s>[INST] hard is it to play? Can you talk about what it feels like to you to play with a random starting position? Is there some intuition you've been building up? [/INST] It's very, very different and I mean understandably engines have an even greater advantage in 960 than they have in, in classical chess? No, it's, it's super interesting and that's why also I really wish that we uh played more classical chess like long games, 4 to 7 hours and in um Fischer random chess chess 9 60 because then you really need, you really need that time, even on the first moves, what usually happens is that you get 15 minutes before the game, you, you're getting told the position 15 minutes before the game and then you, you can think about it a little bit even, you know, check the computer but that's all the time you have, but then you really need to figure it out </s><s>[INST] and like [/INST] some of the positions obviously are a lot more interesting than the others in some of them. It appears that like if you don't play symmetrically at the start, then you're probably going to be in a pretty bad, bad position </s><s>[INST] with [/INST] the ponds. Yeah, </s><s>[INST] so that's the thing [/INST] About, that's the thing about chess though. So let's say why it opens with E4, which is, which has always been the most played move. There are many ways to meet that, but the most solid ways of playing has always been the symmetrical response with the five and then there's the Lopez, there's um, there's the Petrova opening and and and so on and if you just banned symmetry on the first move and just, you would get more interesting games or you you get more decisive decisive games. So that's the good thing about justice that we've played it so long that we've actually devised non symmetrical openings that are also fairly equal and </s><s>[INST] default. [/INST] But yeah, symmetry is a good default. And it's a problem that by playing symmetrical armed with good preparation in regular chess is just a little bit too easy too, it's a little bit too to drive. And um I guess if you analyze, if you analyze a lot in, in just 9 60 then um the a lot of the position would end up being um, pretty dry as well. Um, but </s><s>[INST] because the random starting point so shitty, you're forced to, [/INST] you're actually forced to play symmetrically. Like you cannot actually try and play in a more sort of interesting, interesting manner. </s><s>[INST] Is there any other kind of variations that are interesting to you? Oh [/INST] yeah, there are, there are several, so no Castling chess husband has been promoted by former world champion Vladimir Kramnik. There have been a few tournaments with that. Not any that I've participated in though. Um, I kind of like it also, my coach uses like non castling engines quite a bit to analyze regular positions to just to get a different, different perspective. So </s><s>[INST] Castling is like a defensive thing. So if you remove castling it forces you to be more offensive. Is that why? Yeah, [/INST] just yeah, for sure. Um, </s><s>[INST] it seems like a difference. Um, [/INST] no Castling probably forces you to be a little bit more defensive at the start or I would guess so because you cannot suddenly escape with them with the kings that it's going to make the game a bit slower at the start. But I feel like eventually it's gonna, it's going to make them more games more. Well let's drive for for sure. Then you have some reader variants like um, where the ponds can move both diagonally and and forward. Uh, and also you have self capture chest, which is quite interesting. So the ponds can or </s><s>[INST] commit suicide or [/INST] yeah, people can, </s><s>[INST] why would that be a good move? [/INST] No, sometimes one of your pieces occupy a square. I mean let me just set up a position. Let's put it </s><s>[INST] like [/INST] like this for instance, like here, I mean there are a lot of ways to checkmate for white like this for instance or there are several ways. Um, but like this would be uh, would be </s><s>[INST] uh cool for people who are just listening. Yeah, basically you're bringing in a night close to the the whole the king and the queen and so on and you replace the night with the queen. Yeah, that's interesting. So you can have like a front of of pieces and then you just replace them with the with the second. Yeah, [/INST] I mean that could be interesting. I think also maybe sometimes and it's just clearance basically it adds an extra element of, of, of clearance. So I think that there are many um, many different variants. I don't think any of them are better than the one that has been played for at least 1000 years. But it's certainly interesting to um, to see </s><s>[INST] So one of your goals is to reach the chest rating of 2900. Maybe you can comment on how's this rating calculated and what does it take to get there? Is it possible for a human being to get their, [/INST] Basically you play with the factor of um 10, which means that if I were to play against um an opponent who is rated the same as me, I would be expected score 50% obviously and that means that I would win five points with a win, lose five points with the draw and then equal if I, if I draw, if your opponent is 200 points lower rated, you're expected to score 75% and and and so on and </s><s>[INST] you establish that rating by playing a lot of people and then it slowly converges towards an estimate of how likely you are to win or lose against [/INST] different. And uh my rating is obviously carried through thousands of, of games. Um right now my rating is 28 60 </s><s>[INST] one, which [/INST] is decent, like I think that pretty much corresponds to to the level I have at at the moment, which means in order to reach 2900, I would have to either get better at chess, which I think is fairly hard to to do at least considerably better. So what I would need to do is try and optimize even more in terms of </s><s>[INST] preparations [/INST] everything, but not, not, not necessarily like selecting tournaments and so on, but like just optimizing in terms of of preparation, like making sure I'm um I never have any bad days and </s><s>[INST] you basically can't lose [/INST] Yeah, I basically can't suck up ever if I wanna if if I want to reach that goal and so I think reaching 2900 is pretty unlikely um the reason I have set the goal is to have something, to to play for it to have like to have a motivation to actually try and and be at my best when I play because otherwise I'm playing to some extent mostly for for fun these days in that I love to play, I love to try and win, but I don't have like a lot too, I don't have a lot lot to prove or anything, but that gives me at least the motivation to try and try and be at my best all the time, which I think is something to um to, to aim for. So at the moment I'm quite enjoying that process of um of trying to um yeah, trying to optimize </s><s>[INST] what would you say motivates you in this now and in the years leading up to now, the love of winning or the fear of losing. [/INST] So for the World Championship, it's been fair of losing for sure. Other tournaments, love of winning is great, great factor and that's why I also get more joy from, from winning most tournaments than I do for winning the World Championship because then it's mostly been a a relief, I also think I enjoy winning more now than I did before because I feel like I'm a little bit more relaxed now and um I also know that it's, you know, it's not gonna last forever, so every, every little one, I I appreciate, appreciate a lot more now. And yeah, in terms of fear, fear of losing, like that's a huge reason why I'm not going to play the World Championship because I it really didn't didn't give me give me a lot of joy. It really was all about avoiding losing. </s><s>[INST] Why is it that the World Championship really makes you feel this way? The anxiety. So, and when you say losing, do you mean not just the match, but like every single position? Like, like the fear of a blunder? [/INST] No, I mean the blunder is okay, like when I sit down at the board then it's it's mostly been fine because then then I'm focused on God, then I'm focused on the game and then I know that I can play the game. It's a time like in between like, knowing that, you know, I feel like losing is not an option because it's the World Championship and because in the World Championship, there are two players, there's, there's a winner and a loser. If I don't win a random tournament that I play, then, you know, I'm usually, </s><s>[INST] it [/INST] depends on the tournament, I might be disappointed for sure, might even be pretty piste, but ultimately, you know, you go onto the next one with the World Championship, you don't go on to the next one. It's like, it's years and it also has been like, it's been a core part of my identity for a while now that I am world champion and so there is not an option of Yeah, </s><s>[INST] yeah, there's uh, you're gonna have to at least for a couple of years carry the weight of having lost your the former world champion. Now if you lose versus the current world champion, there are certain sports that create that anxiety and others that don't. For example, I think UFC like mixed martial arts are a little better with losing, its understood like everybody loses but [/INST] not everybody, </s><s>[INST] not everybody, not everybody, not everybody could be bent into the chat. Uh, but in boxing there is like that extra pressure of like maintaining the championship. I mean maybe you could say the same thing about the UFC as well. So for you personally, for a person who loves chess the first time you won the world championship, that was, that was the big, that was the thing, that was fun. [/INST] Yeah. </s><s>[INST] And then everything after is like stressful, [/INST] essentially there was certainly stress involved the first time as well. Um, but it was nothing compared to uh compared to the others. So the only world championship after that that I really enjoyed was the one in 2018 against the American Fabiano Caruana and what that made that different is that I've been kind of slumping for a bit and he had been on the rise. So our ratings were very, very similar. They were so close that if at any point during the, during the match I had lost the game, um he would have been ranked as number one in the world. Like our ratings were so close that for each draw they didn't move. And </s><s>[INST] the game itself was close. [/INST] Yeah, the games themselves were very close. I had a winning position in, in the first game that I couldn't really get anywhere for a lot of games that he he had a couple of games where he could potentially have won, um, than in the last game, I was a little bit better. And eventually there they were all, they were all drawn, but I felt like all the way that this is an interesting match against an opponent who is at this position at this point equal to me. And so losing, that would not have been a disaster because all in all the other matches, I would know that I would have lost against somebody who I know I'm much better than, and that would be would be a lot harder for me to, to take. </s><s>[INST] Well, that's fascinating and beautiful. That the stress isn't from losing this because you have fun. You enjoy playing against somebody who's as good as you may be better than you. That's exciting to [/INST] you. Yeah, </s><s>[INST] it's, it's, it's losing at this high stakes thing that only happens rarely to a person who's not as good as you. [/INST] Yeah, and that's why it's also been incredibly frustrating in other matches, like when I know when we play a draw after draw and I can just, I know that I'm better, I can sense during the game that I understand it better than them, but I cannot, you know, I cannot get over the hump. </s><s>[INST] So you are the best chess player in the world and you're not playing the World Championship really makes the World Championship not seem important or I mean there's an argument to be made for that. Um is there anything you would like to see if you could change about the World Championship that will make it more fun for you and better for the game of chess period for everybody involved. [/INST] So I think 12 games or now 14 games that there is for the World Championship is a fairly, fairly low sample size. If you want to determine who the best player is or at least the best player in that particular matchup, you need more more games. And I think to some extent </s><s>[INST] if [/INST] you're going to have a world champion and call them the best players, your best player, you've got to make sure that the format increases the chance of finding, finding the best players. So I think having more games and if you're gonna have a lot more games, then you need to then you need to decrease the time control of it, which in turn I think is also a good thing because in very long time controls with deep preparation you can sort of mask a lot of your deficiencies as, as, as a chess player um with because you have a lot of time to think and to defend and also yeah you have the preparation um so I think those would be for me to play those would be the main, the main, the main things more, more games and and less time. </s><s>[INST] So you want to see more games and rules that emphasize pure chess. [/INST] Yeah, but already less time emphasize emphasize is pure pure chess because um defensive techniques are much harder to execute with with little time. </s><s>[INST] What do you think? Is there a sweet spot in terms of, are we talking about blitz, how many [/INST] places? A bit too fast? Um to their credit, this was suggested by by feet as well for a start to have two games per day and let's say you have 45 minutes again plus 15 or 30 seconds per move. That means that each sessions will probably be about or a little less than two hours. That would be would be a start also, what's what we're playing in the tournament that I'm playing here in, in, in Miami which is um four games a day with 15 minutes plus 10 seconds per move. Those who would be more interesting than than the one there is now and I understand that there are a lot of traditions, people don't want to change the world championship. That's that's all fine. I just think that um the world championship should do a better job of trying to reflect who who's the best overall chess player. </s><s>[INST] So would you would you say like if it's faster games you probably be able to get a sample size of like over 20 games, 2030, 40 you think there's a number that's good over a long period of time. [/INST] I would prefer as many as possible. </s><s>[INST] Like 100. [/INST] Um Yeah but let's say you play 12 days two games today you know that's 24. I feel like that's already quite a bit better. You play like one black game, one white game each day. </s><s>[INST] That's okay. [/INST] Yeah I think that's fine like you will have three days as well so I don't think that will be will be a problem. Um And also you have to prepare two sets of openings for each day which makes it more difficult for the teams preparing. I think it's also </s><s>[INST] good. Let me ask you a fun question. If Hikaru Nakamura was one of the two people what? I guess I apologize. [/INST] Yeah he could have, he could have finished second so he lost the last round of the candidates </s><s>[INST] and you maybe you can explain to me internet speak opium is something you tweeted. [/INST] Yeah </s><s>[INST] but if he if he got second would you would you would you just despite him still still play the world championship that's Internet question And when the internet asks us to abide the do divides. [/INST] Yeah, sure. Thank you. Internet. So after the last match I did an interview right after where I talked about the fact that I was unlikely to play the next one. I'd spoken privately to both family friends and of course also my chest team that this was likely going to be the last, The last match. Um what happened was that right before the World Championship match there was this young player salaries of Russia. He had a dramatic rise. He rose to second in the world rankings. He was 18, then 19, he's 19 now he qualified for the candidates and it felt like there was like at least a half realistic possibility that </s><s>[INST] he [/INST] could be the challenger for the next world Championship and that sort of lit a fire under me. Um </s><s>[INST] yeah, I [/INST] like that. I like that a lot. I love the idea of of playing him in the next world Championship and originally I just, I was sure that I wanted to announce right after the tournament the match that this was it. I'm done. I'm not playing the next one, but this lit a fire under me. So that made me think, you know, this actually motivates me and I just wanted to get it out there for several reasons to create more hype about the candidates to like sort of motivate myself a little bit, maybe motivate him Also, Obviously I wanted to give people and people a heads up for the candidates that you might be playing for more than more than first place. Like normally the candidates is it's first place or bust. It's like the world championship. Um and then, so Nakamura was one of many people who just didn't believe me, which is fair because I've talked before about not, not necessarily wanting to to defend again, but I never like talked as concretely was as serious as this time. So he simply didn't believe me and he was very vocal about that and he said, nobody believed me. No, no other other players which may or may not have been true. And then yeah, he lost, he lost the last game and he didn't didn't qualify. But to answer the question no, I already at that point decided that I wouldn't, wouldn't play, I would have liked it less if he had, if you have not lost the last round, </s><s>[INST] but the decision, [/INST] but the decision was already was already made. </s><s>[INST] Does it, does it break your heart a little bit that you're walking away from it in all the ways that you mentioned that it's just not fun. There's a bunch of ways that doesn't seem to bring out the best kind of chess, it doesn't bring out the best out of you in the particular opponents involved. Does it just break your heart a little bit like you're walking away from something or maybe the entire chest community is walking away from a kind of a historic event that was so important in the 20th century at least. [/INST] So I won the championship in 2013. I said no to the candidates in 2011. I didn't particularly like the format. I also wasn't, I was just not in the mood, I didn't want the pressure that was connected with the World Championship and I was perfectly content at the time to play the tournaments that I did play. Um also to, to be ranked number one in the world. I was comfortable with the fact that I knew that I was, I was the best and I didn't need a title to, to show others. Um And what happened later is I suddenly decided to play um in 2013 I liked, they changed the format, I liked it better. Um I just decided, you know, it could be interesting, let's try and get this. Um there were, there really wasn't more than more than that to it. It wasn't like fulfilling, fulfilling a lifelong dream or anything. I just thought, you know, let's, let's play. Um </s><s>[INST] it's just a cool tournament. It's [/INST] a cool school tournament. It's a good challenge, you know, why not? It's, it's something that could be a motivation, it motivated me to get in the, In the best shape of my life that had been till then. So it was a good thing uh and 2013 match brought me a lot of, a lot of joy as well. So I'm very, very happy that I that I did that, but I never had any thoughts that I'm gonna like keep the title for for a long time immediately after the match in 2013. I mean also before the match, I've spoken against the fact that the champion is seeded into the final, which I thought was unfair. After the match, I made a proposal that we have a different system where the champion doesn't have these privileges and people's reaction, both players and chess community was general generally like, okay, we're good, we don't, we don't want that, you keep your privileges. I was like, okay, whatever, </s><s>[INST] so you want to fight for it every time. [/INST] Yeah, I want that. </s><s>[INST] Uh I have to ask just in case you have an opinion. Uh if you can maybe from a fantasy chess perspective analyze uh Ding versus NEpo who wins the current, the two people that would play if you're not playing [/INST] generally, I would consider that doing houses slightly better overall chess strength. Um </s><s>[INST] what are the strengths and weaknesses of each, if you can kind of summarize it. [/INST] Um so napoli his even better at calculating short lines than I am. Um but he can sometimes like a little bit of little bit of depth, like he's in short lines, he's an absolute calculation monster. He's extremely, he's extremely quick, but he can sometimes like a bit of death. Also recently he's improved his openings quite a bit. So now he um, he has a lot of lot of good ideas and it's very, very solid. Um Ding is not quite as well prepared, but he has an excellent understanding of dynamics and imbalances in, in chess. I would, I would say, what </s><s>[INST] do you mean by imbalances? [/INST] Um, imbalances like bishop, bishops against knights and material imbalances? </s><s>[INST] You can take advantage of those. [/INST] Yes, I would say he's very, very good at that. And understanding the, you know, the dynamic factories as we call them like material versus time especially </s><s>[INST] I think got the better of him and the candidates. So what's your sense why Ding has an edge in the, in the championship? [/INST] I feel like individual past results hasn't necessarily been a great indicator of world Championship results. I feel like overall stress strength is more More important. I mean to be fair, I only think like thing has a very small edge like differences not big at all. But our individual had to had record was probably the main reason that a lot of people thought had a good chance against me as well. It was like 4-1 in his favor Before the match. But that was just another example of why that may not necessarily mean anything also in our case it was a very, very low sample size I think about the size of the, of of the match in total 14 games. And that generally doesn't doesn't mean much. How </s><s>[INST] Close were those games would you say in your mind for the previous championship? So that game six was a turning point where you won? Um was there any doubt in your mind that you know, like if you do a much larger sample size, you'll get the better of nip? Oh [/INST] no, no larger, larger sample size is always good for me. So, World championship, it's a great parallel to to football because it's a low scoring </s><s>[INST] game. [/INST] And if the better player or the better team scores, they win most of the </s><s>[INST] time. That's generally for for big for championships or in general. [/INST] Yeah, for for championships like they generally generally win because the other slightly weaker team, they're good enough to defend to make it very, very difficult for the others. But when they actually have to create the chances, then they have no chance. And then very often ends with a blowout, as it did in our our match. If I hadn't won game six, it probably would have been very, very close. He might have edged it. There's obviously a bigger chance that I would have edged it. But this is just what happens a lot in in chess, but also in in in football that matches our clothes and then they </s><s>[INST] somebody, somebody [/INST] scores and things, things change and this gives people the illusion that the matchup was very close. Which while actually just means that the nature of the game makes the matches close very often, but it's always much more likely that one of the teams is gonna, or one of the players is gonna break away than the others. And in other matches as well, even though a lot of people before the match in 2016 against uh, against car hierarchy and there were people who thought before the match that I was massively overrated as, as, as a favorite and that essentially the match was pretty, pretty close like whatever, uh, 60, 40 or some people even say like 55, And what I felt was that match when very, very wrong for me and I still won and some people saw that as an indication that pretty much probabilities were probably a bit closer than people thought. Well I would look at it in that in the way that everything went wrong and I I still, I still one which probably means that I was pretty big favorite to begin with. </s><s>[INST] I do have a question to you about that match. But first, so Sergei Carjacking was originally a qualifier for the candidate tournament but was disqualified for breaching the code of ethics after publicly expressing approval for the 2022. Russian invasion in Ukraine when you look at the Cold War and some of the US versus Russian games of the past. This politics, the some of this geo politics politics ever creep its way into the game. Do you feel the pressure, the immensity of that as it does sometimes for the olympics? You know these big nations playing each other, competing against each other almost like fighting out in a in a friendly way the battles, the tensions that they have in the space of geopolitics. [/INST] I think it still does. So the president of the World Chess Federation who was just reelected is is a Russian like I like him personally for sure, but he is quite connected to the Kremlin like and it's quite clear that the Kremlin considers it at least a semi important goal to bring the chess crown home to to Russia. So it's still it's still definitely a a factor and I mean I can answer for in the Carjacking case like I don't have a strong opinion on on whether he should have been banned or not. Obviously I don't agree with anything that he he says, but in principle, I think that you should ban either no Russians or all Russians um generally not particularly against either. But I don't love banning wrong opinions even if there are um as reprehensible as assets have been. </s><s>[INST] Yeah, there's something about the world chess championships or the olympics or it feels like banning is counterproductive to the alleviating some of the conflicts, [/INST] we don't know this is the thing though. We really don't know about the long term conflicts and a lot of people try to do the right the right thing in this sense, which I don't really blame at all. It's just that it's just that we don't know. And I guess sometimes it's, there are other ways you want to try and trying to help as well, </s><s>[INST] like within the competition, within some of those battles of us versus Russia or so on of the past, there's also between the individuals. Um maybe you'll disagree with this, but from a spectator perspective, there's still a camaraderie, like at the end of the day, there's a thing that unites you, which which is this like, appreciation of the fight over the chessboard. It's um even if you hate each other. [/INST] Yeah, for sure. I think for every every match that's been, you would briefly discuss the game with your opponent after after the game, no matter how much you hate each other. And I think that's lovely. And Kasparov, I mean, he was quoted like when somebody in his team asked him like, why, why are you talking to after the game? Like he you hate that guy? And he's like, yeah, sure, but he's the only one who understands </s><s>[INST] Yeah, the only one who understands. [/INST] So that's no, I think that's really lovely and I would love to see that in other in other areas as well that you can, regardless of what happens. You can have, you can have a good chat about the game, You can, you can just talk about the ideas with people who, who understand what you, what you understand. </s><s>[INST] So if you're not playing the World Championships, there's a lot of people who are saying that perhaps the world championships don't matter anymore. Do you think there's some truth to that? I [/INST] said that back a long time ago as well, that for me, I don't know if it never happened, so I don't know what would have happened, but I was thinking like the moment that I realized that I'm not the best player in the world, like I, I felt like morally I have to renounce the World Championship title, you know, because it doesn't mean anything as long as you're not the best player. So </s><s>[INST] the ratings really tell a bigger, a clear story. [/INST] I think. So at least at least over time, like I'm a lot more proud of my streak of being rated number one in the world, which is Now since I think the summer of 2011, uh I'm a lot more proud of that than than the world championships? </s><s>[INST] How much anxiety or even fear do you have before making a difficult decision on the chess board? So it's a high stakes game. How nervous do you get? How much anxiety do you have in all that calculations you're sitting there for 10, 15 minutes because you're in a fog, there's always a possibility of a blunder of a mistake. Are you anxious about it? Are you afraid of? [/INST] It really depends. Um I have been, I have been at times. I think the most nervous I've ever been was Game 10 of uh the world championships in 2018. Although that was just a thrilling game. I was black. Um I basically abandoned the queen's side at some point to attack him on the king's side. And I knew that my attack, if it doesn't work, I'm gonna lose. But I had so much adrenaline. So that was, that was fine. I thought I was gonna win. Then at some point I realized that it's not so clear and my time was ticking and I was just getting so nervous. I I still remember what happened like we played this time. Trouble face where he had fair little time, but I had even less. And I just remember, I cannot remember much of it just that when it was over, I was just so relieved because then it was clear that position was probably gonna peter out in um in a draw. Otherwise I'm often nervous before games. But when I get there, it's all business and especially when I'm playing, well, I'm never afraid of of losing when I when I play because I trust I trust my instincts, I trust my, my skills, </s><s>[INST] how much psychological intimidation is there from you to the other person, from the other person to you. [/INST] I think people would play a lot better if they played against an anonymous me. I would love to </s><s>[INST] you. [/INST] I would love to have a tournament online where let's say you play 10 of the best players in the world and you don't for each round, you don't know who you're playing. </s><s>[INST] That's an interesting question. You know like there's these like videos where people eat Mcdonald's or burger king or diet coke versus Pepsi. Would people be able to tell they're playing you like from the style of play do you think or from the strength of play [/INST] if there was a decent sample size? Sure. What </s><s>[INST] about you? Would you be able to tell others [/INST] into in just one game? Very unlikely. What </s><s>[INST] what sample size would you need to tell accurately? I feel like it's a science. [/INST] Yeah, I think 20 games would help a </s><s>[INST] lot. [/INST] Yeah. But I know that they've already developed ai butts that are pretty good at recognizing somebody's style </s><s>[INST] which [/INST] is um which is quite fascinating. Uh </s><s>[INST] And they'd be fascinating if those bots were able to summarize the style somehow. Maybe great attacking chest. Like some of the same characteristics you've been describing, Like great short line calculations, all that kind of [/INST] stuff. </s><s>[INST] I mean really, [/INST] really all the best chess players, there are basically just two camps? People who are good at long longer lines or or shorter lines. It's the hare and the tortoise basically. And sometimes you know, I feel like I'm the closest you can get to a hybrid of those because </s><s>[INST] you've got both your good in every position to the middle game and end game. [/INST] Yeah. And also I can I can think to some extent both rapidly and deeply which a lot of people that can do both. But I mean to to answer your question from before I think yeah, I sometimes can get a little bit intimidated by my opponent but it's mostly if there's something unknown, if it's mostly if it if it's something that I I don't understand fully and I do think especially when I'm playing well people, they just play more timidly against me than they do against each other sometimes without even realizing it. And I certainly use that to my my advantage. If I sense that my opponent is apprehensive, I sense that they're not gonna necessarily take all their chances. It just means that I can take more risk and I always try and try and find that balance </s><s>[INST] to shake them up a little bit. Yeah. What's been the toughest loss of your career that you remember? Would that be the the World Championship match? [/INST] Oh yeah, sure. </s><s>[INST] Can you take [/INST] 2016. </s><s>[INST] And who was it against [/INST] against in new york? You </s><s>[INST] Take it through the story of that game, where were you before that game in terms of game one through 7. [/INST] Yeah, so game one and two and not much happened. Games three and four, I was winning in both of them and normally I should definitely convert it both. I couldn't partly due to good defense on on his part, but mostly because I just I messed up. Uh and then after that games five, six and seven, not much happened, I was getting impatient that at that point. Um so for Game eight I was probably ready to take a little bit more risks than I had before, which I guess it was insane because I knew that he wouldn't beat me unless I beat myself like he wasn't strong enough to play me and </s><s>[INST] that was leading to impatient somehow and impatience. No, [/INST] Because I knew that I was better. I knew that I was better. I knew that I just needed to win one game and then the match is over. That's what happened in 2021 as well. Like when I won the first game against, I knew that the match was over. Unless I like funk up Royally then he's not gonna be able to beat me. So what happened was that I played a kind of an innocuous opening as whites just trying to get a game trying to get him out of book as soon as possible. Then </s><s>[INST] can you elaborate innocuous, get him out of the book. Uh [/INST] basically I I set up pretty defensively as white. I wasn't really crossing into his half at the start at all. I was just, I played more like a system more than like a concrete opening. It was like I'm going to set up my pieces this way you can set them up however you want and then later where sort of the armies are going to meet. I'm not gonna try and bother you at the start and </s><s>[INST] that means you can have with as many pieces as possible kind of pure chest in the middle game without any of the lines, the standard lines in the opening. [/INST] And so there was at some point a couple of exchanges, then some maneuvering a little bit better. Then he was sort of equalizing and then I started to take too many risks and I was still sort of fine. Um, but then at some point I realized that I've gone a bit too far and I had to be really careful. Now I just </s><s>[INST] froze, I [/INST] just completely froze uh </s><s>[INST] mentally, like [/INST] mentally </s><s>[INST] I [/INST] realized that I mean all the thoughts of </s><s>[INST] I [/INST] might lose this, what have I done? Why did I take so many risks? I knew that I could have drawn at any moment. Just be patient. Don't give him these opportunities. What </s><s>[INST] triggered that like face transition in your mind? [/INST] No, it was one </s><s>[INST] thing a [/INST] position on the board like realizing like there was one particular move he played that I missed and then like, and then I, I realized this could potentially not go my way. So then I made another couple of mistakes and he to his credit, like once he realized he had a chance, he was like, he knew that this was his one chance he had to take it. And so he did. And yeah, that's that's the worst I've ever felt after um after a chess game, I realized that I'm probably gonna lose my title against somebody who's not even close to my level and I've done it because of my own stupidity most of all. Uh and that was really, really um at the time, like I was all in my own head, that was, that was hard to deal with and I felt like I didn't really recover too much for the next game. So what I did, there was a free day after the eighth game, so I did something that I never did at any other world championship, like I after game eight, I just, I got drunk with my team and </s><s>[INST] a standard procedure. [/INST] No, no, that's that's the only time that's happening in the world championship during the match. So yeah, just try to forget. But still before game nine, game nine, I was a little bit more relaxed, but I was still a bit nervous then Game nine, I was almost lost as well. And then only game 10, Game 10, I was still, I wasn't in a great mood, I was really, really tense. Um the opening was good, </s><s>[INST] I [/INST] had some advantage, I was getting optimistic, then I made one mistake, he could have forced to draw and then the old old, the negativity came back. Like I was thinking during game like how I'm going to play for a win with black in the next game? Like what, what, what am I doing? And then, you know, eventually it ended. It ended well, didn't find the right line. I ground him down actually. I played at some point pretty well in the end game. And um after that game, like there was such a weight lifted. No, I after that there was like no thought of losing the match whatsoever. I knew that okay. I had basically gotten away with um not with murder but gotten away with something. </s><s>[INST] What can you say about the after game mate? Where are the places you've gone in your mind? Do you go to some dark places? We're talking about like depression. Do you think about quitting at that point? [/INST] No, I mean I think about quitting every time I lose the classical or at least I used to like, especially if it's in a stupid way, I'm thinking like, okay, if I'm gonna gonna play like this, if I'm going to do things that I know are wrong, then you know, I might as well quit. No, that's happened, that's happened a bunch of bunch of times and I've definitely gotten a bit more carefree about losing these days, which it's not necessarily a good thing, like my hatred of losing led to me not losing a lot. And it also lit the fire under me that I think my performance after losses in, In classical chess over the last 10 years, it's like over 2900. Like I really play well after a loss even though it's really, really unpleasant. So apparently </s><s>[INST] like, [/INST] I don't think the way that I dealt with them is particularly healthy, but it's worked, </s><s>[INST] it's worked so far. But then you've discovered now love for winning to where ultimately longevity wise creates more [/INST] fun. </s><s>[INST] What's the perfect day in the life of magnus carlsen on a day of big chess match, It doesn't have to be world championship, but if it's, if it's a chess match you care about what, what time do you wake up, what do you eat? [/INST] It depends on when the game is, but let's say the game is at three. I'll probably wake up pretty late at about 11, then I'll go for go for a walk. Might listen to some podcasts. Maybe I'll spend a little bit of time looking at some, you know, some NBA game from last night or whatever to </s><s>[INST] not just related stuff. [/INST] No, no, no, no. Uh then I'll I'll get back, I'll have a big lunch like usually like a big omelet with a bunch of salad and stuff, then go to the game win, like a very nice clean </s><s>[INST] game perfect day, [/INST] Just go back after relax. Like the things that make me the happiest that tournaments is just having a good routine and feeling feeling well. Um I don't like it when too much is happening around me. So the tournament that I came from now was um the chess olympiad, which is the team land. So we were a team Norway, we did horribly. I like I did okay, but the team in general did did horribly. No, no, it'll be us, but was based on one in the end, they were this amazing team of young players. It was really, it was really impressive. But the thing is like we had a good camaraderie in the team, we had our meals together, we played a bit of football when swimming and I couldn't understand why things went wrong and I still don't understand, but the thing is for me it was all very nice, but now I'm so happy to be on my own at the tournament just to have my own routines, not see too many people otherwise just have like a very small team of people that I see </s><s>[INST] you are a kind of celebrity now. So you know, people within the chess tournament and outside would recognize you want to socialize, I want to tell you about how much you mean to them, how much you inspire them all that kind of stuff does that get in the way for you when you're like trying to really focus on on the match. Are you able to block that? Like are you able to enjoy that those little interactions and still keep your focus? [/INST] Yeah, most of the time that's uh that's fine, as long as it's not too much. But I have to admit when I'm at home in Norway, I I rarely go out with like without big headphones and something. No, not just to block out the world otherwise, um </s><s>[INST] don't make eye contact. Yeah, [/INST] no. So the thing is </s><s>[INST] people [/INST] in general are nice. I mean people, they wish me well uh and they don't like bother me also when I have the headphones on, I don't notice as much people like turning around and all of that so I can be more of in my own world. So I like that. </s><s>[INST] Yeah. What about after the, in this perfect day after the game? Do you try to analyze what happened? Do you try to think through systematically or do you just kind of loosely think about like, [/INST] no, I just loosely think about it. I've never been very structured in, in that sense. Um I know that it was always recommended that you analyze your, your own games, but I, I generally felt that I mostly had a good idea about that. Like nowadays I will like loosely see what the engine says at a certain point if I'm curious about that. Otherwise I usually move on to the next, </s><s>[INST] what about diet, you said Alma and salad and so on. I heard in your conversation with the, with the other magnus magnus number two about your, you had like this bet about meat you want, you're gonna go vegan if you lose, I forget [/INST] which vegetarian </s><s>[INST] vegetarians and uh, you both have an admiration for me. Is there um, is there some aspect about optimal performance that you look for in food? Like maybe eating only like once or twice a day or a particular kind of food? Like meat heavy diet? Is there anything like that or you just try to have fun with the food? [/INST] I think um whenever I'm tournaments, like it's very natural to eat at least for me to eat only twice a day. So usually I do that when I'm at home as well </s><s>[INST] before you do eat before, determine though you don't, you don't play fasted? [/INST] No, no. Um but I try not to eat too heavy before the game or in general to avoid sugary stuff to have a pretty stable blood sugar level because that's the easiest way to make mistake that your, your energy levels just suddenly suddenly drop and they don't necessarily mean need to be too high as long as they're pretty stable. Yeah. </s><s>[INST] Have you ever tried playing fasted? Like, you know, like intermittent fasting? So playing without having eaten? I mean the reason I asked, you know, uh especially when you do a low carb diet when I have done a person in a low carb diet, I'm able to fast for a long time, like once a day, maybe twice a day. But I just, the mind is most focused on like really difficult thinking tasks when it's fasted, it's an interesting and a lot of people kind of talk about that you're able to kind of like zoom in and if you're doing a low carb diet, you don't have this energy, the energy stable. [/INST] No, that is true. Maybe that will be interesting to try. So what's happened for me if I played a few tournaments where I've had food poisoning and then that generally means that you're both sleep deprived and you have no energy. And what I've found is that it makes me to something, it makes me very calm of course, because I don't have the energy and it makes me super creative like being slipped. It probably, I think in general makes you creative just the first thing that goes away is the ability to do the simple things that that's that's what if it affects you the most like you cannot be precise. So that's the only thing I'm worried about. Like if if I'm faster that I will won't be, won't be um precise when I play, </s><s>[INST] but you might be more creative. It's an interesting. [/INST] Yeah, potentially. </s><s>[INST] What about you have been known to, on a rare occasion play drunk is their mathematical formula for sort of on the X axis, how many drinks you had and on the y axis, your performance slash creativity, is there like an optimal for like one of those, would you suggest for the feeding world championship that people would be required to drink? Would that change things in interesting ways? [/INST] Yeah, not at all. Um maybe for rapid, but for, for blitz. Think if you're playing blitz, you're mostly playing on, on short calculation and intuition and I think those are probably enhanced if you've had a little bit of, a little bit to drink, </s><s>[INST] can you explain the physiology of why that's why it's enhanced or the, [/INST] you're just, you're thinking less, you're more confident? </s><s>[INST] I think, I [/INST] think it's just confidence. I think also like a lot of people feel like they're better at speaking languages. For instance, if they've drunk a little bit, it's just like removing these barriers. I think that it's, it's a little bit of the same in in chest in 2012, I played the World blitz Championship and then I was doing horribly for, for a long time. I also had food poisoning there, I couldn't play at all for, for three days. So before the last break, I was like in the middle of the park, like in, I don't know, 20th place or something. And so I decided like as the last last gasp, I'm going to go to the mini bar and just have a few drinks and um what happened is that I came back and I was suddenly relaxed uh and I was playing fast and I was playing confidence and I thought I was playing so well, I wasn't playing nearly as well as I thought, but it still helped me, like I won my remaining eight games and if there had been one more round, I probably would have won the whole thing, but finally I was, I was second, so generally I wouldn't recommend that, but maybe as the last research sometimes, like if you feel that you have the ability, like obviously none of this is remotely relevant if you don't feel like you have the ability to begin with, but I feel like if you feel like you have the ability, there are just factors that make it impossible for you to um </s><s>[INST] to [/INST] show it like numbing your mind a bit, can probably be a good thing. </s><s>[INST] Yeah, what's interesting, especially during training, you have all kinds of sports that have interacted with a lot of athletes in grappling sports, it's different when you train under extreme exhaustion, for example, you start becoming, you start to discover interesting things, you start being more creative, a lot of people um and at least in Brazilian jiu jitsu, they'll, they'll smoke weed, you know, it does, it creates this kind of anxiety and relaxation that kind of, enables that creative aspect, it's interesting for training, of course you can't rely on any one of those things too much, but it's cool to throw in like a few drinks every once in a while? To uh yeah, one first of all, to relax and have fun and to, to kind of try things differently, to unlock a different part of your brain. Uh What about supplements, Do you uh your coffee guy? [/INST] Oh no, um I quite like the taste of coffee, I've but the thing is, I've never had a job, so I've never needed to wake up early, so my thought is basically that if I'm tired I'm tired, that's fine, then I'll, you know, then I'll work it out, so I don't want to ever um make my brain get used to get used to coffee. Like if you see me drinking coffee, that's, that probably means that I'm massively massively hungover and I don't, I just want want to try anything to make my brain work. </s><s>[INST] Yeah, that's interesting. But for a lot of people, like you said, taste of coffee for a lot of people coffee, it's part of a certain kind of ritual, for sure, enjoy, you know, so you can have yeah, you don't want to rely on it. [/INST] Yeah, </s><s>[INST] I [/INST] also like the taste, so there's no problem there. </s><s>[INST] What about exercise? So how does that, what, like, what what, you know, a lot of people talk about the extreme um stress that chest puts in your body physically and mentally. How do you prepare for that to be physically, mentally, it's just through playing chess, or do you do cardio and any of that kind of stuff, [/INST] This is gonna be up and down. Like, as I said in 2013, I was in I was in great shape. Like, I mean generally I was exercising doing sports every day, either playing football or um tennis or even other other sports. Otherwise if I couldn't do that, I would try and take my my bike for for a ride. I had a few training camps and I played tennis against one of my, my seconds. Like he's not a super fit guy, but he's always been very good at tennis and I never like played in any organized way. Um and that was like, that was that was the perfect exercise because I was running around enough to make the games pretty competitive and it means meant that he had to run a bit less as well, but he was just he said like he he was shocked that if we played like for two hours, I wouldn't flinch at all </s><s>[INST] interesting. So like a combination of fun and uh the differential between skill result in good cardio. Yeah, [/INST] but it is it's just that um so in those days I was I was pretty, I was pretty fit in that sense. I've always liked doing sports, but at times, you know, I think in winter, especially like I never had like a schedule, so at times I left myself go a little bit, uh, and I've always kind of done it more for, for fun than like for a concrete benefit, but now I'm at least after the pandemic, I was not in great shape. So now I'm trying to get back, get better, get better habits and uh, and so on. But I feel like I've always been the poster boy for making being fit a big thing in chess and I always felt that it was not really deserved because I never liked doing weights much at all. Um, I run a bit at times, but I never liked it too much. </s><s>[INST] You just love just [/INST] love playing sports. So I think people confuse that because I'm not like massively athletic, but I, but I do, I am decent at at sports and that, that sort of helped build that, that perception even though others who are top level chess players, um, they're more fit like Corona for instance, he's really, really, um, his body is really, really strong. It's just that he doesn't </s><s>[INST] go to the gym and [/INST] it doesn't play sports. That's, that's the, that's the difference. </s><s>[INST] And the thing about sports is also, is just, uh, it's an escape. It helps you forget for for a brief moment about like the, the obsessions, the pursuits of the main thing, which is chest [/INST] for, uh, for sure. And I think it's, it also helps your main pursuit to feel that you're, even if not mastering, but like doing well in something um in something else like I found that if I just juggle the ball that makes me feel better before a game. </s><s>[INST] Yeah. So uh yeah, skilled activity that you can improve on over time. It's like flex is the same kind of muscle but on the thing that you're much worse at, it focuses, you relaxes you. That's really interesting. What what's the perfect day in the life of magnets? Carl, somebody's training. So like what's a good training regimen in terms of, you know, daily kind of training that you have to put in across many days, months and years to just keep yourself sharp in terms of chess. [/INST] I would say when I'm at home I do very little deliberate practice. I've never been that guy at all. Like I could never force myself to just sit down and work. </s><s>[INST] So deliberate practice just so maybe you can educate me for some grandmasters. What would that look like just doing puzzles kind of thing or [/INST] doing puzzles and opening analysis. That would be the main things, </s><s>[INST] studying games to [/INST] studying games. Yeah, a little bit. But I feel like that's something that I do, but it's not deliberate. It's </s><s>[INST] like [/INST] reading our article or reading a </s><s>[INST] book. Like [/INST] I love chess books, I'll read just anything and I'll find something interesting. So </s><s>[INST] chess books that are like on openings and stuff like that or chest books that go over different games, [/INST] books on, So there are three main categories. There are books on openings and there are books on strategy and there are books on chess history and I find all of them very, very interesting. </s><s>[INST] Like what fraction of the day would you say you have a chessboard floating somewhere in your head meaning like you're thinking about it [/INST] probably be a better question to ask how many hours a day I don't have a chess board. I </s><s>[INST] mean it could be just floating there and nothing is happening. But like I [/INST] I often do it parallel to some other activity though. </s><s>[INST] And what does that look like? Like are you daydreaming like different, is it actual positions you're just walking around with like fumbling with different pieces in your head. [/INST] Often I've looked at a at a random game on my phone for instance or in in the book and then my brain just keeps going at the same position analyzing it and often it goes all the way, you know, to the end game </s><s>[INST] and those are actual games or you conjure up like fake games. [/INST] No, they were often based on real games. Uh and then I'm I'm thinking like, oh but it wouldn't be more interesting if the pieces were a little bit different and then often I play it out from there so </s><s>[INST] you don't have like you don't sit behind a computer or a chessboard and you lay out the pieces [/INST] and I'm not at all a poster board for deliberate practice. I could never, I could never work that way. My first coach, he gave me some exercises at home sometimes but he realized at some point that wasn't gonna work because I wouldn't do it really or enjoy it. So what he would do instead is that at the school where I had the training with him, there was this massive chess library. So he was just like pick up books, you can have anything, you can have anything you want just to pick up books you like and then you give back the next time. So that's that's what I did instead. Yeah, I just absolutely rated the then my next tournament. I will try out one of the openings from that book if it was an opening book and so on. So does </s><s>[INST] it feel like a struggle like challenging, like to be thinking those positions, there is a fun and relaxing. [/INST] No, it's completely fine. I don't </s><s>[INST] like if it's a difficult position to figure out, you know like to calculate [/INST] and I go onto something else. </s><s>[INST] Okay. [/INST] Like if I can't figure it out then you know, go on </s><s>[INST] change it. So that's easier to figure out. There was a point in your life because I was interested in being your coach or trainer training with you. Why why did you choose not to go with him? That's a pretty bold [/INST] move. </s><s>[INST] Was there a good reason for this? [/INST] Um the first like home exercise he gave me was to analyze like he picked out I think three or four of my worst losses and she wanted me to, to analyze them and give him my thoughts. And it wasn't that they were painful losses or anything that that was a problem. I just didn't really enjoy that. Also I felt that this whole structured approach and everything I just felt like from the start there was was a hassle. So I loved the idea of being able to pick his brain with everything else. I just, you know, I couldn't see myself, I couldn't see myself enjoying and at the end of the day I did then and always have played for fun. That's always been like the main reason. So </s><s>[INST] it's great that you have the confidence to sort of basically turned down the approach of one of the greatest chess players of all time at that time, Probably the greatest chess player of all time. [/INST] I don't think I thought of it that </s><s>[INST] way. I [/INST] just thought this is not for me, I want to try another </s><s>[INST] way. I don't [/INST] think I was particularly thinking that this is my one opportunity or anything. It was just, yeah, I don't enjoy this, let's try something </s><s>[INST] else. When you were 13, you faced Kasparov. Uh and he wasn't able to beat, you, can you go through that match. What did that feel like? How important was that? Was that? how epic was [/INST] that? We played three games, I lost two and drew one right, </s><s>[INST] but one draw, [/INST] you know the one draw um </s><s>[INST] and but didn't you say that you kind of had a better position in that? [/INST] Yeah, I remember that day very well, there was a blitz game, this was a rapid tournament and there was a blitz tournament the day before which determined the pairings for the rapids for </s><s>[INST] people who don't know, super short games are called bullet kind of short games are called blitz, semi short games are called and classic chest I guess is like very super long. [/INST] Yeah, yeah, basically bullets just never played over the board. So in terms of over the board, chess blitz is the shortest rapid is like hybrid between classical and blitz, you need to have the skills of both. And then classical is as long the blitz tournament which didn't go so well, like I got a couple of wins but I was beaten badly in a lot of games including by Gary And so there was the pairing that I had to play in which is pretty exciting. So I remember I was so tired after the Blitz tournament, like I slept for 12 hours or something. Then I woke up like okay, I'll turn on my computer, I'll search chest space for Kasparov and we'll go from there. </s><s>[INST] So [/INST] before that I hadn't spent like a lot of time specifically studying his games, it was super intimidating because a lot of these openings, I knew I was like, oh, he was the first one to play that, oh, that was his idea, I actually didn't know that. So I was a bit intimidated before we played that of course, the first game, he um arrived a bit late because they changed the time from the first day to the other, which is a bit strange and but everybody else had noticed it, but him, um, then he tried to surprise me in the opening. I, I think like psychologically the situation was not so easy for him, like clearly it would be embarrassing for him if he didn't win both games against me and then, like I was spending way too much time on my moves because I was playing Kasparov, I was double checking everything too much. Like normally I would would be playing pretty fast in those days and then at some point I calculated better than him, he missed a crucial detail and had a much better position, I couldn't convert it though, I knew what line I had to go for uh in order to have a chance to win, but I thought like I'll play a bit more carefully, maybe I can win still, I couldn't, and then I lost the second game pretty badly, which it wasn't majorly upsetting with, </s><s>[INST] I [/INST] felt that I had two black games against Kasparov, both in the blitz and Rapid and I lost both of them without any fight whatsoever. I wasn't happy about that at all. That was like less than I, I thought I could be able to to do so to me. Yeah, I was proud of that, but it was a gimmick. </s><s>[INST] I [/INST] was like a very strong I am, but had gm strength, I was like, it can happen that a player of that strength makes it a draw against Gary once in a while, </s><s>[INST] but I mean [/INST] I understand I'm 13, but like still I felt a bit more gimmicky than anything. I mean I guess it's it's a good thing that made me noticed, but apart from that wasn't </s><s>[INST] and for people who don't know, I am as international master and grandmaster and you were just on the, I guess on the verge of becoming a young youngest grandmaster ever. I [/INST] was the second youngest ever. Think I'm like the seventh youngest now. I mean these kids these days </s><s>[INST] kids these days, Yeah, [/INST] but but I was the youngest grandmother at the time in the world. </s><s>[INST] Yeah, so there is a, you know, you say it's gimmicky, but there's a romantic notions the especially as things have turned out right, like [/INST] for sure, </s><s>[INST] and have you talked to Gary since then about that? No, [/INST] not really. I think he's embarrassed, he's </s><s>[INST] still bitter, he's like, [/INST] no, I don't think it is bitter, but I think the game in itself was was a bit of embarrassing for him, even </s><s>[INST] he can't see past, like, [/INST] you know, I think he's completely fine with that. I think like in retrospect it's a good story, He appreciates, he appreciates that. I don't think that's the problem, but it never made sense for me to broach the subject with him. </s><s>[INST] Yeah, I I just it's funny just having interacted with Gary now, having talked to you, there is a little thing you still hate losing no matter how beautiful like that moment is, because it's like, in a way, it's a passing of the baton from like one great champion to another, right, But like, you still just don't like the fact that you didn't play a good game from Gary Gary's perspective, like, he still just annoyed probably [/INST] That you could have played better and we did, so we did work together in 2009 quite a lot and that corporation ended um early 2010, but we did play a lot of training games in 2009, which was interesting because he was still very, very strong and at that time it was fairly equal, like he was playing me quite a bit, but I was, I was fighting well, so it was, it was pretty um pretty even then, um so, I mean, I appreciate those games a lot more than Some random game from when I was 13 and I maybe I just don't know what I'm talking about, but I've always found it at least based on that game, you couldn't tell that I was going to take his, That I was going to take his spot. Like I made a horrible blunder and lost to a suspect kid in the World Rapid Championship and in 2018. And I mean, granted he was part of the team that won gold in the chest Olympia, but he wasn't a crucial part. He barely played any games. Like it wasn't like I would think that he would become world champion because he beat me. I'm always skeptical of those who said that they knew that I was going to be world champion after after that game or at all at that time. I mean, it was easy to see that I would become a very, very strong player. Uh, everybody could see that, but to be the best in the world or one of the best ever. </s><s>[INST] It is hard to say, but I do remember seeing Messi when he was 16 and 17. Um, [/INST] but hasn't that happened with other players though. </s><s>[INST] Yeah, but I, I I just had a personal experience. He did look different than there's like magic there. Maybe you can tell he would be uh, one of the greatest ever, but there's there's still magic, but you're right, most of the time we're trying to project. We see a young kid being an older person, you start to think, okay, this could be the next great person, Then we forget when they don't become that. [/INST] Exactly, that's I think what happens. </s><s>[INST] But when it does [/INST] or maybe some people are just so good at seeing this pattern that they can actually </s><s>[INST] aren't you supposed to do that kind of thing with fantasy football? Like see the long shot and bet on them and then they turn out to be good, [/INST] you make a lot of, lot of long shot bets and then some of them come good </s><s>[INST] and then people call you a genius for making the bet. Well, let me ask you the goat question again from a fantasy perspective, can you make the case for the greatest chess player of all time for each yourself, magnus Carlsen for Garry Kasparov, I don't know who else, bobby Fischer, Michael, It'll anyone else? Um for Hikaru Nakamura. Just kidding. [/INST] Yeah, I think I can make a case for myself for for Gary and for fisher. So I'll start with fisher for him. It's very, very simple. He was ahead of his time. But that's like intangible. You can say that about a lot of people. But he had a peak From 1972, 72 when he was so much better than the others. He won 20 games in a row. Also the way that he played was so powerful and with so few mistakes that he just had no opposition there. So he had just a peak. That's been better than anybody like him and others have, was greater than it's ever been in history at any other time and that would be the argument for, for him for Gary, he's played in a very competitive era and he's beaten several generations. He was the best, Well, he was the consensus best player, I would say for almost 20 years, which nobody else has has done in at least in recent time </s><s>[INST] and that [/INST] the longevity for sure. Also at his peak, he was not quite a level of um, of fisher in terms of the gap, but it was similar to, or I think even a little bit better than than mine. As for me, I'm of course Unbeaten as as a world champion in, in five tries. I've been world number one for 11 years straight in an even more competitive era than Gary. I have the highest test rating of all time. I have the longest streak ever without losing a game. I think for me, the main argument would be about the era where there's, the engines have leveled the playing field so much that it's, it's harder to dominate. And still, I haven't always been clear number one, but I've always, I've been number one for 11 years and for a lot of the time the gap has been pretty big. So I think there are decent arguments for, for all of them. Um, I've said before and I haven't changed my mind that Gary generally edges it because of the longevity and in the competitive era, but there are arguments, but </s><s>[INST] people also talk about you in terms of the style of play. So it's not just about dominance or the height or the, it's like just the creative genius of it. Uh [/INST] in terms of the greatest of all time, I'm not interested in in in questions of </s><s>[INST] style. So, so for messy, you don't give credit for the style for the stylistic. [/INST] I like, I like, um no, I like watching it. I just, </s><s>[INST] but you're not going to give points for the so messy. [/INST] I mean, because </s><s>[INST] of the finishing, [/INST] it's it's the, the, no, it's not because of the finishing, it's because of his overall impact on the game is higher than anybody else's. </s><s>[INST] Okay. [/INST] He contributes, he can just contributes more to winning than anybody else does </s><s>[INST] what's um so you're somebody who was advocated for and has done quite a bit of study of classic games. What would you say is, um, I mean, maybe the number one or maybe top three games of chess ever played [/INST] that doesn't interest me at </s><s>[INST] all. You don't think of the nose? [/INST] No, I don't think of it. I mean, I tried to, I find the games interesting. I tried to learn from them, but like trying to to rank them has never interested me. </s><s>[INST] What what what games pop out to you is like super interesting then, is there is there things like where idea like old school games, where there was like interesting ideas that uh [/INST] that </s><s>[INST] you go back or like you find surprising and pretty cool that that that those ideas were developed like then [/INST] is </s><s>[INST] there something that [/INST] yeah, there are several games of young Kasparov, like before he became world champion, if you're gonna ask for like my favorite player or favorite style, that's probably </s><s>[INST] the youngest, [/INST] youngest, can you </s><s>[INST] describe stylistically or in any other way? What what was like that you're that you like? [/INST] It was just an overflow energy in his play. So </s><s>[INST] aggressive, [/INST] extremely aggressive, dynamic chest. It probably appeals to me a lot because these are the things that I cannot do as </s><s>[INST] well [/INST] uh that it just feels very special to me. But yeah, in terms of games, I never, never thought about that too much. </s><s>[INST] Is there uh memories big or small, weird, surprising just any kind of beautiful anecdote um from your chest career, like stuff that pops out that people might not know about this stuff when you look back and just makes you smile. [/INST] No, so I'll tell you about the most satisfying tournament, victory of my career. Um so that was the Norwegian championship under 11 in 2000 before that tournament. I was super anxious </s><s>[INST] because [/INST] I started like kind of late at chess, I I played my first tournament when I was 8.5 and a lot of my competitors had already played for for a couple of years or even 34 years at that point And the first time, so I played under 11 championship in 99 and I was like a little over the middle of the pack, I'd never played against any of them before, so I didn't know what to expect at all. And then over the next year I was like edging a little bit closer in each tournament. I felt like I was getting a little bit better and when we had the championship, I knew that I was ready that I was now at the same level of the best players, I was so anxious to, to show it. I remember I was just the feeling of excitement and nervousness before the tournament was incredible. The tournament was weird because I started out, I gave away a draw to a weaker player whom I shouldn't have drawn to, and then I drew against the other guy Who was clearly like the best story 2nd best. And at that point I thought it was over because I thought he wouldn't, he wouldn't give away points to others. And then the very next day he lost to somebody. So the rest of the tournament, it was just like, I was always like playing my game and watching his and we both won the rest of our games, but it meant that I was half a point, I had like, the feeling when I realized that I was gonna win um That was just so amazing. It was like the first time that I was the best at my age and at that point </s><s>[INST] you're hooked? [/INST] Yeah at that point I realized you know this I could actually be very good at this. So </s><s>[INST] you you you kind of saw, what did you think your ceiling would be? Did you see that? Did you see that one day? You could be the number one. [/INST] No, I didn't, I didn't think that </s><s>[INST] was possible at all. [/INST] Um But </s><s>[INST] when you first I [/INST] thought that could be the best in Norway at that point </s><s>[INST] because [/INST] like I started relatively late, </s><s>[INST] right? And [/INST] also like I knew that I studied a lot more than the others. I knew that I had a passion that they didn't have. They saw chess as something </s><s>[INST] like [/INST] it was, you know, it was a hobby, it was like an activity. It was like um it was like going to to football practice or any other sports. Like you go you practice like once or twice a week and then you play a tournament at the weekend. That's that's what you did for me. It wasn't like that. Like I would go with my books and my board every day after school. Uh And I wouldn't I would just constantly be trying to learn new things. I had like two hours of internet time on the computer each </s><s>[INST] week [/INST] and I would always spend them on on chess. Like I think before I was 13 or 14 I'd never opened a browser for any other reason than to play chess. </s><s>[INST] Would you describe that as love or as obsession or something in between? It's everything, [/INST] everything. But so I mean it wasn't hard for me to tell at that point that I had something that the other other kids then because I was never the one to grasp something very, very quickly. But once I started I always got hooked and then I never stopped learning. </s><s>[INST] What would you say? You've talked about the middle game as a as a place where you can play pure chess. What do you think is beautiful to you about chess? Like the thing when you were 11, what [/INST] is beautiful to me is when your opponent can predict every single one of your moves and they still lose. How </s><s>[INST] does that happen? [/INST] No. Like it means that at some point early you're planning your evaluation has been better so that you play just very simply, very clearly, it looks like you did nothing special and your opponent lost without a chance. So </s><s>[INST] your how do you think about that by the way, are you basically narrowed down this gigantic tree of options to where your opponent has less and less and less options to win to escape? And then they're trapped? That's [/INST] essentially </s><s>[INST] is there some aspect to the patterns themselves, to the positions, to the elegance of like the dynamics of the game that you just find beautiful. That that that doesn't that where you forget about the opponent [/INST] general, I try and create harmony on the board, like what I would usually find harmonious is that the pieces work together that they protect each other uh and that there are no pieces that are sub optimally placed or if they are sub optimally placed, they can be improved pretty easily. Like I hate when I have one piece that I know is badly placed and I kind of improve it </s><s>[INST] when when yeah, when you're thinking about the harmony of the pieces, when you're looking at the position, you're evaluating it, are you looking at the whole board or is it like a bunch of groupings of pieces overlapping? [/INST] I like </s><s>[INST] dancing together kind of thing. [/INST] I would say it's more of the ladder that would be more precise that you look, I mean </s><s>[INST] I [/INST] looked mostly closer to the middle, but then I would focus on one, like there are usually like one grouping of pieces on one side and then some more closer to the other side. So I would um I would think of it a little bit that way. </s><s>[INST] So and everything is kind of gravitating to the middle. If [/INST] it's going well then yes </s><s>[INST] and in harmony, [/INST] Yeah, in harmony other, like if you can control the middle, you can more easily attack on both sides. That applies to pretty much any game, it's as simple as that and like Attacking on one side without control of the middle would feel very non harmonious for for me, like I I talked about the 10th game and in the World championship, that that's the time I was the most nervous and it was because it was a kind of attack that I hate where you just have to, your abandoned one side and you the attack has to work. There was one side and part of the middle as well, which I didn't control at all. That's like the opposite of harmony for me, </s><s>[INST] what advice would you give to chess players of different levels? How to improve in chess? Very beginning, complete beginner. I mean at every level is there is there something you can, [/INST] it's very, very hard for me to say because I mean the easiest way is like love chest be obsessed, </s><s>[INST] but that's a really important statement [/INST] that doesn't work for everybody. So I feel like </s><s>[INST] it can feel like a grind. So you're saying if the less you can feel like a grind, the better the better. [/INST] Yeah, at </s><s>[INST] least for you, [/INST] that's for sure. But I'm also very, very skeptical about giving advice because I think again, my way only works if you have some combination of talented and obsessions. So I'm not sure that I generally recommend it. Like what I've done doesn't go with what most coaches suggest for their kids, I've been lucky that I've had coaches from, from early on that I've been very, very hands off and just allowed me to do my thing basically. Well, </s><s>[INST] there's a lot to be said about cultivating the obsession, like really, really letting that flourish to where you spend a lot of hours, like with the chessboard in your head and it doesn't feel like a struggle. [/INST] No. So like just letting me do my thing, like if you give me a bunch of work, it will probably feel like a sure and if you don't give me, I will spend all of that time on my own without thinking that it's, it's work or without thought that I'm doing this to improve my chest. </s><s>[INST] Well in terms of learning stuff like books, there's one thing that's relatively novel from your perspective, people starting now is there's Youtube, there's a lot of good Youtubers, your part time [/INST] Youtuber, you </s><s>[INST] have stuff on Youtube I guess. [/INST] But I mean if you've seen my youtube, it's most, it's </s><s>[INST] very, [/INST] it's not, it's careful not high effort content. </s><s>[INST] Yeah, but do you like any particular Youtubers, um, I could just recommend like stuff I've seen, so I didn't matter the Gotham chess board says live. Um, I really like ST louis chess club, daniel nordic ski and john Bartholomew, those are good channels, but is there something you can recommend? [/INST] No, all of them are good, you know, the best recommendation I could give is a matter um, purely how </s><s>[INST] much did he pay you to say that? [/INST] No. So the thing about that is that I haven't really, I have, so I can tell you, I've never watched any of his videos from, from start to finish. I'm not like I'm not the target audience obviously, but I think the only chess Youtube video that my dad has ever watched from start to finish is matter. And he said like I watched one of his videos, I wanted to know what it was all about because I think is like </s><s>[INST] the [/INST] Same strength as my father, maybe just a little bit weaker like 1900 or something. My father is probably about 2000 and my father has played chess his whole life. He loves, he absolutely loves the game. It was like that's the only time he's actually sat through one of those videos and he said like, yeah, I get it, I enjoy it. So that's the best recommendation I could give. That's the only channel that my father actually enjoys. </s><s>[INST] This is hilarious. I talked, I talked to him before this to ask him if he has any questions for you and uh, he said no, just just do your thing. You [/INST] know, he's so careful. He wouldn't do that. </s><s>[INST] He did mention jokingly about uh Evans Gambit I think. Is that a thing? Evans gambit is some weird thing he made up. It might be an inside joke. I don't, I don't know, but he asked me to, well anyway, [/INST] I don't even get, it's something </s><s>[INST] I [/INST] didn't even realize that he placed the Evans Gambit like he plays a lot of gambits are </s><s>[INST] Evans Gambit is a thing. [/INST] Yeah, that's the thing, like that's an old opening from the 1800s. Captain Evans apparently invented it. </s><s>[INST] Well, he mentioned that particular something hilarious [/INST] About that one. I don't </s><s>[INST] know, I [/INST] don't think I've ever faced the Evans Gambit and uh in the game </s><s>[INST] I feel like both of you are trolling and trolling me right [/INST] now. But I mean he's he's played a lot of other gambits, maybe this is the one he wanted to to mention. So this maybe this is called the Evans Gambit as well, but I just know it as like the 22 G four gambit maybe this is the one like this one, he has, this one has played a bunch uh and he, he's been telling me a lot about his games in this line, it's like it's not so bad and I'm like yeah, with europe on down, but I can, I can sort of see it, I can sort of, I can sort of understand it and he's like, he's proud of the fact that nobody like told him to play this line or anything, he came up with it himself and there's this, I'll tell you another story about my father. So there's this line that I call that I called the Henry Carlson line. </s><s>[INST] Um, [/INST] so at some point, you know, he never knew a lot of openings in chess, but I taught him, I taught him a couple of openings as black. Um it's the, It's the special Sicilian that I've played a lot myself also. Um during the World Championship in 2018, I won a bunch of games in 2019 as well, so that's one opening and also taught him as black to play the, in defense. Um, and then so the in defense goes like it goes like this, um, it's characterized by, by this bishop move. Um, and so he would play those openings pretty pretty exclusively and as black and the tournaments that it did play and also the special of Sicilian is like, that's the only two of my sisters play have played a bunch of chess tournaments as well and that's the only opening they know as well. So my, my family's reporter is very narrow so so this is the, this is the system, black goes here and then very often white takes a pawn and black takes the pawn. Um, so at some point I was watching one of my, my father's online blitz game this game and as white, he played this, this, so this is called the car can defense, he took upon. Um, it was taken back then he went with a night, um, its opponent one here and then you play the bishop here. So I've never seen this opening before. I was like, wow, how on earth did he come up with that and he said no, I just played the with the different colors because if the night was here it would be the same position. I was like, I never, I was like how am I like one of the best 20 players in the world and I've never thought about that. So I actually started playing, I started playing this line uh as white with pretty decent results and results and it actually became kind of popular and everybody who asked about the line, like I would always tell them, yeah, that's the Henry Carlson, </s><s>[INST] I [/INST] wouldn't necessarily explain why it was called that I would just always call it that. So I really hope at this point at some point this line will be uh </s><s>[INST] will find [/INST] its rightful name </s><s>[INST] in. Yeah, finds its way into the history books. Can you, what, what, what did you learn about life from your dad? What what role has your dad played in your life? [/INST] He's taught me a lot of things, but most of all, as long as you win a chess, then everything else is fine. Um I think my, especially my father, but my parents in general, they, they always wanted me to get a good education and find a job and so on. Um even though my father loves chest and he wanted me to play chess. I don't think he had any plans for me to be professional. I think things changed at some point, Like </s><s>[INST] I [/INST] was less and less interested in school and for a long time we were kind of going back and forth fighting about that, especially my father, but also my mother a little bit, it was at times a little bit difficult. </s><s>[INST] Yeah, [/INST] they sort of wanted me to do more school to have more options and then I think at some point they just gave up. But I think that sort of coincided when I was actually starting to make real money of tournaments and after that, you know, everything's been sort of easy and like in terms of the family, like they've never </s><s>[INST] put [/INST] any pressure on me or they've never put any demands on me. Um, they're just, yeah minus has to focus on chess. That's that, that's um, that's it. Like I think they taught me in general to be curious about the world and to get a decent general education, not necessarily from, from school, but like just knowing um, about the world around you and knowing history and being, you know, just being interested in society. I think in that sense they've done well </s><s>[INST] and he's been with you throughout your chest career. I mean there's something to be said about just family support and love that you have that, that, you know, this world is a lonely place. It's good to have people around you, they're like uh they got your back kind of you [/INST] know uh basically shape but I think to some extent all the people you surround yourself with they can help you a lot. It's the only family that only has their own interests at heart. And so for that reason like my father is like the only one that's been like constantly in the team that and that has always been around and it's it's for that reason that I know he has my back no matter what </s><s>[INST] now there's a cliche question here but let's try to actually get to some deep truth perhaps. But people who don't know much about chess seem to like to use chess as a metaphor for everything in life. But there is some aspect to the decision making to the kind of reason and involved in chess that's transferable to other things. Can you can you speak to that in your in your own life and in general the kind of reasoning involved with chess, how much is that this transfer to life out there? [/INST] It just helps you make decisions of </s><s>[INST] all of all kinds. [/INST] That would be my main takeaway that you learn to make informed guesses in a limited amount of time. </s><s>[INST] I mean does it frustrate you when you know that you have geopolitical thinkers and leaders, you know, Henry Kissinger will often talk about geopolitics is a game of chess or three D. Chess is that too oversimplified of a projection or or do you think that the kind of deliberations you have on the world stage is is similar to the kind of decision making you have on the chessboard. [/INST] Well I never, I'm never trying to get reelected when I play a game of chess, there's </s><s>[INST] no special interest. You have to get happy [/INST] that you know, that kind of helps. You know, I can, I can understand that obviously for every action there's a reaction and you have to calculate far ahead. It probably would be a good thing if more big players on the international scene thought a little bit more like like a chess player in that sense like trying to make a good decision based on based on limited amount of data rather than thinking about other other factors. But it's so tough but it doesn't know me when when people make moves that they know are wrong for different reasons </s><s>[INST] and they should know if they did some calculation, they should know they're wrong. Yeah [/INST] exactly that they should know that are wrong. And so much politics is like it's um you're you're often asked to do something when you're when it would be much better to do nothing. Uh </s><s>[INST] like [/INST] no but that happens in chest all the time. Like you you have a choice. Like I often tell people that in certain situations you should not try and win. You should just let your opponent loose and that happens in politics all the time. Uh, but yeah, just let your opponents continue whatever they're doing and then you'll win. Don't try to do something just to do something often. They say in test that having a bad plan is better than having no plan. It's absolute nonsense. I </s><s>[INST] think it was general said it, but it was like don't interrupt your enemy when they're making a mistake. I think also [/INST] um Patrol Ocean, um the former world champion said um when your opponent wants to play the dutch defense, don't stop them. I mean chess players will know that it's the same thing. </s><s>[INST] Uh Actually this reminds me um is there something you found really impressive about queen's gambit? The tv show, You know that's one of the things that really captivated the public imagination about chess. People don't play chess became very curious about the game, about the beauty of the game, the drama of the game, all that kind of stuff is there in terms of accuracy in terms of the actual games played that you found impressive. [/INST] First of all they did the chest that did the chest well they did it accurately. And also they found actual games and positions that I never never seen before and really captivated me. Like I would, I would not follow the, the story at times. I was just trying to wow where the hell did I find that game, trying to solve the positions. </s><s>[INST] So beth harmon the the main character, Were you impressed by the place she was doing in, in the like was there a particular style that they developed consistent? [/INST] But she was just, at the end she was just totally universal. Like at the start she was probably a bit too aggressive, but no, she was absolutely universal, you </s><s>[INST] know? Wait, what, what were the, what adjective using [/INST] universal in the sense that she could play in any any style? </s><s>[INST] Oh, interesting. And and was dominant in L. A, wow, They said there was a development in style to throughout the [/INST] show, it's </s><s>[INST] really interesting. They did, they did [/INST] that and uh it actually happened with me a bit as well. Like I started out really aggressive, then I became probably too technical at some point taking a little bit too few risks and not playing dynamic enough. And then I started to get a little bit better at dynamic. So that now I'm, I would say definitely the most universal player in terms of in terms of style, </s><s>[INST] are there any skills and chests that are transferable to poker? So as you're playing around poker a little bit now, how fundamentally different of a game is it? [/INST] What I find the most transferable probably is not like letting past decisions dictates future </s><s>[INST] thinking, but in terms of the patterns in the betting strategies and all that kind of stuff. What about bluffing because [/INST] too much </s><s>[INST] it does seem that you enjoy bluffing and Daniel Negreanu [/INST] was saying you're quite </s><s>[INST] good at it, [/INST] but yeah, I was very little material to go by </s><s>[INST] sample size is small. [/INST] Yeah, no, I mean I enjoy bluffing for the more the gambling aspects the thrill of, so </s><s>[INST] not the technical aspect of the bluffing, like you would on the chessboard, [/INST] not bluffing in the same sense, but there is some element um but I do enjoy it on on the chessboard, like if I know that like, oh I successfully scared away my opponent for making the best move that's of course satisfying </s><s>[INST] in that same way. It might be satisfying in poker, right? That you represent something, you scare away your opponent the same kind of [/INST] way. And also like you tell a story, you try and tell a story and then they believe it, </s><s>[INST] yeah, tell a story with your betting, with your um all the different other cues, do you like the money aspect, the betting strategies? So it's like, it's like, it's almost like another layer on top of it, right? Like it's, it's the uncertainty in the cards, but the betting, there's so much freedom to the betting, [/INST] I'm not very good at that. So I cannot say that I understand it completely, you know, when, when it comes to different sizing and another that I just haven't studied it enough, </s><s>[INST] how much of luck is part of poker, would you say from what you've seen versus skill, [/INST] I mean it's so different in the sense that you can be one of the best players in the world and lose two or three years in a row without that being being like a massive outlier. </s><s>[INST] Okay. The thing that more than one person told me that you're very good at is trash talking. [/INST] I don't think I am a lot of people who make those observations about me, I think they just expect very, very little so they expect from the best chess player in the world that just anything that's non robotic is interesting. Also when it comes to trash talking, like I have the biggest advantage in the world that I'm the best of what I'm doing. So trash talking becomes very very, very easy because I can back it up. </s><s>[INST] Yeah, but a lot of people that are extremely good at stuff don't trash talk and they're not good at it. [/INST] I don't think I'm very good at it. It's just that I can back it up which makes it seem that I'm, I'm better. And also you're even doing it now also being non robotic or not completely robotic. </s><s>[INST] Health. Yeah, you're not trash talking and just stating facts. That's right. Have you ever, have you ever considered that, uh, there will be trash talking and over the chessboard and some of the big tournaments like adding that kind of component or even talking, you know [/INST] that </s><s>[INST] would that completely distract from the game of chess? No, [/INST] I think it could be funny and when people play often games, when they play blitz games like people trash talk all the time. It's a normal part of the game. </s><s>[INST] So you, you emphasize fun a lot. Uh Do you think we're living inside of a simulation that is trying to maximize fun? [/INST] But that's only happened for the last, you know, 100 years or so. No, that's like </s><s>[INST] the fun has always been increasing I think. [/INST] Yeah, okay it's always been increasing but I feel like it's been increasing exponentially. </s><s>[INST] Yeah, [/INST] I mean the or at least the importance of fun, but I guess it depends on the society as well. Like in the west we've had such christian influence and I mean Christianity hasn't exactly embraced the concept of fun over over time. So </s><s>[INST] actually to push back I think forbidding certain things kind of makes them more fun. So sometimes I think you need to say you're not allowed to do this and then then a lot of people start doing it and then they have fun doing that because it's like uh um it's doing a thing in the face of the resistance of the thing. So when whenever there's resistance that does somehow make it more fun, [/INST] oppressive regimes has always been kind of good for comedy. No, like I heard supposedly like in the soviet union, I don't know about fun but supposedly comedy like at least underground. It's, it's yeah, </s><s>[INST] there's a well know, it permeates the entire culture. There's a dark humor that sort of the cruelty, the absurdity of life really really brings out the humor amongst the populace plus vodka on top of that. But this idea that for example Elon musk has that um the most entertaining outcome was the most likely. It seems like the most absurd, silly funny thing seems to be the thing. So [/INST] it happens more often than that </s><s>[INST] and it becomes viral in our modern connected world. And so the fun stuff, the memes spread and then we start to optimize for the, for the fun meme that seems to be a fundamental property of the reality we live in and so emerges the the fund maximize er in all walks of life, like in chess in poker and everything. I think you're skeptical. [/INST] No, I'm not skeptical. I'm just, I'm just taking it all in. But I find I find it interesting and not at all impossible. </s><s>[INST] Do you ever get lonely? [/INST] Oh yeah, for sure. Um Like a chess players, life is by definition pretty lonely because you have nobody else to blame but yourself when you lose or you don't achieve the results that you want to achieve? </s><s>[INST] It's difficult for you to find comfort elsewhere. It's it's in your own mind. Yeah. It's you versus yourself. Really? [/INST] Yeah. Really? </s><s>[INST] But [/INST] it's uh you know, it's um it's part of the profession, but I think any like sport or activity where it's where it's just you in your own mind is just by definition lonely. Are </s><s>[INST] you worried that it destroys you? Oh, [/INST] not at all. As long as I'm aware of it, then it's fine. And </s><s>[INST] uh, [/INST] I don't think the inherent loneliness of my profession really affects the rest of my life in in a major way. </s><s>[INST] What role does love play in the human condition and in your lonely life of calculation, you [/INST] know, unlike everybody else. Uh, trying, uh, you know, </s><s>[INST] trying to find love. [/INST] No, not necessarily like trying to find love. Sometimes I am, sometimes I'm, I'm not, I'm just trying to find my way and my love for, for the game, obviously it comes and goes a little bit, but there's like, there's always at least some level of love. So that doesn't, doesn't go away. But I think in other parts of life, I think it's just about doing things that make you happy that give you joy. That that also makes you more receptive to, to love in general. So that, that has been my approach to, to love now for quite a while that I'm just trying to live my best life and then the level, um, will come when it, when it comes. And in in terms of romantic love, it has come and gone in my life. It's not there now, but I'm not worried about that. I'm more worried about, you know, not worried, but more like trying to just be a good version of myself. I cannot always be the best version of myself, but at least try to be good. </s><s>[INST] Yeah and keep your heart open. What is this uh Daniel johnston song, True Love will find you in the end but [/INST] it may or may not, </s><s>[INST] but it will only find you if uh if you're looking so like you have to be open to [/INST] it. Yeah, </s><s>[INST] it may or may not. Yeah. Yeah and no matter what you're gonna lose it in the end because it all ends, the whole thing ends. [/INST] Yeah, I don't think stressing over that like obviously it's so human that you can't help it to some degree. But I feel like stressing over love. That's the blueprint for whether whether you're looking or you're not looking or you're in a relationship or marriage or anything. Like stressing over it is like the blue blueprint for being unhappy. </s><s>[INST] Just to clarify confusion. I have just a quick question, how does the night move? [/INST] So the night moves in an L. Um and uh and like you can move both forwards and backwards. It is quite a nimble piece. It can jump over everything, but it's less happy and open position where it has to move from from side to side quickly. I am generally more of a bishop's guy myself for the old debate. I just prefer quality over the intangibles but I can appreciate a good night once in a while </s><s>[INST] last simple question, what's the meaning of life magnus Carlsen? [/INST] There is obviously no meaning to </s><s>[INST] life that obvious. [/INST] I think we're here by accident. There's no meaning, it ends at some point, but it's still a great thing. So you </s><s>[INST] can still have fun, even if there's no meaning, [/INST] you can still have fun, you can try and pursue your your goals, whatever they may be. But I'm pretty sure there's no special meaning and trying to to find. It also doesn't make a whole lot of sense to me. For me, like life is both meaningless and meaningful for just being here, trying to, to make not necessarily the most of it, but the things that make you make you happy both short term and long term. Yeah, </s><s>[INST] it seems to be full of cool stuff to enjoy. It [/INST] certainly does. </s><s>[INST] And one of those is having a conversation with you. It's a huge honor to talk to you. Thank you so much for spending this time with me. I can't wait to see what you do in this world and thank you for creating so much elegance and beauty on the chessboard and beyond. So, thanks for talking today brother, [/INST] thank you so much. Thanks for having me. Uh and uh, I wanted to say this at the start, but I never really got the chance. I was always a bit apprehensive about doing this podcast because you are a very smart guy and your audience is very smart and I always had a bit of imposter syndrome. So I'll tell you this now after the podcast, so please do judge me. But I hope you have enjoyed it. I </s><s>[INST] love that you're a brilliant man and it's it's I love the fact you have imposter syndrome because a lot of us do. And so that that's beautiful to see even at the very top. But you still feel like an impostor. Thank you brother. Thanks for talking today. Thanks for listening to this conversation with magnus Carlsen to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from bobby Fischer chess is a war over the board. The object is to crush the opponent's mind. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] Also, there's a small tangent, somebody I was supposed to talk to and unfortunately he passed away and he's somebody finding is an incredible mathematician, incredible human being. [/INST] So and I am sorry that you didn't get a chance because having had the chance to talk to him a lot when I was, you know, when I was a postdoc. Yeah, you missed out. There's no way to sugarcoat it. I'm sorry that you didn't get that chance. </s><s>[INST] Yeah, it is what it is. So knots. [/INST] Yeah. So there was a question and again, it doesn't matter the technicalities of the question, but it's a question of whether they're not is sliced. It has to do with something about what kinds of three dimensional surfaces in four dimensions can be bounded by this not, but never mind what it means. That some question uh and it's actually very hard to compute whether or not is sliced or not. Um And in particular, the question of the Conway knot, whether it was slice or not, was particularly vexed um until it was solved just a few years ago by lisa Piccirillo who actually, now that I think of it was here in Austin, I believe she was a grad student at ut Austin at the time. I didn't even realize it was an Austin connection to this story until I started telling us. She is in fact, I think she's now at MIT. So she's basically following you around, if I remember correctly, reverse. There's a lot of really interesting richness to this story. One thing about it is her paper was rather It was very short, it was very short and simple. nine pages of which two were pictures uh very short for like a paper solving a major conjecture. And it really makes you think about what we mean by difficulty in mathematics? Like do you say, oh, actually, the problem wasn't difficult because you could solve it so simply or do you say like, well, no, evidently it was difficult because like the world's top apologist, you know, worked on it for 20 years and nobody could solve it. So therefore it is difficult. Or is it that we need some new category of things that about which it's difficult to figure out that they're not difficult. </s><s>[INST] I mean, this is a computer science formulation, but the sort of the journey to arrive at the simple answer may be difficult, but once you have the answer, it will then appear simple. And I mean, there might be a large category, I hope there's a large a set of such solutions because, you know, once we stand at the end of the scientific process that we're at the very beginning of or at least it feels like I hope there's just simple answers to everything that will look and it'll be uh simple laws that govern the universe? Simple an explanation of what is consciousness of what his love is, mortality fundamental to life? What's the meaning of life? Uh are human special? Or we're just another sort of reflection of uh and all that is beautiful uh in the universe in terms of like, life forms, all of it is life and has different when taken from a different perspectives. All life can seem more valuable or not, but really it's all part of the same thing. All those will have a nice like two equations, maybe one equation. But [/INST] why do you think you want those questions to have simple answers? </s>

<s>[INST] again. So a lot of stuff we're talking about it essentially open problems. Right? So if I ask a question, I don't mean that you would know the answer only just hypothesizing. But how big do you think is the network graph data structure of concepts that's in our head. Like if we're trying to build that ourselves, like if we take it, that's one of the things we take for granted we think. I mean that's why we take common sense for granted within common sense is trivial. But how big of a thing of concepts is that underlies what we think of as common sense for example. [/INST] Yeah, I don't know. And I'm not I don't even know what units to measure it in you say how </s><s>[INST] big beautifully put. Right? But uh but [/INST] you know, we have, you know, it's really hard to know. We have uh what 100 billion neurons or something I don't know. Uh and they're connected fia trillions of synapses and there's all this chemical processing going on. There's just a lot of capacity for stuff and their information is encoded in different ways in the brain. It's encoded in chemical interactions that's encoded in electric, like firing and firing rates and nobody really knows how it's encoded. But it just seems like there's a huge amount of capacity. So I think it's huge. It's just enormous and it's amazing how much stuff we know. Yeah. </s><s>[INST] And but we know and not just know like facts, but it's all integrated into this thing that we can make analogies with. There's a dream of semantic web, there's there's a lot of dreams from expert systems of building giant knowledge bases. Do you see a hope for these kinds of approaches of building of converting Wikipedia into something that could be used in analogy, making [/INST] sure. And I think people have made some progress along those lines. I mean people have been working on this for a long time, but the problem is and this I think is the problem of common sense, like people have been trying to get these common sense networks here at m I t there's this concept net project, right. Uh But the problem is that, as I said, most of the knowledge that we have is invisible to us. It's not in Wikipedia, it's very basic things about, you know, intuitive physics, intuitive psychology, intuitive metaphysics, all that stuff. </s><s>[INST] If you were to create a website that's described, intuitive physics? Intuitive psychology, would it be bigger or smaller than Wikipedia? What do you think? [/INST] I guess, described to whom? Uh Sorry, </s><s>[INST] But it's really good, you know? Yeah, [/INST] that's a hard question, because, you know, how do you represent that knowledge is the question, right? I can certainly write down F equals M A. And of Newton's laws and a lot of physics can be deduced from that. Uh but that's probably not the best representation of that knowledge for doing uh the kinds of reasoning we want a machine to do. So, I don't know, it's it's it's impossible to say now. And people, you know, the projects like there's a famous the famous psych project, right? That doug Douglas Lynn It did. That </s><s>[INST] was trying still [/INST] going, I think it's still going and it's the the idea was to try and encode all of common sense knowledge, including all this invisible knowledge in some kind of logical representation. And it just never I think could do any of the things that he was hoping it could do because that's just the wrong approach, </s><s>[INST] Of course, that's what they always say, you know, and and and then the history books will say, well the psych project finally found a breakthrough in uh 2058 or something. And, you know, we're so much progress has been made in just a few decades that who knows what the next breakthroughs will be could be. It's certainly a compelling notion what the site project stands for. [/INST] I think len it was one of the early people to say common sense is what we need, that's what we need, all this like expert systems stuff that is not going to get you to a i you need common sense. And he basically gave up his whole uh academic career to go pursue that. I totally admire that. But I I think that the approach itself will not 2020 20 </s><s>[INST] what do you think is wrong with the approach? What kind of approach would might be successful? Well, again, that [/INST] I knew that, you know, what one of my talks, uh one of the people in the audience is a public lecture. One of the people in the audience that what ai companies are you investing in? Like, </s><s>[INST] I'm [/INST] a college professor for one thing, so I don't have a lot of extra funds to invest, but also like no one knows what's going to work in ai. Right, that's the problem. </s><s>[INST] Let me ask another impossible question in case you have a sense in terms of data structures that will store this kind of information, do you think they have been invented yet? Both in hardware and software, or is something else needs to be? Are we totally you know, [/INST] I think something else has to be invented. I that's my guess </s><s>[INST] is the breakthroughs that's most promising. Would that be in hardware and software? Do you think we can get far with the current computers or do we need to do something that [/INST] you were saying? I don't know if turing computation is going to be sufficient? Probably, I would guess it will. I don't see any reason why we need anything else. But so in that sense, we have invented the hardware we need but we just need to make it faster and bigger and we need to figure out the right algorithms and the right uh huh sort of architecture </s>

<s>[INST] where he teaches the world about the brain and the human mind also. He's a friend and an inspiration in that he shows that you can be humble, giving and still succeed in the science world. Quick mention of the sponsor, followed by some thoughts related to the episode eight sleep a mattress that calls itself and gives me yet another reason to enjoy sleep. ECM Rush, the most advanced SEO optimization tool I've ever come across and cash app. The app I used to send money to friends. Please check out these sponsors in the description to get a discount and to support this podcast. As a side note, let me say that I heard from a lot of people about the previous conversation I had with Iran Brooke about objectivism, some people loved it, some people hated it. I misspoke in some parts, was more critical on occasion that I meant to be didn't push on certain points that I should have was under educated or completely unaware about some major things that happened in the past or major ideas out there. I bring all that up to say that if we are to have difficult conversations, we have to give each other space to make mistakes to learn to grow. Taking one or two statements from a three hour podcast and suggesting that they encapsulate who I am I was or ever will be is a standard that we can't hold each other to I don't think anyone can live up to that kind of standard at least I know I can't. The conversation with Iran is mild relative to some conversations that I will likely have in the coming year. Please continue to challenge me but please try to do so with love and with patients. I promise to work my ass off to improve whether I'm successful with that or not. We shall see if you enjoy this thing. Subscribe on youtube, review it with five stars on apple podcast. Follow on Spotify, support on Patreon or connect with me on twitter. A lex Friedman as usual. I'll do a few minutes of ads now and no ads in the middle. I try to make these interesting but I give you time stamps So if you skip, please still check out the sponsors by clicking the links in the description. It's the best way to support this podcast. This show is sponsored by eight sleep and its pod pro mattress. It controls temperature with an app is packed with sensors and can cool down to as low as 55° on east side of the bed separately. It's been a game changer for me with a sleep. I just enjoy sleep and power naps more. I feel like I fall asleep faster and get more restful sleep. Something about a combination of a cool bed and a warm blanket is just amazing. Now if you love your current mattress But still are looking for temperature control, eight sleeps. New pod pro cover as dynamic cooling and heating capabilities onto your current mattress. It can cool down to 55° or heat up to 110° and do so on each side of the bed separately. Also it can track a bunch of metrics like heart rate variability, but cooling alone is honestly worth the money. Go to a sleep dot com slash lex And when you buy stuff there during the holidays you get special savings as listeners of this podcast. That's eight sleep dot com slash lex. This show is sponsored by ECM Rush, which if you look around seems to be one of if not the most respected digital marketing tool out there. It does a lot of stuff including sc optimization of keywords, back links, content creation, social media posts and so on. They have over 45 tools and are trusted by over six million marketers worldwide. I personally don't like Ceo type numbers but that's basically because I'm an idiot with that stuff. I speak from the heart and data be damned. But somebody needs to pay attention to numbers because otherwise you can't make optimal decisions. I believe Heart comes first. Data second, but both are necessary. I started using them just for fun to explore non numeric things like what kind of titles or words connect with people as a writer. That information helps me in moderation of course the amount of data that they put your fingertips is amazing. So if you want to optimize your online presence, check them out at ECM rush dot com slash partner slash flex to get a free month of guru level membership. That's ECM rush dot com slash partner slash lex. This show is presented by cash app, the number one finance app in the app store when you get it used collects podcast Cash up, lets you send money to friends, buy Bitcoin and invest in the stock market with as little as $1. I'm thinking of doing more conversations with folks who work in and around the Cryptocurrency space similar to a I there are a lot of charlatans in the space but there are also a lot of free thinkers and technical geniuses that are worth exploring ideas with in depth and with care if I make mistakes in guest selection or specific details within the conversations, I'll keep trying to improve, correct where I can and also just keep following my curiosity wherever it takes me. So again, if you get cash app from the app store, google play and use the code lex podcast, you get $10 in cash app will also donate $10 to first and the organization that is helping to advance robotics and stem education for young minds around the world and now here's my conversation with Andrew Huberman, you've mentioned that in your lab at stanford, you induce stress by putting people into a virtual reality and having them go through one of a set of experiences. I think you mentioned is on Rogan or with Whitney that scare them. So just uh on a practical psychological level and maybe on a philosophical level, what are people afraid of? What are the fears? What are these fear experiences that you find to be effective? [/INST] Yeah, so it depends on the person obviously. Um and we should probably define fear right? Because you can uh without going too far down the rabbit hole of of defining these things. Um you know, you can't really have fear without stress, but you could have stress without fear and you can't really have trauma without fear and stress, but you could have fear and stress without trauma. So you know, we can start playing the word game and that actually is one of the motivations for even having a laboratory that studies these things is that we really need better physiological Euro, scientific and operational definitions of what these things are in the field of understanding um emotions and states, which is mainly what I'm interested in is very complicated but we can um we can do away with a lot of complicated debate and say in our laboratory what we're looking for to assign it a value of fear is a big inflection and autonomic arousal, So increases in heart rate increases in breathing perspiration, pupil dilation, all the hallmark signature features of the stress response. Uh And in some cases we have the benefit of getting neurosurgery patients where we've got electrodes in their amygdala and insula and the orbitofrontal cortex um down beneath the skull. So these are chronically implanted electrodes were getting multi unit signals and we can start seeing some central features of meaning within the brain. And what's interesting is that as trivial as it might seem in listening to it, almost everybody responds to heights and falling from a hi virtual place with a very strong stress if not fear response. And that's because the visual vestibular apparatus, I write the optic flow and how it links to the, you know, balance semicircular canals of the inner ear is all this technical stuff. But really all of that pulls all your physiology, the feeling that your stomach is dropping, the feeling that you're suddenly you're sweating, even though you're not afraid of falling off this virtual platform. But you feel as if you're following falling, Excuse me because of the optic flow. That one is universal. So we've got a dive with great white sharks experience where you actually exit the cage. We went out this in the real world and brought back 360 video that's built out pretty. So this </s>

<s>[INST] and don't be afraid to look stupid, [/INST] don't be afraid to look </s><s>[INST] stupid. Yeah, that's one of the things that I think as you get older, you're expected to be to have it all figured out and so you are afraid to take on new things. But I think as long as you're always okay looking stupid and having a beginner's mind, you can, you can get really, really far even later on in life. So this isn't just advice for young people, this is a really advice for, uh, for everybody, maybe a dark question, but um, has there been, uh, a difficult time in your life, a really dark place you've gone in your mind, um, that stands out, they had to really overcome. [/INST] I would suggest that I've been a pretty firm ground for most of my life. I haven't had too many personal tragedies. I'll say that have really defined me. Um, certainly none that I would think are outside the norm. </s><s>[INST] So there was no truly low point, [/INST] actually, I have one. And it's tough for me because I, you know, I've spent most of my life beating motions and, and, you know, hi, hi, emotional responses out of my system, because that's what flying is, right, It's keeping a steady line and and doing what you need to do. Um, in fact, there's been studies that shown reduced uh, adrenaline production in fighter pilots for a number of years after they get out. But getting out of the Navy was difficult for me, You know, and I wasn't expecting it to be a lot of bravado and macho ism, of course, in the military, especially in fighter community, we all have our plans made up to get out and none of it really, um, accounts for any type of mental health or anything like that. It's all very much where am I gonna get my paycheck from, where am I going to move to and, you know, whether it's a navy or just individuals, truly understanding the difference that makes, when I got out, it was, it was difficult for me. I, you know, I think a lot of guys in that job, when they get out, they almost at least I had anxiety when I got out because it was, I was so used to being highly involved in something that, um, that you know, just was, I was involved with that when I got out, I didn't know how to fill that space essentially. You know. Um, and while I wouldn't say it was overly traumatic experience, I think it's one that's not accounted for enough that people that are getting out, you know, so I would encourage them to take it serious and actually think about it and respect the change because it is a big one. </s><s>[INST] Well, if I may say you found a place in nature currently home is there, can you speak to that being a source of happiness for [/INST] you? Absolutely. An </s><s>[INST] escape from the world. [/INST] Certainly very much is </s><s>[INST] was it deliberate that you found it there? [/INST] That's home for me? So, you know, I moved back up to the boston area and my wife and I had an idea after moving about eight or nine times in the Navy of kind of what we, what we wanted just generally. And it was all really about the land and not about the house. You know, we just wanted privacy and to be nearby And so we end up finding a lot of land, you know, a parcel of land. We put a house on it and it provides me with a sense of peace that um, I think I can only get when I'm in nature, a sense of clarity that helps me think, helps me relax. Maybe so relaxing. That helps me think, I don't know. But being surrounded by nature and birds and animals for me has always allowed me to, I don't feel most in touch with with my own thoughts in a sense just provides clarity. And so this little sanctuary you could say I've built allows me to to, you know, interface via fiber line at my house, but also feel like I'm a million miles away sometimes, which is the best of both worlds. </s><s>[INST] You can just walk outside to escape at all? [/INST] Yes. </s><s>[INST] To experience life as as uh hundreds of generations of human species have experienced it. [/INST] Maybe it's a dichotomy. My desire for the Fastness of technology and experience compared with the most basic baseline that we have. </s><s>[INST] Isn't that strange? How do you, how do you square that? Your draw, how drawn you are to the cutting edge and still the calm you find in nature. [/INST] I think it makes sense. Nature is vastly superior to almost all of our </s><s>[INST] technology. [/INST] It is. And so the way it's being surrounded by perfection. A lot of senses </s><s>[INST] in the military and in general. Have you contemplated your mortality? Have you been afraid of death? What was, what's your relationship like with death? [/INST] I was willing to accept an oversized amount of risk. I'll say when I was younger as an aviator, not not in the jet but just that was my life. You know, I felt like I was gonna live forever. Um and going out in the war, you know, strangely didn't really change that because you know, as an aviator again, we're riding up high on a horse up there. So there were times when I was in situations that could have resulted in death from, from flying or from emergency, um in the aircraft, but I'll be honest, I never really kind of sat down to think about the morality mortality of it afterwards. I feel like I kind of signed a check at the beginning and it was my job perform as well as I could and if something happened in that then I better damn well be sure I would do my best at the time then. Um so you know, I, I maybe didn't personally reflect on it as much as of it. I one would think, you know, because once you get in that machine, it doesn't give you a lot of time to sit back and philosophies on, on your current situation and the same, just like we weren't seeing these when we're seeing these objects off the coast, we weren't necessarily, you know, examining them every day, right? We put them into that bucket because it wasn't something that was going to kill us right away. Um, and thinking about death when you're so close to it all the time would be debilitating. </s>

<s>[INST] So one of the big things I think that feeds the tensorflow fire is people building something on tensorflow and you know, some uh implement a particular architecture, it does something cool and useful and they put that on get hub and so it just feeds this uh this growth. Do you have a sense that with two point oh and one point Oh, that there may be a little bit of a partitioning, like there is with python two and three, that there will be a code base and in the older versions of tensorflow there will not be as compatible easily or a pretty confident that this kind of conversion, it's pretty natural and easy to do. [/INST] So we're definitely working hard to make that very easy to do. There's lots of tooling that we talked about the developer summit this week and we'll continue to invest in that tooling. It's um, you know, when you think of these significant version changes, that's always a risk and we're really pushing hard to make that transition very, very smooth. I think so, so at some level people want to move and they see the value in the new thing, they don't want to move just because it's a new thing and some people do, but most people want a really good thing and I think over the next few months, as people start to see the value, we'll definitely see that shift happening. So I'm pretty excited and confident that we will see people moving. Um, as you said earlier, this field is also moving rapidly, so that will help because we can do more things and you know, all the new things will clearly happen in two point X. So people who have lots separate reasons to move. </s><s>[INST] So what do you think? Uh tensorflow three point looks like? Is that, is there are things happening so crazily that even at the end of this year seems impossible to plan for or is it possible to plan for the next five years? [/INST] I think it's tricky. There are some things that we can expect in terms of okay, change, yes, change is going to happen. Are there some going things going to stick around and something is not going to stick around? I would say the basics of deep learning, the, you know, convolution models or the basic kind of things. They'll probably be around in some form still in five years will Ireland danced very likely based on where they are. We have new things probably, but those are hard to predict and some directionally some things that we can see is, you know, things that we're starting to do right with some of our projects right now is just to point out combining eager execution in grass, where we're starting to make it more like just your natural programming language, you're not trying to program something else. Uh similarly it's a for tensorflow, we're taking that approach, can you do something round up? Right. So some of those ideas seem like, okay, that's the right direction. In five years, we expect to see more in that area. Um, other things we don't know is will hardware accelerators be the same, Will we be able to train with four bits instead of 32 bits? I </s><s>[INST] and I think the Tpu side of things is exploring, I mean Tpu is already on version three, it seems that the evolution of Tpu and tensorflow are sort of uh their co evolving almost uh in terms of both are learning from each other and from the community and from the applications where the biggest benefit is that you, that you've been trying to sort of with eager with carrots to make tensorflow is accessible and easy to use as possible. What do you think for beginners is the biggest thing they struggle with, have you encountered that or is basically what paris is solving is that eager like we talked about [/INST] for, for some of them, like you said, right, pick winners want to just be able to take some image model, they don't care if it's inception or restaurant or something else and do some training or transfer learning on the kind of model being able to make that easy is important. So in some ways if you do that by providing them simple models that say in hub or so on and they don't care about what's inside that box, but they want to be able to use it, so, so we're pushing on, I think different levels, if you look at just a component that you get, which has the layers already smashed in the beginners, probably just want that, then the next step is okay. Look at building layers with errors, If you go out to research then they are probably writing custom layers themselves or they their own loop. So there's a whole spectrum there </s><s>[INST] and then providing the pretrained models seems to [/INST] really decrease </s><s>[INST] the time from you're trying to start, so you could basically Nicole lab notebook achieve what you need. Uh so basically answering my own question, because I think what tensorflow delivered on recently is uh it's trivial for beginners, so I was just wondering if there was other pain [/INST] points you're trying to ease, but I'm not sure there would, no, those are probably the big ones, I mean I see high schoolers doing a whole bunch of things now, which is pretty amazing, it's both </s><s>[INST] amazing and terrifying. [/INST] Yes, </s>

<s>[INST] Do you have thoughts about the current war in Ukraine? Maybe from a military perspective, maybe from the Air force perspective. So I can just mention a few things, there's the Bayraktar drones that are being used, their unmanned, I think they have capability to be autonomous, but they're usually remotely controlled. They're used for reconnaissance, but they're also used by the Ukraine side for reconnaissance and I think um, also to destroy different technology tanks and so on different targets like this. So there's also on the, on the Russian side, the oil intent, there's the fighter jets MIG 29, the Ukraine side, Su 25 in the Russian side, is there anything kind of stands out to you about this particular aspects of what this war looks like that's unique to what you've experienced? [/INST] Maybe not unique, but it's just been absolutely incredible to see the footage, you know, I mean we're watching war on twitter, you know, essentially, and to see, you know, these aircraft flying down low spitting flares out, getting shot down, you know, it's incredible to to see this happening, you know, live for everyone to see. Um, so that's just kind of a quick meta comment. But as far as the actual, you know, I think these small form factor U A V s where they're just like strapping weapon to it and flying over and trying to drop it at the right time or any of these type of commercial applications of technology into this ad hoc warfare area is incredibly interesting because it shows, you know, how useful that technology can be outside of the military, right? Like these, like, especially like D G I right? Like there's obviously a lot of technology in there is being leveraged for other capabilities within, you know, PLC military or at least we would assume, um, what happens if that is more widespread, right? Like what if we were creating our own drones and they were being used against us, would we want to have some type of kill switch or something like that. Right? So what I think government is gonna have to consider like all these tools that are gonna be easily available to just any person could be turned into a tool of war. How do we stop that from being turned against us? You know, especially as we look at, you know, 10 years from now when we have a large number of autonomous U. A. V. S. Delivering packages and doing everything else over our country and any one of those could be potentially a weapon if we don't have the proper security. </s><s>[INST] Well, there's we're now in texas and texas values as guns and seize guns as among other things, a protector of individual freedom. You could see a future perhaps where and I certainly have experienced this in the empowering nature of this in Ukraine, where you can put the fight for independence into your own hands by literally strapping explosives to G. I drones that you purchase on your own salary. I mean that one of the interesting things about the voluntary army in Ukraine is that they're basically using their own salary to buy the ammunition to fight for their independence. That's a very kind of ideal, that sort of uh people speak about when they speak about the Second Amendment in this country, that it's interesting to see the advanced technology version of that, especially in Ukraine sort of using uh computer vision technology for uh surveillance and reconnaissance to try to um and and integrate that information to discover the targets and all that kind of stuff um to put that in the hands of civilians. It's fascinating to see, to sort of fight for their independence. You could say that to fight against authoritarian regime of your own government, all that kind of stuff. [/INST] It shows you how complicated the worst base in the future is going to be, you know, invading a land like that, where people have, you know, that many different types of resources absolutely changed warfare. </s><s>[INST] I mean, hopefully that creates a disincentive to start war, to go to war with a yeah, sort of it changes the nature of Guerilla warfare, [/INST] you know, I don't think Putin was expecting to be in that engagement quite as long as he has, of course. Um but it can show you how you can get caught up. You know, if if if land wars turn into an inescapable quagmire each time due to the complications around the the society's ability to access interesting tools, you know, it could be, you know, it could be a huge de motivator for aggression. Well, </s><s>[INST] let me ask you about this, do you think there will always be war in the world? Is this just a part of human nature? I think [/INST] so, I think I think it is until we, until we move past resource limitation, there's always going to be at least that one particular cause of conflict. And then we can also consider all our psychological lizard brain emotions that cause us to act out. Although, you know, hopefully we have enough things in place to stop that from rising to the level of war. But you know, we have our own biology or psychology and evolution to combat. Um, and then, but there are pragmatic reasons to exert violence sometimes unfortunately. And that one of those cases could be resource limitations. And so your question was, do I think there will be war in this world. My unfortunate answer is perhaps yes, but once there's more than one world and we're less resource constrained, then perhaps it will be a valve of source for that. </s>

<s>[INST] Can I ask you a difficult question. So there's this famous um photograph of a falling man, so many people had to decide when they're above the fire in the fire whether to jump out of the building or to burn to death. What do you make of that decision? What do you make of that situation. [/INST] Those people who jumped those were acts of sheer desperation. I've been in fires and just minor burns but minor, you know, in situation, but I've been trapped or caught somewhat ended up in the burn center for some nothing, nothing serious at all. But like, but I I for those brief seconds, half a minute was, thank God if I didn't have my fire gear on, I would have been burned to very, very horrible level. Those people we're burning alive and they had the choice of either to stay there and burn alive or two launch themselves. And some of them, I don't fault them, but they had a few folks, they won't show it anymore because they say, I don't know why I defend some people, but they had a couple of folks that took umbrellas and they took garbage bags because they thought that it would slow down there except the acceleration rate to the ground and maybe just maybe they wouldn't be killed. And that's to me, a true sense of desperation for humanity to say I'm going to die either way. But let me take my chance and I don't know the exact number of those folks who did that, but our first Member of the Fire Department killed firefighter Daniel sir from 8 to 16 was struck by a jumper and one of my dear friends was ordered to help take him and they knew he was passed away because he was hit by a Flying Missile. I mean 120 mph body lands on you. Those those two bodies are now crushed And they were ordered to take that firefighter and bring him across the street to engine 10 Ladder 10. It was literally a firehouse less than 100 yards from the facade of the trade center from the trade center complex, they literally right there and there was plane parts that went into that firehouse landed into the front doors onto the roof. But the building itself was not destroyed. So it was used as a mini command center for quite a while. So my friend was ordered to take Daniel's body in respect and bring it over to this firehouse and give it some semblance of dignity and lay it out on one of the the bunk room, the bunks we have in the bunkhouse and just cover it with a sheet and put a sign please firefighter kill do not disturb and then we'll get to him later because obviously this operation is going to go on for days and my friend who is such a great, great, wonderful guy is so still to this day filled with guilt because if they weren't taking his body out with the respect and dignity that they did, it took a while because you know it's just it's a tough situation, his ladder company, it's coming over the bridge, there's a famous picture Vlad in 118, you see this tractor trailer fire truck is the one with the guy in the back also drives and it's a zoomed out shot and you see the Brooklyn bridge and you see only the fire truck in the middle and you see the two burning towers in the distance. Well his engine company was just ahead of them on the bridge and the only reason that engine company lived is their initial duty assignment was to take that firefighter and bring his body over. It's like the military, we don't leave anyone behind. These are our guys as we, some guys say it's all about the guy right next to you and nothing else really matters when that guy right next to you goes down, it stops, you get that guy to safety or if he's dead, you get him out. So in that time frame that saved his life. But that's a heavy burden to carry now for the rest of your life because you say if I wasn't helping my dead friend, I'm dead. Yeah. </s><s>[INST] What did it look like a ground zero? What did it feel like? What did it smell like? What you said it? There is a sense that it was almost like a war zone. But can you paint the picture of um how much dust is in the air? How hot is it? How many people are there? And again, how did it feel like [/INST] it was just um, it was a scene of controlled chaos control because there was a semblance of command and we were just trying to do our jobs, but it was such a frantic pace because we're now digging frantically knowing that there's life underneath this pile </s><s>[INST] and this is throughout the afternoon of [/INST] that. Yeah, I mean this was nonstop, you know, uh just nonstop really for for days. But from my particular crew, we literally kept going. We initially were dispatched over towards number seven, had </s><s>[INST] just gone down, [/INST] We were searching the post office that was there, there was reports of people trapped and we painstakingly searched every single inch of that building to make sure no one was left in there. And then we were deployed to the pile and the piles sort of ambiguous because it was just such a vast, vast pile. I mean, it went for city blocks and we were we were assisting in the retrieval of two port Authority police officers were lucky enough to survive, but they were trapped, they were deep down into a crevasse and they had to be physically dugout and extricated. So there was a couple of 100 few 100 guys involved in that process of bringing in equipment, jaws of life airbags to lift steel, you just to cut pieces of steel. It was just a huge operation and we were back toward the logistics end of it. Shuttling in gear and and bring it, bring in stretchers, bringing in oxygen, you know, whatever whatever was needed. And you were trying to climb over this, this jagged pile of debris. It wasn't like you just walked 100 ft on a on a street with something, you were trying to climb over this I beam and then down into this hole and then I'll back up that whole. I mean, just to run one piece of equipment, took a half an hour to get 100 ft, 200 ft mind you, some of these pieces of equipment, £100 you know, generator for her stools, this massive motor on a frame, </s>

<s>[INST] that helped your regular life. [/INST] Yeah, of course it's, you know, it's suddenly when you go into any any situation that might be stressful, It's not like an important meeting or super whatever it is, it's like how much would you worry about that before? Worried? It's not gonna help you anywhere, It's the opposite. Just going to make you more nervous, you how to accelerate your ability to think clearly is gonna be damaged by that. So it's like the more calm, the more relaxed you are, the better you can think of. </s><s>[INST] You ever get angry? [/INST] Yeah, </s><s>[INST] I can traffic, you ever, you ever get like not calm just like you're screaming, [/INST] No, it's not in a screaming no, but </s><s>[INST] just angry. What does angry look like? Is it still [/INST] calm? Yeah, like, you know, a few seconds of complaining but then it goes away. </s><s>[INST] Have you ever like thrown a cell phone at the wall or some like that? No, [/INST] I never get that because that's just silly. It's like it's it's it's if if I would have done that I would not be able to control my emotions prior to fight reflection, </s><s>[INST] letting yourself lose, losing [/INST] control. That will reflect other times. </s><s>[INST] Do you think it has uh make in part made you more emotionally closed off from the world? Like your it's harder for you to be vulnerable to others. [/INST] Probably. Yeah, but I heard that a few </s><s>[INST] times. [/INST] I'm emotionally closed. Its Yeah, maybe that I think that influenced. Yeah. Yeah. For not for many years before that thing maybe I'm getting older something that I mean it's no, I mean </s><s>[INST] the notebook, I [/INST] mean I would say the last few years I've been crying more than before for some reason. I don't know why like silly movies like nothing. Somebody brings tears to my eyes. </s><s>[INST] Yeah. Well I [/INST] already I already </s><s>[INST] just having met you interact with you. I can see that you're kind of opening your heart and mind to the world. You could you could see like here's this historically great athlete now, like the wars have been fought and you're now like waking up to the world. It's it's cool to see [/INST] probably I'm bringing my guard down now. I don't have to get it up. </s><s>[INST] You can even do some podcasts. Um you said you watch like movies beforehand sometimes mentioned Braveheart. What were you doing? Did you watch something beforehand, like the day before I [/INST] used to yeah it was like a thing Braveheart and Gladiator. I mean there's a few others that I've always watched the day before because the day before used to do nothing. I just want to be at home in bed watching tv like saving you know energy stretching by myself. So it's like it's just want to save energy, I don't waste my energy going out going around. So you know those are the movies that I always like to watch kind of trying to bring some you know hyper excitement like you know I'm getting ready to watch tomorrow so I'm like let me watch some movies that like brought their you know some that warrior spirit into me. </s><s>[INST] What is that about human nature? Braveheart, I love even more. Should you put your life on the line for a thing that matters or run away just so you can live, it's like Ronnie, you may live but like years from now when you look back at this moment, would you trade all the days [/INST] just </s><s>[INST] to come back to this moment [/INST] and tell the english </s><s>[INST] you can take our lives but you can't take our [/INST] freedom. I </s><s>[INST] mean man, what is that about human nature? Um is there some aspect of like the glory you were able to achieve? Being more important than anything else. There's some aspect of that that that's that's greatness you know? [/INST] Yeah, I never pursue Gloria. So it just came, you know? It is it came with it, but that was never my goal. I never cared for glory. </s><s>[INST] Were you able to experience? Like like I'm at the height of this thing, whatever whatever humanity is able to achieve in various things, holy sh it I'm flying, [/INST] I felt like um no one can touch me, I can destroy people. Yeah, </s><s>[INST] prolonged periods of time or just momentarily. [/INST] I always knew, you know, from before I got to a black belt. Like I I you know, I can be great because my program, you know, I used to train with the best in the world. I used to, you know for many years and I used to see my progression with then everybody else. So I I knew I was getting somewhere. I know I could be the best and that was that was also my goal since very, very young and I always believed that I could be and that over the years that kept telling me over and over again because I'm getting better and better faster than everybody else. So I just need to carry on with what I'm doing. </s><s>[INST] But I think you've said that you wanted to maybe you thought you could be the greatest of all time like at the very beginning, like when you sucked [/INST] Yeah, not not the greatest of all time because and I never really thought about that, but I thought I'm gonna be the best in the world when I sucked when I suck. </s><s>[INST] Okay so what is that? Uh what is that like that Self belief? Is there a component to that self belief? Being a prerequisite [/INST] is difficult to say because that was a decision. I think like why did I believed I could be, I can't tell you that because I don't know. But </s><s>[INST] you think you decided to, [/INST] I decided to, I decided to be and I believe that could </s>

<s>[INST] And it's just 20 years, 30 years at the level. And so you kind of draw a lot of value from staying close to nature and all of these kinds of ways. They're keeping you humble. Like you said, what is it? The goat is still gonna crap on you. [/INST] Oh yeah, the doggies will shit on you. Oh yeah, the doggies will shit on you, </s><s>[INST] whether you're broker or billionaire. That's a good line. That's not like, the line you'll be remembered for [/INST] if the universe has a sense of humor. </s><s>[INST] Right, it's a Neo Yogi Berra. So I think mushrooms is a good place to ask about my friend, Joe Rogan. So I'll keep folks from the Cardano community keep saying things like, Lex podcast first, then Joe Rogan experience. I guess I'm the moon and Joe is Mars in this metaphor. Since I'm a CS person, I can talk a little bit more fluently about cryptocurrency because fundamentally, cryptocurrency is a computational idea. But then there's somebody like Joe, who's more like an everyman. He does not necessarily know the technical intricacies of cryptocurrencies. What kind of, and I don't think he's had [/INST] a cryptocurrency person on. </s><s>[INST] I did the interview Andreas Antonopoulos. Oh, he did. That's right, a long, long time ago. But that was almost like, the cryptocurrency space goes through phases. And I think we're in a new era of some kind. And how do you talk to Joe about Cardano? How do you talk to Joe about what the heck? I remember somebody tried to explain to him what Dogecoin is. How do you explain this whole space of what Bitcoin is, of where Ethereum is, of where Cardano and smart contracts and some of this proof of stake ideas [/INST] that we've been talking about? You don't. What you do is you start with applications that they're interested in. So he's an elk hunter. And so he's probably interested in elk tags, right? So you start there and you say, that whole system can be put on a blockchain. And here's how it's gonna be better for you. You say that's what you do. You always connect it to something they know and love. And then once they get that, they say, oh, that's really cool. And then they ask, what else can you do with it? What else can you sell me on it? And you kind of work your way outwards there. Problem technologists make is they're so damn in love with the technology. They have that tail wagging the dog where they just wanna talk about the technology and how incredibly cool it is. And that's fun. It's like talking about math. Oh God, let's talk about cohortisms. That's fun. All right, yeah. Everybody's eyes glaze over. You know, you always have to connect it to the interest of the particular person and what they care about, what they love, what they need, royalty payments. You know, he's a big guy. He's got the Spotify thing. He's got all these things going on. Intellectual property is probably pretty important, Joe. It's some juncture. So NFTs, we can talk about this concept of perpetual royalties. So for example, let's say that you create a piece of art. You can build into the token itself. A perpetual royalties is something you care about. Maybe every time it sells, it pays it back to you. Or maybe every time it sells, it donates to some clean water charity or something like that. The point is that the actual acquisition of the NFT requires adherence to that smart contract. So people can't deviate from your desire even after you die. So, you know, stuff from Andy Warhol or from Picasso, that can still be generating some donation every time a Picasso sells to something else. You can do that with NFTs. And so he starts thinking, God, what else can I do? I do shows. Maybe I can do my tickets with these types of things. Maybe I can do loyalty points for my fans. So now you got him engaged and he's thinking all the opportunities for him. And it gives him an incentive to anchor and connect to those concepts. And then over time, he starts asking question, well, how do we know it's secure? Then we can talk about proof of work or proof of stake or these types of things. Well, so this is how it stays secure if you're really interested. And there's an incentive to have the attention span necessary to do the homework, </s>

<s>[INST] they really are giving a part of themselves in the name of service. Maybe over time they become cynical and become jaded and worn down by the whole system. But I think a lot of [/INST] it is </s><s>[INST] healed, I [/INST] think. And </s><s>[INST] I don't think I'm well, I'm in part naive, but not fully that a lot of it is healed through the power of conversation, just basic social interaction. I do think that the effects of this pandemic listen, just sitting there and it doesn't have to be talking about the actual issue. It's actually humor and all those kinds of things about personal struggles, all those kinds of things that remind you that you're all just humans. Yeah, Well, [/INST] the great leaders that I've met because, and I've met some now they go listen to their constituents. It's not a policy discussion. It's not an ideology discussion. They go say, okay, what's, what's your, what's your life like and what are your problems and tell me about them? And then they listen and then they're struck by them and then they gather up all that misery and they bring it to the congressional officer to the parliament and they think here's what the people are crying out for and the good leaders that's a leader leader listens so I talked to jimmy carr about comedy and he's sold out stages worldwide on a tour being funny. That's hard. He said, comedy is the most stand up comedy, which is what I do in some real sense. It's a thing I do that. It's most akin to what I'm doing on my book tours. I would say it's the closest analog. He said it's the most biological enterprise. And I thought, well, why? What do you mean? Because it's just the monologue and and it's a prepared monologue. I mean, you have to interact dynamically with the audience while you're telling your jokes and you gotta get the timing right, but you have a body of jokes said, well, here's how you prepare the jokes. And I've been told this by other comedians, You go to 50 clubs before you go on your tour and you got some new material and you think it's funny and you go into a club and you lay out your new material and people laugh at some of it and you pay attention To what they laugh at and what they don't laugh at. So you subject yourself to the judgment of the crowd and you get rid of everything that isn't funny. And if you do that enough, even if you're not that funny, the crowd will tell you what's funny. So you can imagine imagine you do 50 shows and each is an hour long and you collect two minutes of humor from each show. So you throw away 90, you throw away two hours more than 98% of it, collect two minutes per show. So you're not very funny at all. You're like funny 2% of the time you aggregate that man, you're a scream. </s><s>[INST] So, [/INST] so that's what a leader does is that is what a leader does is goes out and he aggravates the misery, you know, and the hopes and then I do think that's revivifying to someone who would otherwise be cynical and jaded because then the person can say to themselves, despite the inadequacies of the system and my inadequacies. I'm I'm gathering up the misery and, and the hope and I'm bringing it forward where it can be </s><s>[INST] giving, giving it a voice [/INST] giving, that's right, giving it a voice. Can </s><s>[INST] you actually take me through a day? Because it's fascinating. Um, through your comedy tour. Um, what is a day in the life of Jordan Peterson look like? Which is this very interesting day. Let's look at the day when you have to speak, preparing your mind, thinking of what you're going to talk about preparing yourself physically, mentally to interact with the crowd, through the actual speaking, how do you adjust what you're thinking through and how do you come down from that? So you can start all again as a limited biological system? [/INST] Well, I'm usually up by seven and ready to go by 7 30 or eight, </s><s>[INST] coffee, [/INST] no steak and water. How </s><s>[INST] many times a day, steak? [/INST] All that's all I eat </s><s>[INST] three [/INST] Or four, depending on the day, </s><s>[INST] steak [/INST] and sparkling water. Yeah, so monastic asceticism, man. </s><s>[INST] Well, I did the proper, I I usually, just once a day I did the proper Jordan Peterson last night and just ate two steaks. [/INST] And how was that </s><s>[INST] was wonderful? [/INST] Yeah. Well if you have to only eat one thing, you know, could be worse. So anyways, I'm ready to go at eight because we're generally moving, </s><s>[INST] what does that mean? You're flying [/INST] somewhere and we usually use private flights now because the commercial airlines aren't reliable enough and you cannot not make a venue. Right? So that's rule number one on the tour, you make the show. So everything. And then number rule number two, is anybody who causes any trouble on the tour is gone Because there is zero room for error. Now. No, there's zero room for unnecessary unaddressed error. So because there's gonna be errors, the guys I have around me now, if they make a mistake, they fix it right away. So, and that's great. </s><s>[INST] There's a lot of people relying on you to be there. So you [/INST] have like 4000 people typically. So, so then I'm on the plane and I'm usually, I usually write or often because there's no internet on the plane and, and that's a good use of time. So I'm writing a new book. So I write on the plane, typing. Yeah, typing. And uh, then we land and we go to, it's usually early afternoon by then we go to a hotel. It's usually a nice hotel that's not corporate. I don't really like corporate hotels. My secretary and my, one of my logistics guys has got quite good at picking kind of adventurous hotels, boutique hotels are usually in the old parts of the city, especially in europe, somewhere interesting. And so we go there and then lunch usually, and sometimes that's an air fryer and a stake in the hotel room. And I leave a trail of air fryers behind me all across the world. And uh then tammy and I used to go out and have a walk or something and take a look at the city and then I have a rest for like an hour and a half or an hour, half an hour. Now I have to sleep for 20 minutes and that's about all I can sleep. But I need to do that in the late. Yeah that gives me that wakes me up again for the evening and then tam has to sleep longer. She's still recovering from her illness. And so she has to sleep longer in the afternoon. And that's absolutely necessary for both of us or things start to get frayed. And so then we go to the venue and then I usually sit for and an hour if I'm gonna lecture, I've been doing a lot of Q. And A. S. And that's a little easier. But if I'm gonna lecture I have to sit for an hour and then I think okay what question am I trying to investigate? I have to have that that's the point. What mystery am I trying to unravel? It's usually associated with one of the rules in my book because technically it's a book tour. But each of those rules is an investigation into an ethic and each of them points to a deeper sort of mystery in some sense and there's no end to the amount that can be explored. And so I have the question, the question might be something like uh put your put your House in perfect order before you criticize the world. Okay, what does that mean exactly? What does house mean? What does put what does put me in that active verb? What does perfect and order mean? Why before you criticize the world, what does it mean to criticize? What does it mean to criticize the world? How can you do that properly or improperly? So, I start to think about how to decompose the question </s>

<s>[INST] unintentional. [/INST] I thought for a long time, I always labeled it as collateral damage </s><s>[INST] damage. [/INST] But actually just today there was a really impressive threat researcher at Cisco, which has this threat intelligence division called Talus, who said stop calling it collateral damage. They could see who was going to get hit before they deployed that malware. It wasn't collateral damage. It was intentional. They meant to hit any business that did business with Ukraine. It was it was to send a message to them too. So I don't know if that's accurate. I I always thought of it as sort of the sloppy collateral damage, but it definitely made me think </s><s>[INST] so how much of this between States is going to be a part of war? This kind of these kinds of attacks on Ukraine, between Russia and U. S. Russia and china china and us, let's look at china and us, do you think China and us are going to escalate something that would be called the war purely in the space of cyber. [/INST] I believe any geopolitical conflict from now on is guaranteed to have some cyber element to it. The Department of Justice recently declassified a report that said china has been hacking into our pipelines and it's not for intellectual property theft, it's to get a foothold. So that if things escalate in Taiwan, for example, they are where they need to be to shut our pipelines down. And we just got a little glimpse of what that looked like with colonial pipeline and the panic buying and the jet fuel shortages and that assessment I just mentioned about the diesel. So they're, they're, you know, they've they've got in there. Um, anytime I read a report about new aggression from fighter jets, chinese fighter jets in Taiwan or what's happening right now with Russia's build up on the Ukraine border or India Pakistan, I'm always looking at it through a cyber lens and it really bothers me that other people aren't because there is no way that these governments and these nation states are not going to use their access to gain some advantage in those conflicts. And you know, I am now in a position where I'm an advisor to the cybersecurity infrastructure security agency at the D. H. S. So I'm not saying anything classified here, but I just think that it's really important to understand just generally what the collateral damage could be for american businesses and critical infrastructure in any of these escalated conflicts around the world because just generally our adversaries have learned that they might never be able to match us in terms of our traditional military spending on traditional weapons and fighter jets. But we have a very soft underbelly when it comes to cyber 80% or more of America's critical infrastructure. So pipelines, power grid, nuclear plants, water systems is owned and operated by the private sector and for the most part there is nothing out there legislating that those companies share the fact they've been breached, They don't even have to tell the government they have been hit. There's nothing mandating that they even meet a bare minimum standard of cybersecurity. Um, and that's it. So even when there are these attacks, most of the time, we don't even know about it. So that is, you know, if you're going to design a system to be as blind and vulnerable as possible, that's as, that's as pretty, pretty good. That's what it looks like is what we have here in the United States. And everyone here is just operating like, let's just keep hooking up everything for convenience. You know, software eats the world. Um, let's just keep going for cost for convenience sake just because we can. And when you study these issues and you study these attacks and you study the advancement and the uptick in frequency and the the lower barrier to entry that we see every single year, you realize just how dumb software eats world is and no one has ever stopped to pause and think should we be hooking up these systems to the internet, They've just been saying, can we let's do it? And that's a real problem. And this and just in the last year, you know, we've seen a record number of zero day attacks. I think there were 80 last year, Which is probably more than double what it was in 2019. A lot of those were nation states. Uh, you know, we live in a world with a lot of geopolitical hot points right now and where those geopolitical hot points are are places where countries have been investing heavily in offensive cyber tools. </s><s>[INST] If you're a nation state, the goal would be to maximize the footprint of zero day, like super secret zero day that nobody is aware of. And whenever war is initiated, the huge negative effects of shutting down infrastructure or any kind of zero day is the chaos it creates. So if you just there's a certain threshold when you create the chaos, the markets plummet, just everything goes, goes to hell. [/INST] I mean it's not just zero days. You know, we make it so easy for for threat actors. I mean we're not using two factor authentication, we're not patching. Um there was the shellshock vulnerability that was discovered a couple of years ago. It's still being exploited because so many people haven't fixed it. Um so you know, the zero days are really the sexy stuff. And what really got drew me to the zero day market was the moral calculus we talked about um particularly from, you know, the U. S. Government's point of view, how do they justify leaving these systems so vulnerable when we use them here? And we're baking more of our critical infrastructure with this vulnerable software. You know, it's not like we're using one set of technology and Russia's using another and china is using this, we're all using the same technology. So when you find a zero day in windows, you know, you're not just leaving it open so you can spy on Russia and plant yourself in the Russian grid you're leaving americans vulnerable to. But you know, but zero days are like that is the secret sauce, you know, that's the that's the superpower. You know? And I always say like every country now with the exception of Antarctica, someone added the Vatican to my list is trying to find Offensive hacking tools and zero days to make them work. And Those that don't have the skills now have this market that they can tap into where, you know, $2.5 million dollars that's chump change for a lot of these nation states, it's a hell of a lot less than trying to build the next fighter jet. Um but yeah, the goal is chaos. I mean, why did Russia turn off the lights twice in Ukraine? You know, I think part of it is chaos. I think part of it is to to sow the seeds of doubt in their current government, your government can't even keep your lights on. Why are you sticking with them? You know, come over here and we'll keep your lights on at least, you know, there's like a little bit of that </s>

<s>[INST] and what does control mean? So his action is the fundamental element. [/INST] It means making rational decisions now and rational decisions or decisions that maximize the measure of utility </s><s>[INST] and sequentially so many decisions. Time and time and time again now, like it's easy to see that kind of idea in the space of maybe games in the space of robotics. Do you see it bigger than that? Is it applicable? Like we're the limits of the applicability of reinforcement learning. [/INST] Yeah. So rational decision making is essentially the encapsulation of the ai problem viewed through a particular lens. So any problem that we would want a machine to do? Uh intelligent machine can likely be represented as a decision making problem. Classifying images is a decision making problem, although not a sequential one. Typically uh you know, controlling a chemical plant as a decision making problem, deciding what videos to recommend on youtube is a decision making problem. And one of the really appealing things about reinforcement learning is if it does encapsulate the range of all these decision making problems, perhaps working on reinforcement learning is uh you know, one of the ways to reach a very broad swath of ai problems. </s><s>[INST] But what what do you is the fundamental difference between reinforcement learning and maybe supervised machine learning. [/INST] So reinforcement learning can be viewed as a generalization of supervised machine learning. You can certainly cast supervised learning as a reinforcement learning problem. You can just say your loss function is the negative your reward. But you have stronger assumptions, you have the assumption that someone actually told you what the correct answer was uh that your data was idea and so on. So you could view reinforcement learning essentially relaxing some of those assumptions. Now, that's not always a very productive way to look at it because if you actually have a supervised learning problem, you'll probably solve it much more effectively by using supervised learning methods because it's easier. But you can view reinforced morning as a generalization of that. Know for sure, </s><s>[INST] but they're fundamentally different. That's a mathematical statement. That's absolutely correct, but it seems that reinforcement learning, the kind of tools will bring to the table today of today. So maybe down the line, everything will be a reinforcement learning problem just like you said, image classification should be mapped to a reinforcement learning problem. But today the tools and ideas, the way we think about them are are different sort of supervised learning has been used very effectively to solve basic narrow ai problems, reinforcement learning kind of represents the dream of a I it's very much so in the research space now into captivating the imagination of people of what we can do with intelligence systems, but it hasn't yet had as wide of an impact as a supervised learning approaches. So that sort of, my question comes to the more practical sense, like what do you see is the gap between the more general reinforcement learning and the very specific yes, it's a financial decision making with one sequence, one step in the sequence of the supervised learning. [/INST] So from a practical standpoint, I think that one one thing that is uh you know, potentially a little tough now and this is I think something that we'll see this is a gap that we might see closing over the next couple of years is the ability of reinforcement learning algorithms to effectively utilize large amounts of prior data. So one of the reasons why it's a bit difficult today to use reinforcement learning for all the things that we might want to use it for is that in most of the settings where we want to do rational decision making? Um It's a little bit tough to just deploy some policy that does crazy stuff and learns purely through trial and error. It's much easier to collect a lot of data, a lot of logs of some other policy that you've got and then maybe you you know if you can get a good policy out of that then you deploy it and let it kind of fine tune a little bit. But algorithmic li it's quite difficult to do that. So I think that once we figure out how to get reinforcement learning to bootstrap effectively from large data sets then we'll see a very very rapid growth in applications of these technologies. So this is what's referred to as off policy reinforcement learning or offline RL or batch RL. Um And I think we're seeing a lot of research right now that does bring us closer and closer to that. </s><s>[INST] Can you maybe paint the picture of the different methods she said? Uh Off policy, what's value based reinforcement learning, what's policy based, what's model based, what's off policy on policy, what are the different categories of [/INST] reinforcement? So one way we can think about reinforcement learning is that it's it's in some very fundamental way it's about learning models that can answer kind of what if questions So what would happen if I take this action that I hadn't taken before? Um and you do that of course from experience from data and often times you do it in a loop. So you build a model that answers these, what if questions uh use it to figure out the best action you can take and then go and try taking that and see if the outcome agrees with what you predicted. Um So uh the different kinds of techniques basically refer different ways of doing. And so a model based methods answer a question of uh what state you would get, basically what would happen to the world if you would take a certain action. Value based methods? Uh they answer the question of what value you would get, meaning, what utility you would get. Um but in a sense they're not really all that different because they're both really just answering these. What if questions now, Unfortunately for us with current machine learning methods answering what if questions can be really hard because they are really questions about things that didn't happen if you want to answer. What if questions about things that did happen, you wouldn't need to learn model, you would just like repeat the thing that worked before. Um and that's really a big part of why RL is a little bit tough. So if you have a purely on policy kind of online process then you ask these what if questions you make some mistakes, then you go and try doing those mistaken things and then you observe kind of the counter examples that will teach you not to do those things. Again if you have a bunch of off policy data and you just want to synthesize the best policy you can out of that data then you really have to deal with the challenges of making these these counterfactual. </s>

<s>[INST] My dad was like, yeah, say goodbye to him, you know. [/INST] I guess he does, gangster. I got it. Tough guy. He did some gangster shit that day. But on my end, I was being isolated, basically, as COVID is, everybody's slowing down. No more classes, no more excuses to go out there and drink and no more socializing. So social drinking turned into alone drinking more and more and more. I bought a bottle of gin because I was down in Mexico taking care of my dad, and they closed down beer production in Mexico. So beer went away, and beer was a way I kind of managed it. It's not hard alcohol, it's just beer. But that went away, so it was just hard alcohol. That was what's available down there. One night alone at the house, my dad's house, I drank a bottle of gin, a whole bottle of wine, and I almost died. And after that, some people started noticing that I was isolating more and more, and it was kind of eating away at me. I was in a relationship at that point when I started seeing everything just kind of fall apart around me. And I drank half of a glass of wine, and it made me sick internally in my mind. And my kid said to me, and I don't know, nobody coached her, nobody said anything to her. She's a pretty intuitive kid. She said, I don't drink anymore, dad. I thought of nowhere in the middle of the night. And I stopped. I stopped that night. I remember waking up at three in the morning and taking a cooler that I had and just dumping all the beers in it and chucking them in the garbage, and with a knife poking each of them to not be tempted to go pack for them. And then the second day, I went around and started finding the hides that I had because I had some hides. And then I went somewhere and locked myself in for two weeks. I had the withdrawals, the clearest nightmares that I'd ever had in my life for two, three weeks. I went somewhere. I don't want to keep them private, but I went somewhere where they offered a place for me. And when I asked them about it, it's a community. I gave them some money for their school as a donation. I gave them like a few thousand dollars. I said, yeah, never come. You can go through this process here. Cool as fuck people. The first thing they did when I got there is they stood me up in front of everybody to thank me for the donation and then told everybody that I was an alcoholic. And if anybody saw me drinking, I was to be kicked out of there immediately. And I felt horrible. So that was where I started. Is that temptation still there? There was a moment when it was. And some therapy circle. There's a rodeo clown friend of mine who his body's, his spine is basically fused together, you know, type of guy. We've been friends and enemies and friends again, you know, in during the heart therapy circle sessions. Oh, so like there's an intimacy there. Yeah. He didn't know anything about me. One time when we were telling our story, he stood up and told his story and then he heard mine and then he was pissed off at me and didn't want to talk to me for a while. And then later he told me that it was because he saw what I did with my experience and how much of a difference that he's perceived that I was making with it. And he felt jealous that he can do the same with his experience because he was just a broken ex rodeo clown. He told me when I was going through the process, like, Hey, you're an internet celebrity person. You know, you're, you're known. Are you worried about people finding out that you're, that you're recovering drunk? And I said, yeah, it's fucking scary as shit. If people find out that I am going through this process, it's scary that, you know, the critique, you know, I already get a lot of shit for being a ex police officer in Mexico and all that, uh, all the negativity that comes from that. And he said, don't be, you know, that you can't pickpocket a naked man. So just get naked. And what does that mean? Write about it. Post it online. You never know somebody, somebody out there might get inspired to do their own kind of process. So I started posting cowardly in a way because I wanted to make other people keep me on the path, you know, but in other ways, you know, uh, desperation. You know, I w I don't want to drink anymore. I don't want to go back to that. I'm not a bath, which I know leads directly to a bad death. I'm not afraid of death. I just want a good one. I don't want a bad one. I think that was going to lead me to a bad death. As our writing about in sharing it online, you know, through my, uh, fever dreams post. And just being humorous about it online and Getting a lot of hate on one side, having a few people and companies that I work with kind of step back and seeing this guy has some issues to having other people kind of make fun of </s><s>[INST] or make light of that weakness portrayed. Also getting hate, getting criticism, because here you are, a counter narcotics police officer, there's no, that's a drinking problem. [/INST] So is that like supposed to be what like flaws revealed? Weakness or a perception of alpha in the U.S. I guess that some people have, you know. You were supposed to be strong and here you are. I mean, I'm not Jocko Willnick, I'm not David Goggins, you know, I'll wake up at 10 in the morning sometimes and I'll have cornflakes with my eight year old, you know. I like days off. I used to wake up at 3 30 in the morning every day to review what happened during the night and then go off for a jog and then the gym and just be ready to be able to murder somebody with my hands if I had to. But that is, I couldn't maintain that during the whole process of getting out of it. Now leaving alcohol, I remember just being honest with it and just seeing the two sides of it, you know. Joe told me, never read the comments section, right? Which is a beautiful, it's a beautiful piece of advice. But they get you sometimes. When you talk about some of these things openly and some of the comments were positive and I've been seeing people comment, sending me messages and meeting people on the road that are five months in, 10 months. Some people that have been on that wagon for way longer than I have. And there's, it's what's cool when you meet people that are superhuman or perform and take an extreme ownership of things and are just amazing people that are thriving out there, inspirational. I see some of these people and I'm like, holy shit, I need to figure out how to get to some semblance of that. But I'm not that, you know. I've been through the wringer. I've fucked up a shit ton of times. My nose is an example of that, a few missing teeth. But in a way, I think all of that is part of the process that not a lot of people wanna talk about, you know. Independently of the experience I got down there and some of the things that I show and talk about and some of the advocacy I do related to women like her that are, you know, trying to look for a better life and trying to find their missing kids, training people to not get into those situations. But also showcasing the fact that people that go through some of these processes have a journey to go through, you know. I just came into your studio with a duffel bag. Straight from the airport and I'm gonna leave early tomorrow morning to somewhere else. I've been on the road for almost, I think, five years nonstop. I go back to a specific place every week to see my kid for two, three days. And then I'm back out, you know, some people are like, are you running? Like, are you worried, is this afraid about them? No. But I am, you know, on this weird path, I guess, trying to look for something that I think I've been missing. As far as my afterlife of a sort, you know, coming out of that gap. </s>

<s>[INST] Oh no. And you access it the imax. Okay. Do you still program these days? [/INST] I do a little bit um honestly, the last thing I did was um, I had written, I was working with my son description Minecraft stuff. So I was doing a little bit of that. That was the last literally last Kodi maybe. I did. Oh, you know what also I wrote some code to do some cap table evaluation, waterfall modeling kind of stuff. </s><s>[INST] What advice would you give to a young person who said your son today in high school, maybe even college about career, about life. [/INST] This may be where I get into trouble a little bit. We are coming to the end. We're rapidly entering a time between worlds. So we have a world now that's starting to really crumble under the weight of aging institutions that no longer even pretend to serve the purposes they were created for. We are creating technologies that are hurtling billions of people headlong into philosophical crises who they don't even know the philosophical operating systems in their firmware. And they're heading into a time when that gets vaporized. So for people in high school and certainly I tell my son this as well. He's in middle school, people in college, you are going to have to find your own way. You're going to have to have a pioneer spirit. Even if you live in the middle of the most dense urban environment, all of human reality around you is the result of the last few generations of humans agreeing to play certain kinds of games. A lot of those games no longer no longer operate according to the rules. They used to um collapses nonlinear, but it will be managed. And so if you are in a particular social caste or economic cast and it's, it's, it's not um, I think it's, it's not kosher to say that about America, but America is a very stratified and classist society, There's some mobility, but but it's really quite classist and in America. Yeah, unless you're in the upper middle class, you are heading to very choppy waters. So it is really, really good to think and understand the fundamentals of what you need to build a meaningful life for you, your loved ones with your family. Um, and almost all of the technology being created that's consumer facing is designed to own people to take the four stack, you know, of people to the laminate them and to own certain portions of that stack. And so if you want to be an integral human being, if you want to have your agency and you want to find your own way in the world, you know, when you're young would be a great time to spend time looking at some of the classics around, you know what it means to live a good life, what it means to build connection with people and so much of the status games, so much of the staff, you know, one of the things that I sort of talked about as we create more and more technology, there's a gradient technology, integrating technology always leads to gradient of power and this is chocolate point to some extent as well. And that gradient of power is not going to go away. The technologies are going so fast that even people like me who helped create some of the stuff, I'm being left behind on the cutting edge research, I don't know what's going on against today. You know, I go read some proceedings. So as the world gets more and more technological, it will create more and more gradients where people will cease power, economic fortunes and the way they make the people who are left behind okay with their lot in life is they create lottery systems. They make you take part in the narrative of your own being trapped in your own economic sort of zone. So avoiding those kinds of things is really important knowing when someone is running game on you basically. So these are things I would tell young people it's a dark message, but it's realism. I mean, that's what I see. </s><s>[INST] So after you gave some realism, you sit back, you sit back with your son, you're looking out of the sunset. What to him. Can you give as words of hope and to you from where do you derive hope for the future of our world? So you said at the individual level, you have to have a pioneer mindset to go back to the classics to understand what is in human nature, you can find meaning, but at the societal level what trajectory when you look at possible trajectories, what gives you hope? [/INST] What gives me hope is that we have little tremors now shaking people out of the reverie of the fiction of modernity that they've been living in kind of a late 20th century style modernity. Um, that's that's good I think because um, and also to your point earlier, people are burning out of some of the social media stuff. They're sort of seeing the ugly side, especially the latest news with facebook in the, in the whistleblower. Right, It's quite clear these things are not all they're cracked up to be. So do you </s><s>[INST] believe like I believe better social media can be built because they are burning out and that will incentivize other competitors to be built. Do you think that's possible? [/INST] Well, the thing about it is that, um, when you have extractive return on returns, you know, capital coming in and saying, look, you own a network, give me some exponential dynamics out of this network. What are you gonna do? You're gonna just basically put a toll keeper at every single node and every single graph edge, every note and every vertex, every edge. Um, but if you don't have that need for it, if no one's sitting there saying, hey, Wikipedia, monetize every, every character, every bite, every phrase, then generative human dynamics will naturally sort of arise assuming we do, we respect a few principles around online communications. So the greatest and biggest social network in the world is still like email smS. Right. So we're fine there. The issue with the social media, as we call it now is they're all, they're actually just new amplification systems right now. It's benefit of certain people like yourself who have interesting content um, to, to, to, to be amplified. Um, so it's created a creator economy and that's, that's cool. There's a lot of great content out there, But giving everyone a shot at the famed lottery saying, Hey, you could also have your, if you wiggle your butt the right way on Tiktok, you can have your 15 seconds of micro fame, that's not healthy for society at large. So I think if we can create tools that help people b uh conscientious about their attention, spend time looking at the past and really retrieving memory and calling, not calling, but processing and thinking about that, I think that's certainly possible, and hopefully that's what we get. Um So I'm so I think the bigger picture of the bigger question about that you're asking about what gives me hope is that um these early shocks of, you know, covid lockdowns and remote work and all these kinds of things. I think it's getting people to a point where they are, look, they're they're sort of no longer in the reverie, right? As my friend Jim says, there's more people with ears to hear now, right? With pandemic um and education, everyone's like, wait, wait, what have you guys been doing with my kids? Like how are you teaching them that is what is this crap? You're giving them his homework? Right. So I think these are the kinds of things that are getting um and the supply chain disruptions, getting more people to think about, how do we actually just make stuff? This is all good. But the concern is that it's still going to take awhile for these things for people to learn how to be a gent, IQ again, um and to be in right relationship with each other and with the world. So the message of hope is still people are resilient and we build, we are building some really amazing technology. </s>

<s>[INST] That's an incredible success. And uh that's really exciting, especially given that the people who have committed who attempted to commit suicide were let into the study. And so these are the people who are truly suffering. Um I mean that that's incredibly exciting and I mean just to speak to the frustration why things can't move faster. But but for what it is, it's incredibly exciting is there other studies of this nature that you foresee enabling the same kind of positive impact whether it's M. D. M. A. For other things like treating addiction or maybe it's so Simon for [/INST] for other conditions. </s><s>[INST] Is there something else that's promising. [/INST] Yeah. I think that um what we've discovered I don't think is unique to M. D. M. A. So it's M. D. M. A. Assisted psychotherapy. M. D. M. A. Is ideal for PTSD. You know maybe it won't work as well for O. C. D. Or other things. You know it's very strategic why we chose M. D. M. A. And why we chose PTSD. But I don't think that the results that we've got our so unique to MDMA assisted therapy. I think that psilocybin assisted therapy is going to be great for people with life threatening illnesses, cancer. You know we're anxious about dying. It looks like it's really good in the treatment of addiction. Um Again these are in combination with sort of the psilocybin, tobacco was cognitive behavioral therapy with silly Simon. Um I think that it's going to be a little bit more difficult. Still assignment for depression. I don't know if it will be quite as good. You know there are some biological aspects sometimes to depression but I think they'll be really good results for psilocybin for depression. I think it will be approved. It's considered a breakthrough therapy by the FDA. I began as phenomenal for opiate addiction, helping people go through withdrawal and then giving them this chance to deal with the material that they've um that drives them for addiction? There was Ben Sasse a doctor Ben Sasse in England did MDMA for alcohol use disorder and that was really great. The results he got and it's it's the case that he ended up basically treating people for trauma. It's the trauma that people run the emotional challenges that people run from into quieting that pain through drug addiction or alcoholism. So, trauma is behind a lot of addiction. I think that we are going to see um a revolution in psychiatry and that there will be a lot of conditions that have left a lot of people still suffering that psychedelic assisted therapy, different psychedelics, different approaches. But I think that we will see a lot of hope for psychiatry and psychotherapy and that psychedelics would be a big part of changing the practice of of psychiatry and psychotherapy. </s><s>[INST] Yeah, this is really to me, fascinating. So, I I actually um when I was younger for the longest time want to be a psychiatrist. So I was excited by psychotherapy. But then I perhaps incorrectly, maybe you can correct me but became more and more cynical because it felt like it was more about prescribing drugs than psychotherapy. [/INST] I'm not going to correct you. That's I mean right now, like there is a crisis in psychiatry that there are so many psychiatrists that are so Fed up because they have been pharmaceutical Ized, they meet people for 15 minutes, they adjust their medications. This is the way they make the most money. But they've lost the art of talking to people. It's true and that's why we see that so many young psychiatric residents are so thrilled by psychedelics that they really want to get back to treating people as individuals, not just a bunch of chemicals. </s><s>[INST] Yeah, that's truly fascinating. Is that the reason it was appealing to me is a way to to study the human mind and to see ways through talking that you can make people feel better, make people better uh you know, make people suffer less. And that that was really exciting at the time, I ended up going to a I because then I can understand the mind from that angle, but it's exciting that that that could be also uh revolutionized the field of psychotherapy. Take it from its back to its origins to where a psychiatrist would be a scholar of the mind. [/INST] Yeah, Well, you know, Freud talked about dreams as the royal road to the unconscious and there was a lot of you really spent a lot of time with people now um right before he died. Um in his last book, Freud wrote something and again, this will be a rough paraphrase, but he said that in the future we may learn about the energies of the brain and there'll be ways with chemicals to influence that, that will help the therapeutic process. </s><s>[INST] Yeah, yeah. So you could say he was uh he was ahead of his time. This study paints a fascinating picture of a future um where first for medical applications, but then also in general, psychedelics of various forms could be used by the broader society, forgive the perhaps ridiculous question. But, uh, if much of society, including our politicians, are taking psychedelics and Dissolving their Ego and go into this whole process, how do you think the world may look different in 2030, 50 years? [/INST] Okay. So, um, I said that I think licensed legalization happens in 2035. All right. So, um, and I think by 2050, um, we will have uh enough people hopefully, um, spiritualized. Um, we're also talking about, um, we we hear so much in terms of climate change about, you know, net zero carbon. So our goal is net zero trauma. When when do we have a world with net zero trauma? I mean right now, you know, we have two sites in Israel, so we help a few people. But the recent war with Gaza has traumatized millions of people on both sides. So we are a long way away from net zero trauma. Um, but that's the hope and that's I think possible, I think humanity as a whole um, is like lemmings heading over a cliff with climate change and with the nuclear proliferation and just the religious hatreds and the more the retreat authoritarianism and fundamentalism and tribalism. So, I I think that there's a very good chance though that psychedelics used wisely. So it's not just make psychedelics legal, legal and everybody takes them and, you know, as you talked about Ted Kaczynski, you know, it's the context that people take it in. But I think that there's a reasonable chance that enough people can sort of, you could say clean their filters to see people as uh more similar to them than different, not to label them as the enemy stan. Grof. Again had this beautiful phrase about transparent to the transcendent, the that so for our ego, can we be transparent to the transcendent? Can the filter that we look through the world at be cleaned to you can say cleansing the doors of perception, can it be clean to the point where we can see the humanity and everybody and see that one way to say this is that can we get to the point where religions are seen as like languages where we all have this need to communicate. There's thousands of different languages. You know, we don't say that this language is fundamentally better than this language. This language is the only right language, everybody must speak english and Russian is bad or german is better. You know, maybe we'll get to that point that that religions are like that, that they're different cultural backgrounds, different symbol systems, different saints and heroes and messiahs and all this? But that, you know, Yeah, jesus is the son of God, but so are so is everybody, you know, or, you know, the jews are the chosen people, but so is everybody, so can we get there? I think that we can and I think that we need to to survive the challenges that we're facing. And the hope is that by bringing psychedelics as tools forward and trying to bring the context around them to be one of responsibility rather than just profit maximization and just get as many people to do them from all these for profit companies, you know. Can we and then also drug policy reform and embed knowledge in the society. Can we get to honest drug education, you know, Dare the drug uh awareness resistance uh education, you know, it's fundamentally twisted. Uh I mean, but it's the program that's using a lot of schools now. Um So can we get honest drug education, pure drugs, harm reduction and knowledge about therapeutic uses and on the one hand and more of these thousands of flecha del clinics. Um I'm hopeful. Um and that that's our goal, </s>

<s>[INST] recall um, [/INST] when, when another </s><s>[INST] child dies and [/INST] the mother is wailing, </s><s>[INST] we actually [/INST] cut away to Salha </s><s>[INST] who's in the [/INST] hallway who walks into another </s><s>[INST] room and begin sobbing. [/INST] She's </s><s>[INST] not a family member, [/INST] but she has a deep relationship with that family that she forged as soon as they </s><s>[INST] stepped into the ward. [/INST] So that's universal, right? to </s><s>[INST] see a [/INST] woman </s><s>[INST] weep [/INST] because a child has died, even if they're not related to that, that's a </s><s>[INST] universal [/INST] sort of emotion experience we can all relate </s><s>[INST] to. So that's what I mean [/INST] by visual vocabulary </s><s>[INST] and it's especially powerful [/INST] because she has seen much </s><s>[INST] of this kind [/INST] of suffering and she's still, </s><s>[INST] maybe [/INST] she has built up some callus </s><s>[INST] to be able to [/INST] work </s><s>[INST] day to day, but it's still [/INST] there's still an ocean underneath the ice. </s><s>[INST] She's kept her [/INST] heart open despite all the pain that she sees and feels every day. Somehow. She's a human being who's able to do that, </s><s>[INST] which is a very difficult thing to do it, right. [/INST] She still allows herself to be vulnerable. Um, and maybe that's why she can do what she does. What </s><s>[INST] lessons do you draw from [/INST] other famines in history. So for me personally, one that touched my family and one of the great families and histories in Ukraine, </s><s>[INST] Holland more in the 30s, [/INST] 32, right, 33 with Stalin, maybe </s><s>[INST] you could speak to the [/INST] universals of the suffering </s><s>[INST] here. Um, [/INST] what lessons do you draw </s><s>[INST] from those other famines [/INST] if you've looked at them </s><s>[INST] or in [/INST] general about famine that are </s><s>[INST] manufactured [/INST] by the decisions </s><s>[INST] of, let's say [/INST] authoritarian leaders. Yeah. </s><s>[INST] Um, [/INST] famine doesn't have to exist. Or the bulk of famines on this planet, I believe don't have to exist. And most of them, </s><s>[INST] or at least a [/INST] good number of them are manufactured </s><s>[INST] by the [/INST] leaders um that choose to use famine as a weapon, right? And and </s><s>[INST] Ukraine [/INST] is the one of the obvious examples right </s><s>[INST] now, You know with [/INST] siege tactics that are happening in different parts of the country and um you </s><s>[INST] know we [/INST] built </s><s>[INST] international [/INST] humanitarian law for a reason </s><s>[INST] right [/INST] many years ago and it </s><s>[INST] continues to be written to [/INST] this day </s><s>[INST] and [/INST] it's there </s><s>[INST] to prevent [/INST] what's happening in </s><s>[INST] Ukraine right now. [/INST] It's there to prevent what's been happening in Yemen for seven </s><s>[INST] years. And [/INST] yet there hasn't been any </s><s>[INST] teeth behind it. And that's [/INST] what disturbs </s><s>[INST] me [/INST] is that we can </s><s>[INST] see how [/INST] these famines </s><s>[INST] are being used [/INST] as weapons in </s><s>[INST] war. And yet [/INST] we aren't sort of using the levers </s><s>[INST] of power [/INST] that exist um in order </s><s>[INST] to I think to [/INST] call out in important </s><s>[INST] and powerful ways [/INST] those who are causing them and to </s><s>[INST] make sure that we [/INST] hold them accountable </s><s>[INST] on the global stage [/INST] now to some extent that seems to be happening in Ukraine in a way that hasn't happened for a long </s><s>[INST] time and that that gives [/INST] me hope right? And yet I don't believe we've done </s><s>[INST] enough. Um [/INST] and I think the </s><s>[INST] the national community needs [/INST] to do far more than </s><s>[INST] we are both in [/INST] Yemen in Ethiopia. Um and </s><s>[INST] in Ukraine right now, [/INST] there </s><s>[INST] are certain kinds of things that captivate the [/INST] global attention </s><s>[INST] and it seems [/INST] like starvation is not </s><s>[INST] Always one of them [/INST] for some reason </s><s>[INST] murder [/INST] and destruction </s><s>[INST] gets people attention more. [/INST] The death of course </s><s>[INST] is easy to enumerate but it's the suffering. That's the problem. Yeah. [/INST] Yeah. You know when when </s><s>[INST] we went to film [/INST] Hunger Ward, that </s><s>[INST] was one of the creative [/INST] questions that I was really concerned about because starvation, </s><s>[INST] you know, it's not a [/INST] quick action, right? It's a long </s><s>[INST] slow insidious [/INST] process, right? Just like </s><s>[INST] hunger, [/INST] right? And yet </s><s>[INST] when you're hungry, [/INST] right? Um it takes you over, it becomes the most important </s><s>[INST] thing, right? It's just [/INST] absolutely fundamental to life. It's like drawing </s><s>[INST] breath. [/INST] And so I I really </s><s>[INST] before [/INST] I filmed Hunger Ward, I I struggled to sort of answer how we could creatively approach that because you know someone sitting in a clinic, right, starving or being treated for starvation, </s><s>[INST] you know that's a pretty [/INST] static scene, right? Um And what we found was that because of the volume of cases and because of the nature of sort of how </s><s>[INST] quickly [/INST] um </s><s>[INST] people were coming and [/INST] going is that it was more dynamic than we </s><s>[INST] anticipated. [/INST] And there's something also about starvation, you get tired. </s><s>[INST] It's almost like [/INST] it's a quiet suffering. </s><s>[INST] Yeah. Like [/INST] and by the way there's something about </s><s>[INST] when I think about [/INST] dark times, I </s><s>[INST] mean you you [/INST] hear me chuckle for </s><s>[INST] example, I [/INST] don't know what that is, that's almost like it's almost like </s><s>[INST] you have to kind [/INST] of laugh at </s><s>[INST] uh you can't help but laugh at like uh the injustice [/INST] and the cruelty in the </s><s>[INST] world somehow that helps [/INST] your mind deal with it. I mean I see this all the time. </s><s>[INST] Like when you're [/INST] struggling, you can't feed your family, </s><s>[INST] you lost your [/INST] home. </s><s>[INST] The last [/INST] thing you have his jokes about yes, humor. It's like </s><s>[INST] the fucking [/INST] man funk me over again and there's jokes all around </s><s>[INST] that [/INST] and and then and then you laugh and you drink vodka and you play music. I don't know what that is. I don't </s><s>[INST] know what that is. [/INST] It's gallows humor, right? </s><s>[INST] It's it's it's a way of [/INST] a way of I think simultaneously acknowledging and allowing yourself to move forward right beyond the pain and the suffering. </s><s>[INST] So you mentioned Ukraine [/INST] and you mentioned Putin, </s><s>[INST] what are your [/INST] thoughts about the humanitarian crisis and generally this suffering that's resulting from the </s><s>[INST] war in Ukraine. [/INST] Well, first off, I </s><s>[INST] think the conflict is just going [/INST] to exacerbate, you know, </s><s>[INST] sort of [/INST] the global challenge </s><s>[INST] we have [/INST] um </s><s>[INST] with displacement. [/INST] Right? My the last </s><s>[INST] entire trilogy [/INST] I did was about displacement </s><s>[INST] to a great [/INST] extent due to war. And you know, this is a huge </s>

<s>[INST] What about all that crap, my God talk, which is like, you know the whole line of argument that says that jujitsu and wrestling in all of these sports, they fundamentally take you away from the nature of violence. So they're just teaching you how to play versus the reality of violence that is involved in like a self defense situation, that is a totally different set of skills would be needed [/INST] in general. The people that say that jiu jitsu or other martial arts, don't they? It's more of a sport and they don't really understand and I don't really understand violence in general. The people that say that suck. </s><s>[INST] Yeah, [/INST] anybody who thinks like someone's like, you know, hey man I'll just bite you, I'm like are you gonna bite me? Okay? You think I'm gonna bite you too? What do you think of that? What if I punch you in your sucking face? You think you're still gonna bite me when you can't even see when you're you're you barely even know you're alive and I choke you unconscious. If someone's really good at jiu jitsu, good luck stabbing them with your keys. You know, you don't have a chance, you don't have a chance if someone is much better and they trip you and get you on your back and then they fucking elbow you in your face and get a head and arm choke on you. All that crap my gosh, it's out the window son, you're way better off learning what works on trained killers. Like this whole idea that you're gonna poke some of the eye and then you're gonna kick him in the nuts and the like you're you're going through these drills that yeah that's good to know what to do if you run into someone who doesn't know how to fight its way better to know what to do to someone who knows how to fight, That's the best thing, learn how to fight against people who know how to fight. Like all that practice self defense and they're gonna come at you with the knife, you're gonna grab the wrist and do that. Like it's good to know self defense but it's much more important to understand martial arts comprehensively when you understand martial arts comprehensively. Like there's no crop shouldn't say there's no crop my guy guys. But it would be shocking if a Krav Maga guy and a mixed martial arts guy had a fight and the mixed martial arts guy was a trained killer all around didn't fuck that guy up. That's that's what I would expect would happen. I would I would I would not think that some guy who has a little bit of this and a little bit of that and prepares for the streets is going to be able to handle a person who trains with killers on a day to day basis who rolls the jujitsu black belt, who trains with muay thai champions. Like here is the best martial arts of the martial arts that work on martial artists, not the martial arts that work on untrained people. </s><s>[INST] What about, we're in texas now. What about guns? So that's the [/INST] best martial art </s><s>[INST] but would you like in this crazy time, should people carry guns? [/INST] It's not a bad idea to have a gun because if you need a gun you have a gun and if you don't need a gun. If you're a person with self control, you're not going to use it, you're not going to just randomly use it, but you have something to protect you. This is the whole idea of the Second Amendment. The whole idea of the Second Amendment gets distorted by mass shootings or by terrible people, murder people and do terrible things, but it's that all those things are real, but they don't take away from the fundamental efficacy of having a firearm and defending your family or defending your life. And there are real live situations where people have had firearms and it's protected them or their loved ones, or they've stopped shooters. There there's many of these stories, but people don't like those stories because then it it tends to lead to this gun culture argument is pro gun culture argument that people find very uncomfortable. It's human beings are messy and we're messy in so many different ways, right? We're messy, emotionally messy physically, but we're also messy and what's good or bad, what we want things to be binary, want things to be right or wrong, you know, one or zero and they're not. But but there is crime in the world, there is violence in the world and you're better off knowing how to fight, and you're betting better off knowing how to defend yourself and you're better off having a gun. </s>

<s>[INST] Like I said some basket has both the sort of the raw ingredients, but I also really just love their prepared meal kits and they're very affordable too, which is great. They are now offering $90 off for your first four deliveries, including free shipping on the first box. When you go to sun basket dot com slash lex and enter code lex, that's sun basket dot com slash lex with code lex. This show is also sponsored by ladder, I often talk about Ernest Becker's worked in all of death. I often meditate on death together with the stoics I think meditating on your own mortality is both honest and clarifying for who you are as a human being and for who you want to be and how you want to spend your remaining days. The fact that life can end at any moment is, is one hell of a motivator to live an amazing life at least it is for me if you are the same and you also have people in your life you love, you should consider getting life insurance ladder can help you out with that pay a little every month in case something happens to you and the ones you love will be protected anyway, go to ladder life dot com slash lex to see if you're instantly approved. That's L A D D er ladder life dot com slash lex once again for the seats in the back, latter life dot com slash flex. This is Alex Friedman podcast and here is my conversation with chris Duffin, you've been a part of several incredible feats of strength, which was the hardest or maybe one you're most proud of, [/INST] definitely the one I'm most proud of is that journey for the grand goals. It was like a five year scope that I chased this and so when you think about training, it took more than five years. Obviously by that point I've been training for over 25 years, but it makes me proud. I mean, there was three distinct things that I wanted to accomplish out of this, so it was really thought out. Um and this was kind of my exit from being a competitive lifter and basically saying, Hey, I'm going to be, you know, an instagram lifter and exhibition lifter or whatever. I've done this for 16 years that's number one in the world for like eight years straight all time world records and I'm like, I'm not gonna do that anymore. What I want to do is just something deep down to me that is really important and there's three things that were driving this and this is a five year journey that I went through to do this, I really wanted to showcase that you could do something that is well beyond the scope of what people think is humanly possible. So just this inspiration thing this grand over the top, like if you set your mind to a single minded goal, you can go so much further, and I didn't even say what the goal was up front because it was so far out there, I would have been laughed at, and that's I think big goals should be kept pretty damn close to start with for that reason too. Um but and then the second piece was to to walk the walk, to show like the principles of what I believed in around human movement, um the ability to manage and control the spinal mechanics and the output that can have on the body. And so I wanted to take the two most basic movements that every able bodied person should be able to do. So fundamental movement patterns, the squat, which is like in the developmental approaches around nine months as a baby from a developmental kinesiology uh standpoint and a really basic pattern that every able bodied person should be able to master the other one being the hip hinge, being able to pick something up off the ground, a dead lift. And I wanted to do those two, not just one, because I wanted to show the principles that I wasn't built for one. I wasn't a specialist because of my lever links, torso links, all that, any outliers, because nobody had ever done £1000 squat. So this is it is and £1000 dead lift. It was outside of the scope of what anybody's, there's like half a dozen people that have done one or the other, but nobody's ever done both. And I wanted to do something unique. I wanted to do them not only do it, but do them for reps to leave, literally no question out there and there's no competition for that. Uh So it was this is what I'm going to go do and to pull it off. I had some past issues with my elbows and stuff that I couldn't work around. So I had to wear uh straps, which was another reason I couldn't do it in the competition setting. Um So the first year I worked up and I did 1000 and £2 dead lift. We plates were weight afterwards, it was a couple little bit over and I did it for almost three reps. And that still stands as a Guinness world record. Just the one rep does is the most weight ever sumo dead lifted and one other person is dead lifted 1000 for reps at this point. And that was thor Bjornsson uh from game of Thrones. He's done 1000 for a double as well. So then the next four years and I did a bunch of feats of strength on the way. But it was all about building that axial loading capacity, the strength, because now I'm moving the weight from my hands up to my shoulders. And so to do it for eps is like so much harder than a single, like 5 to 10 seconds versus 30 plus seconds to be able to buffer and manage all that with that kind of load is just crazy. So it's </s>

<s>[INST] you're play, don't think about platonic forms [/INST] your platonic because eventually I want this stuff to get used. But uh, it's okay if it takes five or 10 years for the community to realize this is the right thing to do. I've done this before. It's been the case before that, you know, I've made that that case. I mean if you look back in the mid-2000 for example and you ask yourself the question, Okay, I want to recognize cars or faces or whatever. Ah, you know, I can use accomplished on that. So I can use the more conventional kind of computer vision techniques, you know, using interest point detectors or sift density features and you know, sticking an ECM on top at that time, the datasets were so small that those methods that use more hand engineering work better than complex. There's just not enough data for comments and comments were a little, a little sloth with the kind of hardware that was available at the time. And there was a sea change when uh, basically when, you know, datasets became bigger and and Gpus became available that that's what you know, the two of the main factors that basically made people change their, change their mind. Um and you can you can look at the history of like all sub branches of ai or pattern recognition and there is a similar trajectory followed by techniques where people start by you know, engineering the hell out of it. Um you know, be it optical character recognition, speech recognition, computer vision like the major recognition in general natural language understanding like you know, translation, things like that, right? You start to engineer the hell out of it. Um you start to acquire all the knowledge, the prior knowledge, you know about image formation, about you know the shape of characters about you know morphological operations about like feature extraction, fourier transforms, you know, veronica moments, you know whatever, right? People have come up with thousands of ways of representing images so that they could be easily classified afterwards. Same for speech recognition right? There is, you know, two decades for people to figure out a good front end to pre process a speech signal so that you know, the information about what is being said is preserved. But most of the information about the identity of the speaker is gone. Um you know, castro coefficients or whatever. Right? Um And same for for text, right? You do named entity recognition and you parts and you you you do tagging of of of the parts of speech. And you know, you do this sort of tree representation of clauses and all that stuff right, before you can do anything. So that's how it starts, right? Just engineer the hell out of it. And then you start having data and maybe you have more powerful computers, maybe, you know, something about statistical learning. So you start using machine learning and it's usually a small sliver on top of your kind of handcrafted system where, you know, you extract features by hand. Okay. And now, you know, nowadays, the standard way of doing this is that you train the entire thing and to end with the deep learning system and it learns its own features and and you know, speech recognition systems nowadays ocr systems are completely end to end. It's, you know, it's some giant neural net that takes raw wave forms and produces a sequence of characters coming out, and it's just a huge neural net, right? There is no, you know, Markov model, there's no language model that is explicit other than, you know, something that's ingrained in the in the sort of neural language model, if you want the same for translation, same for all kinds of stuff. So, you see this continuous evolution from, you know, less and less handcrafting and more and more learning. Um, and uh, I I think uh I mean it's between biology as well. </s><s>[INST] So, I mean, we might disagree about this, maybe not in this one little piece at the end you mentioned active learning, it feels like active learning which is the selection of data and also the interactivity needs to be part of this general network that you cannot just be an observer to do self supervised learning. You have to well I don't self supervised learning is just a word, but I would whatever this giant stack of a neural network that's automatically learning, it feels my intuition is that you have to have a system whether it's a physical robot or a digital robot that's interacting with the world and doing so in a flawed way in improving over time in order to to form the self supervised learning well you can't just give it a giant sea of data. [/INST] Okay? I agree. And I disagree. I agree in the sense that I think uh I agree. I agree in two ways. The first, the first way agree is that if you want and you certainly need a causal model of the world that allows you to predict the consequences of your actions. To train that model, you need to take actions right? You need to be able to act in the world and see the effect for you to be to learn </s><s>[INST] causal models of the world. So that's not that's not obvious because you can observe others, you can observe others and you can infer that they're similar to you [/INST] and then you can learn from that. Yeah. But then you have to kind of hardware, that part. Right? And you know, mirror neurons analyze stuff. Right? So, um, and it's not clear to me how you would do this in a machine. So, um um, so I think the the action part, it would be necessary for having causal models of the world. The second reason it may be necessary or at least more efficient is that ah active learning basically, you know, goes for the jugular of what you what you don't know right? Is, you know, obvious areas of uncertainty about your your world and about the how the world behaves. And you can resolve this uncertainty by systematic exploration of that part that you don't you don't know. And if you know that you don't know then, you know, it makes you curious. You kind of look into situations that and uh, you know, across the animal world, different species at different levels of </s>

<s>[INST] Used code lex podcast Cash up unless you send money to friends buy Bitcoin and invest in the stock market with as little as $1. I'm thinking of doing more conversations with folks who work in and around the Cryptocurrency space. I definitely need to talk to vitality Budarin again soon. He is at the forefront of a lot of exciting technological developments in the space recently. Plus he's generally both brilliant and really fun to talk to. You should definitely follow him on twitter where you can uh see sample points of the both brilliance and fun. So again, if you get cash out from the app store, google play and use the code lex podcast, you get $10 in cash up. Will also donate $10 to first an organization that is helping to advance robotics, a stem education for young people around the world. And now here's my conversation with john clark. You ready for this? [/INST] I've been ready for this my whole life. </s><s>[INST] All right. I was thinking of doing a Kerouac style road trip across the United States. You know, after this whole covid thing lifts you ever take a trip like that. [/INST] I've done a handful of long distance driving trips, um, up and down the east coast, but also from the west coast back to the east coast and then returning to California. So I've definitely done my fair share of driving in </s><s>[INST] this country. Do you have the longing for the great american road trip? [/INST] I think there are so many things that I've been lucky enough to see in the world that I now at this point in my life, realized there are tons of things that I need to see here in this country and a road trip could potentially be the best way to see them. I think to do it effectively. You need an amount of time where you can be as leisurely as possible. There's no deadline and there's no, I've got to make it from Chicago to ST louis by sundown to get to this place at this time, I think you really need to be able to take your time and uh, and kind of like let the road take you where you need to go. </s><s>[INST] It feels like you need a mission though. Ultimately like there's a reason you need to be in san Francisco, that's like the Kerouac thing. You have to meet somebody somewhere kind of loosely in a few weeks and then it's the, as you struggle on towards that mission, you meet weird characters that get in your way, but ultimately sort of create an experience. [/INST] I think having a loose deadline is good, but that's a beginning and an end point. And what I mean is, I don't want to have to be all right. We're leaving, say boston on sunday night, let's get to new york by monday morning and then from new york we're gonna go to Philly and we've got to be an affiliate for a vague beginning and end is fine. But I think having very strict guidelines in between will rob you of certain experiences along the way. If you have a time frame to get from Philly to Indianapolis in some awesome ship starts to happen in Philly. Do you really want to have to cut it short because you've got to be in Indianapolis by sunup, </s><s>[INST] why do you have to be anywhere by any time for any reason Really? Well, let's change [/INST] plans change all the time. Exactly. But if we're talking about um having a mission or the type of road trip, I just think it would be best to have it as loose and flexible as possible. </s><s>[INST] I don't know, you've got to make hard deadlines and then break them. Totally changed the plans, Disappoint people, Break promises as the way of life, somebody's waiting for you in ST louis and all of a sudden you, you fell in love with a biker in new york. I don't know, I don't know what you're up to, [/INST] I can appreciate that. Um but on a trip like that, I feel like a trip with deadlines is for a different point in your life and at this point in my life, I don't want any of the deadlines because it's not about meeting someone and disappointing them in ST louis, it's about me not disappointing myself. You want to have you want to have enough time in what you're doing to make sure that you get the full breadth of every experience that you encounter, </s><s>[INST] How did you fully experience the place? How would you, you know, I don't think I've actually fully experienced boston, like how if you were showing up to a city for a week on this road trip, what would you do? [/INST] So I'm gonna answer that in two parts, a few years ago, I had an opportunity to move out of boston and the thing that kept me here. No question about it was the fact that I felt like I had um a contract with my students and I did not. I felt like a great many of them took a leap of faith by joining my gym and like you know, asking me to teach them what I know and when I had an opportunity to leave boston, I thought of those people and I thought I want to fulfill my obligation to them. So because I made a decision to stay here and then that summer made a decision to endear myself to the city of boston and I tried to find lots and lots of different things to do. I can tell you that the coolest thing that I've found to do in this city is um, the M. F. A. Where they have like on friday nights, they have like different exhibits and stuff and they'll have like little beer carts and food tents and you can go do a painting class off in the, on the side. Very cool night of things to do. But in general, whenever I'm in a new city, I try not to pay attention to google and I try not to do anything that I find on a travel site. The best thing to do is to walk out of your hotel or wherever it is you're staying and find the most normal looking bar, have a drink and talk to a bartender </s>

<s>[INST] they're speaking to the empathetic to the suffering of the landscape, the full landscape or something. It's interesting to think about suffering. You know, America, the american public american politicians and leaders when they see what is good and evil. They are often not empathetic to the suffering of others and what you're saying is bin laden Perhaps accurately could speak to the ignorance of America, maybe the Soviet Union to the suffering of their people. And I mean if you look at the speeches and the ideas that are public of Hitler in the 1930s, he spoke quite accurately to the injustice and maybe the suffering of the german people. I mean, charismatic politicians are good at telling accurate stories. It's not all fabricated, but they emphasize certain aspects. And then the problem part is the actions you should take based on that. So the narratives and the stories may be grounded in historical accuracy. The actions then cross the line, the ethical [/INST] line I found out too. I mean, it's a again, if you pick up just one of these text, I mean, it's a kaleidoscope. So the Hitler analogy is interesting because it's, you know, Hitler spoke to, he could speak things like inflation, right, which really existed. Um, but he also appealed to the irrational emotions of Germans, right? He sought out scapegoats, you know, jews, Roma, um disabled people, homosexuals and so on. Right. That's also there in bin laden to, I mean, the idea of um you know, a an anti Semitism uh constant flagging of zionists and crusaders. It's a kind of shotgun approach to search for followers, but also hasten to add that it's for all of the things that we can take off saying, well, yes, Kashmiris have suffered, Chechens have suffered and so on. Um Bin laden is um never became a mass movement. I mean, it never really, I think the, I mean this is the encouraging thing, right? About ideology. I mean, I think the the blood on his hands always limited his appeal among Muslims and others. Um, but Dylan did have, I mean, he had a great book by a great scholar at UC SAn Diego. Um, Jeremy pressed all who read a great book about global icons, in which he has been laden, he has um bob Marley, he has two Pac, you know, he asked why, you know, using research in East africa, why did he see young kids wearing bin laden shirts? They're also wearing like tupac shirts, they're wearing been bob Marley shirts and based in the way of looking at um, a kind of partial embrace of some aspects of the rebelliousness of some of these figures, some of the time by some people under certain conditions. </s><s>[INST] Well, the terrifying thing to me. So yeah, there is a longing in the human heart to belong to a group and a charismatic leader somehow, especially when you're young, just a catalyst for all of that. And I tend to think that perhaps it's actually hard to be Hitler, so a leader so charismatic that he can rile a nation to war and bin laden, perhaps we're lucky, was not sufficiently charismatic. I, I feel like if his writing was better if his speeches were butter, if his ideas were stronger, but it's like uh more viral, and then there would be more people, kind of uh, young people uniting around him. So, in some sense, it's almost like accidents of history of just how much charisma, how much charisma, particular evil person has a [/INST] person like bin laden, I think it's fair, you will even work to thank you, think </s><s>[INST] Bin laden is evil, [/INST] Oh yeah, I mean he was a mass murderer, um I'm just saying that his ideas were there are more complex than, than we have tended to acknowledge, um they had, they have a wider potential residents than we acknowledge, I mean, and also, I guess what, I'm just one Fundamental point is that um thinking about the complexity of bin laden is also a way of removing him from Islam. Um he is not an Islamic thinker, he is a cosmopolitan thinker who plays in all kinds of modern ideologies which have proven to mobilize people in the past, right? So um you know, anti Semitism, um populism, environmentalism and the kind of in the urging to like, you know, do something about humanity, do something about suffering, that's why I think the actual us about what motivates people to do this kind of stuff, I think that's why if one goes below the level of leadership and this is being reported, if you look at the trial ongoing now in paris of the article on murders, I think um the court allowed some discussion of the backgrounds of the accused and they come from different backgrounds, but if there's any common bond is kind of that they has some background in petty crime famously in the 77 bombings in London, the Mountain police UK authorities looked at all those guys and what people want is this idea that like they must be very pious, they must be super Islamic to do this kind of stuff. They must be fanatical true believers. But what they found with those guys was that somewhere nominally muslim, some went to mosques, some didn't, um, some were single young guys with like criminal backgrounds. Some, you know, we're like, sorry, they were you kind of misfits who never succeeded anything. But others had, you know, at least one thing, I had a wife and family who he, you know, widowed and orphaned. And so there's no, I mean for policing, I mean, if you're looking at to that lens, there is no kind of typology that will predict who will become violent and that's why I think we have to move beyond thinking about religious ornamentation narrowly or by itself and think about things like geopolitics. Think about how people respond to inequality, you know, the existential threat of, of uh, you know, climate crisis of um, a whole host of matters of, and, and think about this is a mode of political conversation. I mean, the violent ones when I can do them, it is evil, right? But these are people that are trying to be political, they're trying to change things in some way. It's not nearly about like I want to impose Sharia law on you, you must wear a veil, you must eat this kind of food. It's it's not that parochial, but what one another quick thought about your interesting claim about charisma and this? I think that the one self limiting feature of this subculture is that definitely, you know, I mentioned the enigma of not wanting to be seen and that the kind of invisibility is a productive force of power, you know, Which a colleague of mine who knows ancient history far better than I. Yeah, so this is, you know, she looked at me Alomar initially or we come up in laden. I mean, this kind of studied posture of staying in the shadows. Yeah, it's also a source of authority, potentially because it it um it invites the idea, it's probably Dictatorships do this. Well, I mean it's the idea that someone's working and maybe it's the it's the basis for a lot of Q. And on or other conspiracy today that someone's working behind the scenes and things are going to go the right way. You can't see it. That's almost preferable because you can kind of feel it. And so not having someone out front can maybe maybe more effective than having someone out in front constantly then maybe and then the whole bin laden, you know, omar thing, like you can't see me or if you like, you know, Bin laden's photographs and his video stuff. I mean, he's he's coy uh some observers have noted he's kind of effeminate. He doesn't strike this kind of masculine. He's not a Mussolini. He's not a Hitler macho. I'm standing my dumping my chest. He's not doing the theatrical chin, you know, the theater people tell us it's so aggressive. Um You know, Chin what bringing your chin up. I saw a great BBC theater person. It was kind of a, it was a makeover show about how to become a decorator. Oh no, it's </s>

<s>[INST] And one of the things this war in Ukraine has shown, one of the most terrifying things outside of the humanitarian crisis is that at least for me, I realized that the human capacity to initiate nuclear war is greater than I thought. I thought the lessons of the past have been learned. It seems that we hang on the brink of nuclear war with this conflict, like every single day with just one mistake or bad actor or [/INST] the </s><s>[INST] actual leaders of the particular nations launching a nuclear strike and all hell broke breaks loose. So then add into that picture, cyber attacks and so on. They can lead to confusion and chaos. And then out of that confusion, um, calculations are made such that uh a nuclear launches A nuclear weapon is launched. And it's and then you're talking about, I mean, I don't direct probably, of humans on earth are dead instantly. And then the rest, I mean, it's basically 99% of the human population is wiped out in the period of well, it's not [/INST] that bad, but we are devastating for civilization of course. And of course you were quite right that this could happen very quickly because of um, you know, information coming in and there's a there's hardly enough time for human collected and careful thought. And there have been recorded cases of false alarms, several where um, where have been suspected attacks from the other side. And fortunately they've been really to be false alarms soon enough. But this could happen. And there's a new class of threats actually, which in our center in Cambridge people are thinking about, which is that the commander control system Of the nuclear weapons and the submarine fleet and all that is now more automated and could be subject to cyber attacks. And that, that's a new threat which didn't exist 30 years ago. And so I think indeed, it's we're in a sort of scary world I </s><s>[INST] think. [/INST] And it's because things happen faster and human beings aren't in such a direct and immediate control because so much is delegated to machines and also because the world is so much more interconnected, then some local event can cascade globally in a way I never could in the past and much faster. </s><s>[INST] Yeah, it's a double edged sword because the interconnectedness brings, uh, um, brings a higher quality of life across a lot of metrics. [/INST] Yeah, it can do. But of course there again, I mean if you think of supply chains where we get stuff from around the world and um, one lesson we've learned is that there's a trade off between resilience and efficiency and his resilient to have an inventory and stock and to depend on local supplies where it's more efficient to have long supply change. But the risk there is that a break in one link in one chain Can screw up car production and this has already happened in the pandemic. So there's a trade off and there are other examples. I mean, for instance, the other thing we learned was that it may be efficient to have 95% of your hospital intensive care beds occupied all the time, which has been the UK situation. Whereas to do what the Germans do and always keep 20% of them free for an emergency is really a sensible precaution. And so I think we've probably learned a lot of lessons from COVID-19 and they would include rebalancing the trade off between resilience and efficiency </s><s>[INST] Boy. The fact that COVID-19 a pandemic that could have been a lot, a lot worse, brought the world to its knees anyway. It [/INST] could be far worse in terms of its a fatality rate of </s><s>[INST] fatality rate. Yes. [/INST] Yeah. So </s><s>[INST] the fact that that I mean revealed so many flaws in our human institutions. [/INST] Yeah. Yeah. And I think I'm rather pessimistic because um I do worry about the bad actor or a small group who can produce catastrophe. And if you imagine someone with access to the kind of equipment that's available in university labs or industrial labs and they could create some dangerous pathogen, then even one such person is too many. And how can we stop that? Because it's true that you can have regulations. I mean academies are having meetings etcetera about how to regulate these new biological experiments, et cetera, make them safe. But even if you have all these regulations then enforcing regulations is pretty hopeless. We can't enforce the tax laws globally. We can't enforce the drug laws globally. And so similarly, we can't readily enforce the laws against people doing these games experiments, even if all the governments say they should be prohibited. And so my my line on this is that all nations are going to face a big trade off between three things. We value freedom, security and privacy. And I think um, different nations will make that choice differently. Um, the chinese would give up privacy and have more security, if not more liberty, but I think um in in our countries, I think we're going to have to give up more privacy. </s>

<s>[INST] know, I get to actually intensely experience that certainty in many communities, but one in in in Cryptocurrency young folks with a certainty that this technology will transform the world. And I mean this is almost one of the big communities of the modern era where they believe that this will really solve so many of the problems of the world and they believe in it very intensely. And aside from the technology and the details of the thing, all I see is the certainty and the passion in their eyes. They'll stop me. Let me uh let me explain you. Let me let me just give me a chance to tell you why this thing is extremely powerful and I just get to enjoy the glow of that because it's like, well this I I miss having that certainty about anything. It's probably come over for me [/INST] too. But </s><s>[INST] when I was younger, it's it's like only I deeply understand the relationship of man To his mortality. And I understood that most deeply, I think when I was like 16 or 17 and I have I am the representative of the human condition and all these adults with their business of day to day life and their concerns. They don't deeply understand what I understand, which is the only thing that matters is uh the absurdity of the human condition. [/INST] Yeah. </s><s>[INST] And let me quote you some dostoyevsky [/INST] boy and you speak Russian, </s><s>[INST] you've [/INST] read the brothers Karamazov in Russian. </s><s>[INST] Unfortunately, I have to admit that um I read all of the ski in English. Um I came to this country when I was 13 and at least don't remember. We read a lot, but we read uh Tolstoy Pushkin a lot of the Russian literature, but it was in Russian. But I don't remember reading dostoevsky. I wonder at which point does the Russian education system give you dostoyevsky because it's pretty heavy stuff. [/INST] The 2nd Grade Intense. </s><s>[INST] I don't remember. Yes, they are, they're very, they're very much are. I don't remember reading this desk but I did uh tangent upon a tangent upon a tangent. I traveled to paris recently on the way to Ukraine And uh was scheduled to talk to Richard Revere and love this pair that translates ski uh tolstoy just this famous pair that translate most of Russian literature to English. And I was planning to have a sequence of, you know, 5, 10, 15 hour conversation with them about the different details of all the translations and so on. Um I just found myself in a very dark place mentally where I couldn't think about podcasts or anything like that. It caught me off guard. So I went to paris and just laid there for a day, not just being stressed about Ukraine and all those kinds of things, but I'm still the, the act of translation is such a fascinating way to approach some of the deepest questions that this literature raises, which is like how do I capture the essence of a sentence that has so much power and translated into another language? That act is actually really, really interesting. And there I found with my conversations with them, they they've really thought to this stuff, it's not just about language, it's about the ideas in those books. And that's um that that also really makes me sad because I wonder how much is lost in translation. I'm currently, So when I was in Ukraine, I talked to a lot of like half the conversations I had on the record one Russian And basically 100% off the record were in Russian vs in English and just so much is lost in those languages. And I'm now struggling because I'm launching a Russian channel or there will be a Russian overdub of Duncan [/INST] your </s><s>[INST] while will not be translated into Russian, you'll just be, well, probably, I'm so sorry for the, for the difficulties of having to translate. Well, usually, probably with while they will leave it on overdubbed because people understand exactly what you mean, but that's an art form and it's a weird art form. It's like how do you capture the, the chemistry, the excitement, the, I don't know, maybe the humor, the implied kind of wit. I don't know, there's just layers of complexity and language that it's very difficult to capture and I wonder how it is sad for me because I know Russia and how much is lost in translation and the same. You know, there's a brewing conflict and tension with china now and so much is lost in the translation between those languages and cultures. The entire the music of the people is completely lost because we don't know the language. Yeah. [/INST] How much of the conflict is just problems in translation? How much of the all these problems that we're having are just the alien sense of this or that it's just as simple as that words are getting just that just a tiny warp away from the intent of if when we both speak the same language, we can still say something that offends someone when you never intended that at all. How much more? So when like, it's not only is it a completely different sound, but the script itself is different, like what the Russian writing, is it called cyril cyrillic or </s><s>[INST] what's [/INST] and I don't know the name for chinese writing, but it's like, like it's a continuum that like, it's weirder and weirder looking, you know, like it's so Yeah, yeah, I'm sure depending on where you're at. You know, I'm definitely I'm about the farthest thing from a polyglot is there could be man like, but I'll tell you at one point when I was getting fascinated by, I did have this very transient fantasy about learning Russian so that I could like understand the difference in and </s><s>[INST] You're 1718 at the time [/INST] college. Yeah. Brothers Karamazov lost in that book just like oh God so in love with it. There's </s>

<s>[INST] K. And there's this thing called Bang Bang, which people are probably watching, know exactly what I'm talking about. It's this worst possible thing you can do in terms of meals, which is, you go to a restaurant, you're full meal and then go to another restaurant and do a full meal and you, you [/INST] exactly. So </s><s>[INST] they go mexican, italian sushi pizza barbecue, Ihop, that that one is disgusting. This kind of thing reminds me of the [/INST] joy of food. Last time we were hanging out, we went, we want to see joe do comedy and then we went to eat Russian food and it was a particularly </s><s>[INST] fun [/INST] experience to go to a Russian restaurant. I was the only person there that didn't speak Russian and eat Russian food with you and um because I felt walking in, they trusted you, they didn't trust me. Yeah, the </s><s>[INST] funny thing about the people there, they were talking to you in Russian and then they refused to sort of switched to english even though they understood you speak no Russian, this is Russian house in Austin by the way. Uh anyway, what, by way of question, what's the worst or the best, depending on your perspective, cheap meal, let's call it a pigging out meal. But it could be a cheap meal uh, that you've ever had or you want to have, that's like on the bucket list or something that's in the past, like where you did the, something like a bang bang, which is like you're talking about multiple, thousands of calories that you just feel horrible about yourself, but you still keep eating because it's delicious, but also great company, something about the atmosphere is just right, screw the diet, screw all the things, you know, I just like you should be doing, but just throw it all out the window, [/INST] I've done that several times. Yeah, I don't do this anymore. But um the entire time I was a postdoc. So five years and the entire time I was a pre tenured professor. So five years. So I basically followed the tim Ferriss slow carb diet, which is, you know, people can look it up but it worked really well. It was basically some, you know, like good animal proteins, you know, fish and meat and things </s><s>[INST] like that because [/INST] like low glycemic stuff is mostly lentils and beans and things and vegetables. No, no dairy, no. Um anyway, but then one day, no, no pasta. So it wasn't low carb, but it was low glycemic carbs and I did that and it works terrifically well just for energy levels because I wanna be able to train and work and then one day a week you're supposed to go full cheap day. And so I would do what used to be 12 hours, but then it became 20 for, you know, you start to redefine what the day is. Um and I would, and that was when Costello was pretty young and we would do it together. So I would get pizzas and croissants and donuts and I would just do the full thing and by the end of the day, you don't want to look at an item of food, you're just repulsed by food. The only modification I made was the next day, I would fast completely just to avoid the gastric distress of eating anything and so I would do them on Sundays and Mondays that fast all day and then by Tuesday I felt pretty good again, but sunday and monday or you just feel like you're sliding down the slope of just blood sugar disaster, </s><s>[INST] you [/INST] know, at the time I enjoyed it. I love doughnuts, croissants, all that kind of stuff. What's interesting is after stopping that whole protocol. Now, I'm just trying to eat. Well, it's really a protocol now. I basically, I do a sudo, intermittent fasting. I don't, I'm not really strict, but I'll start eating around 11. Eat my first meal around 11. I usually train in the morning, eat my last bite of food somewhere around eight or nine and I'm not super strict. I might have some berries or something late at night, two meals, 2-2 meals and then maybe a little bit of snacking on some nuts or something in the middle, </s><s>[INST] 24 [/INST] hours. Never done a long fast except when I was doing the gaze and then, um, and actually there are a couple different ways to do things that were fun. Like you were in a new city, you could try all the restaurants that you wanted. Yeah. And I think tim and our mutual friend john romaniello did a, I think it was like a cheat day marathon where they did, you know marathons, 26.3 miles. They went to 26.3 different locations in new york. They put it on a map and I never took it to that extreme. But </s><s>[INST] wait, wait over how many days [/INST] one day that was there </s><s>[INST] just [/INST] because they were, you know, </s><s>[INST] just a little bit of something at each [/INST] place. Yeah, exactly. I mean there are things that guys do in their thirties that you just shouldn't do in your forties. I can say that because I'm in my forties and uh now I just try and eat well most days. And what's interesting is about 12 to 14 months ago, I completely lost all appetite for sweets. I don't know what happened. I still love savory foods. So meat and butter and cheese. Uh and I love vegetables too. I love fruit also, but lost all appetite. So if you put a donut in front of me or ice cream or something like I just, it's, it's almost aversive to me and I don't know what happened. I don't know what changed. </s><s>[INST] It's probably a scientific explanation. It has to do [/INST] dementia, the </s><s>[INST] sugar, the, the desire for that [/INST] rush. Maybe </s>

<s>[INST] the field of program synthesis? Like what how many people are working and thinking about it, what where we are in the history of program citizens and uh, what are your hopes for it? [/INST] Well, if it were deplaning, this is like the 90s. So meaning that we already have, we already have existing solutions. We are starting to have some basic understanding of where this is about. But it's still a field that is in its infancy. There are very few people are working on it. There are very few real world applications. So the one of your little application I'm aware of is flash fill in Excel. It's a way to automatically learn very simple programs to format cells in an Excel spreadsheet from, from a few examples for instance, running away from a date, things like that. </s><s>[INST] Oh, that's fascinating. You know? Okay, that's that's fascinating topic. I always wonder when I provide a few samples to Excel, what is able to figure out like just giving it a few dates, What are you able to figure out from the pattern I just gave you. That's a fascinating question. And it's fascinating whether that's learn able patterns and you're saying they're working on that. How big is the tool box currently, are we completely in the [/INST] dark in terms of provinces? I would say so, maybe nineties even even too optimistic because by the nineties, you know, we already understood that probably already understood, you know, the engine of deplaning, even though we could actually see its potential quite uh today, I don't think we found the engine of program synthesis. So </s><s>[INST] we're in the winter before backdrop. Yeah. [/INST] In a way yes. So I do believe program synthesis uh in general discreet search over rule based models. It is going to be a cornerstone of our research in the next century. Right. And um that doesn't mean we're gonna drop depending depending is immensely useful. Like being able to learn is very flexible, adaptable, demetric models just got Anderson that's actually immensely useful like all it's doing, it's better recognition but being good at better recognition given lots of today is just extremely powerful. So we're still going to be working on the planet and we are going to be working on programs until this. We're going to be combining the two increasingly automated ways. Mhm. </s><s>[INST] So let's talk a little bit about data. You've tweeted Uh huh. About 10,000 deep learning papers have been written about hard coding criers about a specific task in a neural network architecture, it works better than a lack of a prior basically summarizing all these efforts they put a name to an architecture but really what they're doing is hard coding some pliers that improve the Yes. But uh get straight to the point is it's probably true. So you say that you can always buy performance by in quotes performance by either training on more data, better data or by injecting task information to the architecture of the pre processing. However, this is an informative about the generalization power of the techniques used the fundamental ability journalists, do you think we can go far by coming up with better methods for this kind of cheating for better methods of large scale annotation of data. So building butter [/INST] prior, if you if you made it it's not sitting anymore. </s><s>[INST] I'm talking about the cheating but large scale. So basically I'm asking um about something that hasn't been, from my perspective, been researched too too much is uh exponential improvement in annotation of data. Do you often think about, [/INST] I think it's actually been being researched quite a bit. You just don't see publications about it because you know, people who publish papers are going to publish about known benchmarks sometimes that there is a new benchmark. People who actually have real world large scale depending problems. They're going to spend a lot of resources into data annotation and good data annotation pipelines. But you don't see any papers. That's interesting. So do you think </s><s>[INST] there are certain resources, but do you think there's innovation happening? [/INST] Oh yeah. To clarify at the point in the twist, So machine learning in general is the science of generalization. You want to generate knowledge that can be reused across different data sets across different tasks. And if instead you're looking at one data sets and then you are hard coding knowledge about this task into your architecture. This is no more useful than training network and then saying, oh I found these weight values uh perform well. Right, so David ha I don't know if if you know David Yeah. The paper the other day about weight agnostic neural networks. And this is this is very interesting paper because it really illustrates the fact that an architecture even with the artworks and architecture is a knowledge about the task includes knowledge and when it comes to architecture that our own crafted by researchers in some cases it is very very clear that all they're doing is artificially uh re including the template that corresponds to the proper way to solve uh task including given dataset for instance. Um I know if if you looked at the baby dataset Which is about natural language question answering, it is generated by an algorithm. So this is a question and the pairs are generated by an algorithm to algorithm is selling a certain template turns out if you craft a network that literally encodes this template, you can solve this dataset with nearly 100% accuracy but that doesn't actually tell you anything about how to solve question answering in general. Which is the point. The </s><s>[INST] question is just to linger on it whether it's from the data side and from the size of the network. I don't know if you've read the blog post by Rich Sutton, the bitter lesson [/INST] or he says the </s>

<s>[INST] Well, I think that's one of the profound ideas and deep work that you don't expand on too much is uh boredom. [/INST] Yeah, well, so the deep work had a superficial idea about boredom which was I had this chapter called embrace boredom and very functional list idea was basically you have to have some boredom in your regular schedule or your mind is going to form a Pavlovian connection between as soon as I feel boredom again, stimuli and once it forms that connection is never going to tolerate deep work. So there's this very pragmatic treatment of boredom of your mind better be used to the idea that sometimes you don't get stimulated because otherwise you can't write for three hours, like it's just not going to tolerate it, but more recently. What I'm really interested in boredom, is it as a fundamental human drive, right? Because it's incredibly uncomfortable and think about the other things that are incredibly uncomfortable like hunger or thirst, they serve a really important purpose for a species, right. Like if something is really distressing, there's a reason, pain is really uncomfortable because we need to worry about getting injured, thirst is really uncomfortable because we need water to survive. So what's boredom? Why is that uncomfortable? And and I've been interested in this notion that boredom is about driving us towards productive action like as a species. I mean think about it like what what got us to actually take advantage of these brains? What got us to actually work with fire? What got us to start shaping stones and the hand axes and figuring out if we could actually sharpen a stick sharp enough that we could throw it as a meal, a weapon or a distance weapon for hunting mammoth, right? Boredom drives us towards action. So now I'm fascinated by this fundamental action instinct because I have this theory that I'm working on that were out of sync with it just like we got, we have this drive for hunger but then we introduce junk food and got out of sync with hunger and it makes us really unhealthy. We have this drive towards action but then we overload ourselves and we have all of these distractions and then that causes uh it's like a cognitive action obesity type things because it short circuits this system that wants us to do things but we put more things on our plate and we can possibly do and then we're really frustrated, we can't do them and we're short circuit all of our wires. So it all comes back to this question. Well what would be the ideal, the ideal, the amount of stuff to do in type of things to do? Like if we wanted to look back at our ancestral environment and say if I could just build from scratch, what type, how much work I do and what I work on to be as in touch with that as like paleo people are trying to get their diets in touch with that. And so now I'm just but see this is I'm just it's something I made up but now I'm going deep on it and one of my podcast listeners I was I was talking about on the show and I was like well I am trying to learn about animals and boredom. And she sent me this cool article from an animal behavioralist journal about what we know about human boredom versus animal boredom. So trying to figure out that puzzle is the wave that's high so I can get through the wave that's low of like I don't know about this pandemic book launch and you know and my research and my research is stumbling a little bit because of the pandemic. And so I needed a nice, you know, high so there we go. There's a case study. </s><s>[INST] Well it's both a case study and very interesting set of concepts because I didn't even realize that it's so simple. I'm one of the people that has uh interesting push and pull dynamic with hunger, trying to understand the hunger with myself. Like I probably have an unhealthy relationship with food, I don't know, but there's probably probably a perfect, that's a nice way to think about diet as action. There's probably an optimal diet response to the the experience that our bodies telling us the signal that the body's sending, which is hunger in that same way boredom is sending a signal. And most of our intellectual activities in this world are creative activities are essentially a response uh, to that signal. [/INST] Yeah. And think about this analogy that we have this hunger instinct that junk food short circuits, right? It's like, oh, well we'll satisfy that hyper palatable e and it doesn't end up well now, think about modern attention engineered, digitally mediated entertainment. We have this board of instinct, oh, we can we can take care of that with a hyper palatable alternative. Is that gonna lead to a similar problem? </s>

<s>[INST] and less typically, much less powerful engine in space. So you mentioned on the multi-stage rockets that maybe the dream would be, if we weren't living on Earth, but maybe we can on Earth to have a single stage to orbit rocket where it's all one package reusable. Reusable gets even harder. It gets even harder. So first of all, what is, just to linger on it, what is the single stage to orbit rocket? Why is it so hard to achieve on Earth? You already kind of explained it a little bit, but just if we were to say like, yeah, that's your assignment. Yeah. Tim, you're supposed to get together with Elon and other brilliant people and like, you have to do this. Yeah. [/INST] Why is it so hard? It's so hard. Why is it so hard? It, your, the payload fraction of a rocket is like three to five or six or 7% would be like, that's the amount of payload compared to the total mass of the rocket. Like you're lucky to get into beyond 5%. So if you're now having to deal with the weight of the rocket by the time you're in orbit, like your payload fraction, just you're talking about like margins. It's such, it's so small amount of leftover. If you have to take all of it with you. So the sooner you can ditch weight, the better. The sooner you can ditch weight, the better. The sooner you can, and that's what you're doing. A rocket the whole time is actually ditching weight. All of that fuel and all that big giant flame you see is literally mass being thrown out the back of the rocket. But what typically isn't expended, at least during nominal operations, you're not seeing the engines being expelled out the thing until you get to staging of course. And that's where you're ditching all that dead weight. So single-staged orbit. your margins just become so small that it's border, it's not impossible, but it's just at the end of the day, like almost no matter who you are, you end up saying it's just simply not worth it. Like it'd be, if you have two rockets that are using the same amount of propellant, you know, they're the same physical sizes and one of them is cutting, you know, on a third and has another little engine, it'll have a hundred or a thousand times more payload capacity than the one sitting right next to it. And now, so there's tricks you can do to like try to offset that, things like aerospike engines, which operate as efficiently at sea-level, at kind of optimized efficiency at sea level by the way they're designed the physics of them. They're also efficient in a vacuum too. You can do the things like that. And at the end of the day, though, you just end up with a worse rocket than if you had just done stage like no matter what and people say like, well, what if you would develop the new technologies? like, okay, you apply that technology to a multistage rocket and it's gonna do better, you know, like no matter where you end up, </s><s>[INST] it's just always better to ditch that weight. Is there a cost to having multi-stage? [/INST] Because you can still reuse the different stages. The dream becomes easier to reuse multiple stages because now the booster doesn't have to survive orbital reentry temperatures and extreme environments and you only have to make survivable the upper stage. You'll only have to put a big heat shield. Starship's the perfect thing of this. The upper stage has a big giant heat shield, the booster doesn't need it. The booster's not going to orbit. It's only going a fifth or a quarter of orbital velocity. So it's heat that it experiences, it's survivable just by the stainless steel. You don't need an additional heat shield. Pretend that you just welded the two stages of Starship together, remove those engines on Starship. That whole vehicle. If you're trying to reuse it, the whole vehicle now has to have a heat shield on one side of it. The whole thing has to have these big heavy wings. By the time you come down to it, there's probably just zero payload capacity. you basically put your fuel tank in space, you know? </s><s>[INST] Good job. So the dream of a single stage to orbit, a rocket, [/INST] is that just even the wrong dream on Earth? That's what most convention tells you. You know, by the time, if your goal is cheap, then you're going to spend, you're gonna have a physically larger rocket that has more engines, that has more propellant, blah, blah, blah, to put the same amount of mass into orbit compared to something else. You know, we're talking like Rocket Lab's Electron, a really small rocket, it's like, I think, 1.3 meters wide, and something like, you know, 18 meters tall or something. It's a small rocket. If you were to, you know, and it can put something like 300 or so kilograms into orbit, you could either launch something that size or again like a full, like big old Falcon 9 booster, the huge, huge thing, and that would be lucky to put 300 kilograms into orbit, you know, so it's like which one's gonna be cheaper to build, you know, ship around, all this stuff, And then you also look at, you have fixed costs. Like the idea of flying a, this, again, everything in rocket science is compromised because now you have things like people on console time, all the people that are, you know, on comms and working on the rocket, going down to the pad, you know, filing paperwork, doing range control, making sure there's not planes and boats in the way, flight termination. You have all these fixed costs for any launch. I don't care how big the rocket is, there's a relatively fixed cost. So now you say like, okay, I'm going to be paying, well, let's just make a win over. I'm going to pay $5 million to fly a rocket between all the people going on site, all the propellant, all the licenses, blah, blah, blah. If your fixed cost is $5 million, you can put 300 kilograms in space versus you have a $5 million cost of operation and you can put 5,000 kilograms into space. Like it, the business case is going to send you </s>

<s>[INST] Like, [/INST] you know, it's not everything. It's cracked up to be, you know necessarily. </s><s>[INST] But no matter what, you know, a new place allows the possibility for new ideas. Even if they're somehow left leaning and all those kinds of things. I do think the only two things missing from Austin and texas are two dudes in a suit that sometimes have a podcast talking much nonsense and mike. So let's let's bring the best suit game to texas. I hope you do make it to texas at some point. Thanks so much for talking to me. Thanks for listening to this conversation with Sagarin Jetty and thank you to our sponsors Jordan's Harvard's show, Graham, early grammar assistant eight, sleep, self cooling bed and magic spoon, low carb cereal, click the sponsored links to get a discount and to support this podcast. And now let me leave you with some words from martin Luther king Jr about the idea that what is just and what is legal. I'm not always the same thing. He said, never forget that. What Hitler did in Germany was legal. Thank you for listening and hope to see you next time [/INST] </s>

<s>[INST] you can learn a lot in just a few words right from a human being. [/INST] Well, that's true. But I think that the bigger issue was I saw something that I don't hear much remarked upon, which is Jeffrey Epstein is all there that there is in other words, there's the National Science Foundation, National Institute of Health Howard Hughes, there's all this stuff that kind of has the same feel to it a little bit of variation and difference, department of energy. If you fall outside of that, there's just Jeffrey Epstein, that's what you're told. Yes, that's not quite true. There's Kavli maybe jim Symons is now in the game, Peter thiel has done some stuff. You had your E milner and Mark Zuckerberg try. So there is other money running around Templeton, but very strongly. There was a belief that if you're doing something really innovative and the system can't fund it because it's, we become pussy's Jeffrey Epstein is your guy because </s><s>[INST] because it's fun, you're supposed to go through, [/INST] That's right. And the idea is that you get called to the Great Man's house and you know, sort of lubricious version of ralph Lauren, you know, takes you in and asks you bizarre questions and maybe he has an island, maybe he has a plane and you know, when you're starved, uh you know, somebody showing you a feast or when you're dehydrated in a death's door and somebody says, oh, you know, I have a well, um you know, that's what it is. And so the thought is, wow, can you, can somebody get some effing money into the science system so that we don't have super creeps trying to learn all of our secrets ahead of time. WTf what is your problem with transparency and Taxpayer dollars, just all of you, you wouldn't have a country, you'd be speaking german, </s><s>[INST] so essentially you believe that human beings would not be able to when the money is lacking in the system like a research produce [/INST] public goods, you and I are meant to produce public goods. Now, I sell athletic greens and I saw kerrigan and I sell unagi scooters and chili pad are going to be honest. I love these products but I didn't get into this game for the purpose of selling. I'm trying to figure out how do you have an F you lifestyle? But you know something like, I don't know why you built this channel. It's kind of a mystery. I </s><s>[INST] don't know why I'll [/INST] tell you why I built my channel. It's gonna be a lot harder to roll me this time in an alley. Yeah, I got rolled multiple times and my point is I didn't want to become a celebrity. I didn't want to become well known, but it's a lot harder to roll somebody who's getting, you know, I think I'm, I don't know if this is mistaken, but I think I'm the math PhD with the largest number of followers on twitter and there was nothing you could do before. </s><s>[INST] I mean, again, to put a little responsibility and you know, you've created something really special for the distribution of your own ideas. I mean, but because it's not necessarily currently scalable, you also perhaps you and I have the responsibility of giving other people also a chance to spread their ideas. I mean joe Rogan did this very effectively for a bunch of people. That [/INST] that's why they're angry at him because he's a gatekeeper and he let all sorts of people through that gate from roger from roger penrose to Alex jones </s><s>[INST] to Jordan Peterson to I mean even well, first of all to you, [/INST] Abby martin </s><s>[INST] to abby martin [/INST] to Bari weiss. Yeah, </s><s>[INST] that's the problem. Well, but you you have not successfully built up a thing that allows that to carry that. [/INST] We are all vulnerable to reputational attack. Because what happens, you see the problem Lexus is that you are now an institution at some level, you walk around with all this equipment in a duffel bag. Uh huh. The last the last suit you'll ever need and um you have the reach of something like CNN to people who matter. Okay, so now the question is how do we control something? It doesn't have a board doesn't have shareholders, doesn't have to make sec filings FCC. So the best answer they have is, well, we just have to destroy reputations. All it takes is for us to take something that gets said or done or alleged. Mhm. And I think it's incredibly important. One of the things people don't understand is that I'm I'm going to fight general reputational attacks not because some people don't deserve to have their reputations drunk dragged through the mud but because it's too powerful of a tool to hand it to CNN MSNBC Princeton Harvard the state department. </s><s>[INST] But some of it is also jpmorgan Muhammad, ali style being good enough at uh doing everything you need to do without giving enough meat for the reputational attacks. Not being afraid, but not giving enough meat? I don't [/INST] see why the people who have good ideas have to lead lives that are that clean. If you can do it can </s><s>[INST] be messy. Yeah, you should be able to be messy that otherwise we're suppressing too many people. Too many two billion minds. Can you believe [/INST] Elon musk smoked the blood? </s><s>[INST] I still people told me this. Okay, okay. I have discussions about Ellen and people uh the Avi Loeb, the Harvard scientist who's talking about a more and more that it might be alien technology. He told me his this outside the box thinker. Yeah. When speaking to me about Ellen said called him the guy who smoked, he smokes weed the blunt in a dismissive way. Like this guy is crazy because he smoked some weed. [/INST] I would look at it. </s>

<s>[INST] consequence that Lauren's talking about. That's the category of security that Bitcoin has talked about that it's very difficult to do that with Bitcoin. But I would argue that's exceptionally difficult to do that with gold. [/INST] It is now, it is now, but the thing is there's not a huge incentive. If gold is the basis and if gold is worth that much, it's right. Gold isn't worth that much, gold is worth— I'm saying in this world that we're talking about, in the future. In the future, yeah. Gold is not going to be worth more—let's say right now gold is about $2,000. Let's say it's $2,000. That a price in terms of dollars, you'd have to— it would have to be worth your while to create something that's $2,000, how much would you be willing to put into it? At some point you're right, and at that point I think gold stops bring money because it's useless. Once I can create it like silicon, then once I can make out official gold. I'm just not, I don't think Bitcoin is the solution. I think, I don't know what the solution is. I wish I was that innovative, but I think you need a solution that has more of the characteristics of gold than Bitcoin currently has. And I guess I'm surprised because they're useless at a lot of the technologists who view Bitcoin as the end game, where it strikes me as it's the birth of a new technology, it represents the birth of a new technology. And who the winner in that technology is going to be, we have no clue, Bitcoin is one of the players, there are other players. They might be a new technology that is even better than anything we can imagine right now. So Bitcoin doesn't strike me as optimal, and that we should be moving towards something Can you please stop shilling Rand coin for five minutes? You know where there was Rand coin? South Africa? No. There's currencies for Rand. No, that's true. Iron Rand is the South African, there's currencies for Rand. That's true. No. Iron Rand is the South African $1 dollar. Iron Rand coin was, I was in China in 20, I think it was 2015 or 2014. China. China. I was in China 20, something like that, and this entrepreneur came up to me, she said she's bought this massive quantity of land in this area in China, it's a little secluded. She's starting what she's calling Goldsculch, she's serious, and she's issuing, and she issued cryptocurrency based on the land, right, backed by the land called Rand, but Ayn Rand, a little portrait of Ayn Rand, you know, a little portrait in the in the in the marketing. I don't think it went anywhere. You're not gonna be a janitor? A janitor? You're not gonna be a janitor? A janitor in China Goldsculch, yeah. By the way, I do want to point out something I do enjoy about objectivists. I constantly talk about Ayn Rand and her vampire novels, and that's the joke you're on, thank you. And inevitably someone feels the need to point out that she did not write vampire novels, and her name is actually Ayn, so thank you. We've been talking for two hours, I own her copy of Fountainhead, somehow I thought her name was Ayn thank you. Ayn is an anthem. We've been talking for two hours, thank you. So this is really interesting way of phrasing it. I was kidding with the Ein. I know you knew how to pronounce it. I know you know you know. Yeah, he just got </s><s>[INST] confusing. I think we all know and we all know that we're jokers here. We're all one. There's no Batman in this conversation. So it's an interesting way to frame it is Bitcoin the end or the beginning of something and I've as sort of with an open mind and seeing kind of all the possibilities of technologies out there, I also kind of thought that Bitcoin is the beginning of something. But what the Bitcoin community argues is that Bitcoin is the end of the base layer, meaning all the different innovations will come on top of it. Like for example, there's something called Lightning Network where it's basically just like gold is the end and everything is built like the monetary systems like cash and all that is built on top of gold. Bitcoin is the end in that other technologies that build on top of Bitcoin. That's their argument. I get that and I hear that [/INST] all the word jokers here. We're all one. There's no Batman in this conversation. I get that and I hear that all the time and I don't quite understand that and I think Bitcoin has limitations that potentially other cryptocurrencies might not have. My attitude too with something like this is large extent I don't understand technology. My view is let it play out. I think I have more fear of physical the ability of the government to crush these things than I think many in the community. So for example, so I gave a talk of Bitcoin and they were hyping the acceptance now. A lot of vendors are willing to accept Bitcoin and this is great. I said, yeah, it's absolutely great. More options is better than fewer options. But I said, you know that that could be taken away like that. Now it's true that we could exchange Bitcoin and the government wouldn't know, I think wouldn't know that we do. But once he's advertising on his website that he accepts Bitcoin or once he tries to turn his Bitcoin into particular goods, once you manifest it in the physical world, now the government can step in. So the government could say you can't sell anything to anybody using Bitcoin. They can do that and you won't be able to sell it. It will have to go into the black market. That isn't able to sell it just to just sell you in the black market. Yeah. But that's where the government thrives, right. The government thrives on letting you do stuff in the black markets so they can decide when to put your jail or not. So if I'm buying a sweatshirt from the government, sorry, if I'm buying a sweatshirt from somebody using Bitcoin, the government can't monitor my exchange of Bitcoin to him, but they can monitor the sweatshirt being sent to me. That's where they can interfere. And I think that at some point, to the extent Bitcoin is successful, it will be stopped. And that's what will stop it from becoming money. See, money can only become money if people are using it as money. And if the government can stop it being used, if I can't go to the grocery store and use my ATM that charges on Bitcoin or whatever, jail or not, then it's not money. And I think that the government is going to step in and stop people from doing that. And that's what I saw. I have more respect and fear for the power of government today. I don't see that at all. However, I could be wrong. And I'm sure Yaron hopes he's wrong. Absolutely. I hope the government just give in and the Fed tomorrow says, yeah, let Bitcoin thrive. But I think that one of regulated control and </s>

<s>[INST] the following is a conversation with Rajat Monga. He's an engineering director of google leading the tensorflow team, tensorflow is an open source library at the center of much of the work going on in the world? And deep learning both the cutting edge research and the large scale [/INST] application of learning </s><s>[INST] based approaches, but it's quickly becoming much more than a software library. It's now an ecosystem of tools for the deployment of machine learning in the cloud, on the phone, in the browser, on both generic and specialized hardware, CPU, Gpu and so on. Plus there's a big emphasis on growing a passionate community of developers. Roger, Jeff Dean in a large team of engineers at Google brain are working to define the future of machine learning with Tensorflow 2.0 which is now in alpha. I think the decision to open source tensorflow is a definitive moment in the tech industry. It showed that open innovation can be successful and inspire many companies to open source their code to publish and in general engage in the open exchange of ideas. This conversation is part of the artificial intelligence podcast. If you enjoy it, subscribe on youtube itunes are simply connect with me on twitter at lex Friedman spelled F R I D and now here's my conversation with roger manga, You were involved with Google brain since its start in 2011 with Jeff Dean. It started with disbelief, the proprietary machine learning library and turn into tensorflow in 2014? The open source library. So what were the early days of google brain, Like what were the goals the missions? How do you even proceed forward once? There's so much possibilities before you? [/INST] It was interesting back then, you know, when I started, when you were even just talking about it, the idea of deep learning was interesting and intriguing in some ways, it hadn't yet taken off, but it held some promise that had shown some very promising in early results. I think that the idea where Andrew and Jeffords started was what if we can take this, what people are doing in research and scale it to what google has in terms of the computer power and also put that kind of data together, what does it mean? And so far the results have been, If you scale the computer, scale the data, it does better. And would that work. And so that, that was the first in order to, can we prove that out brain and with disbelief. When we started the first year we got some early wins, which is always great. </s><s>[INST] What were the winds like? What was the winds where you were there some problems to this? This is gonna be good. [/INST] I think they're too early ones where one with speech that we collaborated very closely with the speech research team, who is also getting interested in this and the other one was on images where we, you know the cat paper as we call it, that was covered by a lot of folks </s><s>[INST] and uh, the birth of google brain was around neural networks, that was so it was deep learning from the very beginning, that was the whole mission. So what would uh in terms of scale, what was the sort of dream of what this could become like, what were their echoes of this open source tensorflow community that might be brought in? Was there a sense of TP us, was there a sense of like machine learning is not going to be at the core of the entire company is going to grow into that direction? [/INST] Yeah, I think so. That was interesting. Like if I think back to 2012 or 2011 And first of all, can we scale it in in the year or so? We had started scaling it to hundreds and thousands of machines. In fact we had some runs even going to 10,000 machines and all of those shows great promise. Uh in terms of machine learning at google, the good thing was, Google's been doing machine learning for a long time. Deplaning was new, but as we scale this up to be sure that yes, that was possible and it was going to impact lots of things like we started seeing real products wanting to use this against speech was the first, there were image things that photos came out of in many other products as well. So that was exciting. Um as he went into without a couple of years externally, also Academia started to, you know, there was lots of push on. Okay, Deep learning is interesting, we should be doing more and so on, And so by 2014 we were looking at, Okay, this is a big thing, it's going to grow and not just internally externally as well. Yes, maybe Google's ahead of where everybody is, but there's a lot to do. So a lot of this starts to make sense and come together. </s><s>[INST] So the decision to open source, I was just chatting with chris Latner about this. The decision go open source with tensorflow. I I would say, sort of, for me personally, seems to be one of the big seminal moments in all of software engineering ever. I think that's a when a large company like google decides to take a large project that many lawyers might argue has a lot of I p just decide to go open source of it, and in so doing lead the entire world and saying, you know what open innovation is is a pretty powerful thing, and it's okay to do. Uh That that was I mean, that's an incredible, incredible moment in time. So, do you remember those discussions happening there? Open source should be happening. What was that? Like, [/INST] I would say? I think so, the initial idea came from Jeff who was a big proponent of this, I think it came off of two big things. one was research wise, we were a research group, we were putting all our research out there if you wanted to. We were building another's research and we wanted to push the state of the art forward. And part of that was to share the research. That's how I think deep learning and machine learning is really growing so fast. So the next step was okay. No word software helped with that. And it seemed like they were existing a few libraries out there to know being one torch being another and a few others, but they were all done by academia and so the level was significantly different. The other one was from a software perspective google have done lots of software or that we used internally, you know, and we published papers often there was an open source project that came out of that that somebody else picked up that paper and implemented. And they were very successful. Yeah. Back then it was like okay, there's her dupe which has come off of deck that we built, we know the tax we've built is very better for a number of different reasons. We've invested a lot of effort in that and turns out we have schools out and we are now not really providing our tech but we are saying okay, we have big table which is the additional thing, we're going to now provide H B A S A P. I. S on top of that, which isn't as good, but that's what everybody is used to. So there's there's like, can we make something that is better and really just provide, helps the community in lots of ways, but also helps push the right, a good standard forward. </s><s>[INST] So how does cloud fit into that? There's a tensorflow open source library and how does the fact that you can uh use so many of the resources that google provides and the cloud fit into that strategy? [/INST] So tensorflow itself is open and you can use it anywhere, right? And we want to make sure that continues to be the case on google cloud, we do make sure that there's lots of integrations with everything else and we want to make sure that it works really, really well there. So </s><s>[INST] you're reading the tensorflow effort, can you tell me the history and the timeline of tensorflow project in terms of major design decisions, so like the open source decision, but really uh you know what to include and not, there's this incredible ecosystem that I'd like to talk about, all of these parts, but what if you just some sample moments that defined what tensorflow eventually became through it? I don't know if you're a lot to say history when it's just but in deep learning everything moves so fast that just a few years is already history. [/INST] Yes, yes, so looking back, we were building tensorflow, I guess we open source that in 2015 november 2015, If you started on it in the summer of 2014 I guess And somewhere like 3 to 6, late 2014 By then we had decided that okay, there's a high likelihood real open source search. So we started thinking about that and making sure we're heading down that path at that point. By that point we had seen a few, you know, lots of different use cases at google. So there were things like, okay, yes, we want to run in at large scale in the data center. Yes, we need to support different kinds of hardware. We had GPS at that point we had our first tpu at that point was about to come out, you know, roughly around that time. So the design included those we had started to push on mobile. So we were running models on mobile at that point people were customizing cord so we wanted to make sure dance of local support that as well. So that that sort of became part of that overall design. </s><s>[INST] When you say mobile, you mean like a pretty complicated algorithms running on the phone. [/INST] That's correct. So so when you have a model that you deployed on the phone and run it the right </s><s>[INST] already at that time there was ideas of running machine learning on the phone. [/INST] That's correct. We already had a couple of products that we're doing that by then. Right. And in those cases we are basically customized handcrafted cord or some internal libraries that we're using. </s><s>[INST] So I was actually at google during this time in a parallel I guess universe. But we were using Theano and cafe. Yeah. Was there some degree to which you were bouncing? I like trying to see what cafe was offering. People trying to see what theano was offering that you want to make sure you're delivering on whatever that is. Perhaps the python part of thing maybe uh did that influence any design decisions? [/INST] Um, totally. So when we built this belief and some of that was in parallel with some of these libraries coming up. I mean piano itself is older but we were building this belief focused on our internal thing because our systems are very different. By the time we got to this we looked at a number of libraries that were out there to know they were folks in the group who had experienced with torch with lou uh there were folks here who had seen cafe. I mean actually yanking was here as well. There's uh, what other libraries? I think we looked at a number of things might even have looked at jane are back then. I'm trying to remember of course there in fact we did discuss ideas around okay, should we have a graph or not? And uh, they were so supporting all these together was definitely you know, there were key decisions that we wanted. We, we had seen limitations in our prayers, disbelief, things a few of them were just in terms of research was moving so fast. We wanted the flexibility you want, the hardware was changing fast, we expect it to change that so that those probably were two things and yeah, I think the flexibility in terms of being able to express all kinds of crazy things was definitely a big one then. </s><s>[INST] So what the graph decisions so that was moving towards Tensorflow 2.0 there's more by default will be eager, eager execution. So sort of hiding the graph a little bit, you know, because it's less intuitive in terms of uh, the way people developed and so on. What was that discussion like with in terms of using graphs? It seems it's kind of the theory in a way that it seemed the obvious choice. [/INST] So I think where it came from was are like this belief had a graph like thing as well much more so it wasn't a general graph, it was more like a straight line, you know, thing more like what you might think of cafe I guess in that sense. But the graph was and we always cared about the production stuff like even with disbelief you're deploying a whole bunch of stuff in production. So graph did come from that when we thought of, okay should we do that in python and we experimented with some ideas where it looked a lot simpler to use but not having a graph went okay, how do you deploy now? So that was probably what tilted the balance for us and eventually we ended up with the </s><s>[INST] graph and I guess the question there is, did you, I mean the production seems to be a really good thing to focus on, but did you even anticipate the other side of it, where there could be uh What is it, what are the numbers? Something crazy. A 41 million downloads? Uh, I mean was that even like a possibility in your mind that it would be as popular as it became? [/INST] So I think we did see a need for this a lot from the research perspective and like early days of deep learning in some ways 41 million. No, I don't think, I imagine this number then uh it seemed like there's a potential future where lots more people would be doing this and how do we enable that? I would say this kind of growth, I probably started seeing somewhat after the open sourcing where I was like okay, you know, deep learning is actually growing way faster for a lot of different reasons and we had just the right place to push on that and and leverage that and delivered on lots of things that people want. </s><s>[INST] So what changed once the open source, like how you know this incredible amount of attention from a global population of developers, what how did the project start changing? I don't you actually remember during those times, I know looking now there's really good documentation, there's an ecosystem of tools, There is a community block is a Youtube channel now. Right? Yeah. It's very, very community driven back then, I guess zero [/INST] one version. Is that the version 1? I think we call 3.6 or five or something that I don't forget what </s><s>[INST] Changed leading into 1.0. [/INST] It's interesting, you know, I think we've gone through a few things there when we started out, when we first came out. People love the documentation we have because it was just a huge step up from everything else because all of those were academic projects people doing, you know, we don't think about documentation. Uh, I think what that changed was instead of deep learning being a research thing. Some people who were just developers could now suddenly take this out and do some interesting things with it. But who had nuclear machine learning was before then. Um, and that I think really changed how things started to scale up in some ways and pushed on it over the next few months as we looked at, you know, how do we stabilize things as we look at? Not just researchers now, we want stability, people aren't deploy things. That's how we started planning for renato and there are certain needs for that perspective. And so again, documentation comes up, um, designs, more kinds of things to put that together. And so that was exciting to get to a stage where more and more enterprises wanted to buy and and really get behind that. And I think Postwar Nardo and you know, with the next few releases that enterprise adoption also started to take off, I would say between the initial release and when. Otto it was okay, researchers of course, uh then a lot of hobbies similarly interest people excited about this, who started to get on board and then over the one dot x thing. Lots of enterprises, </s><s>[INST] I imagine anything that's you know, below one point, oh, gets pressured to be uh, enterprise probably want something that's stable. Exactly. And uh do you have a sense now that tensorflow this state, like it feels like deep learning in general is extremely dynamic field as so much is changing. Do you have a and tensorflow has been growing incredibly, you have a sense of stability at the helm of it. I mean, I know you're in the midst of it, but yeah, [/INST] it's, it's, I think in the midst of it, it's often easy to forget what uh, an enterprise warrants and what some of the people on that side. One, there are still people running models that are three years old, four years old. So inception is still used by tons of people, Even less than 50 is what a couple of years old now or more, but there are tons of people who use that and they're fine, they don't need the last couple of bits of performance or quality. They want some stability and things that just work. And so there is value in providing that with that kind of stability and making it really simpler because that allows a lot more people to access it. And then there's the research crowd which wants, okay, they want to do these crazy things exactly like you're saying, right, not just deep learning in the straight up models that used to be there, they weren't, um, are in ends and even our own ends or maybe all their transformers now and um, now it needs to combine with a bottle and Ganz and so on. So there's definitely that area that like the boundary that's shifting and pushing the state of the art. But I think there's more and more of the past starts, much more stable and even stuff that was 23 years old is very, very usable by lots of people. So that makes that part, makes it a little easier. </s><s>[INST] So I imagine maybe you can correct me if I'm wrong. One of the biggest use cases is essentially taking something like resnet 50 and doing some kind of transfer learning and a very particular problem that you have, it's basically probably what majority of the world does and you want to make that as easy as possible. [/INST] So I would say for the hobbyist perspective, that's the most common case, right? In fact, apps on phones and stuff that you will see the early ones that's the most common case. I would say there are a couple of reasons for that one is that everybody talks about that. It looks great on slides. That's a visual presentation. Yeah, exactly what enterprises warn is that is part of it. But that's not the big thing. Enterprises really have data that they want to make predictions on. This is often what they used to do with the people who are doing animal was just regression models, linear, regression logistic, regression linear models or maybe gradient boosted trees and so on. Some of them still benefit from deep learning, but they weren't that, that that's the bread and butter, like the structure data and so on. So depending on the audience, you look at that a little bit differently </s><s>[INST] and they just have, I mean the best of enterprise probably just has a very large dataset or deep learning can probably shine. [/INST] That's correct. That's right. And then they, I think the other pieces that they weren't again with two point or the developer summit we put together is the whole tensorflow extended piece, which is the entire pipeline. They care about stability across doing their entire thing. They want simplicity across the entire thing. I don't need to just train a model, I need to do that every day again over and over again. </s><s>[INST] I wonder to which degree you have a role in. Uh, I don't know. So I teach a course on deep learning, I have people like lawyers come up to me and say, you know, say one is machine learning going to enter legal legal realm the same thing and um, all kinds of disciplines, uh immigration insurance. Often when I see what it boils down to is these companies are often a little bit old school and the way they organized the day. So the data is just not ready yet. It's not digitized. Do you also find yourself being in the role of and an evangelist for like uh let's get organized your data folks and then you'll get the big benefit of tensorflow. Aw, do you get those? Have those conversations? [/INST] So yeah, you know, I get all kinds of questions there from, Okay, what can I, what do I need to make this work right to really need deep learning. I mean they're all these things. I already use this linear model. Why would this help? I don't have enough data or let's say, you know, or I want to use machine learning to have nuclear where to start. So it really starts to all the way to the experts who wise for very specific things. It's interesting </s><s>[INST] is there a good answer. It boils down to. Oftentimes digitizing data. So whatever you want, automated, whatever day you want to make predictions based on, you have to make sure that it's in an organized form you like with within intensive for ecosystem, there's now you're providing more and more data sets and more and more pretrained models. Are you finding yourself also the organizer of datasets? [/INST] Yes, I think the tensorflow datasets that we just released that's definitely come up where people want these datasets. Can we organize them and can we make that easier? So that's, that's definitely one important thing. The other related thing I would say is I often tell people, you know what, I don't think of the most fanciest thing that the newest model that you see make something very basic work and then you can improve it. There's just lots of things you can do with their </s><s>[INST] Yeah, I started with the basic truth. One of the big things that makes it makes sense of flow even more accessible was the appearance whenever that happened of caress the care is standard sort of outside of tensorflow. I think it was carrots on top of piano at first only and then uh paris became on top of tensorflow. Do you know when uh paris chose to also add tensorflow as a back end. Who was the, was it just the community that drove that initially? Do you know if there was discussions, [/INST] conversations? Yeah. So Francis started the campus project before he was at google and the first thing with piano. I don't remember if that was Africans flows created away before and then at some point in tensorflow started becoming popular, there were enough similarities that you decided to okay create this interface and and pretends flows back in um, I believe that might still have been before he joined google. So I, you know, we weren't really talking about that. He decided on his own and I thought that was interesting and relevant to the community. In fact, I didn't find out about him being a google until a few months after he was here. He was working on some research ideas and doing caress and his nights and weekends project and </s><s>[INST] so interesting. So he wasn't like part of the tensorflow, he didn't join, she [/INST] joined research and he was doing some amazing research, has some papers on the iron research he's done, he's a great researcher as well. And at some point we realized, oh he's he's doing this good stuff. People seem to like the FBI and he's right here. So we talked to him and he said, okay, why don't I come over to your team and work with you for a quarter and let's make that integration happen. And we talked to his manager and he said sure, my quarters fine. And that quarter has been something like two years now and so he's fully on this. </s><s>[INST] So chara's got integrated into tensorflow like in a deep way And now with 2.0 Tensorflow 2.0, sort of caress is kind of the recommended way for a beginner to interact with which makes that initial sort of transfer learning or the basic use cases even for enterprise? Uh Super simple. Right? So what what was that decision like? That seems like uh uh it's kind of a bold decision uh as well, we [/INST] did spend a lot of time thinking about that one, we had a bunch of api somebody by us, uh there was a parallel layers api that we were building and when we decided to do keras in parallel, so they were like okay, two things that we're looking at, and the first thing we was trying to do is just have them look similar, like being as integrated as possible, share all of that stuff. They were also like three other mps that others had built over time because we didn't have a standard one. Um but one of the messages that we keep kept hearing from the community, okay, which one do we use? And they kept saying like, okay, here's a model in this one and here's a model in this one which is like pick. Um so that that's sort of like, okay, we had to address that straight on with two point. Oh, the whole idea is you need to simplify, you had to pick one based on where the where you're like, okay let's see what what are, what are the people like and carries was clearly one that lots of people loved, there were lots of great things about it. Uh so pretty settled on night, </s><s>[INST] organically, that's kind of the best way to do. It was, it was great, it was surprising that were less to sort of bring in an outside, I mean there was a feeling like paris might um be almost like a competitor and it's a certain kind of uh to tensorflow in a sense, it became an empowering element of tensorflow. [/INST] That's right, yeah, it's interesting how you can put two things together, which don't, which kind of line, right? And in this case, I think francois, the team and I, you know, a bunch of us have chattered and I think we all want to see the same kind of things, you all care about making it easier for the huge set of developers out there and that makes a difference. </s><s>[INST] So python has Guido Van Rassam who until recently held the position of benevolent dictator [/INST] for life, </s><s>[INST] right? So there's a huge successful open source project, like tensorflow need one person who makes the final decision. So you've did a pretty successful tensorflow deV summit just now the last couple of days, there's clearly a lot of different new features being incorporated, an amazing ecosystem, so on whose uh how are those design decisions made, is there, is there a B D F L intensive flow and uh or is it more distributed and organic? [/INST] I think it's, it's somewhat different, I would say, I've always been involved in the key design directions, but there are lots of things that are distributed, where uh the number of people martin rick being one who is really driven a lot of open source stuff, a lot of the A. P. I. S. Um and there are a number of other people who have been, you know, pushed and being responsible for different parts of it. We do have regular design reviews over the last year, we've really spent a lot of time opening up to the community and adding transparency. We're setting more process in place. So our FCS special interest groups really grow that community and skill that I think the kind of scale that ecosystem is in, I don't think we could scale with having me as this lone point of decision maker, so </s><s>[INST] I got it. So yeah, the growth of that ecosystem, maybe you can talk about it a little bit first of all when I started with Andrea Carpathia, when he first did come that Js, the fact that you can train a neural network in the browser does in javascript was incredible. So now tensorflow Js is really making that a serious like a legit thing away to operate, whether it's in the back end or the front end and then there's the tensorflow extended, like you mentioned, there's tensorflow lite for mobile uh and all of it as far as I can tell, it's really converging towards being able to uh you know, save models in the same kind of way you can move around, you can train on the desktop and then move it to mobile and so on. Is that cohesiveness? So can you maybe give me whatever I missed a bigger overview of the mission of the ecosystem that's trying to be built and where is it moving forward? [/INST] Yeah, so in short, the way I like to think of this as our goal is to enable machine learning and in a couple of ways, one is, we have lots of exciting things going on in Ml Today we started with Deep learning, but we now support a bunch of federal guardians two. So one is to on the research side, keep pushing on the state of the art. Can we, you know, how do we enable researchers to build the next amazing thing? So Bird came out recently, you know, it's great that people are able to do a new kinds of research and there's lots of amazing research that happens across the world. So that's one direction the other is how do you take that across all the people outside who want to take that research and do some great things with it and integrated to build real products to, to have a real impact on people? Um and so if that's the other axes in some ways, um you know, at a high level, one way I think about it, is there a crazy number of computer devices across the world and we often used to think of ml and training and all of this as okay. Something you do either in the workstation or the data center or cloud, but we see things running on the phones, we see things running on really tiny chips when we had some demos in the developer summit and so the way I think about this ecosystem is how do we help get machine learning on every device that has a compute capability and that continues to grow and so uh in some ways the C ecosystem has looked at various aspects of that and grown over time, recover more of those and we continue to push the boundaries in some areas. We've built uh more tooling and things around that to help you. I mean the first tool we started was tense aboard, you wanted to learn just the training piece, uh the effects or tensorflow extended to really do your entire ml pipelines, if you're, you know, care about all that production stuff, but then going to the edge, going to different kinds of things and it's not just us now, um there a place where there are lots of libraries being built on top, so there's some for research, maybe things like hence flow agents or tensorflow probability that started as research things or for researchers for focusing on certain kinds of algorithms, but they're also being deployed or used by production folks and uh some have come from within google, just teams across google who wanted to do to build these things, others have come from just the community because there are different pieces that different parts of the community care about and I see our goal as enabling even that right, it's not weak, we cannot and won't build every single thing that just doesn't make sense, but if we can enable others to build the things that they care about and there's a broader community that cares about that and we can help encourage that and um, that, that's great, that really helps the entire ecosystem, not just those. Uh, one of the big things about two point oh, that we're pushing on is okay, we have so many different pieces, right? How do we help make all of them work well together. So there are a few key pieces there that we're pushing on, uh, one being the core format and there and how we share the models themselves through save model and more in tensorflow hub and so on. Um, and you know, a few of the pieces that we really put this together, </s><s>[INST] I was very skeptical that that's, you know, intensive for Jazz came out, I didn't seem, or deep learning Js as [/INST] early as the first, </s><s>[INST] it seems like technically very [/INST] difficult project </s><s>[INST] as a stand alone is not as difficult, but as a thing that integrates into the ecosystem seems very difficult, so I mean there's a lot of aspects of this, you're making look easy, but uh, the technical side, how many challenges have to be overcome here [/INST] lot </s><s>[INST] and still have to be. That's the question here [/INST] too. There are lots of steps to it and and we we traded over the last year, so there's large, we have learned. I yeah, often when things come together well things look easy and that's exactly the point. It should be easy for the end user, but there are lots of things that go behind that if I think about still challenges ahead, there are, you know, we have a lot more devices coming on board, for example, from the hardware perspective, how do we make it really easy for these vendors to integrate with something like tensorflow? Right. Uh so there's a lot of compiler stuff that others are working on their things we can do in terms of R A P S and so on that we can do as we, you know, tensorflow started as a very monolithic system and to some extent it still is there less lots of tools around it, but the core is still pretty large and monolithic. One of the key challenges for us to scale that out is how do we break that apart with clearer interfaces? It's um, you know, in some ways it's software entering one on one, but for a system that's now four years old I guess or more and that's still rapidly evolving and that we're not slowing down with, it's hard to, you know, change and modify and really break apart. It's sort of like, as people say, right, it's like changing the engine with a car running or fringe benefits, that that's exactly what we're trying </s><s>[INST] to do. So there's a challenge here because the downside of so many people being excited about tensorflow and becoming to rely on it and many of their applications is that you're kind of responsible, it's the technical debt, you're responsible for previous versions to some degree, still working. So when you're trying to innovate, I mean, it's probably easier to just start from scratch every few months. [/INST] Absolutely. </s><s>[INST] So do you feel the pain of that? Uh 2.0, does break some back compatibility, but not too much. It seems like the conversion is pretty straightforward. Uh do you think that's still important given how quickly deep learning is changing? Can you just the things that you've learned, can you just start over or is there pressure to not? [/INST] It's a it's a tricky balance. So if it was just a researcher writing a paper who a year later will not look at that code again, sure. It doesn't matter. Uh There are a lot of production systems that rely on tensorflow, both at google and across the world and people worry about this. I mean, these systems run for a long time. Uh so it is important to keep that compatibility and so on and yes, it does come with a huge cost. There's uh we have to think about a lot of things as we do new things and make new changes? Uh I think the it's a tradeoff right? You can you might slow certain kinds of things down, but the overall value you're bringing because of that is much bigger because it's not just about breaking the person yesterday, it's also about telling the person tomorrow that you know what, this is, how we do things, we're not going to break you and you come on board because there are lots of new people who are also going to come on board. Um you know, one way I like to think about this and I always pushed the team to think about as well and you want to do new things, you want to start with a clean slate designed with a clean slate in mind and then we'll figure out how to make sure all the other things work. And yes, we do make compromises occasionally, but unless you're designed with the clean slate and not worry about that, you will never get to a good place. </s><s>[INST] That's brilliant. So even if you're you are responsible when you in the idea stage, when you're thinking of new, just put all that behind you, that's okay. That's really, really well put, so I have to ask this because a lot of students, developers asked me how I feel about pytorch for tensorflow. So I've recently completely switched my research group to tensorflow. I wish everybody would just use the same thing in tensorflow is as close to that I believe as we have, but do you enjoy competition? Uh, tensorflow is leading in many ways on many dimensions, in terms of ecosystem, in terms of the number of users, momentum, power production levels on. But you know, a lot of researchers are now also using pytorch. Do you enjoy that kind of competition or do you just ignore it and focus on making tensorflow the best that it can be. [/INST] So just like research or anything, people are doing right, it's great to get different kinds of ideas. And when we started with tensorflow, like I was saying earlier one, it was very important for us to also have production in mind. We didn't want just research, Right? And that's why we chose certain things. Now Pytorch came along and said, you know what, I only care about research, this is what I'm trying to do. What's the best thing I can do for this? And it started trading and said, okay, I don't need to worry about drafts, let me just run things. Um, I don't care if it's not as fast as it can be, but let me just, you know, make this part easy and there are things you can learn from that, right? They again had the benefit of seeing what had come before, but also exploring certain different kinds of spaces and they had some good things they're building on, say things like Jenna and so on before that. So, uh, competition is definitely interesting. It made us, you know, this is an area that we had talked about. Like I said, you know, we early on overtime, we had revisited this a couple of times. Should we add this again? Uh, at some point we said, you know what? Here's, it seems like this can be done well. So let's try it again. And that's how, you know, we started pushing on eager execution and how do we combine those two together? Which has finally come very well together in two points, but it took us a while to get all the things together and so on. So let </s><s>[INST] me, I mean, ask, uh, put another way, I think eager execution is a really powerful thing that was added. You think he wouldn't have been, you know, Muhammad ali versus Frazier. Right. You think it wouldn't have been added as quickly if pytorch wasn't there, [/INST] it might have taken longer. Yeah, it was when we drive some variants of that before. So I'm sure it would have happened, but it might have taken longer. </s><s>[INST] I'm grateful that tensorflow responded in the way they did it, doing some incredible work last couple of years. What other things that we didn't talk about it, You're looking forward in to point out, uh, that comes to mind. So we talked about some of the ecosystem stuff, making it easily accessible to caress eager execution. Is there other things that we miss? Yeah. [/INST] So I would say one is just where to 10.0 is and you know, with all the things that we've talked about, I think as we think beyond that there are lots of other things that it enables us to do and that we're excited about. So what it's setting us up for Okay, the hair, the Israeli clean api s, we've cleaned up the surface for what the users want. What it also allows us to do a whole bunch of stuff behind the scenes once we've, we're ready with two point Oh, so, uh, for example, intensive flow with drafts and all the things you could do, you could always get a lot of good performance if you spend the time to tune it. Right? And we have clearly shown that lots of people do that. The two point know that these Api's there, we are, we can give you a lot of performance just with whatever you do. You know, if your because we see these, it's much cleaner. We know most people are going to do things this way. We can really optimize for that and get a lot of those things out of the box. Uh and it really allows us, you know, but for single machine and distributed and so on. Clearly explore other spaces behind the scenes after, you know, two point in the future versions as well. So, uh, right now the team is really excited about that over time, I think we'll see that the other piece that I was talking about in terms of just restructuring the monolithic thing into more pieces and making it more modular. I think that's going to be really important for a lot of the other people in the ecosystem or their organizations and so on that. Wanted to build things. </s><s>[INST] Can you elaborate a little bit what you mean by making tensorflow more ecosystem or modular? [/INST] So the way it's organized today is there's one there are lots of repositories in the tens of organization and get a job the core one where we have tensorflow, it has the execution engine, it has, you know, the key beckons for Cpus and gpu s it has uh work to do distributed stuff and all of these just work together in a single library or binary. There's no way to split them apart easily. There are some interfaces but they're not very clean. In a perfect world. You would have clean interfaces where okay, I want to run it on my fancy cluster with some custom networking, just implement this and do that, we kind of support that but it's hard for people today, I think as we're starting to see more interesting things in some of these cases having that clean separation will really start to help um and and again going to the large size of the ecosystem and the different groups involved, they're enabling people to evolve and push on things more independently, just allows it to scale better </s><s>[INST] and by people, you mean individual developers and an organization, an organization, that's what so the hope is that everybody sort of major, I don't know, Pepsi or something uses like major corporations go to tensorflow to this kind [/INST] of Yeah, if you look at enterprise, like Pepsi or these mean a lot of them are already using tensorflow, they are not the ones that do the development or changes in the core, some of them do, but a lot of them don't they cut small pieces, There are lots of these, some of them being, let's say hardware vendors who are building their custom hardware and they want their own pieces or some of them being bigger companies say IBM, I mean they're involved in some of our special interest groups and they see a lot of users who want certain things and they want to optimize for that, folks like that, often </s><s>[INST] autonomous vehicle companies perhaps. [/INST] Exactly, yes. </s><s>[INST] So uh yeah, like I mentioned tensorflow has been downloaded 41 million times 50,000 commits? Almost 10,000 pull requests, 1800 contributors. So I'm not sure if you can explain it, but what does it take to build a community like that? What in retrospect, what do you think? What, what is the critical thing that allowed for this growth to happen and how does that growth continue? [/INST] Uh yeah, that's an interesting question, I wish I had all the answers that I guess. So you could replicate it? I think there's a, there are a number of things that need to come together, right. Um one, you know, just like any new thing it is about, there's a sweet part of timing, Watch needed, you know, does it grow with watch needed? So in this case, for example, tensorflow is not just going because there is a good tool, it's also grown with the growth of deep learning itself. So those factors come into play Other than like two, I think just hearing, listening to the community, what they're to what they need being open to like in terms of external contributions, we've spent a lot of time and making sure we can accept those contributions. Well, we can help the contributors in adding those, putting the right process in place, getting the right kind of community welcoming them and so on. Like over the last year we've really pushed on transparency. That that's important for an open source project. People want to know where things are going and we're like, okay, here's a process where you can do that here are our seas and so on. Uh so thinking through, there are lots of community as aspects that come into that you can really work on as a small project that's may be easy to do because there's like two developers and you can do those as you grow putting more of these process in place. Thinking about the documentation, thinking about what do developers care about, what kind of tools would they want to use? one of these come into play thing. </s><s>[INST] So one of the big things I think that feeds the tensorflow fire is people building something on tensorflow and you know, some uh implement a particular architecture, it does something cool and useful and they put that on get hub and so it just feeds this uh this growth. Do you have a sense that with two point oh and one point Oh, that there may be a little bit of a partitioning, like there is with python two and three, that there will be a code base and in the older versions of tensorflow there will not be as compatible easily or a pretty confident that this kind of conversion, it's pretty natural and easy to do. [/INST] So we're definitely working hard to make that very easy to do. There's lots of tooling that we talked about the developer summit this week and we'll continue to invest in that tooling. It's um, you know, when you think of these significant version changes, that's always a risk and we're really pushing hard to make that transition very, very smooth. I think so, so at some level people want to move and they see the value in the new thing, they don't want to move just because it's a new thing and some people do, but most people want a really good thing and I think over the next few months, as people start to see the value, we'll definitely see that shift happening. So I'm pretty excited and confident that we will see people moving. Um, as you said earlier, this field is also moving rapidly, so that will help because we can do more things and you know, all the new things will clearly happen in two point X. So people who have lots separate reasons to move. </s><s>[INST] So what do you think? Uh tensorflow three point looks like? Is that, is there are things happening so crazily that even at the end of this year seems impossible to plan for or is it possible to plan for the next five years? [/INST] I think it's tricky. There are some things that we can expect in terms of okay, change, yes, change is going to happen. Are there some going things going to stick around and something is not going to stick around? I would say the basics of deep learning, the, you know, convolution models or the basic kind of things. They'll probably be around in some form still in five years will Ireland danced very likely based on where they are. We have new things probably, but those are hard to predict and some directionally some things that we can see is, you know, things that we're starting to do right with some of our projects right now is just to point out combining eager execution in grass, where we're starting to make it more like just your natural programming language, you're not trying to program something else. Uh similarly it's a for tensorflow, we're taking that approach, can you do something round up? Right. So some of those ideas seem like, okay, that's the right direction. In five years, we expect to see more in that area. Um, other things we don't know is will hardware accelerators be the same, Will we be able to train with four bits instead of 32 bits? I </s><s>[INST] and I think the Tpu side of things is exploring, I mean Tpu is already on version three, it seems that the evolution of Tpu and tensorflow are sort of uh their co evolving almost uh in terms of both are learning from each other and from the community and from the applications where the biggest benefit is that you, that you've been trying to sort of with eager with carrots to make tensorflow is accessible and easy to use as possible. What do you think for beginners is the biggest thing they struggle with, have you encountered that or is basically what paris is solving is that eager like we talked about [/INST] for, for some of them, like you said, right, pick winners want to just be able to take some image model, they don't care if it's inception or restaurant or something else and do some training or transfer learning on the kind of model being able to make that easy is important. So in some ways if you do that by providing them simple models that say in hub or so on and they don't care about what's inside that box, but they want to be able to use it, so, so we're pushing on, I think different levels, if you look at just a component that you get, which has the layers already smashed in the beginners, probably just want that, then the next step is okay. Look at building layers with errors, If you go out to research then they are probably writing custom layers themselves or they their own loop. So there's a whole spectrum there </s><s>[INST] and then providing the pretrained models seems to [/INST] really decrease </s><s>[INST] the time from you're trying to start, so you could basically Nicole lab notebook achieve what you need. Uh so basically answering my own question, because I think what tensorflow delivered on recently is uh it's trivial for beginners, so I was just wondering if there was other pain [/INST] points you're trying to ease, but I'm not sure there would, no, those are probably the big ones, I mean I see high schoolers doing a whole bunch of things now, which is pretty amazing, it's both </s><s>[INST] amazing and terrifying. [/INST] Yes, </s><s>[INST] in a sense that when they grow up it's uh some incredible ideas will be coming from them. So there's certainly a technical aspect to your work, but you also have a management aspect to your role with tensorflow, leading the project, a large number of developers and people, so what do you look for in a good team, What do you think, You know, google has been at the forefront of exploring what it takes to build a good team and tensorflow is one of the most cutting edge technologies in the world. So in this context, what do you think makes for a good team? [/INST] It's definitely something I think a favorite about, I think the uh in terms of, you know, the team being able to deliver something, well, one of the things that's important is a cohesion across the team, so being able to execute together and doing things, it's not like at this scale and individual engineer can only do so much, there's a lot more that they can do together, even though we have some amazing superstars across google and in the team, but there's, you know, often the way I see it as the product of what the team generates is way larger than the hole or, you know, the uh individual put together, and so how do we have all of them work together? The culture of the team itself, hiring good people is important, uh but part of that is, it's not just that okay, we hire a bunch of smart people and throw them together and let them do things, it's also people have to care about what they're building, people have to be motivated for the right kind of things, that's often an important factor. Um and, you know, finally, how do you put that together with uh somewhat unified vision of where we want to go? So are we all looking in the same direction or just going all over? And sometimes it's a mix of google is a very bottom up organization in some sense, uh also research even more so, uh and that's how we started, but as we've become this larger product and ecosystem, I think it's also important to combine that well with uh mix of, okay, here's the direction we want to go in, there is exploration, we'll do around that, but let's keep staying in that direction are just all over the place. </s><s>[INST] And is there a way you monitor the health of the team, sort of like, is there a way, you know, you did a good job team is good, like, I mean, you're sort of, you're saying nice things, but it's sometimes difficult to determine how aligned, because it's not binary, it's not like it's, there's tensions and complexities and so on and the other element to visit the measure superstars, you know, there's so much even a google, such a large percentage of work is done by individual superstars too. So there's a, uh and sometimes those superstars could be against the dynamic of a team and those, those tensions have, it was a, I mean, I'm sure in tensorflow it might be a little bit easier because the mission of the project is so sort of beautiful, you're at [/INST] the cutting edge is </s><s>[INST] exciting. Uh but have you had struggled with that? Has there been challenges? [/INST] There are always people challenges in different kinds of fairs that I think we've been, what's good about getting people who care and are, you know, have the same kind of culture and that's google in general to a large extent, but also, like you said, given that the project has had so many exciting things to do, there's been room for lots of people to do different kinds of things and grow, which, which does make the problem a bit easier, I guess, and it allows people depending on what they're doing, if there's room around them and that's fine. But yes, we do it, we do cared about whether superstar or not, like they need to work well with the team </s><s>[INST] across google, that's interesting to hear. So it's like uh superstar, not the productivity broadly is about the team. [/INST] Yeah, I mean, they might add a lot of value, but if they're putting the team then that's a problem. </s><s>[INST] So, in hiring engineers, it's so interesting. Right, the hiring process, what do you look for? How do you determine a good developer, a good member of the team from just a few minutes or hours together. [/INST] So </s><s>[INST] again, no magic answers, I'm [/INST] sure Yeah, and google has a Hiding process that we've refined over the last 20 years I guess and that you've probably heard and seen a lot about, so we do work with the same hiding process and that that's really helped for me in particular. I would say in addition to the core technical skills, what does matter is their motivation in what they want to do because if that doesn't align well with where you want to go, that's not going to lead to long term success for either of them or the team. Um And I think that becomes more important, the more senior the person is, but it's important at every level, like even the junior most engineer, if they're not motivated to develop what they're trying to do, how we're smart there, it's going to be hard for them to succeed. </s><s>[INST] There's the google hiring process, touch on that passion. So like trying to determine because I think as far as I understand maybe you can speak to it that the google hiring process sort of helps the initial like determines the skill set. There is your puzzle solving, ability, problem solving, ability, good. But like I'm not sure but it seems that the determining whether the person is like fire inside them that burns to do anything really, it doesn't really matter. It's just some cool stuff I'm gonna do it uh that I don't know is that something that ultimately ends up in when they have a conversation with you or once it gets closer to. [/INST] So one of the things we do have as part of the process is just a culture fit, like part of the interview process itself in addition to just the technical skills in each engineer or wherever the interviewer is, is supposed to rate the person on the culture and the culture fit with google and so on, so that is definitely part of the process now, uh there are various kinds of projects and different kinds of things, so there might be variants and the kind of culture you weren't there and so on and yes, that does vary. So for example, tensorflow has always been a fast moving project and we want people who are comfortable with that, but at the same time now for example, we are at a place where we are also very full fledged product and we want to make sure things that work really, really work right, you can't cut corners all the time, so they're balancing that out in finding the people who are the right fit for fit for those is important and I think those kind of things do vary a bit across projects and teams and product areas across google and so you'll see some differences there in the final checklist, but a lot of the core culture, it comes along with just engineering excellence and so on, </s><s>[INST] what is uh the hardest part of your job, take your pick, I [/INST] guess it's fun, I would say right, hard, yes, I mean lots of things at different times. I think that that does very, </s><s>[INST] so let me clarify that difficult things are fun. Yeah, when you saw them right, it's fun in that, in that sense. [/INST] I think the key to successful thing across the board and you know, in this case it's a large ecosystem now, but you're in a small product is striking that fine balance across different aspects of it. Sometimes it's how fast you go versus how perfect it is. Sometimes that's how do you involve this huge community, who do you involve or do you decide? Okay, now it's not a good time to involve them because it's not the right fit. Sometimes it's saying no to certain kinds of things. Those are often the hard decisions, some of them you make quickly because you don't have the time, some of them you get time to think about them, but they're always hard when </s><s>[INST] both both choices are pretty good. It's that those decisions, what about deadlines is just do you find tensorflow to be driven mm uh by deadlines to a degree that a product might or is there still a balance to where it's less deadline? You had the deaf summit that came together incredibly looked like there's a lot of moving pieces and so on. So that that deadline make people rise to the occasion releasing, that's the flow. Two point of Alpha, I'm sure that was done last minute as well. I mean like the up to the up to the up to the last point. [/INST] Again, you know, it's one of those things that uh, you need to strike a good balance. There is some value that deadline spring that does bring a sense of urgency to get the right things together instead of, you know, getting the perfect thing out, you need something that's good and works well. And the team definitely did a great job in putting that together. So it was very amazed and excited by everything how that came together. Uh That's it across there. We try not to put artificial deadlines, We focus on key things that are important, figure out what, how much of it's important and, and we are developing in the open, but you know, internally and externally everything is available to everybody so you can pick and look out where things are. Uh, we do releases at a regular cadence, so fine. If something doesn't necessarily end up this month, it will end up in the next release in a month or two. Uh and that's okay, but we want to get like, keep moving as fast as we can in these different areas, um, because we can iterate and improve on things. Sometimes it's okay to put things out that aren't fully ready if you make sure it's clear that okay, this is experimental, but it's out there. If you want to try and get feedback, that's very, very useful. I think that quick cycle and quick iteration is important. That's what we often focus on rather than here's a deadline where you get everything else? </s><s>[INST] It's 2.0, is there pressure to make that stable? Or like for example, wordpress five point, I just came out and there was no pressure to, it was a lot of build updates to deliver it way too late but and they said, okay, well, but we're going to release a lot of updates really quickly to improve it. Does, do you see tensorflow two point on that same kind of way? Or is there this pressure to once it hits two point? Oh, once you get to the release candidate and then you get to the final that that's going to be the stable thing, [/INST] so it's going to be stable in just like when your ex was where every api that's there is going to remain and work? Uh it doesn't mean we can't change things in another covers, it doesn't mean we can't add things so there's still a lot more for us to do and we can't really have more releases. So in that sense there's still, I don't think we'll be done in like two months when we release this, </s><s>[INST] I don't know if you can say but is there, You know, there's not external deadlines for Tensorflow 2.0 but is their internal deadlines, the artificial or otherwise that you're trying to set for yourself [/INST] or is it </s><s>[INST] whenever it's ready? [/INST] So we wanted to be a great product and that's a big important piece for us, tensorflow is already out there. We have, you know, 41 million downloads for one dot X. So it's not like we have to have this. Yeah, exactly. So it's not like a lot of the features that we've, you know, really polishing and putting them together are there? We don't have to rush that just because so in that sense we want to get it right and really focus on that. Uh that said, we have said that we are looking to get this out in the next few months in the next quarter and you know, as far as possible, we let me try to make that happen. </s><s>[INST] Yeah. My, my favorite line was spring is a relative concept and I love [/INST] it. Yes, spoken </s><s>[INST] like a true developer. So you know something I'm really interested in and your previous line of work is before tensorflow. You let a team I google on search ads I think uh this is like this is a very interesting topic on every level on a technical level because at their best ads connect people to the things they want and need so and and that their worst, they're just these things that annoy the heck outta you to the point of ruining the entire user experience of whatever you're actually doing. So they have a bad rap I guess Uh, and at the, on the other end. So that this connecting users to the thing they need to want is a beautiful opportunity for machine learning to shine like huge amounts of data that's personalized and you kind of map to the thing they actually want, won't get annoyed. So what have you learned from this google that's leading the world in this aspect? What have you learned from that experience And uh, what do you think is the future of ads? Thank you back to the [/INST] yes, it's been a while, but I totally agree with what he said. I think the search ads, the way it was always looked at and I believe it still is is it's an extension of what such is trying to do. The goal is to make the information and make the world's uh, information accessible. That it's not just information, but maybe products or, you know, the things that people care about. And so it's really important for them to align with what the users need and you know, the in such as there's a minimum quality level before that, that would be shown if you don't have an act that it's that quality, but it will not be shown even if we have it and okay, maybe we lose some money there. That's fine. That that is really, really important. And I think that that is something I really liked about being there. Advertising is a key part. I mean as a model that's been around for ages. Right. It's, it's not a new model, it's been adapted to the web and, you know, became a core part of search and in many other search engines across the world. I I do hope, you know, like I said, there are aspects of ads that are annoying and I go to a website and if it just keeps popping out in my face not to write like me, that's that's going to be knowing clearly. So, um, I hope we can strike that balance between showing a good ad where it's valuable to the user and provides the monetization to the, to the service and this might be searched. This might be a website. All of these, they do need the monetization for them to provide that service, but if it's done in a good balance between showing just some random stuff that's distracting versus showing something that's actually valuable. </s><s>[INST] So, do you, do you see it moving forward as to continue being a uh, model that, uh, you know, that funds businesses like google? That's a that's a significant revenue stream because that's one of the most exciting things, but also limiting things on the internet is nobody wants to pay for anything and advertisements again coupled at their best are actually really useful and not annoying. Do you continue? Do you see that continuing and growing and improving or is there? Do you see sort of uh more netflix type models where you have to start to pay for content? [/INST] I think it's a mix, I think it's gonna take a long while for everything to be paid on the internet if at all. Um probably not. I mean I think there's always going to be things that are sort of monetized with things like cowards, but over the last few years I would say we have definitely seen that transition towards more page services across the web and people are willing to pay for them because they do see the value, netflix is a great example, we have youtube doing things, people pay for the apps to buy more people I find are willing to pay for newspaper content for the good news websites across the web? That wasn't the case a few years, even a few years ago, I would say, and I just see that change in myself as well and just lots of people around me, so definitely hopeful that we'll transition to that uh mixed model where maybe you get to try something out for free maybe with ads, but then there's a more clear revenue model that that sort of helps go beyond that. </s><s>[INST] So speaking of revenue, how is it that a person can use the tpu and a google collab for free. So what's the, I guess the question is, what's the future of tensorflow in terms of empowering, say, teach a class of 300 students and they are masked by M. I. T. What is going to be the future of them being able to do their homework intensive flow, like where are they going to train these networks? Right, what's that future look like with Cpus, with cloud services and so on. [/INST] I think a number of things that I mean any tensorflow, open source, you can run it whatever, you can run on your desktop and your desktops always keep getting more powerful, so maybe you can do more, my phone is like, I don't know how many times more powerful than my first desktop, probably training on your phone though. Yeah, right, so, so in that sense, the power you have in your hand is a lot more clouds are actually very interesting from say students or our courses perspective because they make it very easy to get started, I mean collab, the great thing about is go to a website and it just works, no installation needed, nothing too, you know, you're just just there and things are working, that's really the power of cloud as well. And so I do expect that to grow again, you know, collab is a free service, it's great to get started to play with things to explore things uh that said, you know, with three, you can only get so much, yeah, so just like we were talking about, you know free versus creation. Yeah, there there are services, you can pay for and get a lot more </s><s>[INST] Great. So if I'm a complete beginner interested in machine learning intensive flow, what should I do? [/INST] Probably start with going to our website and playing their tents for that organ. Start clicking on things, yep, Jacquard tutorials and guides. There's stuff you can just click there and cardio, collab and do things. No installation. Either. You can get started right there. </s><s>[INST] Okay, awesome. Roger. Thank you so much for talking today. [/INST] Thank you. Like it's fun. It's great. </s><s>[INST] Yeah. [/INST] </s>

<s>[INST] Yeah I think so because I I so there's this fear of robots that they become super intelligent and run away from us humans and basically become so intelligent and then they almost just not giving a damn will destroy us. Um But I think in order for for robots to become intelligence, they have to integrate themselves with society. So they they by the very nature of of how they become intelligent have to bring us along. So it's not that there will be this separate thing. They have to like we'll have robots in the home. Well they'll be interacting with us. You have human kids and you have a bunch of robots, you have robot friends, you have human friends and they the robots make your human to human relationships much more meaningful and richer. They bring more love to the world. But they it's integrated it's not like they'll be developing smarter and smarter as like um sentient beings by themselves. I think that's very difficult to do. You have to be doing that together with humans and so will come for the right? There's technical things like we might merge like cyborgs more and more. We [/INST] already saw are cyborgs </s><s>[INST] right? With the phones and so on. But more and more so with Ellen and neuralink deeper integration of robots and ai into like increasing the bandwidth at which they can communicate. So if we do implants in the brain. I think um again a lot of people are really nervous about this. As am I But I think there's a lot of trajectories that are positive there and that to music side. And also I just don't think it's possible to stop this development so we should uh steer it. [/INST] Yeah. Did you? I mean you must have watched the movie terminator right? Yeah of course. I love terminator. Yeah. My favorite movie of all time. Yeah. Yeah. I mean that's that's the big fear right? </s><s>[INST] Yeah. What's the conclusion with terminator isn't ultimately humanity wins. [/INST] I think there are like terminator eight now, you know, I don't </s><s>[INST] know. Yeah. The so there it's interesting actually. I was going to bring this up as you were talking about it. But uh but China and the United States actually don't know where Canada is on this. But they both have agreed that they're not going to put limits an autonomous weapon uh system development, so they're not going to, so because China said we're not going to and our US officially announced that we're not we can't [/INST] well you can't, it's like it's like you never could write as soon as it exists and it's better people will use it. </s><s>[INST] Well, but you um there's been a global ban on bioweapons. So you were able to come to an agreement there that we're not going to use biological weapons in war. So it was a lot of people are really upset that in the case of ai driven weapons, the world said, nope, that's okay. And so now you have this potential for greater and greater automation and drones for example and picking bombing locations. And so the area at which they attack. And so you get some of that stuff that you mentioned that that drew you to the military is that teamwork between humans that decision making. So there's strategy but built into that team is a deep humanity, even when there's an enemy there's lines that you are aware of of what is ethical and what is not what is just and what is not and it's so easy for a machine uh to ah to miss all of that plow through it and do deeply inhumane acts, commit atrocities. That that's something that worries a lot of people. Um Because yeah an Ai based war is just it's terrifying especially with cybersecurity which is becoming more and more of an issue which is hacking sort of people that look a lot like me being the warriors of the future which is meaning people behind a keyboard versus uh versus the traditional warriors. [/INST] Probably inevitable. </s><s>[INST] Yeah and terrifying. It is. It [/INST] is. But I think if you believe that it's possible it's certainly going to happen like at some point it's just when right when does it happen? </s><s>[INST] So that I mean to me I'm optimistic, ultimately optimistic about the future and to me I'm excited about the world with ai I'm even excited about the metaverse and all these kinds of things, living more and more in the digital space in the virtual reality I think so it's a part of me that grew up in the non internet world, non computer world, you know it says oh kids these days with the video games, you know there's part of me that's like that. Um But I think what it wants technology at its best can bring out the best of humanity. And so I think virtual reality all of these things over time, we'll figure out how to how to fix it to bring out the humanity, social networks, the first generation social networks now facebook twitter and so on. They have so many problems they're bringing out the worst in people. But I think we're learning from that and I think the next generation of social networks will be better and better and better. And so I'm optimistic. But of course, you know, one reason we may have not seen aliens yet, obviously, like in a way that's obvious is because once you get clever and smart and have all this cool technology, you destroy yourself and we sure as humans are pretty close to that. [/INST] Yeah. Yeah, there might be that limit. That is hard to get right. </s><s>[INST] I'm hoping we get all our aggression between nations out through arm wrestling competition. Right? Just all [/INST] like, oh my God, wouldn't that be great if that was, if it was that simple? </s>

<s>[INST] you're looking for the echoes of the same kind of experience in order to predict what the future holds. Yeah, the victor, franco in his book Man's Search for meaning. Not sure if you've read describes his experience at the concentration concentration camps during World War Two, as a way to describe that finding identifying a purpose in life, a positive purpose in life, you can save one from suffering, first of all, do you connect with the philosophy that he describes there? [/INST] Not really. I mean, the so I can I can really see that somebody who has that feeling of purpose and meaning and so on, that that could sustain you uh I in general don't have that feeling and I'm pretty sure that if I were in a concentration camp give up and die, you know? So he talks he's he's a survivor and you know, he survived with that and I'm and I'm not sure how is central to survival. The sense is, but I do know when I think about myself that I would have given up uh oh yeah, this isn't going anywhere. Uh And there is there is a sort of character that that manages to survive in conditions like that. And then because they survived, they tell stories and it sounds as if they survived because of what they were doing, We have no idea they survived because the kind of people that they are and the other kind of people who survived and will tell themselves stories of a particular kind. So I'm not </s><s>[INST] so you don't think seeking purpose is a significant driver and are being. [/INST] It's a very interesting question because when you ask people whether it's very important to have meaning in their life, that's Oh yes, that's the most important thing. But when you ask people, what kind of a day did you have? And and you know, what were the experiences that you remember? You don't get much meaning. You get social experiences then. Uh and and some people say that for example, in and and child, you know, taking care of Children. The fact that they are your Children and you're taking care of them uh makes a very big difference. I think that's entirely true. Uh But it's more because the story that we're telling ourselves, which is a very different story when we're taking care of our Children or when we're taking care of other things, </s><s>[INST] jumping around a little bit in doing a lot of experiments, Let me ask a question. Most of the work I do for examples in the world, in the real world. But most of the clean good science that you can do is in the lab. So that distinction, do you think we can understand the fundamentals of human behavior through controlled experiments in the lab. If you talk about people diameter for example, it's much easier to do when you can control lighting conditions, right? Uh So when we look at driving lighting variation destroys almost completely your ability to use pupil diameter. But in the lab for, as I mentioned semi autonomous or autonomous vehicles and driving simulators, we can't we don't capture true honest human behavior in that particular domain. So your what's your intuition? How much of human behavior can we study in this controlled environment of the lab [/INST] a lot? But you'd have to verify it. You know, that your conclusions are basically limited to the situation to the experimental situation, then you have to jump that big inductive leap to the real world. Uh So and and that's the flare. That's where the difference. I think between the good psychologist and others that are mediocre is in the sense that that your experiment captures something that's important and something that's real and others are just running experiments. </s><s>[INST] So what is that like the birth of an idea to his development in your mind, to something that leads to an experiment is that similar to maybe like what Einstein or a good physicists do is your intuition you basically use your intuition to build up. [/INST] Yeah, but I mean, you know, it's it's very skilled intuition. I mean, I just had that experience actually. I had an idea that turns out to be a very good idea a couple of days ago. And and you and you have a sense of that building up. So I'm working with a collaborator and he essentially was saying, you know, what, what are you doing, you know, what's what's going on? And I was really I couldn't exactly explain it, but I knew this is going somewhere. But you know, I've been around that game for a very long time. And so I can you develop that anticipation that yes, this this is worth </s><s>[INST] following something. Something here [/INST] that's part of the skill </s><s>[INST] is that something you can reduce two words in describing a process in the form of advice to others. [/INST] No, </s><s>[INST] follow your heart essentially. [/INST] You know, it's it's like trying to explain what it's like to drive. It's not, you've got to break it apart and it's not and then you lose and then you lose the experience. </s>

<s>[INST] And you said that if I wear this around new york, am I getting a little bit, you [/INST] might get a guy from the Bronx? Good, well screw you, you know? But I mean, it's all, it's all that good rivalry. You know, we like to, you know, we like to kid each other back and forth, you know? Uh, guys from Manhattan was yeah. You guys in Brooklyn? Yeah. Short buildings, tall stories and yeah, but you guys are Manhattan? Tall, tall buildings, no story. You know, it's all that jocular ball breaking. It's good stuff, you know? </s><s>[INST] Um, let me ask a I guess it's a difficult question if you just step back on the events of 9 11 on the side of the people that flew into the towers, what do you take away from that day about the nature, about human nature, about good and evil, how did that change your view of the world? [/INST] I witnessed evil firsthand. Um, I remember Later on, well into that night when we were trying to help get those police officers out, remember looking up at the building. Century 21, the store runs along the east side of the towers and it was still there and you know, the debris had come down right almost to the edge and Century 21 is this old story department store in new york city and the sign was was there and it was still lit up. Like some of the neon was broken and but I think some of it was actually still lit up and I just looked around and I was like, yeah, this is this is a war zone, like we're at war and you know, we knew we were attacked, we heard the fighter planes and you know, back then it wasn't the extensive communication network and we had cell phones, but they were the old school flip phones and there was no news on them. And so plus we we didn't have signal down there. Anyway, I couldn't reach my family for like 12, 13 hours. And my dad had deployed down to the ferry terminal to retrieve bodies. Uh he was retired but he still went and they deployed him to go be basically the more transport guys, they expected to be sending hundreds and thousands of bodies across on the ferry and they set up these tractor trailers as a mobile morgue. And that never happened because there were no bodies to take. They were all buried. Um, so it's so evil firsthand, I don't know how someone can inflict such vent revenge or eventual act for in the name of anything in the name of religion, in the name of a cause and the name like what the hell? You know, </s><s>[INST] were you ever able to make sense of that? Why men are able to commit such acts of terror in the days and the years after? [/INST] No lex. I haven't, you know, my mom's from Ireland and um, I still have a lot of family there and you know, my my great uncles, one of them was dragged out and shot. You know, he lived but, but just based on a rumor that he was in the I. R. A. And I wasn't happy to see what happened to my mom's people because they were victimized and brutalized by England at that time. But blowing up bombs and killing innocence in the name of that, it doesn't make it right. I couldn't justify something like that. I I can see, you know, I was a cop, I was a soldier and you never want to take life and in those jobs, but sometimes you have to, but you don't do it with a vengeance. You don't do it with a thirst. You do it because it's necessary for survival when you do it out of a bloodlust out of a thirst out of a cause that's evil. There's something wrong with you. I have no, I, I respect life to the highest level. I mean I'm very, life is sacred to me. It's precious, it's beyond, it's not a commodity, it's a gift, but to take life just so randomly. So there's something way wrong with that person and, and maybe I'm a conflicted soul, but I would have no problem seeing someone like that put to death because they do not deserve life. Um, there's, there's many, uh, many Children around this world that are being taught to hate someone who is different than them just because the person who is allegedly teaching them says so I don't understand. Well </s><s>[INST] that starts with just having a basic um respect and appreciation of other other human beings and that starts with empathy. So, and one of the reasons I love this country why while joking that I'm Russian, uh maybe you could say the same as you being irish uh, is your actually truly an american. And that's why I consider myself very much an american. And one of the reasons I love this country is it serves as a beacon, I still believe it serves as a beacon of hope and that empathy and love uh for the rest of the world that like hate is uh not gonna get you far that love will get you a lot farther and I still think, you know, sometimes it's easy to um see the press, uh mainstream media, you can see social networks because you can make so much money on division sometimes because it makes so much money, it's easy to think like we're really divided. I honestly don't think we are. That's just [/INST] like the very </s><s>[INST] surface level thing [/INST] That we see on Twitter. It's that you're, you're 100% right. There's people out there that are maximizing off this whole division, right? They want us divided. They want people angry because it sells, you know, a lot of these people that are in charge of certain organizations. Well, they all seem to have nice cars and nice houses, nice vacations and they're constantly trying to convince everybody that we hate each other to me. I'll use a fireman analogy, right? It's like a little campfire and if you just let the ambers flutter, they'll, they'll go out. But if you take a little cup of gasoline with those embers were to blow right up in your face. And that's what a lot of these politicians and a lot of these media folks are doing because there's something in it for them. </s>

<s>[INST] you're focused on the hardware side, which requires all the disciplines that you mentioned. And then of course, you know, science may be a source of inspiration for some of the long term vision, [/INST] I would actually call it more than inspiration I would call it, sort of um a road map, you know, we're not trying to build exactly the brain, but I don't think it's enough to just say, oh neurons kind of work like that, let's kind of do that thing. I mean we're very much following the concepts that the cognitive sciences have laid out for us, which I believe is a really robust roadmap, I mean just on a little bit of a tangent, it's often stated that we just don't understand the brain and so it's really hard to replicate it because we just don't know what's going on there and I maybe five or seven years ago I would have said that, but as I got more interested in the subject, I read more of the neuroscience literature and I was just taken by the exact opposite sense, I can't believe how much they know about this, I can't believe how mathematically rigorous and um sort of theoretically complete a lot of the concepts are that's not to say we understand consciousness or we understand the self or anything like that, but why is the brain, what is the brain doing and why is it doing those things? We have a neuroscientists have a lot of answers to those questions, so there's a lot if you're a hardware designer that just wants to get going, whoa, it's pretty clear which direction to go in, I think. </s><s>[INST] Okay, so I love I love the optimism behind that. But in the implementation of these systems that uses super super connectivity, how do you make it happen? [/INST] So to me it starts with thinking about the communication network, you know, for sure that the ability of each neuron to communicate to many thousands of colleagues across the network is indispensable. I take that as a core principle of my my architecture, my thinking on the subject. Uh coming from coming from a background in photonics, it was very natural to say, okay, we're going to use light for communication just in case listeners may not know. Light is often used in communication. I mean if you think about radio, that's light, it's long wavelengths, but it's electromagnetic radiation, it's the same. It's the same physical phenomenon, obeying exactly the same Maxwell's equations. And then all the way down to fiber fiber optics. Now you're using visible or near infrared wavelengths of light. But the way you send messages across the ocean is now contemporary over optical fibers. So using light for communication is not a stretch, it makes perfect sense. So you might ask, well, why don't you use light for communication in a conventional microchip? And the answer to that is I believe physical, if we if we had a light source on a silicon chip that was as simple as a transistor, we would there would not be a processor in the world that didn't use light for communication at least above some distance. </s><s>[INST] How many light sources are needed? Oh, you need a light source at every single point. [/INST] A light source per neuron </s><s>[INST] for neuron political. But then if you could have a really small and nice light source, you can your definition of neuron could be flexible. [/INST] Could be Yes. Yes. Sometimes it's helpful to me to say in this hardware, a neuron is that entity which has a light source that I can then </s><s>[INST] there was light. [/INST] I can explain more about that. But um </s><s>[INST] somehow this like rhymes with consciousness because the people will often say the light of consciousness. So that consciousness is that which is conscious. I got it. [/INST] That's not my quote, </s><s>[INST] that's me, that's my quote. Uh see that quote comes from my background, yours is in optics. Mine in light minds and [/INST] darkness. </s><s>[INST] Go ahead. [/INST] So what's the point I was making there is that if it was easy to manufacture light sources along with transistors on a silicon chip, they would be everywhere. And it's not easy. It's people have been trying for decades and it's actually extremely difficult. I think an important part of our research is dwelling right at that at that spot there. So </s><s>[INST] it's a physics or engineering physics. [/INST] So, okay, so it's it's physics I think. So what I mean by that is as as we discussed, silicon is the material of choice for transistors. And it's very difficult to imagine that That's going to change anytime soon. Silicon is notoriously bad at emitting light and that has to do with the immutable properties of silicon itself. The way that the energy bands are structured in silicon, you're never going to make silicon efficient as a light source at room temperature without doing very exotic things that degrade its ability to interface nicely with those transistors in the first place. So that's that's like one of these things where it's why why is nature dealing us that blow? You give us these beautiful transistors and you give us all the motivation to use light for communication. But then you don't give us a light source. So well, okay, you do give us a light source compound semiconductors like we talked about back at the beginning, an element from Group three and an element from group five from an ally where every other lattice site switches, which element it is. Those have much better properties for generating light. You put electrons in light comes out Almost 100% of the electron hold. It can be made efficient. I'll </s><s>[INST] take your word however [/INST] I say it's physics not engineering because it's very difficult to get those compound semiconductor light sources situated with your silicon in order to do that ion implantation that I talked about at the beginning, high temperatures are required. So you you got to make all of your transistors first and then put the compound semiconductors on top of their, you can't grow them afterwards because that requires high temperature. It screws up all your transistors. You try and stick them on there. They don't have the same lattice constant. The spacing between atoms is different enough that it just doesn't work. So nature does not seem to be telling us that hey, go ahead and combine light sources with your digital switches for conventional digital computing. </s>

<s>[INST] So I agree with you very much. It's not often heard that most people in the world have good intentions at the core. Their intentions are good and they're good people. That's a, it's a beautiful mother. It's not often heard [/INST] we make this mistake and this is a friend of mine exhibit uh penis that we judge ourselves by our intentions and others by their actions. And I think the biggest skill, I mean here in Silicon Valley were full of engineers who have very little empathy and, and, and I'm kind of befuddled by, it doesn't work for them. The biggest skill I think that, that people should acquire is to put themselves into the position of the other and listen and listen to what the other has to say. And they'd be shocked how similar they are to themselves and they might even be shocked how their own actions don't reflect their intentions. Um, I often have conversations with engineers and I say, look, hey, I love you. You're doing a great job. And by the way, what you just did has the following effects. Are you aware of that? And then people would say, oh my God not, I wasn't because my intention was that and say, yeah, I trust your intention. You're a good human being, but just to help you in the future, if you keep expressing it that way, then people just hate you. And I've had many instances would say, oh my God, thank you for telling me this because it wasn't my intention to look like an idiot, It wasn't my intention to help other people. I just didn't know how to do it. Very simple. By the way, there's a book dale Carnegie, 1990 36 How to make friends and how to influence others has the entire bible, you just read it and you're done and you apply it every day and I wish I could, I was good enough to apply it every day, but it's just simple things, right? Like be positive, remember people's name, smile and eventually have empathy, Like really think that the person that you will hate and you think it's an idiot, it's actually just like yourself, it's a person who's struggling who means well and who might need help and guess what you need help. </s><s>[INST] I've recently spoken with Stephen Schwarzman, I'm not sure if you know who that is, but so [/INST] he said on my list, I </s><s>[INST] noticed, but he said uh sort of to expand what you're saying that uh one of the biggest things that you can do is here people when they tell you what their problem is and then help them with that problem. He says, it's surprising how few people, like actually listen to what troubles others and because it's right there in front of you and you can benefit the world the most and in fact yourself and everybody around you by just hearing the problems and solving [/INST] them. I mean that's my my little history of engineering that is while I was engineering with computers, I didn't care at all what the computer's problems for because I just told him to do and to do it and it just doesn't work this favorite people, it doesn't work with me if you come to me and said with the way I do the opposite, </s><s>[INST] but let's return to the comfortable world of engineering. Can you, can you tell me in broad strokes in how you see it? Because you're the core of starting at the core of driving it, the technical evolution of autonomous vehicles from the first DARPA grand challenge to the incredible success we see with the program you started with google self driving car and way more in the entire industry that's sprung up all the different kinds of approaches, debates and so on. [/INST] When the idea of self driving car goes back to the eighties, there was a team of Germany and the team at Carnegie Mellon that did some very pioneering work. But back in the day, I'd say the computers were so deficient that even the best professors and engineers in the world basically stood no chance. It then folded into a phase where the U. S. Government spent at least half a billion dollars that I could count on research projects. But the way the procurement works. A successful stack of paper describing lots of stuff that no one's ever gonna read was a successful product of a research project. So we trained our researchers to produce lots of paper that all changed for the DARPA grand challenge. And I really got to credit the ingenious people at DARPA and the US government in Congress that took a complete new funding model where they said that's not fund effort, let's fund outcomes. And it sounds very trivial but there was no tax code that allowed the use of congressional tax money for a price. It was all effort based. So if you put in $100 in you could charge 100 hours, you put in $1000 and you could build $1000 by changing the focus on making the price we don't pay you for development, we pray for the accomplishment. They drew in, they automatically drew out all these contractors who are used to the drug of getting money power and they drew in a whole bunch of new people and these people are mostly crazy people. There were people who had a car and a computer and they wanted to make a million bucks. The million bucks for visual price money was then doubled and they felt if I put my computer in my car and program it, I can be rich and that was so awesome like like half the teams, there was a team that was a surfer dudes and they had like two surfboards on the vehicle and brought like these fashion girls, super cute girls like twin sisters. Um and you could tell these guys were not your common uh beltway bandit who gets all these big multi million and billion dollar countries from the U. S. Government um and there was a great reset universities moved in. I was very fortunate at stanford that had just received tenure, so I couldn't get fired when I want to do otherwise, I would have done it and I had enough money to finance this thing. Uh and I was able to attract a lot of money from from third parties and even car companies moved in, They kind of moved in very quietly because they were super scared to be embarrassed that they are covered flip over, but Ford was there and Volkswagen was there and a few others and GM was there. So it kind of reset the entire landscape of people and if you look at who's a big name in self driving cars today, these were mostly people who participated in those challenges. </s>

<s>[INST] When you talk about look ahead uh for deep stack or when they brought us, does it mean considering every possibility that the game can involve, Are we talking about extremely sort of like this exponentially growth of a tree? [/INST] Yes, so we're talking about exactly that much like you do in Alfa beta search or want to crawl research but with different techniques, so there's a different search algorithm and then we have to deal with the leaves differently. So if you think about what liberators did, we didn't have to worry about this because we only did it at the end of the game. So we would always terminate into a real situation and we would know what to pay out is it didn't do this depth limited local heads. But now in this new paper which is called depth limited, I think it's called depth limited search for imperfect information games, we can actually do sound depth limited, look ahead. So we can actually start to do with the local head from the beginning of the game on because that's too complicated to do for this whole long game. So in liberals we were just doing it for the end. </s><s>[INST] So and then the other side, the belief distribution. So is it explicitly modeled what kind of beliefs that the opponent might have? [/INST] Yeah, yeah, it is explicitly modeled but it's not assumed the beliefs are actually output, not input. Of course the starting beliefs are input, but they just fall from the rules of the game because we know that the dealer deals uniformly from the deck. So I know that every pair of cards that you might have is equally likely. I know that for a fact that just follows from the rules of the game of course, except the two cards that I have, I know you don't have those uh you have to take that into account. That's called card removal. And that's very important is </s><s>[INST] the dealing always coming from a single deck and heads up so you can assume [/INST] single deck that so it's hard for a mobile, you know that if I have the ace of spades, I know you don't have an ace of space. </s><s>[INST] So in the beginning, your belief is basically the fact that it's a fair dealing of hands. But how do you adjust start to adjust that [/INST] belief? Well, that's where this beauty of game theory comes. So nash equilibrium, which John Nash, introduced in 1950 introduces what rational play is when you have more than one player. And these are pairs of strategies where strategies are contingency plans, one for each player uh so that neither player wants to deviate a different strategy given that the other doesn't deviate, but as a side effect, you get the beliefs from base role. So nash equilibrium really isn't just deriving in this imperfect information games nash equilibrium, It doesn't just define strategies. It also defines beliefs for both of us. And the refines beliefs for each state. So at each state each if they call information sets at each information set in the game, there's a set of different states that we might be in. But I don't know which one we're in. Nash equilibrium tells me exactly what is the probability distribution over those real world states in my mind. </s><s>[INST] How does nationally give you that distribution? So while [/INST] I'll do a simple example, so you know the game rock paper scissors. So we we can draw it as player one moves first and then player two moves. But of course It's important that player two doesn't know what player one moved otherwise, players who would win every time. So we can draw that as an information set where player one makes one of three moves first and then there's an information set for player two. So player two doesn't know which of those notes the world is seen. But once we know the strategy for player one, nash equilibrium will say that you play one third rock, one third paper, one third caesar's from that. I can derive my beliefs on the information. Said that they're one third one third, one third, </s><s>[INST] there's a base gives you that gives you but is that specific to a particular player? Or is it uh is that something you quickly update with? [/INST] The game theory isn't really player specific? So that's also why we don't need any data, We don't need any history how these particular humans played in the past or how any ai or human had played before. It's all about rationality. So we just think the idea just thinks about what would a rational opponent do and what would I do if I were I am rational and what that's that's the idea of game theory. So it's really a data free opponent free </s><s>[INST] approach. So it comes from the design of the game as opposed to the design of the player. [/INST] Exactly. There's no opponent modeling per se. Okay, I mean we've done some work on combining opponent modeling with game theory. So you can exploit weak players even more. But that's another strand. And in liberators who didn't turn that on because I decided that these players are too good. And when you start to exploit an opponent, you typically open yourself self up to exploitation. And these guys have so few holes to exploit. And the world's leading experts in counter exploitation. So I decided that we're not gonna attend that stuff on </s><s>[INST] actually, I saw a few papers and exploiting opponents. It sounds very interesting to uh explore. Uh Do you think there's room for exploitation. Generally outside of Lebron does is their subject uh or people differences. That could be exploited maybe not just in poker, but in general interactions negotiations. All these other domains that you're considering? [/INST] Yeah, definitely. we've done some work on that and I really like the work that hybridize is the two. So you figure out what would a rational opponent to and by the way that's safe in the zero sum games, two player zero sum games. Because if the opponent does something irrational. Yes, it might show throw off my beliefs, but the amount of the player can gain by throwing off my belief is always less than they lose by playing poorly. So so it's safe. But still if somebody's weak as a player you might want to play differently to exploit them more so that you can think about it this way a game theoretic strategy is unbeatable but it doesn't maximally beat other opponents. So the winnings per hand might be better with a different strategy. And the hybrid is that you start from a game theoretic approach. And then as you gain data from about the opponent in certain parts of the game three, that in those parts of the game three, you start to tweet your strategy more and more towards exploitation While still staying fairly close to the game 30 strategy. So as to not open yourself up to exploitation too much. </s>

<s>[INST] combining all those reward functions of the different selves you have. [/INST] Yeah. And accepting that they are, they're like, you know, often people, they have a negative self talk or they say, I don't like when I'm angry like a try to imagine, try to imagine if there would be okay small baby lex, like a five years old, angry angry and then they are like you shouldn't be angry like I stopped being angry but like instead actually want the legs to come over and give him a hack and it's like I say it's fine, okay, you can be angry as long as you want and then he would stop </s><s>[INST] or or [/INST] maybe not or maybe not, but you cannot expect it even. </s><s>[INST] Yeah, but still that doesn't explain the why of love. Like why is love part of the human condition? Why is it useful to combine the reward functions? It seems like that doesn't mean I don't think reinforcement learning frameworks can give us answers to why even even the hotter framework has an objective function that's static. [/INST] So we came to existence as a consequence of evolutionary process and in some sense the purpose of evolution is survival. And then the this complicated optimization objective baked into us. That's a compression which might help us operate in the real world and it baked into us various reward functions. Uh then to be clear at the moment we are operating in the regime which is somewhat out of distribution where they even evolution optimize us. </s><s>[INST] It's almost like love is a consequence of cooperation that we've discovered is useful [/INST] correct in some way. It's even the case if you I </s><s>[INST] just love the idea that love is like the out of distribution [/INST] or it's not out of distribution is like as you said above all for cooperation. Yes. And I believe that the corporate like in some sense corporation ends up helping each of us individually. So it makes sense evolutionary. And there is a in some sense. And you know, love means there is this dissolution of boundaries that you have a shared reward function. And we evolved to actually identify ourselves with larger groups. So we can identify ourselves, you know with a family. We can identify ourselves with a country to such an extent that people are willing to give away their life for the country. Uh So there is We are wired actually even uh for love. And at the moment I guess the mm hmm Maybe it would be somewhat more beneficial if you will if we would identify ourselves with all the humanity as a whole. So So you can clearly see when people travel around the world when they run into person from the same country. They say oh which ctr and all this. Like all the sudden they find all these similarities. They find some they befriend those folks earlier than others. So there is like a sense some sense of the belonging. And I would say I think it would be overall good things to the world for people to move towards. Uh I think it's even called open individualism move toward the mindset of a larger and larger groups. </s><s>[INST] So the challenge there that's a beautiful vision And I share it to expand that circle of empathy. That circle of love towards the entirety of humanity. But then you start to ask well where do you draw the line? Because why not expand it to other conscious beings? And then finally for our discussion something I think about is why not expanded to ai systems like we we start respecting each other when the person, the entity on the other side has the capacity to suffer because then we develop a capacity to sort of empathize. And so I could see A. I systems that are interacting with humans more and more having conscious like displays So like they display consciousness through language and through other means. And so then the question is like well is that consciousness because they're acting conscious. And so you know the reason we don't like torturing animals is because they look like they're suffering when they're tortured and if a I looks like it's suffering when it's tortured. How is that not requiring of the same kind of empathy from us and respect and rights that animals do it? Another humans [/INST] do. I think it requires empathy as well. I mean I would like guests us or humanity or so make a progressing understanding what consciousness is because no one just to be speaking about that the philosophy but rather actually make a scientific uh they have a like you know, there was a time that people thought that there is a force of life and uh the things that have this force they are alive. And uh I think that there is actually a path to understand exactly what consciousness is. And uh um in some sense it might require essentially putting probes inside of a human brain what neuralink uh does. </s>

<s>[INST] liability, the ethics, How do you get it right? It's tricky. It's really, really tricky because like drinking is one of those things that's funny and hilarious and loves its social, the so on and so forth. But it's also the thing that hurts a lot of people, like a lot of people like alcohol is one of those things, it's legal, but it's really damaging to a lot of lives, It destroys lives and not just in the driving context. Um I should mention, people should listen to Andrew Huberman who recently talked about um alcohol. He has an amazing pocket. Andrew Huberman is uh neuroscientists from stanford and a good friend of mine and he he's like a human encyclopedia about all health related wisdom. So that there's a podcast you would love. [/INST] No, no, </s><s>[INST] no, no, no. Oh you don't know. Andrew Huberman. Okay, listen, you listen to to Andrew, he's called human lab podcast. This is your assignment. Just listen to one. I guarantee you this will be a thing where you say, lex, this is the greatest human I've ever discovered. So, [/INST] oh my God, because I've really, I'm really on a journey of kind of health and wellness and I'm learning lots and I'm trying to like build these, I guess atomic habits around just being healthy. Um So I'm definitely gonna do this, I'm gonna </s><s>[INST] his whole thing. This is this is, this is, this is great. Uh he's a legit scientist, like um really well published, but in his podcast, what he does, he's not he's not talking about his own work, he's like a human encyclopedia of papers. And so he, his whole thing is he takes the topic and in a very fast you mentioned atomic habits, like very clear way summarizes the research in a way that leads to protocols of what you should do. He's really big on like, not like this is what the science says, but like this is literally what you should be doing according to science. So like he's really big and there's a lot of recommendations he does, which several of them I definitely don't do, like get sunlight um as soon as possible from waking up and like for prolonged periods of times. That's a really big one. And he's, there's a lot of science behind that one, there's a bunch of stuff, very [/INST] system, you're </s><s>[INST] gonna, you're gonna be like lex, this is, this is my new favorite person, I guarantee you [/INST] and </s><s>[INST] if you guys somehow don't know Andrew Huberman and you care about your well being. Um you know, you should definitely listen to him, I love you. Andrew Anyway, so uh what were we talking about alcohol and detecting alcohol. So this is a problem you care about trying to [/INST] solve and actually like broadening it. Um I do believe that the car is going to be a wellness center like because again, imagine if you have a variety of sensors inside the vehicle tracking, not just your emotional state or level of distraction and drowsiness and drowsiness, level of distraction, drowsiness and intoxication, but also maybe even things like, um, your physical, you know, your heart rate and your heart rate variability and your breathing rate. Um, and it can start like optimizing, yeah, can optimize the ride based on what your goals are. So I think we're going to start to see more of that and I'm excited about that. </s><s>[INST] Yeah. What are the, what are the challenges you're tackling well with smart? I currently, what's like the trickiest things to get? Is it, is it basically convincing? More and more car companies that having a i inside the car is a good idea or is there some, is there more technical algorithmic challenges? What's what's been keeping you mentally busy? I [/INST] think a lot of the car companies we are in conversations with are already interested in definitely driver monitoring. Like I think it's becoming a must have, but even interior sensing, I can see like we're engaged in a lot of like advanced engineering projects and proof of concepts. Um, I think technologically though, and even the technology, I can see a path to making it happen. I think it's the use case like how does the car respond once it knows something about you because you wanted to respond in a thoughtful way. That doesn't, that isn't off putting to the consumer in the car. So I think that's like the user experience. I don't think we've really nailed that and we usually, that's not part were the sensing platform, but we usually collaborate with the car manufactured to decide what the use cases. So, so, so you figure out that somebody's angry while driving, okay, what should the car, do you know, </s><s>[INST] Do you see yourself as a role of, of nudging of like basically coming up with solutions essentially that and then, and then the car manufacturers kind of put their own little spin on it, [/INST] right? Like we, we, we are like the ideation, creative thought partner, but at the end of the day, the car company needs to decide what's on brand for them, right? Like maybe when it figures out that you're distracted or drowsy, it shows you a coffee cup, right? Or maybe it takes more aggressive behaviors and basically said, okay, if you don't, like take a rest in the next five minutes, the car is gonna shut down right? Like there's a whole range of actions the car can take and doing the thing that is most yeah, that builds trust with the driver and the passengers. I think that's what we need to be very careful about. </s>

<s>[INST] to. You don't think it's a slippery slope from one to the other to, at first you're like, I'd like to work harder, but then you keep failing and the weather sucks and you keep failing, and the other person become more successful, plus, he's got a new hot wife now, there's a nice tractor, Does it fill this all working? And then you get this idea that, you know what, I'm going to steal all this stuff and got to murder him. And that do you know, they're just you think that's just like a leap of the same. [/INST] phenomena. Of the same phenomenon. No, because I think there are things that are in us as humans, right? So the things that just by being human like we can for example, feel, we can feel compassion, right? We can feel interest, right? We can feel jealousy in that benign sense like It's all part of just being human. If we start going from, hey, you have more crops than I have, and you know, it seems like I actually have a better life in a lot of ways than I have, I'm gonna kill you. That is not a progression of something benign, right? </s><s>[INST] That is- Wait a minute, but that is a human leap of the same thing, isn't it? Is it good, because you're drawing a line of stuff. You're saying like, this is human stuff, it's regular life, it's benign, but it feels like this benign thing is just a low magnitude thing version of the thing that's not benign. Like there's probably a gray area where it stops being, but like jealousy, you can have like healthy jealousy. You can have a little bit slightly unhealthy. There's a, I think, jealous guy, this John Lennon song that I love, it's just beautiful. I mean, there's like, this jealousy inside relationships can make you feel like, you know, could take your minds in all kinds of silly directions. And it's crazy, but like, it feels like that, that's an next door neighbor to like being really crazy and toxic and all that kind of stuff inside relationships. And then that feels like an ex-door neighbor. It's like an apartment building, that feels like an ex-door neighbor that eventually gets to Hitler with the envy and resentment [/INST] of entire population of people. You're right and that there's a causal, there can be a causal chain, right? Like if I'm not feeling jealous, maybe I won't ever feel envious, right? So as you can see, okay, so it can kind of lead to, it can open gates to huh, How much do I dislike that you have things that I don't have? Right? So yes, in that sense, but, and I think this is the part that I think is so important that I think there is a disjunction, right? There's an asymptotic shift, right? From one thing to another because it is- </s><s>[INST] Not just speaking my language, math in my language, mathematically. [/INST] Yeah. Symptotically, yep. Yes. That's, it's a way to convey, right, something that's entirely different because if I start thinking, you know, I'm not going to try and make things better, right? I'd like instead to harm you, that's qualitatively different. </s><s>[INST] Oh, it's almost like, you know what it is? It could be, I don't know what you think about this, but it's in which direction your motivation is pointing. So if in the response to the feeling of jealousy, your sort of, the motivation says, okay, I understand this feeling, I want to do less of it. I think there must be a threshold to which you actually want to do more of, like it becomes a vicious downward cycle. So that's what envy becomes. Like the first feeling, this idea that I'm going to kill the farmer turns into like more and more and more and you can't sleep and you're visualizing the farmer and he becomes the devil and like you have this very, you know, it's basically a thing that builds into the negative direction versus returns to the stable center. [/INST] Now a person is cultivating evil, right? They're saying, hey, there can be seeds of evil in all of us. Let me take that seed out, dust it off, plant it, nurture it, right? And then grow that seed of evil, which will affect all other parts of the person's life, right? They won't behave the same towards others in their life. They'll become different as they nurture fantasies of evil, as they begin to create inside of themselves the motivation and the will, right, to enact evil, right? The Hitler analogy would say, look, you take someone who had a bad childhood, right, who was not loved, who was taught and told that he was less than. Okay, like that, we know that happens. I mean, that's why child abuse is so evil, right? It's telling children the worst possible wrong lessons, right? They're not good enough. They'll always be hurt. You know, they can't keep themselves safe. They don't deserve safety, right? So then you take someone who then nurtures that seed of evil, which is a choice. And this is why I can't paint well enough and no one appreciates me and I don't like how I look and I don't fit in with the people I want to fit in with and then, and on and on and on and on and on. And there's a hatred of self through that lens of misery, of just being repulsed by the self. But that's unacceptable to the self. So, oh, it has to be someone else's fault, right? It's not my fault, whose fault is it, right? And then you see en masse the inaction of evil towards groups of people who somehow, in this person's mind, right, are responsible for his misery. And there's the justification of evil and then all the, you know, whether it's this will be better for the economy, this will be good, this will be that. Like that's all lies built to justify the evil. </s>

<s>[INST] and like the key point you're making, which I think is quite beautiful is like we shouldn't measure. If you talk about measurement, we should measure the skill. We should measure like the creation of the new skill, the ability [/INST] to create the annual </s><s>[INST] skill. Yes. But it's tempting like it's weird because the skill is a little bit of a small window into the, into the system. So whenever you have a lot of skills, it's tempting to measure the [/INST] skills. I mean, this kid is the only thing you can objectivity measure. Yeah. So the thing to keep in mind is that when you see skill in the human. Um it's gives you a strong signal that that human is intelligence, because, you know, they weren't born with that skill typically, like you see a very, you see a very strong chess player, maybe you're you're a very strong chess player yourself. </s><s>[INST] I think you're you're saying that because I'm Russian and now you're prejudiced. They assume. [/INST] Yeah, well your um so if you see a very strong chess player, you know, they weren't born knowing how to play chess. So they had to acquire that skill with their limited resources, with their limited lifetime. And, you know, they did that because they are generally intelligent. And so they may as well have required any other skill, you know, they have this potential. And on the other hand, if you see a computer playing chess, you cannot make the same assumptions because you cannot just assume the computers general intelligence, the computer may be born uh knowing how to play chess in the sense that it may have been programmed by a human that as understood chess for the computer. And that's just included um the output of that understanding in a city program. And that program is not intelligent. </s><s>[INST] So that let's well, just for a second and say, like, what is the goal of the on the measure of intelligence paper? Like, what do [/INST] you hope to achieve that? So the goal of the paper is to clear up some longstanding misunderstandings about the way we've been conceptualizing intelligence in the community. And uh in the way we've been evaluating progress in ai um there's been a lot of progress recently in machine learning and people are extrapolating from that progress that we're about to solve general intelligence. And if you want to be able to evaluate these statements, you need to precisely define what you're talking about when you're talking about general intelligence. And you need um a formal way, reliable way to measure how much intelligence, how much general Intelligence assistant processes. And ideally this measure of intelligence should be actionable. So it should not just describe what intelligence is. It should not just be a binary indicator that tells you this system is intelligent, It isn't um it should be actionable, it should have explanatory power. Right? So you could use it as a feedback signal. It would show you the way towards building more intelligent systems. </s><s>[INST] So at the first level you draw a distinction between two divergent views of intelligence. Of uh as we just talked about intelligence is a collection of tax task specific skills and a general learning ability. So what's the difference between kind of this memorization of skills and a general learning ability? We talked about it a little bit, but can you try to laying around this topic for a [/INST] bit? Yes. So the first part of the paper is an assessment of the different ways we've been thinking about intelligence in different ways we've been evaluating progress in the eye and the history of cognitive sciences has been shaped by two views of the human mind and one of you is the evolutionary psychology view in which the mind as a collection of anesthetic, special purpose, ad hoc mechanisms. It has been hard coded by evolution over our history as a species very, very long time. And um early ai researchers, people like Marvin Minsky for instance, they're clearly subscribed to the zoo and they saw they saw the mind as a kind of, you know, collection of static programs uh similar to the programs they would they would run on like mainframe computers. And in fact, they, I think they very much understood the mind through the metaphor of the mainframe computer because it was too all day they were working with. Right. And so you have the aesthetic programs, this collection of different static programs operating a database like memory. And in this picture, learning was not very important. Learning was considered to be just memorization. And in fact Uh learning is basically not featured in Ai textbooks until the 1980s with the rise of machine learning. </s><s>[INST] It's kind of fun to think about that learning was the outcast, like the weird people working learning like the mainstream AI world was. I mean, I don't know what the best term is, but it's not learning. It was seen as like reasoning. Yes. Would not be learning [/INST] based. Yes, it was seen. It was constituted the mind was a collection of programs that were uh, primarily logical in nature and that's all you needed to do to create a mind was to write down these programs and they would operate on their knowledge which will be stored in some kind of database and as long as your database with encompass, you know, everything about the world and theological rules where uh uh comprehensive then you would have in mind. So the other view of the mind is the brain uh as a sort of blank slate. Right. This is a very old idea. You find it in john locke's writings. This is the tabula rasa. Um and this is this idea that the mind is some kind of like information sponge uh that starts uh empty, that starts blank and that absorbs uh knowledge and skills from experience. Right? So it's a, it's a sponge that reflects the complexity of the world, the complexity of your life experience essentially. That everything you know and everything we can do is a reflection of something you found in the outside world essentially. So this is an idea that's very old That was not very popular for instance in the, in the 1970s, but that had gained a lot of vitality recently with the rise of connection is um in vascular de planning. And so today the planning is the dominant paradigm in the eye and I feel like lots of ai researchers are conceptualizing the mind. Uh yeah, deplaning metaphor, like they see the mind as a kind of uh randomly initialized neural network that starts blank when you're born and then that gets trained. Yeah, exposure to train data. That requires knowledge and skills, exposure to train data. </s>

<s>[INST] years. Do you think those mistake? Yes. What do you think that was the motivation behind saying that other companies are also promising L5 vehicles With their different approaches in 2020, 2021, 2022. [/INST] If anybody would like to bet me that those things do not pan out. I will, I will bet you even money even money. I'll bet you as much as you want. So </s><s>[INST] are you worried about what's going to happen because you're not in full agreement on that? What's going to happen when 2020-21 come around and nobody has fleets of autonomous vehicles? [/INST] Well, you can look at the history if you go back five years ago, they were all promised by 2018 and 2017 </s><s>[INST] but they weren't that strong of promises. I mean ford really declared pretty I think not many have declared as as like definitively as they have now these dates? [/INST] Well, okay, so let's separate L four and L five. Do I think that it's possible for Waymo to continue to uh Kind of like like hack on their system until it gets to level four in Chandler Arizona. Yes. </s><s>[INST] When there's no safety driver [/INST] Chandler Arizona </s><s>[INST] by what? By which year are we talking about. [/INST] Oh, I even think that's possible by like, 2020 2021 But level four Chandler Arizona not level five New York City </s><s>[INST] level for meaning some very defined streets. It works out really well, [/INST] very defined streets and then practically these streets are pretty empty if most of the streets are covered in way most Waymo can kind of change the definition of what driving is right? If your self driving network is the majority of cars in an area, they only need to be safe with respect to each other and all the humans will need to learn to adapt to them now go drive in downtown new york. Yeah that's already, you can talk about autonomy and like like on farms already works great because you can really just follow the GPS line. </s><s>[INST] Yeah. So what does uh success look like for comma ai what what are the milestones like where you can sit back with some champagne and say we did it boys and girls. [/INST] Um Well it's never over. </s><s>[INST] Yeah, but it was drink Champagne every show what is good. What are some winds? [/INST] Um A big milestone that we're hoping for uh by mid next year is profitability of the company. Um and we're going to have to revisit the idea of selling a consumer product but it's not going to be like the common one when we do it, it's going to be perfect. Open pilot has gotten so much better in the last two years we're gonna have a few few features, we're gonna have 100% driver monitoring. We're gonna disable no safety features in the car. Um actually I think the really cool what we're doing right now, our project this week is we're analyzing the data set and looking for all the http triggers from the manufacturer systems. We have better data set on that than the manufacturers. How how much does, how many does Toyota have 10 million miles of real world driving to know how many times they're a be triggered. </s><s>[INST] So let me give you because you asked right uh financial advice because I work with a lot of automakers and one possible source of money are you, which I'll be excited to see you take on is basically selling the data. So which is something that most people and not selling in a way we're here here automaker but creating, we've done this actually at M. I. T. Not for money purposes, but you can do it for significant money purposes and make the world a better place by creating a consortium to where automakers would pay in and then they get to have free access to the data. And I think a lot of people are really hungry for that and we pay a significant amount of money for it. Here's [/INST] the problem with that. I like this idea. All in theory would be very easy for me to give them access to my servers and we already have all open source tools to access this data. It's in a great format. We have a great pipeline, but they're gonna put me in the room with some business development guy and I'm going to have to talk to this guy and he's not going to know most of the words I'm saying. I'm not going to tolerate that. </s><s>[INST] Okay. Mick Jagger. No, no, no, no. I think I agree with you. I'm the same way. But you just tell them the terms and there's no discussion needed. If I [/INST] could, if I could just tell them the terms and then like all right, who wants access to my data, I will sell it to you for uh let's say you wanna, you wanna subscription. I'll sell you for 100 came up Any 100 k month, 100 a month. I'll give you access to the data subscription. Yeah, I think that's kind of fair came up with that number off the top of my head. If somebody sends me like a three line email where it's like we would like to pay 100 a month to get access to your data. We would agree to like reasonable privacy terms of of of of the people who are in the data set. I would be happy to do it. But that's not going to be the email. The email is gonna be, hey, do you have some time in the next month where we can sit down and we can, I don't have time for that. We're moving too fast. You </s>

<s>[INST] So whenever you have to invest that capital it's it doesn't it doesn't come back. Yeah that they can't be your main criticism of the way more approach. [/INST] Oh I'm saying even if it does technically work </s><s>[INST] even if it does technically work. That's a problem. I don't I don't know if I were to say I would I would say you're already there. I haven't even thought about that but I would say the bigger challenge is the technical approach the [/INST] way most </s><s>[INST] cruises and not just the technical approach but of creating value. I still don't understand how you beat Uber the human driven cars in terms of financially, it doesn't, it doesn't make sense to me that people want to want to get an autonomous vehicle. I don't understand how you make money in the long term, guess like real long term, but it just feels like there's too much capital investment needed [/INST] and they're going to be worse than Uber's because they're gonna, they're gonna stop for every little, you know, thing everywhere. Um, I see the nice thing about cruise, that was my nice thing about waiting for three years and it was a </s><s>[INST] nice because [/INST] three years technically ahead of everybody. Their tech stack is great. My nice thing about Cruz is GM buying them was a great move for GM For $1 billion. GM bought an insurance policy against Waymo, They put Cruz is three years behind Waymo, that means google will get a monopoly on the technology for at most three years </s><s>[INST] and technology works. You might not even be right about the three years, might be less, [/INST] might be less. Cruise actually might not be that far behind. I don't know how much Waymo has waffled around or how much of it actually is just that long tail. </s><s>[INST] Yeah, okay, if that's the best you could say in terms of nice things, that's more of a nice thing for GM that that's the smart insurance policy. [/INST] It's a smart insurance policy. I mean, I think that's how I, I can't see crews working out any other for crews to leapfrog Waymo would really surprise me. </s><s>[INST] Yeah. So let's talk about the underlying assumptions of everything is [/INST] we're not going to leapfrog Tesla. Tesla would have to seriously mess up for us because you're </s><s>[INST] okay. So the way you leapfrog right is, uh, you come up with an idea or you take a direction perhaps secretly that the other people aren't taking. And so cruise Waymo, even Arora [/INST] don't know Aurora's uses the same stack as well. They're all the same code base even and they're all the same dark urban challenge code base. </s><s>[INST] Uh, so the question is, do you think there's a room for brilliance and innovation that will change everything like say, okay, so I'll give you examples. It could be if revolution and mapping for example, that allow you to map things, do HD maps of the whole world. All weather conditions somehow really well or revolution in simulation to where the, what you said before becomes incorrect, that kind of thing in your room for breakthrough innovation. [/INST] Um, what I said before about, oh, they actually get the whole thing. Well, I'll say this about uh, we divide driving into three problems and I actually haven't solved the third yet, but I have an idea how to do it. So there's the static, the static driving problem is assuming you are the only car on the road, right? And this problem can be solved 100% with mapping and localization. This is why farms work the way they do. If all you have to deal with is the static problem and you can statically schedule your machines, right? It's the same as like statically scheduling processes. You can statically schedule your tractors to never hit each other on their paths because they, you know, the speed they go at. So, so that's the static driving problem. Maps only helps you with the static driving problem. </s><s>[INST] Yeah, the question about static driving, you just made it sound like it's really easy. Really easy. How easy how well because the whole drifting out of lane when when Tesla drift out of lane, it's failing on the fundamental static driving problem. [/INST] Tesla is drifting out of lane. The static driving problem is not easy for the world. The static driving problem is easy for one route. </s><s>[INST] one route in one weather condition with one state of lane markings in like no deterioration, no cracks in the [/INST] room. I'm assuming you have a perfect localizer. So that's solved for the weather condition and the lane marking </s><s>[INST] condition. That's the problem is how good you have to have a perfect, [/INST] you can build perfect localizer are not that hard to build. </s><s>[INST] Okay, come on now with, with lighter, [/INST] lighter with lighter. Okay. Yeah, but you use lighter, right? Use lighter build a perfect localizer building a perfect localizer without light are it's gonna be it's gonna be hard, you can get 10 centimeters about later. You can get one centimeter with lighter </s><s>[INST] May be concerned about the one or 10 cm. I'm concerned if every once in a while you're just way [/INST] off. Yeah. So this is why you have to carefully make sure you're always tracking your position. You want to use lighter camera fusion, but you can get the reliability of that system up to 100,000 miles and then you write some fallback condition where it's not that bad if you're way off, right? I think that you can get it to the point. It's like a cell d that you're you're never in a case where you're way off and you don't know it. </s><s>[INST] Okay, so this is brilliant. So that's the static, static we can, especially with light are and good. HD maps, you can solve that problem. You [/INST] just just it Easy, static, static. Very </s>

<s>[INST] I don't know, just linger a little bit, it does feel like from my study of Hitler that the time molded demand versus genghis khan where it feels like he, the man molded his time. [/INST] And I feel that way about a lot of those nomadic confederacy builders, that they really seem to be these figures that stand out as extraordinary for one in one way or another, remembering by the way that almost all the history of them were written by the enemies that they so mistreated, that they were probably never going to get any good press. They didn't write themselves. That's a </s><s>[INST] caveat. We should always have basically, [/INST] no matter where native american peoples or tribal peoples anywhere generally do not get the advantage of being able to write the history of their heroes. </s><s>[INST] Okay, I've uh have recently almost done with the rise in the fall of the third Reich, one of the historical descriptions of Hitler's rise to power. Nazis rise to power. There's there's a few philosophical things I'd like to uh, ask you to see if you can help, Like, one of the things I think about is uh, how does one Be a hero in 1930s, Nazi Germany, what does it mean to be a hero? What do heroic actions look like? I think about that, because I think about how I move about in this world today, you know, that we live in really chaotic, intense times where I don't think you want to draw any parallels between Nazi Germany and modern day in any of the nation's can think about, but it's not out of the realm of possibility that authoritarian governments take hold. Authoritarian companies take hold. And I'd like to think that I could be in my little small way and inspire others to take the heroic action before things get bad. And I kind of try to place myself in what would 1930s Germany look like. Is it possible to stop a Hitler? Is it even the right way to think about it? And how does one be a hero in it? I mean, you often talk about that, living through a moment in history is very different than looking at that history. Looking, you know, when you look back, I also think about it, would it be possible to understand what's happening that the bells of war are ringing? Uh, it seems that most people didn't seem to understand, you know, late into the 30s, that war is coming. That's fascinating on the United States side. Inside Germany, like the opposing figures, the german military didn't seem to understand this. Maybe, uh, the other country certainly France. And uh, England didn't seem to understand this, that kind of tried to put myself into nineties thirties, Germany as I'm jewish, which is another little twist on the whole, like, what would I do? What should one do? Do you have interesting answers? [/INST] So earlier, we had talked about Putin and we had talked about patriotism and love of country and those sorts of things in order to be a hero in Nazi Germany by our views here, you would have had to have been anti patriotic to the average Germans viewpoint in the 19 thirties, right? You would have to have opposed your own government and your own country. And that's a very it would be a very weird thing to go to people in Germany and say, listen, the only way you're going to be seen as, as, as a good german and a hero to the country that will be your enemies is we think you should oppose your own government. It's it's a strange position to put the people in a government and saying you need to be against your leader, you need to oppose your government's policies. You need to oppose your government. You need to hope and work for its downfall. That doesn't sound patriotic. It wouldn't sound patriotic here in this country. If you if you made a similar argument, um I will go away from the 1930s and go to the 1940s to answer your questions. So there's movements like the White Rose movement in Germany, which involved young people really, and and from various backgrounds, religious backgrounds, often who worked openly against the Nazi government at a time when power was already consolidated the gestapo was in full force and they execute people who are against the government and these young people would go out and distribute pamphlets and many of them got their heads cut off with guillotines for their trouble. And they knew that that was going to be the penalty. That is a remarkable amount of bravery and sacrifice and willingness to die. And almost not even willingness because they were so open about it. It's almost a certainty, right? Um that's incredibly moving to me. So when we talk and we talked earlier about sort of the human spirit and all that kind of thing. There are people in the german military who opposed and worked against Hitler for example. But to me that's almost cowardly compared to what these young people did in the White Rose movement, because those people in the in the Wehrmacht for example, who were secretly trying to undermine Hitler. They're they're they're not really putting their lives on the line to the same degree. Um and so I think when I look at heroes and listen, I remember once saying there were no conscientious objectors in Germany as a way to point out to people that you didn't have a choice, You know, you were going to serve in there. And I got letters from Jehovah's witnesses who said yes, there were, and we got sent to the concentration camps. Those are remarkably brave things. It's one thing to have your own set of standards and values. It's another thing to say, oh no, I'm going to display them in a way that with this regime, that's a death sentence and not just for me for my family, right in these regimes, there was not a lot of distinction made between father and son and wives. That's a remarkable sacrifice to make and far beyond what I think I would even be capable of. And so the admiration comes from Seeing people who appear to be more morally profound than you are yourself. Um, so when I look at this, I look at that that kind of thing. And I just say, Wow! And the funny thing is if you have gone to most average Germans on the street in 1942 and said, what do you think of these people? They're going to think of them as traitors who probably got what they deserved. So that's the eye of the beholder thing. It's the power of the state to um to so propagandized values and morality in a way that favors the state that you can turn people who today we look at is unbelievably brave and moral and crusading for righteousness and turn them into enemies of the people. Um, so I mean, in my mind, it would be people like that. </s>

<s>[INST] I mean, everything. Everything. I wonder what that trade-out discussions are like cause you can't really perfectly plan everything. So, and you always have to have some spare leeway, especially as you're testing new vehicles like Starship. Yeah, margins are important. Yeah, having a margin, giving all the uncertainty that's there. That's really interesting, like how they do those kinds of trade-offs, because they're also rapidly designing and redesigning and re-engineering. And ultimately, you want to give yourself the freedom to constantly innovate, but then through the process of testing, you solidify the thing that can be relied upon, especially if it's a crude mission. Yeah. [/INST] How to do that in a rapid cycle. Yeah, margins are important. Yeah. I remember at some point that NASA, as they're leading up to flying humans for the first time for NASA, you know, there's some talk that like, we're gonna do a design freeze, because SpaceX does evolve and iterate so quickly. You know, they were saying that it was leading, because especially at the time, it was a mission called AMOS 6, and they lost a rocket. They only lost two rockets, like ever really, as far as trying to get something to space, for the Falcon 9, sorry. And the second one, AMOS 6, I mean, that was back in 2016, so it's been a long time. And, but at the time, they're looking at flying humans in the near future. And it's like, if you guys keep tweaking this thing every time you take it out to the pad, well, there's gonna be a problem, you know? And so there is some pressure from NASA to kind of slow down on that iterative process. And, but that is also why they were able to evolve the Falcon 9 to be what it is today, is because they did just evolve it so quickly. Literally like one after another was never really the same. And we're definitely seeing that with Starship now, like it's evolved so quickly that you just can't even keep up with it, you know? </s><s>[INST] So there's a fascinating culture clash there. Have you just, in observing and interacting with NASA folks, seen them sort of grow and change and evolve themselves, sort of inspired by this new developments [/INST] in commercial space flight? Oh, yeah, yeah, yeah. There's a lot of, especially like around DM2, there's a lot of talks in the press conferences and stuff where you'd hear people say, you know, this was a big, this is well outside of our comfort zone to work with SpaceX in this manner, because we take this approach to things, we're X, Y, and Z in this way, the way we normally certify things. And we're not used to SpaceX, like, well, let's just try it, you know? Like, and do something, you know, to a point. And so they said it ended up being fantastic. They loved working that way because it was just less paperwork almost and more just do. And, but at the same time, SpaceX, I think, even expressed, I don't remember if it was Hans Königsmann or someone in a press conference said, well, we really liked having someone just double check us so that we're not doing something super stupid right before we test something, you know? So there was a cool collaboration because it is two very different philosophies of development and managing, you know, space programs. </s><s>[INST] I wanted to talk to you a lot about engines and maybe about Starship and maybe about your own becoming an actual astronaut. But like, let's just go there before all that and talk about the actual culture of SpaceX and your conversations with Elon. You've toured SpaceX facilities with him. You've interviewed him. You've interacted with him. What have you learned about rockets, about propulsion, about engineering, about design, about life from those interactions? He's pretty transparent, open human being [/INST] as an engineer, as a leader, as a person. I would definitely say the biggest takeaway I've had from my times with Elon at SpaceX is really, like, the idea of questioning your constraints. He says that a lot, but he also does it a lot. Like, there'll be times where, like, you'll see him change on a dime because he's, like, rethinking of something in a newer, different way. And for me, I think we all put constraints on ourselves. We think about our own limits on things that we can or cannot do. And I think it's made me kind of question, like, well, why am I, why did I say, no, I can't do that? Or, you know, just off the top of my head. A good example. Yeah, I, so in Iowa, I live in Iowa or half the time, or whatever, there's a bike ride across the state of Iowa called RAGBRIE. And every year, you just, you know, like thousands of people get together and they ride across to Iowa. And there was the last summer, I met up with some friends and like, hey, you don't wanna go on RAGBRIE this year. I'm like, it's like a week away. And so I did, you know? And it was one of those moments where I was proud of myself cause, like, it's easy to just be like, no, you know, I'm not ready this is my constraint, it's like I'm not in shape, but like just question that, you know? And so I think when it comes down to questioning your own constraints, it's yes, even to that level of like, why do you question yourself </s>

<s>[INST] I do ask myself of that like because I'm more in the tax base of constructing systems that prevent me from being corrupt because right now I'm all about love and all about those kinds of things, but I wonder you said like it just reveals the darkness. The problem is we might not be aware of our own darkness. I have the same feeling about money actually. I've been avoiding thinking about money. Like basically constructing my moral system, my moral compass around money, It's like the moment I feel a little too happy, but about the idea of owning some cool shiny thing. I started to think, okay, I'm not going to own that shiny thing because I'm afraid of the slippery slope of it. You ever think about that kind of stuff? Yeah, [/INST] the funny thing about our capitalist system is it's uh, it's um, it puts sort of profit motive above beauty. And you notice when you see certain cities, especially in the old days where like buildings used to be beautiful and uh now they're just like boxes, they throw a kid up and it's just for all profit margin. It's um, it's the illusion of permanence that, you know, it's like, oh, let me get as much money as they can be. Like, yeah, you know, my dad used to say, you know everyone, it's a cliche, but you can't take it with you. So it's kind of, it's comical to me that we're here trying to get this infinite amount like that where it's like Sisyphus we're all trying to climb this hill, but I mean the rock's gonna fall on us. So I think that's a healthy outlook. Yeah, my dad always used to say before he passed, you know, he would say, you can't, you have to survive, not only physically, but we have to survive emotionally. I think a lot of people forget about the emotional part of survival. You have to survive emotionally and humor and and and understanding reality in its objective context helps with that accepting reality as this ephemeral uh thing that urine is really just a part of, but not as significant as your ego wants you to believe is that is a start. That's a good foundation for surviving emotionally. </s><s>[INST] What's that mean? Surviving emotionally? Like [/INST] what's an ideal </s><s>[INST] life look like for you? You can't you [/INST] can't take things too seriously. You can't because they're ephemeral, they're not permanent. Nothing is permanent. Your bank accounts are permanent. Problems aren't permanent. Uh, nothing's permanent. Your abilities aren't permanent. Um Your memory is not permanent. You're you're you're getting hard is not permitted to curse on this or just go out there. You </s><s>[INST] can curse to your heart's content. Yeah. [/INST] Gender's not even permanent. More. I think I'm gonna I'm gonna change maybe and live my second half as another gender just to have on board with this gender. So it's like nothing is permanent. And so accepting that emotionally uh, is a good start to being more flexible. You gotta be flexible. Like my dad used to say anything to stiff snaps. You gotta, you know, it's a cliche. And people have said a bunch of different ways. But Bruce lee is right, man, be water be water. </s><s>[INST] Yeah. Makowski has this quote about love. That love is a fog that phase with the first light of reality. So he's a romantic, that guy. Uh but that even love is the thing that just doesn't last very long. Um you know, some people will disagree with that. Maybe morphs like like like water. It changes right? It might not be, might not be because he's mostly just loved like prostitutes I think. So it was kind of love, [/INST] no demand, no responsibilities. </s><s>[INST] Financial transaction. Yeah. Uh thermal has ever, you mentioned your dad, he passed away uh a year and a half ago. What did you learn from him? [/INST] I love my dad. My dad, I would say my dad was my, my hero. He was just, my dad really embodied those values and I think um for better or worse, it's made me who I am. He's he uh my dad was, was a painter, he was a lawyer. He was uh, he was, you know, a lieutenant in the military new yorker, new yorker born and bred Brooklyn. His dad, his dad, you know, surprise owned a diner. So that's, that's sort of the greek passport. That's the immigration passport for Greeks into America. And yeah, my dad played football. He just, my dad did what he wanted. He lived as he wanted at all costs and I think I got that from him for better or worse. I think it's hurt me in my pursuits. Uh, if you consider money and fame uh to be paramount. You know, I've always done what I wanted if I stopped wanting to do it, I just stopped doing it. I think I got that from my dad. So maybe for better or worse, that's what I learned from him. But that's a real currency. You know, feeling like you're in love with what you're doing when you're doing it. Maybe perhaps that's worth more than money. I don't know. You miss him. Yeah, every day. Every day. But I'm happy that uh He he got 91 years. It's very rare. I mean he smoked for 60 years. Talk about like a guy who was an outlier. He smoked like 60 years like packs. I mean, and he didn't die from that. He died. He had a prostate cancer, which is the way men should go. Your Dick should give out. It should start from the Dick. I mean we focus so much of our life on the Dick. That that's the way that's a successful life and that's why every man eventually gets prostate cancer because that is the universe's way is saying like the thing you focused on the most is you put the most energy into is the thing that's spent and it's going to your, your rotting is gonna start there. So that's a successful life and it just spread all over his body and he slowly died. I was with him when he died. And that meant a lot to me because me and my brother weren't talking at the time because we're Greeks. Uh we're talking again. But that's how it is. You've </s>

<s>[INST] That's so interesting. I mean [/INST] because their election is going to be pretty much at the same time </s><s>[INST] as the U. S. Election. [/INST] That will be before. I mean because at some time in that you know only part of with the presidential election. </s><s>[INST] Yeah. And also I don't know if you know about us elections but they actually last way longer than [/INST] we already </s><s>[INST] already starting. So there's going to be a significant overlap. [/INST] You think </s><s>[INST] that actually comes into play in their calculus? I [/INST] think it was one of the reasons why Putin invaded in february 2022 because it's gonna be two years and it would be over by March of 2022 he got two years to prepare for, you know the election and you got a big boost, you know, not only he got a boost from Crimea. I mean I didn't mention that before. I mean one of the reasons for invading Crimea and annexing or invading Ukraine the first time, annexing Crimea was look what happened to his ratings, they went from kind of declining and it was still pretty good, you know, by anybody's standards to just rocketing off into the stratosphere. I mean, I didn't really meet anybody in Russia who thought that Alex in Crimea was you know, kind of a bad thing. I mean even, you know, kind of people who were post putting on so many other things. Crimea was, you know, Cream Nash, they kept saying, you know, this is kind of, you know, we got it back, you know, should never have gone away, it was ours, you know, and but you know, this is more complex and he wasn't, I don't think at the time planning on fixing all of Ukraine when he went in this special multi operation, he was going to try to turn it into what Belarus has become part of a, you know, bring back the commonwealth of independent states of the Union, then a new union with Belarus and Ukraine and Russia over time, but certainly, you know, remove Ukraine as a major factor, independent factor on the world stage and you know, consolidate Crimea and maybe, you know, kind of incorporate Donetsk and Luhansk, you know, kind of that was that was also a possibility, but it wasn't it wasn't in his intention in any case to have something on this kind of scale, he wanted to get on with then preparing for what was gonna be, he would think the cakewalk the shoe in of the next presidential election, I mean, last time around he had to invent a bit of competition with his person who is reputed to be his god daughter, senior subject, you know, for a bit of, you know, kind of entertainment for people, you know, the next time around, you know, maybe he wasn't really planning on running, you know, against any other, you know, serious opposition, he was just gonna have the acclaim of, you know, the kind of the great leader like President xi in china, you know, Putin was basically, I think, you know, he also hoped that he would be able to devolve some authority away, you know, kind of, so he's more like the, you know, the supreme leader kind of figure the czar like figure the monarch and then, you know, other people get on with the chief executive, prime ministerial running the country and he could kind of like step back and just enjoy this. You know, maybe there was gonna be again, a new union of Belarus Russia and um in Ukraine and some, you know, fashion and he would preside over that. So </s><s>[INST] speaking of opposition, you've criticized the famed Putin critic alexei Navalny, what's the nature of your criticism? [/INST] Well, it hasn't really been a kind of a criticism in the way that, you know, people have implied, but more just reminding people that Navalny isn't some stooge of the west as other people have, you know, kind of depicted him in the in the Russian firm, but, you know, saying that this is kind of, you know, his pro Western, he's he's a Russian nationalist and a Russian patriot, you know, in the past, he's articulated, you know, things are not so dissimilar from some of the people around Putin, and it's more just reminding people that, you know, just because you kind of see somebody, you know, is kind of in an opposition figure or somebody who might be more palatable from your perspective, looking from the West, they're not always going to be, you know, what you think they are Aleksei Navalny is a Russian, and, you know, in a particular Russian context is different from Putin, but he wouldn't necessarily, you know, kind of run, you know, the Russian system in ways that we would like. So that's kind of it's kind of a criticism, it's more of a critique of the way that we look at things, you know, I think it's a mistake to always, you know, so this is pro Western or this is a, you know, liberal. I mean, what the heck does that mean? Pro Western? I mean, he's a Russian is a Russian nationalist and the Russian patriot, and he's often, you know, been, you know, quite critical about immigration. Um, he's had some negative views about, you know, at one point, He said, don't feed the caucuses, you know, kind of played upon some of the, you know, the racial and ethnic tensions inside of, you know, Russia itself as well. Now he is a pluralist and, and he's, kind of, and he wants to have, you know, different, uh, set of political actors there, but he also isn't promoting revolution. He's not Lennon, he's not want to bring down the state, he wants to kind of, you know, change the people who are in charge. That's what he's being basically focused on. And, you know, he might have and have things to do things that, you know, we elsewhere might not like. </s>

<s>[INST] He runs at a million times the speed and therefore can solve tougher problems, quite a lot tougher. It's very hard to have an intuition about what that looks like. Especially like you said, the intuition I kind of think about is it maintains the humanness. I think it's hard to separate my hope from my objective intuition about what super intelligence [/INST] systems look like. If one studies evolutionary biology with a bit of math, and in particular books from when the field was just properly coalescing and knowing itself, not the modern textbooks were just memorized this legible math so you can do well on these tests, but what people were writing as the basic paradigms of the field were being fought out. In particular, a nice book, if you've got the time to read it, is Adaptation and Natural Selection, which is one of the founding books. You can find people being optimistic about what the utterly alien optimization process of natural selection will produce in the way of how it optimizes its objectives. You got people arguing that in the early days, biologists said, well, organisms will restore and restrain their own reproduction when resources are scarce so as not to overfeed the system. This is not how natural selection works. It's about whose genes are relatively more prevalent in the next generation. If you restrain reproduction, those genes get less frequent in the next generation compared to your conspecifics, and natural selection doesn't do that. In fact, predators overrun prey populations all the time and have crashes. That's just like anything that happens. Many years later, the people said, well, but group selection. What about groups of organisms? Basically the math of group selection almost never works out in practice is the answer there, but also years later, somebody actually ran the experiment where they took populations of insects and selected the whole population to have lower sizes. You just take pop 1, pop 2, pop 3, pop 4, look at which has the lowest total number of them in the next generation, and select that one. What do you suppose happens when you select populations of insects like that? Well, what happens is not that the individuals in the population evolved to restrain their breeding, but that they evolved to kill the offspring of other organisms, especially the girls. People imagined this lovely, beautiful, harmonious output of natural selection, which is these populations restraining their own breeding so that groups of them would stay in harmony with the resources available. And mostly the math never works out for that, but if you actually apply the weird, strange conditions to get group selection that beats individual selection, what you get is female infanticide, like if you're reading on restrained populations. And so that's the sort of... So this is not a smart optimization process. Natural selection is so incredibly stupid and simple that we can actually quantify how stupid it is if you read the textbooks with the math. Nonetheless, this is the sort of basic thing of, you look at this alien optimization process and there's the thing that you hope it will produce, and you have to learn to clear that out of your mind and just think about the underlying dynamics and where it finds the maximum from its standpoint that it's looking for, rather than how it finds that thing that leapt into your mind as the beautiful aesthetic solution that you hope it finds. And this is something that has been fought out historically as the field of biology was coming to terms with evolutionary biology, and you can look at them fighting it out as they get to terms with this very alien in-human optimization process. And indeed, something smarter than us would also be much like smarter than natural selection, so it doesn't just automatically carry over. But there's a lesson there. </s><s>[INST] There's a warning. If a de-natural selection is a deeply suboptimal process that could be significantly improved [/INST] on, it would be by an AGI system. Well, it's kind of stupid. It has to run hundreds of generations to notice that something is working. It doesn't be like, oh, well, I tried this in one organism, I saw it worked, now I'm going to duplicate that feature onto everything immediately. It has to run for hundreds of generations for a new mutation to rise to fixation. </s><s>[INST] I wonder if there's a case to be made in natural selection. [/INST] As inefficient as it looks is actually quite powerful, that this is extremely robust. It runs for a long time and eventually manages to optimize things. It's weaker than gradient descent because gradient descent also uses information about </s><s>[INST] the derivative. Yeah. [/INST] Evolution seems to be, there's not really an objective function. There's inclusive genetic fitness is the implicit loss function of evolution which cannot change. The loss function doesn't change the environment changes and therefore what gets optimized for in the organism changes. There's GPT-3, there's like, you can imagine different versions of GPT-3 where they're all trying to predict the next word, but they're being run on different data sets of text. That's like natural selection, always includes their genetic fitness but like different environmental </s><s>[INST] problems. It's difficult to think about. If we're saying that natural selection is stupid, if we're saying that humans are stupid, [/INST] it's hard. It's hard. Smarter than natural selection. </s><s>[INST] Smarter. Smarter than the upper bound. [/INST] by the way. That's another hopeful place. That's another hopeful place. I mean, if you put enough matter energy compute into one place, it would collapse into a black hole. There's only so much computation can do before you run out of nagentropy and the universe dies. So, there's an upper bound, but it's very very very far up above here. Like the supernova is only finitely hot. It's not infinitely hot, but it's really really really, really hot, </s>

<s>[INST] That's okay. [/INST] That's okay. </s><s>[INST] It really is one of my favorite sponsors. It's the first thing I drink every day or rather it's the thing I drink before I break the fast. I guess it counts as the thing you break the fast with fast. It makes me feel good eating low carb makes me feel good and you have to be careful with that stuff to make sure you get the nutrition that you need and that's what I rely on athletic greens to do to make sure I have that like nutritional base for all the wild things I do in terms of work, in terms of food in terms of exercise, all that kind of stuff. Anyway, they'll give you one month supply of fish oil. Another thing I love when you sign up to athletic greens dot com slash lex, that's athletic greens dot com slash lex. This is the lux Friedman podcast and here's my conversation with Ariel at bla, when did you first fall in love with space exploration and space in general? [/INST] My parents are both ex Air Force, so my dad's an 8 10 fighter pilot and my mom trained and had qualified to be a fighter pilot. But it was early enough that when we're not letting combat at that time. And so I grew up with these two pilots and although they themselves did not become astronauts, there's a really rich legacy of Air Force pilots becoming astronauts. And this loomed large in my childhood. What does it mean to be courageous to be an explorer, to be at the vanguard of something hard and challenging and to couple with that My dad was a huge fan of science fiction and so I was a kid read Heinlein and Isaac Asimov, um all these different classics of science fiction that he had introduced me to and that just started a love affair with space exploration and really thinking about civilization, scale space exploration. </s><s>[INST] So did they themselves dream about going to the stars as opposed to flying here in earth's atmosphere, just looking up? [/INST] Yeah, my dad always said he was absolutely convinced because he was a child of the Apollo years that he would get to go in his lifetime, really thought it was going to happen. And so it was a challenge. And you know, sad for many people when um to their view on the outside space exploration slowed down for a period of time. In reality, we were just catching up, I think we left so far ahead with Apollo more than the rest of society was ready for. And now we're coming back to this moment for space exploration where we actually have an economy and we have the other Jamal that society needs to be able to make space exploration more real. And my dad's thrilled because finally, you know, not nearly, I hope not anywhere near the end of his life, but as he's an older man, he now can see still within his lifetime, people really getting a chance to build a sustainable lunar settlement on the moon or maybe even go to mars </s><s>[INST] so settlement civilizations and other planets. That's the that's the cool thing to dream about in the future. What was the what was the favorite sci fi authors when you're growing up? [/INST] Probably Isaac Asimov's Foundation trilogy, this is an amazing story of Harry Seldon this, you know, foundation that he forms at different ends of the Well, according to the story differences, the universe and has this interesting focus on society. So it's not just space exploration, for the sake of space exploration or novel technology, which is a lot of what I work on data, data mighty. But how do you structure a society um across those vast expanses of distance and time? And so I'd say absolutely favorite now though, my favorite is NEal Stephenson and Seven Eves. It's a book that inspired my own PhD research and some ongoing work that we're doing with Nasa now for the future of swarm robotics for spacecraft. </s><s>[INST] We're saying offline about, you know, Stevenson and because I just recently had a conversation with him and I said that, you know, not until I was doing the research for him that I realized he also had a role to play in Blue Origin. So it's like sci fi actually having a role to play in the design engineering. Just the implementation of ideas that come kind of um percolate up from the sci fi world and actually become reality. It's kind of fascinating figure in that way. So, do you do you also think about him beyond just his work in science fiction, but his role in coming up with wild crazy ideas that actually become reality. [/INST] Yes, I think it's a great example of this cycle between authors and scientists and engineers that we can be inspired in one generation by what authors dream up. We build it, we make it a reality and then that inspires another generation of really wild and crazy thought for science fiction. I think NEal Stephenson does a beautiful job of being what we would call a hard science fiction author. So it's really grounded in a lot of science which makes it very compelling for me as a scientist and engineer to read and then be challenged to make that vision of reality the other community, you know that Neil is involved with and some of my other mentors are involved with that. We are thinking about more and more in the work that we do at M. I. T. Is the Long Now Foundation. And this focus on what does society need to take in terms of steps at this juncture this particular inflection point in human history to make sure that we're setting ourselves up for a long and prosperous horizon for humanity's horizons. There's a lot of examples of what the Long Now Foundation doesn't think about, but when I think about this in my own work, it's what does it take to scale humanity's presence in orbit. We are seeing some additional investment in commercial space habitats. Um so it'll no longer be just Nasa running the international space station but to really democratize access to space to have um like Bezos wants to have millions of people living and working in space. You need architecture that's bigger and grander and can actually scale. That means you need to be thinking about how can you construct things for long time horizons that are really sustainable in orbit or on a surface of a celestial body that are bigger than the biggest rocket payload fairing that we currently have available. And that's what led me to self assembly and other models of in space construction. </s><s>[INST] Okay. Every every time you speak, I get like a million tangent ideas. [/INST] But no, </s><s>[INST] no, no, no, no, no. Please keep talking. This is amazing. I just there's a there's like a million of ideas. So one sort of on the dark side. Let me ask, do you think about the threats to human civilization that kind of motivate the scaling of the expansion of humans in space and on other planets? What are you worried about nuclear war pandemics? Ah, super intelligent artificial intelligence systems, you know, more not uh existential crisis, but ones that have significant, potentially significant detrimental effects on society like climate change, those kinds of things. And then there's of course the fun asteroid coming out from the darkness and hitting on earth. There's been a few movies on that anyway. Is there something that you think about um that threatens us in this century? Mm hmm. [/INST] I mean as an ex military family, we used to talk about all of this, we would say that luck favors the prepared and so growing up, you know, we had a plan actually a family plan for what we would do in a pandemic. Didn't think we're gonna have to put that plan into place and here we are. We do certainly, you know, among my own family and my friends and then our work at M. I. T. We do think about existential threats and risks to humanity and what role does space exploration in getting humans off world have to play in a resilient future for humanity. But what I actually find more compelling recently is instead of thinking about the need to ever abandon earth through a path of space exploration of space foraging is to see how we can use space technology to keep earth livable. The obvious direct ways of doing this would be, you know, satellite technology that's helping us learn more about climate change or um emitters or C. 02. But there's also a future for geoengineering that might be space based. A lot of questions that would have to be answered around that. But these are examples of pivoting our focus away from maybe the Hollywood vision of oh and Astrid's gonna come. We're gonna have to escape earth to let's use our considerable technology prowess and use space technology to save Earth and be very much focused on how we can have a worthwhile life for earth citizens. Even if some of us go want to go out and for their venturing, </s><s>[INST] right? Just the desire to explore the mysterious. Yes. But also it does seem that by placing us in harsh conditions, the harsh conditions of space, the harsh conditions of planets on the biology of the chemistry of the engineering, the robotics, the materials, all of that. That's just a nice way to come up with cool new things. [/INST] Yeah, </s><s>[INST] it's a force. Exactly, it's a forcing function like survival. You don't get this right, you die. So and that you can bring back to earth and it will improve um like figuring out food and space will make you figure out what how to eat. You know, live healthier lives here on earth. [/INST] So true. I mean some of the technologies that were directly looking at right now um for space habitats, it's hard to keep humans alive in this really fragile little pocket against the vacuum and all of the dangers that the space environment presents. Some of the technologies we were going to have to figure out is energy efficient, you know, cooling and air conditioning, air filtration, scrubbing C. 02 from the air. Being able to have habitats that are themselves resilient to extremes of space, weather and radiation. And some of these are direct translational opportunities for areas from by natural disasters. You know, people in California a decade ago would never have had to think about having an airtight house. But now with wildfires, maybe you do want something close to an airtight house. How do you manage that? There's a lot of technologies from the space habitation world that we are hoping we can actually bring back down to benefit life on Earth as well in these extreme environment contexts. </s><s>[INST] Okay, so you mentioned to go back to swarm. So that was interesting to you, first of all, in your own work, but also I believe you said something that was inspiring from neal Stephenson as well. So when you say uh swarm, are you thinking about um architectures? Are you thinking about artificial intelligence? Like robotics or those kind of intermixed? I [/INST] think the future that we're seeing is that they're going to be intermixed, which is really exciting. So the future space habitats are one of intelligent structures. Maybe not all the way to how and the, you know, 2001 space odyssey reference that scares people about the habitat having a mind of its own. But certainly we're building systems now where the habitat has sensing technology that allows it to communicate. It's basic functions, you know, maintaining life support for the astronauts, but could also communicate in symbiosis with these swarm robots that would be on the outside of the spacecraft, whether it's in a microgravity orbiting environment or on the surface. And these little robots, they crawl just Allah Neal Stephenson and 70s, they crawl along the outside of the spacecraft looking for micrometeorite puncture or gas leaks or other faults and defects. And right now we're just working on the diagnosis. So can the swarm with its collective intelligence act in symbiosis with the spacecraft and detect things, but in the future, we also love for these little micro robots to repair in situ and really be like ants living in a tree all together connected to the spacecraft. </s><s>[INST] Do you envision the system to be fully distributed and just like an ant colony for one of them is damaged or, you know, whatever loses control and all those kinds of things that that that doesn't affect the performance of the complete system or doesn't need to be centralized? This is more like almost like a technical question. Do you think? Right from the ground up, it's so scary to go fully distributed, [/INST] but </s><s>[INST] it's also exceptionally powerful, right? A robust resilient to the harsh conditions of space? Where do you, um if you look into the next 10, 20 100 years, um, starting from scratch, you think we should be doing architecture wise, distributed systems [/INST] for space? Yes. Because it gives you this redundancy and safety profile, it's really critical. So whether it's small swarm robots, where doesn't matter if you lose a few of them to habitats that instead of having a central monolithic habitat, you might actually be able to have a decentralized note of a space station, uh, so that you can kind of right out of Star Wars, you can shut a blast door if there's a fire or if there's a conflict in a certain area and you can move the humans and the crew into another decentralized note of the spacecraft, There's another idea out of Neal Stephenson's 70s actually where these are chocolates which were decentralized spacecraft that could form and doc little temporary space stations with each other and then separate and go off on their way and and have a decentralized approach to living in space. </s><s>[INST] So the self assembly component of that too. So this is your PhD work and beyond. You explored autonomously self assembling space architecture for future space tourists, habitats and space stations in orbit around earth, moon and mars there, there's a few things I personally find uh sexier than self assembling space are autonomously self assembling space architecture in general doesn't even need to be space. The idea of like self assembling architectures. It's really interesting like building a bridge or something like that. There's self assembling materials. It feels like incredibly efficient way to do it because optimization is built in so you can build like the most optimal structures given dynamic, uncertain changing conditions. So maybe, can you talk about your PhD work about this, This work about Tessa Rae. What is it in general? All the any any cool stuff because this is super cool. [/INST] So test raise my PhD research. It's this idea that we could take tiles that construct a large structure, like a buckyball. Yeah, this is exactly what we're looking at here, which is the tiles that are packed flat in a rocket. They're released to float in microgravity magnets, pretty powerful electro permanent magnets on their edges, draw them together for autonomous docking so there's no human in the loop here and there's no central agent coordinating saying tile one go to tile to, it's completely decentralized system. They find each other on their own. What we don't show in this video is what happens if there's an error, Right? So what happens if they bond incorrectly? The tiles have sensing? So proximity sensing magnetometer, other sensors that allow them to detect a good bond versus a bad bond and pulse off and self correct which anybody who works in this, you know, the field of self assembly will tell you that error detection and correction just like error detection in a. D. N. A sequence or protein folding is really important part of the system for that robustness. And so we've done a lot of work to engineer that ability for the tiles to be self determining. They know whether they're forming the structure that they're supposed to form or not. </s><s>[INST] They know if they're in a toxic relationship but they need to get out [/INST] right, right. If they need it, they need to separate. Exactly. Yeah. </s><s>[INST] Alright, this is like so amazing. And for people who just listening to this. Yeah, there's I mean, how large are these tiles? [/INST] So the size that we use in the lab, they can really be any size because we can scale them down to do testing in microgravity. So we sent tiles that were about three inches wide to the international space station a couple of years ago to test the code, test the state machine, test the algorithm of self assembly. But now we're actually building our first ever human scale tiles. They're me human size, a little, you know, a little smaller than maybe your average human. Um but there are 2.5 ft on edge length. The larger scale that we would love to build in the future would actually be tiles that are big enough to from a buckyball big open, spherical volume, spherical approximation volume would be about 10 m in diameters of 30 ft, which is much bigger and grander in terms of open space than any current module on the iss. And one of the goals of this project was to say, what's the purpose of next generation space architecture? Should it be something that really inspires and delights people when you float into that space? Can you get goose bumps in the way that you do when you walk into a really stunning piece of architecture on earth? And so we think that self assembly, this modular reconfigurable algorithm for constructing space structures in orbit is going to give us this promise of space architecture that's actually worth living in </s><s>[INST] living in. Oh, I thought you also meant from like outside artistic perspective, you see the whole thing is just [/INST] with the aesthetics of it. Absolutely. </s><s>[INST] You know, when you like go like into Vegas whenever you go into a city and it's like over the hill appears in front of you? And I mean there's something majestic about uh seeing like, wow humans created that. It gives you like hope about like these, a bunch of ants were able to figure out how to build sky skyscrapers that light up and in general the design of these towels in the way you envision it are pretty scalable. [/INST] Yes. And they're inspired by exactly what you mentioned a moment ago, which is we have these patterns of self assembly on earth and there's a lot of fantastic M. I. T. Research that we're building this concept on. So like Daniela, Russo, etc. Sale and pebbles taking the power of magnets to create units that are themselves interchangeable. This notion of programmable matter. And so we're interested in going really big with it to build big scale space structures with programmable tiles. But there's also a really fascinating, you know, end of that on the other side of the spectrum, which is how small can you go with matter that's programmable and stacks and builds itself and creates a bridge or something in the future. </s><s>[INST] What do you envision the thing would look like? Like when you imagine a thing far into the future where there's um so we're not even thinking about like a small space, let's not call them small but are currently sized space stations, but like something gigantic. What do you envision? Is this something with symmetry or is this something we can't even come up with yet. Is they're beautiful structures that you imagine in your mind. [/INST] I've got three candidates that I would love to build if we're talking about monumental space architecture. One is, what is the space cathedral look like? It can be a secular cathedral doesn't necessarily have to be about religion but that notion of long sightlines, inspiring stunning architecture. When you go in and you can imagine floating instead of you know, being on the ground and only looking up in space, you could be in a central node and each direction you look at all the cardinal directions are spires going off in a really large and long way. So that's concept number one. Number two would be something more organic. That's not just geometric. So here one of the ideas that we're working on an M. I. T. In my lab is to say could you, instead of the Tesseract model right, Which is self assembling a shell. Could you define a module? That's a note, a small note that someone can live in and you self assemble a lot of those together. They're called please. Oh Hadrian's like space filling solids and you doc a bunch of them together and you can create a really organic structure out of that. So this is the same way that muscles accrete to appear. You can have these nodes that docked together and one shape that I would love to form out of this is something like a nautilus, a seashell that beautiful. You know, fibonacci spiral sequence that you get in that shape. Which I think would be a stunning and fabulous um aggregated space station. </s><s>[INST] You said so many cool words. Please please theo Hedren. [/INST] Yeah. So that </s><s>[INST] that's uh space filling [/INST] solid. The simplest thing to think about </s><s>[INST] like a cube [/INST] cube. Right? So you can stack cubes together And if you had an infinite number of cubes you fill all that space. There's no gaps in between the cubes they stack and fill space. Another pleasure, Hedren is a truncated octahedron and that's actually one of the candidates structures that we think would be great for space stations. </s><s>[INST] What's the truncated part? [/INST] Ah So if you cut off an octahedron actually has a little pointy areas, you truncate certain sections of it and you get some surfaces that are on the structure that are cubes and I think hexagons. I have to remind myself exactly what the faces are. But overall a truncated octahedron can be bonded to other truncated octahedron and just like a cube. It fills all the gaps as you build it out. So you can imagine too truncated octahedron as they come together at an airlock which is what we space people called doors in space and you dock them on all sides. And you've basically created this decentralized network of space nodes that make a big space station and once you have enough of them and you're growing with enough big units, you can do it in any macro shape you want. That's where the nautilus comes in. This could be designed and organically inspired shape for space station. Can </s><s>[INST] I just say how awesome it is to hear you say we space people. I know you meant people, they're doing research on space exploration, space technology. But it also made me think of the future. There's Earth people. Mm hmm. And there's those space people and then there's the market, [/INST] you </s><s>[INST] know know for sure for sure. But like it's like new Yorkers and like Texans or something like that. Yeah, of course. You you live for a time in new york and then you go up to boston and but for a time you're the space people, I know those space people, they're they're kind of wild up there. Exactly. There's that culture, culture forms and I would love to see what kind of culture. Once you once you have sort of more and more civilians. I mean there's a human I mean I love psychology and sociology and and I'll maybe ask you about that too, which is like the dynamic between humans. You have to kind of start considering that you start spending more and more time up in space and and start sending civilians start sending bigger and bigger groups of people and then of course the beautiful and the ugly emerges from the from the human nature that we haven't been able to escape up to this point. But when you say the Pleaser Hadrian's these kinds of shapes, are they multifunctional? Like he is the idea you'd be able to humans cannot occupy them safely and some of them and some others have some other purposes. [/INST] Exactly, one could be sleeping quarters, one could be a greenhouse or an agricultural unit, one could be a storage depot, essentially all of the different rooms or functions that you might need. A space station could be subdivided into these nodes and then stacked together and one of the promises of both Tessa Rae, my original PhD research which is these shells and then this follow on node concept is that right now we build space stations and once they're built they're done, you can't really change them profoundly. But the benefit of a modular self assembling system is you can disassemble it, you can completely reconfigure it as your mission changes or the number of people in space that you want to host. If you have a space conference happening like south by southwest, then maybe all of a sudden you want to change out what we're window tiles yesterday Coppola tiles and make them into a berthing ports so that you can welcome five new spaceships to come and join you in space. That's what this promise of reconfigurable space architecture might allow us to explore. </s><s>[INST] I've been hanging out with grimes recently. I just feel like she belongs up in space. This is like designed for for artists essentially. I imagine. I mean this is what South by keeps introducing me to is there's like the weird and the beautiful people and like the artists and it feels like there's a lot of opportunities for art and design. [/INST] It's </s><s>[INST] like space is a combination of arts design and and great engineering with with [/INST] uh </s><s>[INST] it's a safety critical with like the highest of stakes. So don't you can't you can't mess it up. And is this is their first of all you're talking about tiling. So Neil stephens is obsessed about. I don't know if it's related to any of this but he seems to be obsessed with like how do you tell a space that's like a mathematical geometric [/INST] notion like the </s><s>[INST] test elation. And it's I mean it's a beautiful idea for architecture that you can self assemble these different shapes and you can have probably some centralized guidance of the kind of thing you want to build. But they also kind of figure stuff out themselves in terms of the low level details in terms of the figuring out when the when if everything fits just right for the O. C. D. People like what's that subreddit? Uh Pleasantly. It's like really fun. Everything they have like videos of everything is just pleasant when everything just fits perfectly. Very [/INST] pleasing. All the tolerances come together so </s><s>[INST] they figured that out on themselves and and the local robotics problem. But by the way was Daniel, those pebbles, What's the pebbles project? [/INST] The pebbles project our little cubes that have E PMS and them electro permanent magnets and they can self disassemble so they will turn off and so you'll have this little structure that all of a sudden can flip the little pebbles over and essentially just disaggregate </s><s>[INST] they have to make some pleasing sounds what what that's gonna, I'm supposed to talk to Danielle so I'll probably spend an hour just discussing the sounds on the pebbles. Okay, uh, what were we talking about? So the, so that's because you mentioned too, I think. [/INST] Right. My 3rd 1. </s><s>[INST] Yeah. Is there a 3rd 1? [/INST] My third one is a Ring World. Just because every science fiction book ever that's worth anything has a ring world in it and just </s><s>[INST] get a donut [/INST] donut. Yeah, so a really big Taurus that could encircle the planet or encircle another celestial body, maybe an asteroid or a small moon. And um, the promise here is just the, the beauty of being able to have that geometry in orbit and all that surface area for solar panels and talking. And um, essentially just all of what that enables to have a ring world at that scale in orbit </s><s>[INST] by the way, for the viewers, we're looking at figure alone and what paper is this from this hexagonal tiling of a tourist generated in Mathematica referencing code an approach from two citations. So we're looking at a tiled donut and I'm not hungry. So this is the, is this, is this from your thesis or not? [/INST] This is probably, I mean this is in my thesis. This looks like it was one of my earlier papers. This was an approach to say great. We've come up with this test elation approach for a buckyball and we picked the buckyball because it is the most efficient surface area to volume shape and what's expensive in space, the surface area shipping up all that material. So we wanted something that would maximize the volume. But if we think about ring worlds and other shapes, we wanted to look at how do you tile a Taurus? And this is one example with hexagons to be able to say, could we take the same test array approach of self assembling tiles and create other geometries? </s><s>[INST] So freaking cool. That's awesome. So you mentioned microgravity and I saw, I believe that there's a picture of you floating in microgravity. When when did you get to experience that? What was that like? [/INST] So I've flown nine times on the affectionately known as the vomit comet. It's the parabolic flight And essentially it does what you want to play never to do. It pitches really steeply upwards at 45 </s><s>[INST] degrees. [/INST] Yeah, that's test. Right. That's super early in my PhD some of just the passive tiles before we even put electronics. And we were just testing the magnet polarity and the essentially is it an energy favorable structure to self assemble on its own? So we tweaked a lot of things between. </s><s>[INST] Are we looking at a couple of them? [/INST] Yeah. You're looking at a bunch of them. There's </s><s>[INST] almost 30 [/INST] two of them. </s><s>[INST] Yeah, they're clumping [/INST] clumping. Can </s><s>[INST] you comment on what's the difference, jean microgravity and and zero gravity? [/INST] Yes. So there is, it's important difference. There is no zero gravity, there's no nothing, there's in the universe. There is no such thing as zero gravity. So Newton's the law of gravity tells us that there's always gravity attraction between any two objects. So zero G. Is a shorthand that some of us fall into using. It is a little easier to communicate to the public. The accurate term is microgravity. Where you are essentially floating. You're weightless but generally in free fall. So on the parabolic flights, the vomit comet, you're in free fall at the end of the parabola and in orbit around the Earth when you're floating, you're also in free fall. </s><s>[INST] What [/INST] was it like? Uh </s><s>[INST] so affectionately call vomit comment. I'm sure there's a reason why it's called affectionately. So so what's it like? What's uh your first time to both philosophically spiritually and biologically. What's it like? [/INST] It's profound. It is unlike anything else you will experience on earth because it is this true feeling of weightlessness. With no drag. So the closest experience you can think of would be floating in a pool, but you move slowly when you float in a pool and your motion is restricted when you're floating. It's just you and your body flying like in a dream. Um It takes the littlest amount of energy, like a finger tap against the wall of the plane to shoot all the way across the fuselage </s><s>[INST] and you can move at full speed, you can move your arms exactly your muscles. [/INST] There's no yeah, </s><s>[INST] there's no resistance. And they [/INST] actually tell you to make a memory when you're on the plane because it's such a fleeting experience for your body that even a few days later you've already forgotten exactly what it felt like. It's so foreign to the human experience. </s><s>[INST] They kind of suggested you explicitly tried to really form this into a memory that you could do the replay training save when we have neural link, we can replay that that that memory. So in terms of how much stress it has on your body, is it biologically stressful? [/INST] You do feel A to G pullout? Right? So the cost of getting those micro g parabolas is you then have a to G pullout and that's hard, you have to train for it if you move your neck too quickly on that to g pull out, you can strain muscles. But I wouldn't say that it's actually a a profound um tough thing on the body, it's really just an incredibly novel experience and when you're in orbit and you're not having to go through the ups and downs of the parabolic plane, there's a real grace and elegance and you see the astronauts learn to operate in this completely new environment. </s><s>[INST] What are some interesting differences between the parabolic plane and when you're actually going up in orbit? Is it that with orbit you can look out and see that blue little planet of ours, [/INST] you can see the blue marble, the stunning overview effect, which is something I hope to see one day. Um What's also really different is if you're in orbit for any significant period of time, it's gonna be a lot more physiological changes to your body than if you just did an afternoon flight on the vomit, comet, everything from your bones, your muscles, your eyeballs change shape. Uh There's a lot of different things that happened for long duration spaceflight. And we still have to, as scientists, we still have to solve a lot of these interesting challenges to be able to keep humans thriving in microgravity or deep duration space missions. </s><s>[INST] Deep duration space missions. Okay let's talk about this. Um I was just gonna ask a bunch of dumb questions. So approximately how long does it take to travel to mars asking for a friend [/INST] asking for a friend about three years for a round trip and that's not that it actually </s><s>[INST] why the round trip is that? Well you're just asking [/INST] it's </s><s>[INST] Okay cool. So for just like literally flying to Mars and around it takes three years [/INST] there's some interstitial time there because you really can only go between Earth and mars at certain points in their orbits Where it's favorable to make that journey. And so part of that three years is you take the journey to Mars a few months, 6-9 months You're there for a period of time until the orbits find a favorable alignment again and then you come back another 6-9 months. </s><s>[INST] So one way travel 69 months they hang out there on vacation and come back [/INST] for vacation. </s><s>[INST] Well me who loves working all the time. All vacations. Fortification. Alright so okay so that gives us a sense of of duration and we can maybe also talk about longer and longer and longer duration uh as well. What are the hardest aspects of this of living in space for Many days? For let's say 100 days, 200 days maybe there's a threshold when it gets really tough. What are what are some stupid little things or big things that are very difficult for human beings to go through. [/INST] One big thing and one little thing and there's two classic problems that we're trying to solve in the space industry. One is radiation, it's not as much of a problem for us right now on the international space station because we're still protected by part of Earth's magnetosphere. But as soon as you get further out into space and you don't have that protection once you leave the Van allen belt area of the Earth and the, you know, cocoon around the earth, we have really serious concerns about radiation. The effect on human health, long term, that's the big one, the small one. And I say it's small because it seems mundane, but it actually is really big in its own way is mental health and how to keep people happy and balanced. And you were alluding to some of the psychological challenges of having humans together on missions and especially as we try to scale the number of humans in orbit or in space. So that's another big challenge is how to keep people happy and balanced and cooperating. </s><s>[INST] That's not an issue on Earth at all [/INST] at all. Okay, </s><s>[INST] so we'll talk about each of those in a, in a bit more detail but [/INST] let </s><s>[INST] me continue on the chain of dumb questions. What about food? What's a good food source for food and space and what are some sort of standard go to meals menus [/INST] right now, your go to menu is going to be mostly freeze dried every so often Nasa will arrange for a fun stunt or fresh food to get up to station. So they did bake Doubletree cookies with Hilton a couple of years ago, as I recall, I think sometime before the pandemic. But there's work actually in our lab at MIT Maggie Coblentz, one of my staff researchers is looking at the future of fermentation. Everybody loves beer, right? Beer and wine and kimchi and miso. These foods that have just been, you know, really important to human cultures for eons because we love the umami and the better flavor in them. But it turns out they also have a good shelf life if done properly. And they also have additional health benefit for the microbiome for probiotics and probiotics. So we're trying to work with Nasa and convince them to be more open minded to fermented food for long duration deep space missions that we think is one of the future elements in addition to in situ growing your own food. </s><s>[INST] Okay. This is, this is essential for the space party. Is the space beer? [/INST] Yes. Is the fermented product? Yes. </s><s>[INST] Okay, cool. In terms of water, what's a good source of drinkable water? Like where do you get water? Do you have to always bring it on board with you? And is there a compressed efficient way of storing it? [/INST] So to steal a line from charlie Bolden, who's the former Administrator of Nasa? Uh This morning's freshwater? Is yesterday's coffee. So you think about what that means? You drank the coffee </s><s>[INST] yesterday [/INST] through the body as the recycling system and then you drink what you peed out as um you know, clarified refined fresh water the next day. That is one source of water. Another source of water in the near neighborhood of our solar system would be on the moon. So water ice deposits, there's also water on mars. This is one of the big things that's bringing people to want to develop infrastructure on the moon is once you've gotten out of the gravity well of earth, if you can find water on the moon and refine it, you can either make it into propellant or drinkable water for humans. And so that's really valuable as a potential gateway out into the rest of the solar system to be able to get propellant without always having to ship it up from earth. </s><s>[INST] So how much water is there on mars? [/INST] That's a great question. I do not know. We </s><s>[INST] don't know the water the [/INST] caps I suspect nasa from all of the satellite um studies that they've done on MArs have a decent idea of what the water deposits look like. But I don't know to what degree they have characterized those. I </s><s>[INST] really hope there's life for traces of previous life on MArs. [/INST] This is a special spot in my heart because I got to work on Sherlock, which is the Astrobiology experiment that's on MArs right now, searching for. What they would say in a very cautious way is signs of past habitability. They want to be careful not to get people overly excited and say we're searching for signs of life. They're searching to see if there would have been organics on the surface of mars or water in certain areas that would have allowed for life to flourish. And I really love this prospect. I do think within our lifetimes will get a better answer about finding life in our solar system if it's there. If not on mars maybe Europa one of the icy Worlds. </s><s>[INST] So you like the you like Astrobiology this is part of part of the it's not just about human biology it's also other extraterrestrial alien biology. [/INST] Search for life in the universe. </s><s>[INST] Okay that's scary you excite you. [/INST] It excites me profoundly. </s><s>[INST] There's other alien civilizations potentially very different than [/INST] I think there's got to be some humility there. And certainly from science fiction we have plenty of reasons to fear that outcome as well. But I do think as a scientist it would be profoundly exciting if we were to find life especially in the near neighborhood of our solar system right now we would expect it to be most likely microbial life. But we have a real serious challenge in astrobiology which is it may not even be carbon based life. And all of our detectors we only know to look for D. N. A. Or RNA. How would you even build a detector to look for silicon based life or different molecules than what we know to be the fundamental molecules for life. </s><s>[INST] And then you mentioned offline Sarah walker when she heard the question that she's obsessed with even just defining life what is life to look outside the carbon based means to look outside of basically anything we can even imagine chemically uh to look outside of any kind of notions that we think of as biology. Yeah, it's it's really weird. So you now get into this land of like complexity of a measuring of like how many assembly steps it takes to build that thing and maybe maybe uh dynamic movement or some maintenance of some kind of membrane structures. Like we don't even know like which properties life should have, whether it can should be able to reproduce and all those kinds of things or pass information genetic type of information we don't know. And it's like it's it's so humbling. I mean I tend to believe that there could be something like alien life here on earth and we're just to human biology obsessed to even recognize it. [/INST] The shadow biosphere. I remember you and Sarah we're talking about. I </s><s>[INST] mean that's that's like speaking of beer, I mean that's something I wanted to make sure in all of science to shake ourselves out of like remind ourselves constantly how little we know because they might be right in front of our nose. Like I wouldn't be surprised if like trees are like orders of magnitude more intelligent than humans. They're just operating at a much slower scale and they're like talking sh it about us the whole time, Like about silly humans that take everything seriously. And we start all kinds of nuclear wars and we quarrel and we tweet about it and then but the trees are always there just watching us silly humans. Exactly. So I mean I don't know I mean obviously I'm joking on that one but there could be stuff like that. Uh Well let me ask you the drake equation. The big the question how many like obviously nobody knows but what's your gut, what's your hope as a scientist, as a human? How many alien civilizations are out there? [/INST] As a ex physicist? I'm now much more on the aerospace engineering side for space architecture but as an ex ex physicist, I hope it is prolific. I think the challenges if it's as prolific as we would hope, if there are many, many, many civilizations, then the question is where are they? Why haven't we heard from them? Uh And the fermi paradox is there's some great filter that life only gets to some level of sophistication and then kills itself off through war or through famine or through different challenges. That filter that society out of existence. And it would be an interesting question to try to understand if the universe was teeming with life, why haven't we found it or heard from it yet? To our knowledge? </s><s>[INST] Yeah, I personally believe that it's teeming with life and you're right, I think that's a really useful productive engineering. Scientific question of what kind of great filter can just be destroying all that life or preventing it from just constantly talking to to us silly descendants of apes. That's a really nice question. Like what are the ways civilizations can destroy themselves and [/INST] there's too many. </s><s>[INST] Well we, I don't think we've come up with most of them yet. That's the thing. It's uh, I mean, and like if you look at nuclear war, some of it is physics, but some of it is game theory. It's um, it's human nature. It's how societies built themselves, how they interact, how we create and resolve conflict. And it gets back to the human question on when you're doing long term space travel, how do you maintain this dynamical system of, of flawed, irrational humans such that it persists throughout time to not just maintain their biological body but get people from not murdering each other like, like each other sufficiently to where you kinda fit well. But I think, you know, if the songs or poetry or books taught me that if you like each other a little too much. Um, I mean the problems arise because then there's always a third person who also likes and then there's the drama is like, I can't believe you did that and then last night whatever. So, and then there's beer [/INST] gets </s><s>[INST] complicated quickly. Okay, anyway, um, back to the dumb questions because you, you answered this. Um, there's an interview we're gonna answer a bunch of cool little questions from, from your young students and so on about like space. One of them was playing music in space. Um and he mentioned something about what kind of instruments you could use to play music in space. Because you could you mention about like the Spotify working space and if I wanted to do a live performance, what what kind of instruments would I need? [/INST] Yeah, I mean you reference culture before and I think this is one of the most exciting things that we have at our fingertips. Which is to define a new culture for space exploration. We don't just have to import cultural artifacts from earth um to make life worth living in space. And this musical instrument that your reference was a design of an object that could only be performed in microgravity. </s><s>[INST] So [/INST] it doesn't sound the same way when it's um it's a percussive instrument when it's rattled or moved in a gravity environment. </s><s>[INST] Look it up. [/INST] It's called the telemetry on. It's created by </s><s>[INST] that is so awesome. [/INST] Created by Sands, Fish and Nicole Dubilier, two Amazing Graduate Students and Staff Researchers on My Team. </s><s>[INST] What does it look like? [/INST] It looks steampunk actually. Yeah, it's pretty cool design. It looks like it's a geometric solid that has these interesting artifacts on the inside. And it has a lot of sensors actually, additionally on the inside, like I am us inertial measurement sensors that allow it to detect when it's floating and when it's not floating and provides this really kind of ethereal. Um they later signify it. So they use electronic music to turn it into a symphony or turn it into a piece. And yeah, this is the object that dilemma tron </s><s>[INST] how does the human interact with it [/INST] by tossing it? So it's an interactive musical instrument. It actually requires another partner. So the idea was that it's something like a dance um or just like something like a choreography in space. </s><s>[INST] Got it. And then speaking of which you also talked about sports and like ball sports, like playing soccer. So what you mentioned that so you you also can move with full speed and then if you push off the wall lightly you fly across, zoom, zoom across. So how does the physics of that work for? Can you still play soccer? For example, in space? [/INST] You can but one of the most intuitive things that we all learn as babies right is whenever you throw something, if I was going to toss something to you, I toss it up because I know that it has to compensate for the fact that that florian arc is going to draw it down, the you know, equations of motion are going to drop down. I would in space. I would just shoot something directly towards you. So like straight line of sight. And so that would be very different for any type of ball sports is to retrain your human mind to have that as your intuitive arc of motion or lack of arc </s><s>[INST] from your experience, from understanding how astronauts get adjusted to the stuff, How long does it take to adjust to the physics of this world, this other world? [/INST] So even after one or two parabolic flights, you can gain a certain facility with moving in that environment. I think most astronauts would say maybe several days on station or a week on station and their brain flips. It's amazing the plasticity of the human brain and how quickly they are able to adapt and so pretty quickly they become creatures of this new environment. </s><s>[INST] Okay, so that's cool. It's it's creating a little bit of an experience. What about if you go for more than 100 days for one year, for two years for three years, what challenges start to emerge in that case? [/INST] So scott kelly wrote this amazing book after he spent a year in space and he's a twin, it's absolutely fantastic that Nasa got to do a twin studies. Perfect. Um so he wrote a lot about his experience on the health side of what changed things like bone density, muscle atrophy eyesight changing because the shape of your eyeball changes, which changes your lens, which changes how you see if we're then thinking about the challenges between a year and three years, especially if we're doing that three year trip to mars for your friend who asked earlier then you have to think about nutrition and so how are you keeping all of these different needs for your body alive? How are you protecting astronauts against radiation either having some type of a shell on the spacecraft, which is expensive because it's heavy, you know, if it's something like lead a really effective radiation shell, it's going to be a lot of mass, or is there a pill that could be taken to try to make you um less uh in danger of some of the radiative radiation effects? A lot of this has not yet been answered. But radiation is really significant challenge for that three year journey. </s><s>[INST] And what are the negative effects of radiation on the human body out in space? [/INST] A higher likelihood to develop cancer at a younger age. Um, So you'd probably be able to get there and get back, but you'd find yourself um in the same way, if you were exposed to significant radiation on earth, you'd find significant bad health effects as you age. </s><s>[INST] What do you think about like decades? Do you think about decades or is this like an entire, [/INST] I think about centuries. </s><s>[INST] For [/INST] Myspace marks. But yeah, for decades, I think as soon as we get past the three year mark. Well, absolutely want somewhere between three years in a decade. We'll want artificial gravity and we know how to do that. Actually. The engineering questions still need to be tweaked for how we really implemented. But the science is there to know how we would spin habitats in orbit generate that force. So even if the entire habitats not spinning you at least have a treadmill part of the space station that is spinning and you can spend some fraction of your day in a near to one G. Environment and keep your body healthy </s><s>[INST] literally from just spinning [/INST] from spinning. Yes centripetal force. So you generate this force. If you ever been in those um carnival rides the gravity Iran's that spin you up around the side. That's the concept. And this is actually one of the reasons why we are spinning out a new company from my M. I. </s><s>[INST] T. Lab spinning [/INST] out accidental but well well noted space planets as </s><s>[INST] possible. [/INST] Um But yeah we're spinning out a new company to look at next generation space architecture and how do we actually scale humanity's access to space? And one of the areas that we want to look at is artificial gravity. </s><s>[INST] Is there a name yet, [/INST] yep there's a name, we are brand new, we are just exiting stealth mode. So your podcast listeners will literally be among some of the first to hear about it. It's called Aurilia Institute or alia is an old english word for Chrysalis and the idea with this is that we humanity collectively are at this next stage of our metamorphosis like a Chrysalis into a space faring species and so we felt that this was a good time unnecessary time to think about next generation space architecture but also Starfleet Academy, if you know that reference from star trek. </s><s>[INST] Uh Yes. So let me ask a silly sounding ridiculous sounding but probably extremely important question sex in space including intercourse, conception, procreation, birth like being a parent like raising the baby. So basically from birth well from the before birth part um like the birds and the bees and stuff and then the whole thing how complicated is that? I remember looking at the thank you. I remember looking at this exact Wikipedia page actually and it's I remember being uh the Wikipedia pages. Sex in space. And fascinating how difficult of an engineering problem. The whole thing is is that something you think about to how to have generations of humans self self replicating [/INST] these </s><s>[INST] societies essentially. I mean I guess with Micro like if you solve the gravity problem you solve a lot of these problems. [/INST] That's the hope. Yeah it's like the central challenge of microgravity to human reproduction. But we do host a workshop every year and beyond the cradle which is the space event that we rented M. I. T. And we always do want on pregnancy in space or motherhood or raising Children in space because there are huge questions um there have been a few mammal studies that have looked at reproduction in space. But there are still really major questions about how does it work? How does the fetus evolve in microgravity if you were pregnant in space? And I think the near term answer is just gonna be we need to be able to give humans a one g environment for that phase of our development. </s><s>[INST] Yeah. So there's some studies on mice in microgravity and it's interesting like I think the mice like one of them the mice weren't able to walk or like their their understanding of physics I guess is all for something like that. [/INST] Yeah. The mental model when you're really young and you're kind of getting your mental model of physics. We do think that that would change um kids abilities to if they were born in microgravity, their ability to have that intuition around an Earth based one G environment might be missing because a lot of that is really crystallized in early development, early childhood development. So that makes sense that they would see that in mice. </s><s>[INST] Yeah. So what about life when we are choose to park our vehicles on another planet on the moon? But let's go to mars first of all, does that excite you humans going to mars like stepping foot on mars and when do you think it will happen? It [/INST] does excite me. I think visionaries like Elon are working to make that happen in terms of building the road to space. We are really excited about building out the human lived experience of space once you get there. So how are you going to grow your food? What is your habitat gonna look like? I think it's profoundly exciting, but I do think that there's a little bit of a misunderstanding of MArs anywhere in the near future being anything like a replacement for earth. So it is good for humanity to have these other pockets of our civilization that can expand out beyond earth. But MArs is not in its current state, a good home for humanity. Too many prickly rates in the soil. You can't use that soil to grow crops. Atmosphere is too thin, certainly can't breathe it, but it's also just really thin compared to our atmosphere, a lot of different challenges that would have to be fundamentally changed on that planet to make it a good home for a large human civilization. </s><s>[INST] How does a large civilization of humans get built on MArs? And what do you think? Um Where do you think it gets started being difficult? So, can you have a small base of like 10 people essentially kind of like the international space station kind of situation? And then can you get it to 100 to 1000 to a million. Are there some interesting challenges there that worry you saying that Mars is just not a good backup at this time for earth? [/INST] I think small outpost. Absolutely like McMurdo. Right, so we have these models of really extreme environments on earth in Antarctica for example, where humans have been able to go and make a sustainable settlement. McMurdo style life on MArs probably feasible in the twenties thirties. So we want to send the first human missions to MArs and maybe as early as the end of this decade, more likely early twenties thirties moving anywhere beyond that in terms of a place where like an entire human life would be lived, where it's not just you go for a three month deployment and you come back. That is actually the big challenge line is just saying is there enough um technological sophistication that can be brought that far out into space? If you imagine your electronics break, there's no radio shack. This dates me a little bit that my mind jumps to radioshack but there's no, you know, there's no supply chains on MArs that can supply the level of technological sophistication for all the products that we rely on on day to day life. So you'd be going back to actually a very simple existence more like pioneer life out west in the story of the U. S. For example. And I think that the future of larger scale gatherings of humans in orbit or so in space is actually gonna be in microgravity floating space cities, not so much trying to establish settlements on the surface. </s><s>[INST] So you think sort of a significant engineering investment in terms of our efforts and money should be on large um spaceships that perhaps are doing this kind of self assembly, all these kinds of things and doing an orbit, maybe building a giant donut around the planet over time. [/INST] Yeah, that is the goal. And I think the current political climate is such that you can't get the trillion dollar investment to build, to start from scratch and build the sci fi mega structure. But if you can build it in fits and starts in a little different pieces, which is another advantage of self assembly, it's much more like how nature works. So it's biomimicry inspired way for humanity to scale out in space, </s><s>[INST] whether it's out in space or on MArs. The idea that sort of two people fall in love have sex. Uh a child is born and then that couple has to teach that child that like we, that they came from earth. I just love the idea that somebody is born on MArs or out in space and you have to be like that, this is not actually like the original home. Just them looking at her at Earth and being like, this is where it came from. I don't know, that's really inspiring to me and the child being really confused and wanting to go back to Tiktok or whatever they, whatever they do [/INST] whatever they do in that </s><s>[INST] area. I mean, [/INST] there's great sci fi right about people being born on MArs and because it's a lower gravity environment, they're taller, they're more gangly if they were actually able to develop their and then they come back to Earth and there like second class citizens because they can't function here in the same way because the gravity is too strong for them. You see this in series like the expanse with the belters and these, you know, different societies that uh if we were to succeed in having human societies, grew up in different pockets, not necessarily going to be easy for them to always come back to earth as their home. </s><s>[INST] Yeah, different cultures form which is the positive way of phrasing it. But it's also this human history teaches us that we have, we like to form the other. So there's this kind of conflict that naturally emerges. Um let me ask another sort of dark question, What do you think about coming from a military family? There's still sadly wars in the world do you think wars a military conflict will follow us into space? Wars between nations? Like from my perspective, currently, it just seems like space is a place for scientists and engineers to explore ideas. But the more and more progress you make, does it worry you that nations start to step in and form, you know, that's that go out on full out military conflict, whether it's in cyberspace in space or actual hot war. [/INST] I am really concerned about that and I do think for decades the scientific community in space has hung on to this notion from the 1967 outer space treaty which is spaces the province of all humankind, peaceful uses of outer space only. But I do think the rise in tensions and the geopolitical scene that we're seeing. Um I do yeah, I do harbor a lot of concern about hot wars following humanity out into space. And it's worth trying to tie nations together with more collaboration to avoid that happening. The international space station is a great example. I think it's something like 18 countries are party to this treaty. It might be less, it might be more. Um and then of course there's a smaller number of countries that actually send astronauts. But even at the fall of the soviet Union and through some tense times with Russia, the I. S. S. Had been a place where the U. S. And Russia were actually able to collaborate between Mirror and I. S. S. I think it'd be really important right now in particular to find other platforms where these hegemonic powers in the world and developing world nations can come and collaborate on the future of space and purposefully intertwine our success so that there's a danger to multiple parties if somebody is a bad actor. </s><s>[INST] So we're now talking as a there's a war in Ukraine and I haven't been sleeping much at family um friends, colleagues in both countries. And I'm just talking to a lot of people, many of whom are crying refugees and I you know, there's a basic human compassion and love for each other that I believe technology can help catalyze and accelerate. But there's also science, there's there's something about rockets, there's something about and I mean like space exploration that inspires the world about the positive possibilities of the human species. So in terms of Ukraine and Russia and china and India and the United States in europe and everywhere else, it seems like collaborating on giant space projects is one way to escape these wars um to escape these sort of geopolitical conflicts. I mean there's something there's so much camaraderie to the whole thing. And um even in this little um period of human history we're living through it seems like that's essential. Even through this pandemic there's something so inspiring about those like SpaceX rockets going up. For example, this reinvigoration of the space exploration efforts by the commercial sector. I don't know that was I have some as many of us have sort of some dark times during this pandemic, just like loneliness and sometimes emotion and anger and just and just hopelessness and politics. And then you look at those rockets going up, it just gives you hope. So I think that's an understated sort of value of space exploration is the thing that unites us and gives us hope obviously also inspires young generations of young minds to also contribute and not necessarily in space exploration but in all of science and literature and posters, there's something about when you look up to the stars that makes you dream. And um so that that's a really good reason to sort of invest in this whether it's building giant mega structure which is so freaking cool. But also colonizing mars. Yeah it's it's something to look forward to. Something that that that and not make it a domain of war but a domain of human collaboration and human compassion. I think you're the founder and director of the M. I. T. Space Exploration initiative. It includes a ton of projects so I just want to um their focus I guess on life and space. From Astrobiology. Like we talked about habitats. Are there some other interesting projects part of this initiative that you're that popped to mind that you find particularly cool. [/INST] Absolutely. One is the future of in space manufacturing. So if we're going to build large scale space structures. Yes it's great to ship them up from earth and self assemble them. But what about extrusion in orbit? It's one of the best technologies to leverage in microgravity because you can extrude a particularly long beam that would sag in a normal gravity environment but might be able to become the basis of a trust or a large scale space structure. So we're doing miniature tests of extrusion and are excited to fly this on the international space station in a few months. We are working on swarm robots. We have just announced actually M. I. T. S. Return to the moon. So my organization is leading this mission for M. IT going back to the surface of the moon as early as the end of this year. 2022, maybe early 2023. And trying to take data From our research payloads at this historic South Pole site where NASA's supposed to send the first humans back on the Artemis three mission. So our hope is to directly support that human mission with our data. </s><s>[INST] How does that connect to the swarm aspects? Does it connect? [/INST] Yeah. So we're actually gonna fly one of the little astro ants. That's the current plan. One of the little swarm robots on the top of a rover. Um That's part of the uh </s><s>[INST] riding a rover. [/INST] Yes and exactly and and writing a rover that rover gets packed in a lander that lander gets packed in a SpaceX rocket. So it's a whole nesting doll situation to get to to get to the moon. </s><s>[INST] Mother of Robot Dragons. So this one A swarm of one [/INST] form of one. Exactly. We're testing out it's a tech demonstration mission. Not a true and not a true swarm. Yeah. There they are. Those are the asteroids, </s><s>[INST] wow. And they this was a distributed system and they in theory you could have a ton of these. [/INST] Yes these could also be centralized so they they have wireless technology that could also talk to a central base station and will be assessing kind of case by case whether it makes sense to operate them in a decentralized form or to command them in a centralized form. </s><s>[INST] Each robot is equipped with four magnetic wheels which enabled the robot too attached to any magnetic surface. So you can operate basically any environment. He tested the we tested the mobility of all robots on different materials in a microgravity environment [/INST] on the vomit comet prior to going to the moon. </s><s>[INST] That was so cool. So they're basically moving along different like metallic services. [/INST] Yeah, exactly. It's interesting when you you know just a minute ago talking about the reflection of how space can be so aspirational and so uniting there's a great quote from Bill Anders from the Apollo eight mission to the moon which is he it's the Earthrise photo that was taken where you see the Earth coming up over the horizon of the moon. And the quote is something along the lines of we came all the way to discover the moon and what we really discovered was the Earth. This really powerful image looking back. And so we're also trying to think for our lunar mission. We realize we're very privileged group at M. I. T. To get the opportunity to do this. How could we bring humanity along with us? And so one of the things we're still testing out. I don't know if we're gonna be able to swing it would be to do something like a twitch plays Pokemon but with the robot so let a lot of people on earth actually control the robot or at least benefit from the data that we're gathering and try to release the data openly. So we're exploring a couple of different ideas for how do we engage more people in this mission? </s><s>[INST] That would be surreal to be able to interact in some way with the thing that's out there on another surface, direct connection. Um I think about artificial intelligence in that same way which is like building robots, put some mirror to us humans. It makes us like wonder about like what is intelligence, What is consciousness and what is actually valuable about human beings when when ai system learns to play chess better than humans. You start to let go of this idea that humans are special because of intelligence. It's it's something else. Um Maybe the flame of human consciousness, it's the capacity to to feel deeply to sort of to both suffer and to love all those things and that they somehow ai to me to put some mirror to that you mentioned uh hal 9000 you have to bring it up with with with the swarm bots crawling on the surface of your cocoon in space. I mean all right, let me steal man. The the hal 9000 [/INST] perspective. </s><s>[INST] The poor guy just wanted to maintain the mission and the astronauts were I mean I don't know if people often talk about that but you know um like doctors have to make difficult decisions to when there's limited resources, you actually do have to sacrifice human life often because you have to make decisions and I think how is probably making that kind of decision about what what's more important the lives of individual astronauts or the mission and I feel like a eyes on other humans will need to make these decisions and it also feels like a I systems will need to help make those decisions. I don't know. Um I guess my question is about greater and greater collective intelligence by systems. Um do you worry about that? What is the right way to sort of solve this problem keeping a human in the loop? Do you think about this kind of stuff or are they sufficiently dumb now the robots that that's not yet on the horizon to think about? [/INST] I think it should be on the horizon. It's always good to think about these things early because we make a lot of technical design decisions at this phase working with swarm robots that it would be better to have thought about some of these questions early in the lifecycle of a project, there is a real interest in Nasa right now. Thinking about the future of human robot interaction? H. R. I. And what is the right synergy in terms of level of control for the human versus level of dependence or control for the robot. And we're beginning to test out more of these scenarios. For example the Gateway space station which is meant to be in orbit around the moon as a staging base for the surface operations is meant to be able to function autonomously with no humans in it For months at a time because I think it's going to be seasonal. They think we might not be constantly staffing it. So this would be a really great test of I don't know that anybody is yet worried about how 9000 evolving but certainly just the robustness of some of these Ai systems that might be asked to autonomously maintain the station while the humans are away um or detection algorithms that are gonna say you know if you had a human pilot they might see debris in orbit and steer around. It will be a lot of autonomous navigation that has to happen. That'll be one of the early test beds where we'll start to get a little bit closer to that future. </s><s>[INST] Well the HR I component is really interesting to me and especially when the I includes like almost friendship because people don't realize this. I think that we you know we humans long for connection and when you have even the basic interaction that's just like it's supposed to be just like serving you or something. You still project. It's still um there is still a source of Meaning and connection and so you do have to think about that. I mean how 9000 you know the movie maybe doesn't portray it that way. But I'm sure there's a relationship there between the astronauts and the and the robot. Especially when you have greater and greater level of intelligence. Maybe that addresses the the happiness question too. [/INST] I think there's a there's a great book by kate darling who's one of my colleagues. </s><s>[INST] Yeah she's amazing. We've been she's already been on this podcast but we talk all the time and we're supposed to talk and we've been missing each other and we're going to make it happen soon coming down in texas. All right. Anyway. Yeah she's amazing. And she has this book and she has her whole work is about this [/INST] connection with </s><s>[INST] this beautiful connection that we have with robots. But I think it's greater and greater importance when it's out in space because it could help alleviate some of the loneliness. [/INST] One of the projects in the book that I gave you just a catalog of the projects that we worked on over the last five years is the social robot that was developed at the media lab. And we one of the first years and 2017 that we flew a zero G. Flight. We took the social robot along and tried to do a little bit of a very scaled down human study to look at these questions because you do imagine that we would form a bond a real bond with the social robots that might be not just serving us on a mission, but really be our teammates on a future mission? And I do think that that could have a powerful role in the mental health and just the stability of a cruise to have some other robot friends come along. </s><s>[INST] The book you mentioned is into the anthropocene cosmos, whole space catalog from the catalog. [/INST] Yeah. </s><s>[INST] So call out to Earth catalog the whole space catalog from the M. I. T. Space Exploration initiative. Um what about the happiness you said that? That's one of the problems of when you're out in space. How do you keep humans happy again, asking for a friend? [/INST] Yes. I mean, one of the big challenges is you can't just open a window or walk out a door and blow off steam, right? You can't just go somewhere to clear your head. And in that sense you need to build habitats that are homes that really care for the humans inside them and have whether it's biophilia and a place where you can go and feel like you're in nature or a VR headset, which for some people is a a poor simple crumb, but it's maybe better than nothing. Um you need to be thinking about these technological interventions that are going to have to be part of your home and be part of your maybe day to day ritual to keep you steady and balanced and happy or feeling fulfilled. </s><s>[INST] What about other humans, relationship with other humans? Do those get, do those get weird when you get past a certain number of humans? I'm [/INST] not an expert in this area, but an anecdote that I'll share my understanding is that Nasa has still not decided whether it's better to send married couples or single crew members in terms of uh you want some level of stability. You don't want to have the drama of romantic relationships like you're, you know, alluding to before, but they can't decide because married couples also fight and have a really tough dynamic. And so there's a lot of open questions still to answer about what is the ideal psychological makeup of a crew. And we're starting to test some of these things with the civilian crews that are growing up with inspiration for like last fall with SpaceX and acts one that's going to fly in a few days here in March as we begin to lengthen the time of those civilian crews, I think we'll start to learn a little bit more about just average everyday human to human dynamics and not the astronauts that are themselves selected to be perfect human specimens. Very good to work with. Easy to get along with. </s><s>[INST] I wish you collected more data about this pandemic because I feel like it's a good rough simulation of what would be out in space. A lot of people were locked down, some married couples? I think a lot of marriages broke up. A lot of marriages got closer together. Um just like, and then the single people, some of them went off the cliff and some of them discovered their new happiness and meaning and so on. It's a beautiful little experiment, a painful one. Is there a thorough way to really test that two? Because it's such a costly experiment to send humans up there? But I guess you can always return back to Earth if it's not working out. [/INST] That's what we hope that you hope you don't have like a, you know, Apollo 13 situation that doesn't quite make it back. But yeah, the this is also why MArs is such a challenge. The moon is only three days away. That's a lot quicker to recover from if there's a psychological problem with the crew or any type of maintenance problem, anything three years is such a challenge compared to these other domains that we've been getting more used to in terms of human spaceflight. So this is a question that we will need to have explored more before we start really sending crews to mars. </s><s>[INST] So you're a young scientist. Do you think in your lifetime you will go out into orbit, you will go out beyond into deep space and potentially step you, I don't know if you can call yourself a civilian. I don't know if that's what you count as, but you as a, as a curious ant Uh from M. I. T. Land step on mars [/INST] the firm </s><s>[INST] as a firm [/INST] firm. Yes. Yeah I'm coming back I don't want that one way mission. I want the two way mission. Um But yes I mean I think we're already talking about a pretty near term opportunity where I could send graduate students to the international space station. Yeah not not you know not a sacrifice but send graduate </s><s>[INST] students parents [/INST] send graduate students to the I. S. S. To do their research. I do think you and I both would have an opportunity to go to a lunar base of some sort within our lifetime and there's a good chance if we really wanted to we might have to really advocate for it. You know apply to an astronaut program. There will be some avenues for humans in our lifetime to go to mars </s><s>[INST] what's the bar for like health. Do you do you think that bar will keep getting lower and lower in terms of how healthy how athletic like how [/INST] the </s><s>[INST] psychological profile all those kinds of things. [/INST] Yeah for one we're going to build more robust habitats that don't depend on astronauts being so impeccably well trained. So we're going to make it better for inclusion. Um and just opening access to space but there's a fantastic group called astro access that is already helping disabled space fliers do zero G. Flights and potentially get access to the ISs and some of the things that we think of as disabilities on earth are hyper abilities in space. You don't need really powerful legs in space. What you'd really benefit from having is a third arm. Um more ways to kind of move yourself around and grip and interact. So we are already seeing a much more open minded approach to who gets to go to space and ask for access is a wonderful organization doing some of that work. </s><s>[INST] I'm hoping introversion will also be a superpower in space. Okay, well first I'd love to get your opinion on commercial spaceflight, what SpaceX and Blue Origin are doing. And also another question on top of that is because you've worked with a lot of different kinds of people culturally what's the difference between uh SpaceX or commercial type of efforts, Nasa and [/INST] yeah, so the first part of the question, I am thrilled by all of the commercial activity in space. It is really empowered our program. So instead of me waiting for five years to get a grant and get the money from the grant and only then can you send a project to space? I got my fundraise a lot like a startup founder and I directly by access to space on the international space station through SpaceX or nana racks. Same with blue Origin and their suborbital craft. Same with axiom. Now Axioms making plans for their own commercial space station, it's not out of the realm of possibility that in a few years I will rent lab space in orbit, I will rent a module from the axiom space station or the orbital reef, which is the blue origin space station or nana racks, is thinking about star lab oasis. There's probably some other companies that I'm not even aware of yet that are doing commercial space habitat. So I think that's fabulous. Um and really empowering for our research. </s><s>[INST] Is it affordable? So like uh loosely speaking, does it become affordable for like mitt type of research lab, does it, you know, um or does it need to be a multi university, like a gigantic effort consortium thing. [/INST] One of the reasons were spinning out of Australia is we actually realized it's cheap enough. It doesn't even have to be M. I. T. And we wanted to start democratizing access to these spaceflight opportunities to a much broader swath of humanity. Could you take a, you know, khan Academy educational course about hey students around the world, this is how you get ready for a zero G. Flight and by the way, come fly with us next year, which is something we're going to do with the Israelis were going to bring you know, much more just kind of day to day folks on zero G. Flights and get them access to engaging in the space industry. So it's become cheap enough. Um and the prices have dropped enough to consider even that. So that's amazing. It definitely doesn't have to be a consortium of universities anymore, depends on what you want to fly if you want to fly James webb huge telescope that's decades in the making sure you need a Nasa allocation budget, you know you need billions but for a lot of the stuff in the book and our research portfolio it's actually becoming far more accessible. </s><s>[INST] So that's a commercial. What about Nasa and M. I. T. Academia? [/INST] Yeah I think you know people have been worried about Nasa the last few years because in some people's minds they are ceding ground to these commercial efforts but that's really not. That's really not what's happening. Nasa empowered these commercial efforts because they want to free themselves up to go to MArs and go to Europa and um continue being that really aspirational force for humanity of pushing the boundary, always pushing the boundary. And if they were anchored in low earth orbit maintaining a space station indefinitely, that's so much a part of their budget that it was keeping them from being able to do more. So it actually is really fantastic for Nasa to have grown this commercial ecosystem. And then that frees Nasa up to go further and in academia we like to think that we will be able to do the provocative next generation research that is going to unlock things at that frontier. And uh we can partner with Nasa, we can go through a program if we want to send a probe out really far, but we can also partner with SpaceX and see what human life in a SpaceX mars settlement might look like and how we can design for that. </s><s>[INST] Speaking of projects, maybe other other projects that pop to mind from the Space exploration initiative or maybe stuff from the book the convention. Something super cool. I mean everything we've been talking about is cool, but just something that pops to mind again. [/INST] Yeah, so we talked about life in space and you might need more arms than legs. One of the projects by Valentina Simeoni was a air powered robotics tail. So it's a soft robotics tale that essentially has a little camera on the back end of it can do computer vision and knows where to grapple. So it's behind you. It grapples onto something and holds you in space and then you can actually free up both of your hands to work. So we're already starting to think about the design of bionic humans or prosthetics or things that would make you kind of like a cyborg to augment your capabilities when you're in a space environment, </s><s>[INST] would you control something like that? It's kind of like a I mean you can't call it a leg but whatever its [/INST] additional appendage </s><s>[INST] appendage. So how would you what what are ideas for controlling something like that? [/INST] Yeah, so right now it's super. Yeah, </s><s>[INST] there you go. That's cool [/INST] right now. It's super manual. Um it's basically just like a kind of a set pattern of inflating as we're testing it. But in the future if we had a neuralink I mean this is something that you could imagine directly controlling just thinking thoughts and controlling it. That's a ways away. </s><s>[INST] So we talked about on the biology side Astrobiology there's probably agriculture stuff. Um Is there other things that kind of feed the ecosystem of out in space for survival or or the robotics architecture of the self assembly? [/INST] So kind of combining something we were talking about you can form these relationships with objects and anthropomorphizing. One of the things that we're thinking about for agriculture created by um man way. And so mu so two students at M. I. T. Was this little it looks like a planet but it's inspired by I think a mandala or nepalese spinning wheel and you plant plants on the inside and the astronaut has to spin it every day to help the plants survive. So it's a way to give the astronauts something to care about something that they are responsible for keeping alive and can really invest themselves in and it's not necessary. Right? We have other ways to grow in orbit. Um hydroponics liquid medium trying to keep the liquid around the plant roots. It's hard because there's no gravity to pull it down in a particular direction. But what I loved about this project was they said sure we have ways that the plants could grow on their own. But the astronauts might want to care for it in the same way that we have little plants that come to be important to us. Little plant friends. Yeah, so there's ag refuge, that's an early model of this spinning manually spinning plant habitat. I </s><s>[INST] guess this is the best of academic researchers. You can do these kinds of wild well you know, I get to spend quite a bit of time with mr Elon musk and he's very stressed, especially about starship and all those kinds of engineering efforts. What do you think about how damn hard it is to get out? [/INST] Like </s><s>[INST] are we humans going to be able to do this? I don't know. I think it feels like it's an engineering problem, it's a scientific problem but it's also just a motivation problem for the entire human species. And you also need to have superstar researchers and engineers working on it. So you have to get like the best people in the world inspire them and starting from a young age and kind of uh [/INST] I guess </s><s>[INST] that's why it's exciting. You don't know if we're gonna be able to pull this off but we can like fail miserably and that I suppose I mean that's where the best of engineering is done. There's like success is not guaranteed. And even if it happens it might be very painful. [/INST] I think that's what's so special about what Ellen is doing with SpaceX is he takes these risks and he tests iterative lee and he'll we'll see the spectacular failures on the path to a successful starship. It's something that, you know, people have said, why isn't Nasa doing that? Well, that's because Nasa is doing that with taxpayer dollars and we would all revolt if we saw Nasa failing at all these different stages. But that level of, you know, spiral engineering theory of development isn't super impressive and it's a really interesting approach that SpaceX has taken. And I think between people like Elon and Jeff Bezos and Firefly and Nasa and esa, we are going to get there there building the road to space, these trailblazers are doing it. And now part of the challenge is to get the rest of the public to understand that it's happening right. A lot of people don't know that we're going back to the moon, that we're going to send the First woman to the moon. Um Within a few years, a lot of people don't know that there are commercial space stations in orbit that it's not just Nasa that does space stuff. So we have a big challenge to get more of humanity excited and educated and involved. Again, kind of like in the Apollo era where it was a big deal for everybody. </s><s>[INST] Well, a lot of that is also one of the big impressive things that Ellen does. I think extremely well is the social media is getting people excited and I think that actually he's helped Nasa step their game up in terms of social media. There's something about yeah this storytelling but also not like um you know like authentic and just real and raw engineering. There's a lot of excitement for that humor and fun. Also all of those things you realize the thing that make ups the vire al Itty of the meme is beautiful, you have to kind of embrace that and um to me this kind of uh okay I criticized a lot of companies based on this. I talked I talked to a bunch of C. E. O. S and and so on. It's just like there's a caution like let us let us do this like press conference thing where we when the final product is ready and it's overproduced as opposed to the raw. The gritty just showed off. It's something that I think my tea is very good at doing. It's just showing the raw by nature the mess of it and the mess of it is beautiful and people get really excited and failure is really exciting when the thing blows up and you're like oh ship that makes it even more exciting when it doesn't blow up and doing all of that on social media and showing also the humans behind it, the individual young researchers or the engineers or the leaders where everything is at stake. I don't know I think I'm really excited about that. I do want my t to do that more for students to show off their stuff and not be pressure to do this kind of generic official presentation, but show show their become a Youtuber. Also like show off your raw research as you're working on it in the early days. I hope that's the future. Things like I was teasing about Tiktok earlier, but you know, these kinds of things, I think inspire young people to uh, to show off their stuff to show their true self the rawness of it because I think that's where engineering is best and I think that will inspire people about all the cool stuff we could do. [/INST] I should say I couldn't agree more. And I actually think this is why we need a real life Starfleet Academy right now. It was the place where the space cadets got to go to learn about how to engage in in the future of life and space and uh, we can do it in a much better way. They're a bunch of groups that traditionally haven't thought that they could engage in aerospace, whether it's because you were told you had to be into math and science now, we need space lawyers, we need space artists like grimes, right? We need really creative, profoundly interesting people to want to see themselves in that future. Um, and I think it's a big challenge to us in the space industry to also do some more diversity, equity and inclusion and show a broader swath of society that there's a future for them in this space exploration missions </s><s>[INST] push back on one thing we don't need space lawyers. Okay, it's a joke. [/INST] We do, </s><s>[INST] okay, we do. The lawyers are great, I love them. Okay, let me ask a big ridiculous question. What is the most beautiful idea to you about space exploration? Whether it's the engineering, the Astrobiology, the science, the inspiration that the human happiness or aliens, I don't know what, what do you like um inspires you every day in terms of its beauty. It's all [/INST] as a ex physicist, but I've always found so profound um it's just that at a really, really small scales like particle physics and really, really big scales like astrophysics, there are similarities in the way that those systems behave and look and there's a certain beautiful symmetry in the universe. It's just kind of waiting for us to tie together the physics and really understand it. That is something that is just um just really captivates me and I would love to, even though I'm now much more on the applied space exploration side, I really try to keep up with what's happening in those physics areas because I think that will be a huge answer for humanity along the lines of are we alone in the universe. </s><s>[INST] One of the fascinating things about you is you have a degree in physics, mathematics and philosophy and now I don't know what you want to know what you call aerospace engineering maybe kind of thing. So you're you have a foot in all of these worlds, the theoretic uh the the sort of the beauty of that world and the philosophy somehow is in there and now the very practical pragmatic implementation of all these wild ideas um plus your incredible communicator, all of those things. What did you pick up from those different disciplines? Um or maybe I'm just romanticizing all those different disciplines, but what is there? What did you pick up from? The variety of that? Physics, mathematics, philosophy, [/INST] what I loved about having this chance to do a liberal arts education was trying to understand the human condition and I think more designers for space exploration should be thinking about that because there's so much depth of like we were talking about issues of issues and opportunities around human connection, human life meaning in life, how do you find fulfillment or happiness? And I think if you approach these questions just purely from the standpoint of an engineer or a scientist, you'll miss some of what makes it a life worth living. Um and so I love being able to combine some of this notion of philosophy and the human condition with my work, but I'm also a pragmatist and I didn't want to stay just purely in these big picture questions about the universe. I wanted to have an impact on society and I also felt like I had such a, a wonderful childhood and a really fantastic setup that I owe society some work to really make a positive impact for a broader swath of citizens. And so that kind of led me from the physics domain to thinking about engineering and practical questions for life and space </s><s>[INST] in physics, was there a dream? Are you also captivated by this search for the theory of everything that kind of unlocks the deeper and deeper in the, in the simple, elegant way the function of our universe. Do you think they will be useful for us um for the actual practical engineering things that you're working on now? [/INST] It could be, I mean, I worked at cern for two summers in undergrad and we were looking for supersymmetry, which was one of these alternatives to the standard Model and it was sad because my professors were getting sadder and sadder because they weren't finding it, they were excluding what we would call this parameter space, of finding these supersymmetric particles, but the search for what that theory of everything could be, or a grand unified theory that kind of answers some of the holes within the standard model of physics would presumably kind of unlock a better understanding of certain fundamental physical laws that we should be able to build a better understanding of engineering and day to day services from that. It might not be an immediately obvious thing When we discovered the Higgs the Higgs Boson. I was there at Cern that day, it was July 4, 2012 that it was announced. We all waited like nerds overnight in line to get into the announcement chamber. I've never waited for even like a harry potter premiere in my life, but we waited for this like announcement of the Higgs boson to get into the </s><s>[INST] chamber [/INST] overnight, but did that immediately translate to technology for engineering? No. Um, but it's still a really important part of our understanding of these fundamental laws of physics and so I don't know that it's always immediate, but I think it is really critical knowledge for humanity to seek. </s><s>[INST] It might just shake [/INST] up understanding of the </s><s>[INST] world. What scares me is that might help us create more dangerous weapons. So, um, and then we'll figure out that great filter situation and I still believe that human compassion and love is actually the way to defend against all these greater and greater and more impressive weapons. Let me ask a weird question in terms of you disagreeing with others, what important idea do you believe is true that many others? Uh, don't agree with you on. Maybe it's a tough question, you might have to think about that one, but well, that's very specific, like which material to use something about a particular project or um, it could be grand priorities on missions. I think one you actually mentioned is interesting is like um the thing we should be looking for is that colonization of space versus colonization of planets meaning like [/INST] my best hot take that people would disagree with me on is life in floating cities as opposed to life on on the surface. How do you </s><s>[INST] envision that like spread of humans? Because you said at the beginning of the conversation, something about like scale increasing the scale of basically humans in space. Are they just like in um they're in orbit and then they get a little farther and farther out. Like do you see this kind of uh floating cities just getting farther and farther from earth? You can always kind of return but like if you look a few centuries from now and you just see us all these like floating [/INST] cities. Yes. And </s><s>[INST] it just kinda in envelopes the space around us and this like neighborhoods. Yeah, rural and there's like giant structures and there's small pirate structures and that kind of structures. [/INST] Yeah, I think low earth orbit might come to look like that and it's a really interesting regulatory challenge to make sure that there's some cross purposes. So the more cool space cities we have in orbit, the more shiny objects in the night sky, the worse it is for astronomers in a really kind of overly simplified case. So there's some pushback to this like amoeba in where we just grow kind of um incongruously or indiscriminately as an amoeba in low earth orbit beyond that though, I think we'll grow in pockets where there are resources so we won't just expand around the gravity well of Earth will do some development around the moon, some development around asteroids, some development around mars because there will always be purposes for which we want to go down to a physical object and study it or extract something or learn from it. But I think we'll grow in fits and starts in pockets. Um some of the coolest pockets are the gravity balanced pockets like the Lagrange points which is where we just sent, we, not me personally, but Nasa just sent James webb, The big telescope. I think it's at L two. So </s><s>[INST] what's the nice feature about those pockets? [/INST] So it's a stable orbit. Um there are several different Lagrange points and so it just requires less energy to stay where you're trying to stay. </s><s>[INST] Yeah, that's fascinating. What's also fascinating is the interaction between nations on that regard? Like who owns that? Do you would you would you say in those floating cities do you envision independent governments? [/INST] That was gonna be my next answer to you which pushed me harder for a more provocative question where I might disagree with other people. I don't yet have my own opinions fully formed on this but we are trying to figure out right now what happens to the moon with all of these first come first served actors just arriving and setting precedents that might really affect future access. And one example is property rights. We do want companies that have the expertise to go to the moon and mind stuff that will help us uh, you know, develop a human settlement. There are a gateway, but companies need to know generally that they have rights to a certain area or that they have some legal right to sell things that they're getting. So that mean we're gonna grant property rights on the moon to companies who has the right to give that right away. So there's a bunch of really kind of gnarly questions we have to think about, which is why I think we need space lawyers. Maybe that's the true provocative answers I think </s><s>[INST] I mean, yeah, yeah, I mean, but those questions, again, as you said, eloquently will help us answer questions about here. It is a little strange. I mean it's obvious, but it's also strange if you look at the big picture of it all that we draw these like borders around geographical areas and we say this is mine, like and then we fight wars over what's mine and not there there it seems like there there's possible alternatives, but also it seems like there needs to be a public ownership of some parts, um like, you know, what is the central Park in new york. Is there something like preserving [/INST] commons </s><s>[INST] commons [/INST] commons. That's why we titled the book into the anthropocene cosmos. We know it's a long kind of a mouthful, but this notion of the anthropocene, we have a lot of commons problems in humanity. How are we treating the earth? Global climate change. How are we going to treat and behave in space? How can we be responsible stewards of the space commons? And I would love to see an approach to the moon that is commons based, but it's hard to know who would be the protector or the enforcer of that. </s><s>[INST] And if it's which it will be probably in the early days, a lot of companies sort of working on the moon, working on MArs working out in space. It feels like they're still needs to be a civilian representation of like the greater effort or something like that. Like where there should be a president, there should be a democracy of some kind where people can vote [/INST] representative government. </s><s>[INST] Those are all again the same. The same Human questions. Uh, what advice would you give to a young person today? Thinking about what they want to do with their life career? So, somebody in high school, somebody in college, maybe somebody that looks up to the stars and dreams to one day, take a one way ticket to mars or to contribute something to the effort. [/INST] I'd say you should feel empowered because it's really the first time in human history that we're at this cusp of interplanetary civilization and I don't think we're going to lapse back from it. So the future is incredibly bright for young people that even younger than you and I who will actually really get a chance to go to mars for certain. Um The other thing I would say is be open minded about what your own interests are. I don't think you anymore have to be shoehorned into a particular career to be welcomed into the future of space exploration if you are an artist and that is your passion. But you would love to do space art or if not space art use your artistry to communicate a feeling or a message about space. That's a role that we desperately need just as much as we need. Space scientists and space engineers. So </s><s>[INST] well when you look at your own life, you're an incredibly accomplished scientist, young scientists. But you know and you hopped around from you know physics to aerospace. So going from the biggest theoretical ideas to the biggest practical ideas, is there something from your own journey? You can give advice to like how to end up doing incredible research at M. I. T. Um maybe the role of the university and college and education and learning all that kind of stuff. [/INST] I say one piece of advice is find really good teammates because I get to be the one that's talking to you. But there are 50 graduate students, staff and faculty that are part of my organization back at M. I. T and I'm actually you guys can't see it on camera but I'm sitting here with my co founder and Ceo Daniel. Um and that is really what makes these large scale challenges for humanity possible is really fantastic teams working together to scale more than what I could do alone. So I think that's an important model that we don't talk about enough in academia. There's a big push for this like lone wolf genius figure in academia but that's certainly not been the case in my life. I've had wonderful collaborators and people that I work with along the team </s><s>[INST] also cross disciplinary. So [/INST] absolutely yeah. Cross disciplinary, interdisciplinary, whatever you want to call it. But </s><s>[INST] artists where do artists come in? Do you do you work with artists? [/INST] We do. We have an arts curator on the space exploration initiative side. She helps make sure partly around that communication challenge that we talked about, that we're not just doing zero G. Flights and space missions but that we take our artifacts of this sci fi space future, two museums and galleries and exhibits. She pushed me to make sure her name is showing glue. She pushed me for our first ISS mission. I was just gathering all the engineering payloads that I wanted to support for the students to fly including my own work. And she said you know what we should do an open call internationally for artists to send something to the I. S. S. And we found out it was the first time we were the first ever international open call for art to go to the I. S. S. And that was thanks to shing an artist bringing a perspective that I might not have thought about prioritizing. </s><s>[INST] Yeah, that's awesome. So when you look out there it's the flame of human consciousness, there does seem to be something quite special about us humans. Well first of all, what do you what do you think it is? What's consciousness? What what are we trying to preserve here? What is it about humans that should be preserved or life here on earth? They what gives you hope to try to expand it out farther and farther? Like what makes you sad if it was all gone? [/INST] I think we're a remarkable species that we are aware of our own thoughts. We are meta aware of our own thoughts and of ourselves </s><s>[INST] and are able to speak on a podcast about a meta awareness about our own thoughts [/INST] about our own thoughts, yet turtles all the way down. Um I think that is a really special gift that we have been given as a species and that there's a worth to expanding our circles of awareness. So we're very aware of as an earth based species. We've become a little bit more aware of the fragility of earth and how special a place it is when we go to the moon and we look back, what would it mean for us to have a presence and our purpose in life as a inter solar system species are eventually an intergalactic species. I think it's a really profound opportunity for exploration. For the sake of exploration. A real gift for the human mind. </s><s>[INST] Yeah, if we're for anything, we're curious creatures. You so you do believe we might one day become intergalactic civilization [/INST] long, long time from now. We have a lot of propulsion challenges to answer to get that far. </s><s>[INST] Do you have a hope for this? Another big ridiculous question building on top of that, What do you think is the meaning of life? This individual life of ours, your life that unfortunately has to come to an end as far as we know for now. Um and our life here together, is there a y or do we just kind of like, let our curiosity carry us away? [/INST] Oh, interesting. Is there a single kind of driving purpose y or can it just be curiosity based? I certainly feel. And this is not the scientist in me talking, but just more of like a human soul talking. I certainly feel some sense of purpose and meaning in my life and there's a version of that that's a very local level within my family, which is funny because this whole conversation has been big grand space exploration themes, but you asked me this question and my first thought is what really matters to me, my family, my biological reproducing unit. Um </s><s>[INST] but [/INST] then there's also another purpose. Like another version of the meaning in my life that is trying to do good things for humanity. So that sense that we can be individual humans and have our local meaning and we can also be global humans. Maybe someday like the star trek. Utopia will all be global citizens. I don't want to sound too naive. Um But there is I think that beauty to a meaning and a purpose of your life that's bigger than yourself. Working on something that's bigger and grander than just yourself. </s><s>[INST] The deepest meaning is from the local biological reproduction unit and then it goes to the engineering scientific uh what is it corporate like company unit that can actually produce and compete and interact with the world. And then there's the giant human unit that's struggling with pandemics [/INST] and comments </s><s>[INST] and together struggling against the forces of nature that keeps wanting to kill us. [/INST] Yeah there'd be nothing like an alien invasion to unite the planet. We think </s><s>[INST] I can't wait bring it on aliens. Listen to your your work. You're an incredible, communicated incredible young scientists. So it's a huge honor that you spend your time with me. I can't wait what you do in the future. And thank you for representing M. I. T. So beautifully so masterfully your incredible person. Thank you thank [/INST] you so much for having me. It's been an absolute pleasure. It's a great conversation. </s><s>[INST] Thanks for listening to this conversation with area like blah. To support this podcast, please check out our sponsors in the description. And now let me leave you with some words from Seneca, the roman, stoic philosopher. There is no easy way [/INST] from Earth </s><s>[INST] to the stars. Thank you for listening and hope to see you [/INST] next time. </s>

<s>[INST] I mean there's metrics there's um data can obscure the key insight if you're not careful. So so time spent in the app that's one there's so many metrics you can put out this and that will give you totally different insights especially when you're trying to create something that doesn't obviously exist yet. So you know um measuring maybe why you left the app or measuring special moments of happiness that will make sure you return to the app or moments of happiness that are long lasting versus like dopamine short term all of those things. But I think I suppose in the beginning you can just get away with just asking the question which features are used a lot. Let's do more of that. And how hard was the decision? And uh I mean maybe you can tell me what instagram looked in the beginning but how hard was it to make pictures the first class citizen. That's a revolutionary idea like um whatever point instagram became this feed of photos. That's quite brilliant. Plus I also don't know when this happened but they're all shaped the same. [/INST] It's like I have to tell you why. That's the interesting part. </s><s>[INST] Why is that? [/INST] So a couple of things. one is data data like you're right you can overinterpret data like imagine trying to fly a plane by staring at I don't know a single metric like air speed. You don't know if you're going up or down. I mean it correlates with up or down, but you don't actually know will never help you land the plane. So don't stare at one metric, like it turns out you have to synthesize a bunch of metrics to know where to go. Um but it doesn't lie like if your speed is zero, unless it's not working right? If it's zero, you're probably gonna fall out of the sky. So generally you look around and you have the scan going and you're just asking yourself, is this working or is this not working? But people have trouble explaining how they actually feel. So just it's about synthesizing both of them. So then instagram, right? Uh we were talking about revolutionary moment where the feed became square photos basically </s><s>[INST] in photos 1st and [/INST] then square foot. Yeah. Um it was clear to me that the biggest, so I believe the biggest companies are founded when enormous technical shifts happen and the biggest technical shift that happened right before instagram was founded was the advent of a phone that didn't suck the iphone right? Like in retrospect, were like, oh my God, the first iphone almost had like it wasn't that good. But compared to everything else at the time it was amazing. And by the way, the first phone that had an incredible camera that could, that could like do as well as the point and shoot you might carry around was the iphone for and that was right when instagram launched and we looked around and we said, what will change because everyone has a camera in their pocket. And it was so clear to me that the world of social networks before it was based in the desktop and sitting there and having a link you could share. Right? And that was going to be the case. The question is, what would you share if you were out and about in the world? If not only did you have a camera that's in your pocket. But by the way that camera had a network attached to it that allowed you to share instantly. That seemed revolutionary and a bunch of people saw it at the same time. It wasn't just instagram. There were a bunch of competitors. Um, the thing we did I think was not only, well we focused on two things. So we wrote down those things, we circled photos and he said, I think we should invest in this. But then we said what sucks about photos. one. They look like crap. Right? They just at least back then now my phone takes pretty great photos right back then they were blurry. Not so great compressed right to uh, it was really slow. Like really slow to upload a photo And I'll tell a funny story about that and explain to you why they're all the same size and square as well. Um, and three and if you wanted to share a photo on different networks, you have to go to each of the individual apps and select all of them and upload individually. And so we're like, all right, those are the pain points. We're gonna focus on that. So one instead because they weren't beautiful. Um were like, why don't we lean into the fact that they're not beautiful? And I remember studying in Florence, my photography teacher gave me this whole get camera and I'm not sure everyone knows what a whole game cameras, but they're these old school plastic cameras. I think they're produced in china at the time. And there, I want to say the original ones like from the 70s or the 80s or something. They're supposed to be like $3 cameras for the every person. They took nice medium format films, large, large negatives, but they kind of blurred the the light and they kind of like light leaked into the side. And there was this whole resurgence where people looked at that and said, oh my God, this is a style, right? And I remember using that in Florence and just saying, well why don't we just like leaning into the fact that these photos suck and make them suck more? But in an artistic way? And it turns out that had product market fit people really like that. They were willing to share their not so great photos if they looked not so great on purpose. Okay, It's the second part </s><s>[INST] that's where the filters come [/INST] into the picture. So </s>

<s>[INST] For me also the flavors are inextricably tied to the memories I've had with those flavors. So for better or worse back when I used to eat a lot of ice cream for some reason had a lot of pleasant experience with coconut ice cream. So that particular flavor just permeates throughout my life. Like I'm stuck with it for better or worse as a flavor. That brings up pleasant memories. And I have a few such flavors. I have. I have such relationship with all kinds of meat to like, it's just so many pleasant memories and that's it. Like you're almost tasting the memories and uh, that there's no way to separate the flavor from the memories, I suppose and that's a powerful thing. What's your favorite meal to cook? [/INST] I, I'll roast a couple of chickens and then I'll poach them, like I'll boil them and let it cool. That's complicated one. Um I'll let them cool down. I'll pull all the meat off, put the bones back into the pot and then cook that for like three or four hours. Um and then add in like shiitake mushrooms and all the chicken meat and the, and I'll throw in a bottle of white wine into the, into the stock as well, a bunch of thyme and garlic and I love it because it's uh, it's the way the house smells, It's very laborious. It's soothing for me to spend time picking apart me and chopping things up. There's like a lot of manu al itty around it. Um So I'd say from a personal, like, I mean, I love grilling a steak and doing those things as well, but there's something about making a stock from scratch and the way it smells the way I feel the time it takes the kind of checking in on it that I really, really love, there's many things I love to make that I don't even love to eat. you know, I think you see this a lot in baking and bakers? People who bake a ton and I love the process of it, even if they don't eat that many baked goods. So anything for me that's really like enjoyable is typically things like making cinnamon buns. I don't get very many cinnamon buns, but I love making them because it takes all the sort of like fussing around and taking your time and watching it the way it smells, the way the house smells, All of that stuff is like, it's like almost like a, like a meditative exercise for me. </s><s>[INST] Is there a science, is there an art to cooking meat well and the different kinds of meats? Is there something you can convert in towards in uh to say ideas how to bring out the best of it out of What particular, meet whatever steak we're talking about, whatever before talking about. Is there something that could be said? [/INST] The basic approach to cooking any type of meat beyond the artistry of it is pretty scientific and it's, what type of muscle is it in the animal and what's the surface area to volume ratio? Okay, so let's look at those two questions. So the first pieces, what's the type of muscle in the animal? What's the functionality? You don't necessarily need to know that um to evaluate it, but you need to understand, is it a tender muscle that's not used very frequently in the animal? Or is it a big load bearing muscle that gets a lot of action like cheek, right? Or the shin? Or the those pieces the muscles like um those along the spinal cord that make up rabbis in new york steaks and things. Those aren't very exercised their right next the spinal cord, spinal cords doing most of the work. They're they're kind of like um stabilizing muscles around this big functional piece of skeletal structure in the animal. Other muscles, like the ones around the diaphragm with the flat iron steaks and skirt steaks and things. Those are those are really functional muscles that are doing a ton and moving. And if they're moving a lot what happens? Well, functionally they've got lots of muscle she needs because muscles that move frequently have to do a lot of like complex contraction. That's why, you know, there's um in the cheek for example, there's tons of visible fiber of collagen is connective tissue. That connective tissue is everything in how the meat cooks. Because connective tissue doesn't respond to high heat with becoming more tender muscles do, right? They can get a sear on them, you can cut them and eat them. The collage in situ will glom up and get really tough. So you either have to liquefy it with really low slow heat with moisture, right? Or you have to barely cook it? And that's so that's the major piece? That's the question of like why wouldn't you just throw a brisket on the grill? Okay. It's not about the fat. You can get the fat out the reason you're not going to throw brisket on the grill and cook it hot and fast. It just got too much collages, connective tissue in it. Those are these giant muscles that have all this college and these fibers and tendons in them effectively. So you're never going to be able to just cook that up hot fast. So that's the first piece. It's like, what, where is this muscle in the architecture of the animal? And then what does that mean for what's going on in the muscle? And that's actually more important than fat content. We get really kind of, we pay a lot of attention to fat content in muscles. You can make a steak tender if it doesn't have a ton of fat in it, it actually has more to do if, if there's, if there's collages and connective tissue in it. </s>

<s>[INST] my head. Like I have different voices. Like, you know, obviously it just in I've been getting so much information, so many thoughts in all the complexities of the war in Ukraine for example and all the different voices within Ukraine. I just interviewed hundreds of people and they have very different perspectives in nuanced ways about the war. Uh some are full of hate, some are full of love, like hate for the other, love for their own country, love for family and tradition, all of it. It's a beautiful mix and I have to walk, I have to like carry those ideas in my head and empathize with them deeply. And then I have to listen to people that live elsewhere that live in India. They have a very different perspective, There's a lot of people in India that have a very different perspective the people in Ukraine. So I don't know and some of that will bleed out into the thoughts I expressed publicly and like when people judge you harshly for it it it, first of all me as a human being is psychologically difficult but also it makes me less willing to be fragile. I still try to be strong enough to be fragile in front of the camera just say like say things that are on my mind even if I know it's going to create ah people that are going to be like ruthlessly negative towards me. So I try to wear my heart on my sleeve and still try to be fragile but it's harder you're gonna pay a psychological cost. Like like I'm you know, in some sense, I try to be tough, but like, I could be a softie in that in like certain certain, like attacks can get to me. So I'm surprised that they don't get, I mean, does there's some negativity get to you or is this the way you deal with it by responding? Uh like that that guy saying like, what value does talking to let me add to the world? [/INST] No, but that was, I mean, that was so good. I was looking at was thinking at various moments you went to jump in and I was I was kind of letting, letting you speak. One of the things I wanted to mention was significantly simpler to talk about chess than it is to talk about. Some of the things you talk about and you have a big responsibility because you have to absorb information like a sponge. But you also then need to present it in a way where you potentially have an opinion while trying to be fair to everybody and you're talking about things that will literally never please everybody. Just literally whatever you're going to talk about, some issues that are going to get out there into the people are gonna watch it, eyes, right the years of millions of people and not everybody is going to be satisfied. And these are issues where people are going to be much more likely to speak up in all sorts of ways, tremendous support or tremendous hatred, vitriol and God knows what else. Yeah, you you that's one of the reasons I'm I'm blown away to even be sitting here frankly, because up until a few months ago, you weren't talking to, you know, I'm not saying you weren't talking to, but you haven't spoken to chess players, you were speaking to people who are doing much more substantial things in the world. </s><s>[INST] I appreciate the humility there [/INST] just </s><s>[INST] to me is an incredible is a beautiful game. But I think the reason comments hurt is not I mean, they hurt no matter what to me. Like [/INST] not to me because I'm in a simpler space. </s><s>[INST] That's what you have [/INST] to understand. I even </s><s>[INST] so if it's chess based criticism, [/INST] it </s><s>[INST] doesn't hit as hard. [/INST] No, if you had a podcast about you, you have a podcast, photography, you gotta you gotta realize like it wouldn't it wouldn't be the same way you talk about potentially existential things. You talk about cyber, you know, things things in cybersecurity or or ai or people who are massive heads of companies that are just inherently going to be a bit more controversial. So that I can't imagine being in your shoes because you have so many complex emotions about situations where you may not necessarily agree with everything that someone has said publicly, but you still invite them for a conversation because they're a human being, it's totally different. Like I </s><s>[INST] don't know, I not the way I experience it to me. I think what hurts is it's not even on mine because I'm super self critical usually where more than the internet can be, it's that like human beings can be cruel to each other. So like the reason it hurts for some reason, it's like this almost like this disappointment in people, they don't give each other a chance. So in that sense the negativity doesn't have to be about Ukraine or geopolitics. It could be about the silliest of things I said and like to me it's like why why be mean to each other in a context where the mean doesn't like it's out of place because for example, there is like a gaming culture where they just talk to each other now stop. I think it's more acceptable there. It seems to fit, it seems to be funnier there and like one streamer stock shipped to each other. I've been listening to several streamers recently and it's like it somehow works a little better even if they're just like cruel to each other. It makes more sense. But I think when people are genuinely trying to educate or to help and so on and you still get the shitty comments. I don't know, it makes me sad. No, [/INST] it doesn't, it doesn't make me it doesn't make me sad. I think part of that is also the way I was brought up. So I was I skipped kindergarten. So I was always the smallest kid and </s>

<s>[INST] we shouldn't assume that that's the case, which it may be. We may be able to engineer shortcuts. [/INST] Yeah, Elia had this, you know, believe that maybe one has to go for a week or six months, do some challenging camp. The just experienced, you know, a lot of difficulties and then comes back and actually everything is bright. Everything is beautiful. I'm </s><s>[INST] with Jillian is, it must be a Russian thing. Where are you from? Originally [/INST] I'm polish </s><s>[INST] polish Okay. I'm tempted to say that explains a lot. But yeah, there's something about the Russian, the necessity of suffering. I believe I believe suffering or rather struggle is necessary. [/INST] I believe that struggle is necessary. I mean in some sense, you even look at the story of any superhero, that movie it's not that it was like everything goes easy, easy, easy, </s><s>[INST] easy. But that's your ground truth is the story superheroes. Okay uh you mentioned that you used to do research at night and go to bed at like six a.m. Or seven a.m. I still do that often. What sleep schedules have you tried to make for a productive and happy life? Is there um is there some interesting wild sleeping patterns that you engage that you found that works really well for you? [/INST] I tried at some point decreasing number of hours of sleep like a gradually okay half an hour every few days to this. You know I was hoping to just save time that clearly didn't work for me like at some point there's like a phase shift and I felt tired all the time. Ah You know there was a time that I used to work during the nights. The nice thing about the nights is that no one disturbs you. And even I remember when I was meeting for the first time with Greg brockman, his ceo and chairman of opening, Our meeting was scheduled to five p.m. And I overstepped for the meeting, </s><s>[INST] overslept for the meeting at five p.m. Yeah now you sound like me. That's hilarious. Okay. [/INST] Yeah and at the moment in some sense uh my sleeping schedule also has to do with the fact that I'm interacting with people. I sleep without an alarm. </s><s>[INST] So so yeah the team thing you mentioned extroverts thing because most humans operate during a certain set of hours, you're forced to then operate at the same set of hours. But I'm not quite there yet. I found a lot of joy just like he said working through the night because it's quiet because the world doesn't disturb you and there's some aspect counter to everything you're saying, there's some joyful aspect is sleeping through the mess of the day because people are having meetings and sending emails and there's drama meetings. I can sleep through all the meetings. [/INST] You know, I have meetings every day and they prevent me from having sufficient amount of time for focused work. And uh then I modified my calendar and I said that I'm out of office Wednesday thursday and friday every day and I'm having meetings only monday and Tuesday and that vast the positively influenced my mood that I have literally like three days for fully focused work. </s><s>[INST] So there are better solutions to this problem than staying awake all night. Okay, you've been part of development of some of the greatest ideas and artificial intelligence. What would you say is your process for developing good novel ideas? [/INST] You have to be aware that clearly there are many other billion people around. So you have to ask yourself a question why they give an idea, let's say wasn't tried by someone else and in some sense it has to do with, you know, kind of simple, it might sound simple, but like thinking outside of the box and what I mean here. So for instance, for a while, people in academia, they assumed that you have a fixed data set and then you optimize the algorithms in order to get the best performance. And uh that was so in great assumption that no one thought about training models on anti internet or like that, that maybe some people talk about it, but if it felt to do many as unfair, I mean some sense that's almost like it's not my idea or so, but that's an example of breaking a typical assumption. So you want to be in the paradigm that you're breaking a typical assumption </s><s>[INST] in the context of the ai community. Getting to pick your data set is cheating [/INST] correct. And in some sense, so that was that was assumption that many people had out there and then if you free yourself from assumptions then they are likely to achieve something that others cannot do. And in some sense, if you are trying to do exactly the same thing as others, it's very likely that you're going to have the same results. </s><s>[INST] Yeah, but there's also that kind of tension which is uh asking yourself the question, why haven't others done this because uh I mean I get a lot of good ideas, but I think probably most of them suck when they meet reality. [/INST] So, so actually I think the other big piece is getting into the habit of generating ideas, training your brain to our generating ideas and not even uh suspending judgment of the ideas. So in some sense, I noticed myself that even if I'm in the process of generating ideas, if I tell myself oh that was a bad idea then that actually interrupts the process and I cannot generate more ideas because I'm actually focused on the negative part of why it won't work. But I created also environment in the way that it's very easy for me to, to start new ideas. So for instance, next to my bed, I have a voice recorder and it happens to me often, like I wake up in there during the night and I have some idea in the past, I was writing them down on my phone, but that means you know, turning off the, turning on the screen and that wakes me up or like pulling a paper which requires, you know, turning on the light these days, I just started recording it. </s>

<s>[INST] Well, for me, emotionally, there's nothing that sickens me more in the university than the abuse of power. [/INST] Right. </s><s>[INST] And there's an awful lot of people who abuse power in the university. And especially when it comes to abuse power over students. So sexual harassment, so in the realm of sexual abuse of power and all kinds of other. [/INST] Well, it is a crime to use one's power position in order to take sexual advantage of a student. It's a crime. </s><s>[INST] This is not a close question. Yeah, but there's a legal crime and there's a deeply ethical crime and there's an emotional response that I have. You are a good lawyer and perhaps a good man to want to defend some folks who are evil in this world. I don't think I have that emotional fortitude. Well, then you shouldn't be a criminal defense lawyer or a cardiologist. I think you're right. I'm still deeply sickened by Jeffrey Epstein and the faculty, the administration that still might be in these great American universities that are abusing their power in small ways and big ways. But that's human nature. You get a little bit of power and you're a bad man or a bad woman and you take advantage of it. We see that in the smallest of ways and in the biggest of ways in institutions and regimes all across the world. Boy, Harvey, it's a complicated situation. [/INST] Well, it's a complicated world and it's complicated to be a human being and this is nothing new. </s><s>[INST] And we should talk about it without restriction. All right, just to linger on liberal arts, in 2014 and probably still today, you wrote that liberals are killing the liberal arts. Yes. [/INST] So can you explain? Yes, the problem with, I'm a political liberal. The problem with the political left is that it has divided between what's called progressives and liberals. Liberals are people of the left who believe in the First Amendment, an absolute First Amendment and in due process of law. And the problem with what progressives now, in the pursuit of equality, what they view as equality, they're willing to bend those rules. And this movement actually started in Brandeis, the critical race theory. It started Herbert Marcuse, who was a professor at Brandeis and he came up with his theory. The theory was this, this is right out of Orwell. In order to create true equality in a society where you have some downtrodden and some who are the Uber mentioned, in order to create real equality, you have to reduce the rights of the upper classes and artificially increase the rights of the lower classes. And that will produce, out of unequal treatment, true equality will be attained. This is nonsense. The idea of discrimination producing true equality is nonsense. My view is, as I've said earlier in our discussion, that the way to increase the opportunities for the lower classes is to give them real educations. And until we do that, it's not going to happen. And in order to do that, we have to overcome the problem of the teachers' unions at the elementary and secondary school levels. Until we're willing to do that, honestly, and then improve those schools, we're going to have a problem of a large number of uneducated people who need a boost because we haven't given them proper educations. </s><s>[INST] What do you think about some of the more controversial faculty in the world? So an example of somebody I've spoken with many times on mic and offline is Jordan Peterson. I'm not sure if you're familiar with his work. Yes. But he is an outspoken critic or proponent of free speech on campus and he's been attacked quite a bit. He's a controversial figure. [/INST] Which through all of the university to protect the Jordan Peterson's of the world? Yeah. I think the university has an absolute, absolute, not relative, not watery, absolute role, obligation to protect the academic freedom of even the most controversial faculty members. And you can imagine, on a university campus, you have more people who are outliers than you do in the general population. And that's the hope at least. Hopefully, yeah. And those outliers have to be protected. They can't be pressured, they can't be fired, they can't be disabled from spewing their views whether they're considered racist, whether they're considered to be, you know, promote an idea of human society that's considered obnoxious. It doesn't matter if you can't, if you can't have freedom of thought on the college campuses, where can you? You know, then we're lost as a society, we're lost. And as an educational institution, educational institutions no longer will educate, they will indoctrinate. That we have to avoid at all costs. </s><s>[INST] And we should also remember that the outlier might also be the only bearer of truth. So in Nazi Germany, speaking against the fascism, fascist regime, and communist Soviet Union [/INST] speaking against communism, they might hold the key to solving the ailments of that society. Absolutely. And some of the most important discoveries in science, for example, were mocked at the </s>

<s>[INST] Let me ask you another depressing and difficult question, which is once we achieve that goal, uh do you of creating a no of understanding intelligence, Do you think we would be happier more fulfilled as a species? [/INST] To understand intelligence? Or understanding the answers to the big questions? </s><s>[INST] Understanding [/INST] intelligence? How are totally, totally being far more fun place to live? So, Yeah. Why not? I mean, you know, just put aside this, you know, terminator nonsense. And and and and just think about, you can think about, we can talk about the risk of they are if you want. But I I think the world is far better. Knowing things were always better than no things. Do you think it's better? Is it a better place? The world, the living? That I know that our planet is one of many in the solar system, in the solar cell is one of many of the galaxy. And I think it's more, I dread. I used to I sometimes think like, God, what would be like to live 300 years ago, I'd be looking at the sky. I can't understand anything. Oh my God, I'd be like going to bed and I go and what's going on here? </s><s>[INST] Well, I mean, in some sense, I agree with you, but I'm not exactly sure. I'm also a scientist. So I have I share your views, but I'm not, we're like rolling down the hill together, uh [/INST] what's down the hill? I feel like we're climbing a hill. </s><s>[INST] Whatever. [/INST] Getting we're getting closer to enlightenment and whatever the downtown </s><s>[INST] we're climbing, we're getting pulled up a hill by [/INST] curiosity. Put polio cities, we're pulling ourselves up the hill by our curiosity. </s><s>[INST] Yeah, because we're doing the same thing with the rock. Uh, but okay, our happiness aside, do you have concerns about, you know, you talk about Sam Harris, you know, musk of existential threats of intelligence. [/INST] I'm not worried about existential threats at all. I there are there are some things we really do need to worry about. Even today, I have things we have to worry about. We have to worry about privacy and about how impacts um false beliefs in the world. And we have real problems that uh, and things to worry about with today's Ai um and that will continue as we create more intelligent systems. There's no question, you know, the whole issue about, you know, making intelligent armament and weapons is something that really we have to think about carefully. I don't think of those as existential threats. I think those are the kind of threats we always face. And we'll have to face them here. And and uh, and we have to deal with them. Um, the we can we can talk about what people think are the existential threats. But, uh, when I hear people talking about them, they all sound hollow. To me. They're based on ideas. They're based on people who really have no idea what intelligence is. And and if if they knew what intelligence was, they wouldn't say those things. So those are not experts in the field, you know? </s><s>[INST] So, yeah, So there's two right there. So one is like super intelligence. So a system that becomes far far superior in reasoning ability than us humans. [/INST] How is that an existential threat </s><s>[INST] then? So there's a lot of ways in which it could be one way as us humans are actually irrational and efficient and get in the way of uh of not happiness, but whatever the objective function is of maximizing that objective function and super intelligent [/INST] paperclip problem and things like </s><s>[INST] that. So the paperclip problem. But with the super intelligent. [/INST] Yeah. So uh we already faced this threat in some sense. Uh they're called bacteria. These are organisms in the world that would like to turn everything into bacteria. And they're constantly morphing their constantly changing to evade our protections. And in the past they have killed huge swaths of populations of humans on this planet. So if you want to worry about something that's gonna multiply endlessly we have it. And I'm far more worried in that regard. I'm far more worried that some scientists in the laboratory will create a super virus or super bacteria that we cannot control. That is a more existential strip, putting putting an intelligent thing on top of it actually seems to make it less existential. To me, it's like it limits its power, has limits where it can go. It limits the number of things that can do in many ways that bacteria is something you can't you can't even see </s><s>[INST] uh so that's [/INST] only one of those problems. </s><s>[INST] Exactly. So the the other one. Just in your intuition about intelligence when you think about intelligence as humans, do you think of that as something? Uh If you look at intelligence on the spectrum from zero to us, humans, do you think you can scale that to something far superior? All the mechanisms would [/INST] be let me I want to make another point here before I get there. Intelligence is the new york cortex. It is not the entire brain. If I the goal is not to be make a human, the goal is not to make an emotional system. The goal is not to make a system that wants to have sex and reproduce. Why would I build that if I want to have a system that wants to reproduce, have sex. Make bacteria make computer viruses. Those are bad things don't do that. Those are really bad. Don't do those things regulate those. But if I just say I want an intelligence system, why doesn't have to have any of the human like emotions. Why couldn't why doesn't even care if it lives, Why does it even care if it has food? It doesn't care about those things. It's just you know, it's just in a trance thinking about mathematics or it's out there. Just trying to build the space plan? You know for it on mars it's a we don't that's a choice we make. Don't make human like things don't make replicating things don't make things that have emotions just stick to the new york cortex. </s>

<s>[INST] Yeah, but the existence is shown already gives a deep lesson about what's out there in the universe. That means that other stars have similar types of variety as we have in our solar system. They have an Io, they have Europa, and so on, which means there's a lot of possibility for icy planets, for water, for planets that enable planets and moons. I mean, that's super exciting because that means everywhere through our galaxy and beyond, [/INST] there is just innumerable possibility for weird creatures, life forms. You don't have to convince me. I mean, NASA has been on this quest for a long time and it's sometimes called E to Earth. It's the frequency of Earth-like, usually they say planets in the universe. How common are planets similar to our Earth? Ultimately, we'd like to know everything about these planets in terms of the amount of water they have, how much atmosphere they have, but for now, it's kind of focused just on the size and the distance from the stars, essentially. How often do you get similar conditions to that? That was Kepler's primary mission and it really just kind of flirted with the answer, didn't quite get to a definitive answer. But I would say, look, if that's our primary goal, to look for Earth-like, I would say worlds, then moons has to be a part of that because we know that Earth-like, from the Kepler data, the preliminary result is that Earth-like planets around Sun-like stars is not an inevitable outcome. It seems to be something like a 1% to 10% outcome, so it's not particularly inevitable that happens. But we do often see about half of awesome-like stars have either a mini Neptune, a Neptune, or a Jupiter in the habitable zone of their stars. That's a very, very common occurrence that we see, yet we have no idea how often they have moons around them, which could also be habitable. And so, there may very well be, if even one in five of them has an Earth-like moon or even a Mars-like moon around them, then there would be more habitable real estate in terms of exomunes than exoplanets in the universe. </s><s>[INST] You can essentially 2x, 3x, 5x, maybe 10x the number of habitable worlds out there in the universe, our current estimate, like the Drake equation. Absolutely, yeah. So, this is one way to increase the confidence and increase the value of that parameter. [/INST] Absolutely, yeah. And just know where to look. I mean, we would like to know where should we listen for techno signatures? Where should we be looking for biosignatures? And not only that, but what role does the Moon have in terms of its influence on the planet? We talked about these directly-imaged telescopes earlier, these missions that want to take a photo to quote Carl Sagan, the pale blue dot of our planet, but the pale blue dot of an exoplanet. And that's the dream to one day capture that. But as impressive as the resolution is that we are planning and conspiring to design for the future generation telescopes to achieve that, even those telescopes will not have the capability of resolving the Earth and the Moon within that. It'll be a pale blue dot pixel, but the Moon's grayness will be intermixed with that pixel. And so, this is a big problem because one of the ways that we are claiming to look for life in the universe is a chemical disequilibrium. So, you see two molecules that just shouldn't be there. They normally react with each other, or even one molecule that's just too reactive to be hanging around the atmosphere by itself. So, if you had oxygen and methane hanging out together, those would normally react fairly easily. And so, if you detected those two molecules in your pale blue dot spectra, you'd be like, okay, we have evidence for life. Something's metabolizing on this planet. However, the challenge is, what if that Moon was Titan? Titan has a methane-rich atmosphere. And what if the pale blue dot was, in fact, a plant devoid of life, but it had oxygen because of water undergoing this photolysis reaction, splitting into oxygen and hydrogen separately? So, then you have all of the hallmarks of what we would claim to be life, but all along you were tricked. It was just a Moon that was deceiving you. And so, we are never going to, I would claim, really understand or complete this quest of looking for life by signatures in the universe unless we have a deep knowledge of the prevalence and role that Moons have. They may even affect the habitability of the planets themselves. Of course, our main Moon is freakishly large. By mass ratio, it's the largest Moon in the solar system. It's a 1% mass Moon. If you look at Jupiter's Moons, they're like 10 to the power minus 4, much smaller. And so, our own Moon seems to stabilize the obliquity of our planet. It gives rise to tides. Especially early on when the Moon was closer, those tides would have covered entire continents. And those rock pools that would have been scattered across the entire plateau may have been the origin of life on our planet. The Moon-forming impact may have stripped a significant fraction of lithosphere off the Earth, which without plate tectonics may not have been possible. We'd heard a stagnant lid because it was just too much lithosphere stuck on the top of the planet. And so, there are speculative reasons but intriguing reasons as to why a large Moon may be not just important but central to the question of having the conditions necessary for life. So, Moons can be habitable in their own right, but they can also play a significant influence on the habitability of the planets they orbit. And further, they will surely interfere </s>

<s>[INST] there's like two questions I want to ask. Do you have sort of a good example of rigorous thinking, where it's easy to get lazy and not do the rigorous thinking? And the other question I have is like, do you have advice of how to practice rigorous thinking and um you know, and all the computer science disciplines that we've mentioned? [/INST] Yeah, I mean there are times where problems that can be solved with well known mature methods um could also be solved with with a deep learning approach. And there's an argument that you must use learning even for the parts we already think we know because if the human has touched it, then you've give biased the system and you suddenly suddenly put a bottleneck in there. That is your own mental model. But something like inverting a matrix. You know, I I think we know how to do that pretty well, even if it's a pretty big matrix. And we understand that pretty well and you could train a deep network to do it, but you shouldn't probably </s><s>[INST] so in that sense, rigorous thinking is understanding the the scope and limitations of the method of the methods that we have like how to use the tools of mathematics properly. Yeah, [/INST] I think, you know, uh taking a class on analysis is all I'm sor sort of argument is to take a chance to stop and and force yourself to think rigorously about even, you know, the rational numbers or something. You know, it doesn't have to be the end all problem. But that exercise of clear thinking, I think uh it goes a long way and I just want to make sure we keep preaching </s><s>[INST] and lose it. But do you think uh when you're doing like rigorous thinking or like maybe trying to write down equations or sort of explicitly like formally describe a system, do you think would naturally simplify things too much? Is that a danger you run into? Like in order to be able to understand something about the system? Mathematically we uh make it too much of a toy example, [/INST] but I think that's the good stuff, right? </s><s>[INST] That's how you understand the fundamentals. [/INST] I think so. I think maybe even that's a key to intelligence or something. But I mean, okay, what if Newton and Galileo had deep learning and they had done a bunch of experiments and they told the world here's your weights of your neural network. I've we've solved the problem, you know, where would we be today? I don't I don't think we'd be as far as we as we are. There's something to be said about having a the simplest explanation for a phenomenon. So I don't doubt that we can train neural networks to predict, even physical, you know? Uh huh ethical dilemma type equations, but I may be I want another newton to come along because I think there's more to do in terms of coming up with the simple models for more complicated tasks. </s><s>[INST] Yeah. Uh let's not offend the Ai systems from 50 years from now. They're listening to this that are probably better at might be better coming up with ethical dilemma equations themselves. [/INST] So, sorry, I actually think um learning is probably a route to achieving this. Um But the representation matters right? And I think having a function that takes my inputs to outputs that is arbitrarily complex, may not be the end goal. I think there's still, you know, the most simple or parsimonious explanation for the data. Um Simple doesn't mean low dimensional, that's one thing I think that we've a lesson that we've learned, so, you know, a standard way to do um model reduction or system identification and controls is the typical formulation is that you try to find the minimal state dimension, realization of a system that hits some error bounds or something like that. And that's maybe not. I think we're learning that that was the state dimension is not the right metric </s><s>[INST] of complexity of [/INST] complexity. But for me, I think a lot about contact, the mechanics of contact with the robot hand is picking up an object or something. And when I write down the equations of motion for that they're they look incredibly complex. Not because um actually not so much because of the dynamics of the hand when it's moving but it's just the interactions and when they turn on and off right? So having a high dimensional you know But simple description of what's happening out here is fine. But if when I actually start touching if I write down a different dynamical system for every polygon on my robot hand and every polygon on the object whether it's in contact or not with all the combinatorics that explodes there then that's too complex. So I need to somehow summarize that with a more intuitive physics way of thinking. And yeah I'm very optimistic that machine learning will get us there </s><s>[INST] first of all I mean I'll probably do it in the introduction but you're one of the great robotics people at M. I. T. You're a professor at M. I. T. You've teach them a lot of amazing courses. You run a large group uh And you have a uh important history for M. I. T. I think as being a part of the DARPA robotics challenge can you maybe first say what is the DARPA robotics challenge and then tell your story around it your journey with it. [/INST] Yeah sure. Um So the DARPA robotics challenge. It came on the tails of the DARPA grand challenge and DARPA urban challenge which were the challenges that brought us um put a spotlight on self driving cars. Um Gill pratt was at DARPA and pitched a new challenge that involved disaster response? Um, it didn't explicitly require human rights, although humanoids came into the picture, this happened shortly after the Fukushima disaster in Japan. And our challenge was motivated roughly by that because that was a case where if we had had robots that were ready to be sent in through the chance that we could have averted disaster and certainly after the, in the disaster response, there were times we love, we would have loved to have sent robots in. So in practice, what we ended up with was a grand challenge therapy robotics challenge where boston dynamics was uh, was to make humanoid robots, people like me and the amazing team at MIT. Um, we're competing first in a simulation challenge to try to be one of the ones that wins the right to work on one of the boston dynamics humanoids in order to compete in the final challenge, which was a physical challenge. </s>

<s>[INST] actually on that point. Let me I don't know if you know the work of Donald Hoffman, who talks about who uses the argument um the mechanism of evolution to say that there's not necessarily a strong evolutionary value to seeing the world as it is. So objective reality, that our perception actually is very different from what's objectively real. We're living inside an illusion and we're basically the entire uh the entire set of species on earth, I think, I guess are competing in a space that's an illusion that's distinct from this far away from physical reality as it is. As defined by physics. [/INST] Not sure it's an illusion so much as a bubble. I mean, we we have a sensory input which is a fraction of what we could have a sensory input on. Um and we interpret it in terms of what's useful for us to know to stay alive. So, yes, it's an illusion in that sense. But </s><s>[INST] the tree [/INST] is physically there. And if you walk into that tree, you you know that there is it's not purely a delusion of some physical reality to it. So </s><s>[INST] it's a it's a sensory slice into reality as it is. But because it's just a slice, you're missing a big picture, But he says that that slice doesn't necessarily need to be a slice. It could be a complete fabrication that's just consistent amongst the species, which is an interesting or at least it's a humbling [/INST] realization </s><s>[INST] that our perception is limited and our cognitive abilities are limited. And at least to me it's argument from evolution. I don't know how much how, how strong that is an argument, but I do think that life can exist in the mind. [/INST] Yes, </s><s>[INST] in the same way that you can do a virtual reality video game and you can have a vibrant life inside that place and that place is not real in some sense, but you can still have a vibe all the same forces of evolution, all the same competition, the dynamics of between humans. You can have. But I don't know if um I don't know if there's evidence for that being the thing that happened on earth, It seems that Earth, [/INST] I think in either environment, I wouldn't deny that you could have exactly the world that you talked about and it would be very difficult to, you know, the the the idea in matrix movies and so on that the whole world is completely a construction. Um and where fundamentally deluded. It's it's difficult to say that's impossible or couldn't happen or and certainly we construct in our minds what the outside world is, but we do it on input and that input. I would hesitate to say it's not real because it's precisely how we do understand the world. We, you know, we have eyes, but if you keep someone, apparently this kind of thing happens, someone kept in a dark room for five years or something like that and they never see properly again because they the what neural wiring that underpins how we interpret vision never developed. You know, you need, when you watch a child develop, it walks, walks into a table, it bangs his head on the table and it hurts. And now you've got two inputs, you've got one pain from this sharp edge and and number two, you probably you've touched it and realize it's there is a sharp edge and you've got the visual input and you put the three things together and think I don't want to walk into a table again. So you're learning and and it's a limited reality, but it's a true reality. And if you don't learn that properly then you will get eaten, you will get hit by a bus, You will not survive. And the same. If you're if you're in in some kind of, let's say computer construction of reality, not in my ground here. But if if you construct the laws that this is what reality is inside inside this and then you play by those laws. </s><s>[INST] Yeah, well, I mean as long as the laws are consistent. So just like you said in the lab, the interesting thing about the simulation question, yes, it's hard to know for living inside a simulation, but also, yes, it's possible to do these kinds of experiments in the lab now more and more to me, the interesting question is how realistic there's a virtual reality game need to be for us to not be able to tell the difference. A more interesting question to me is how realistic or interesting does a virtual reality world need to be in order for us to want to stay there forever or much longer than physical reality prefer that place. And also prefer it not as we prefer hard drugs but prefer in a deep meaningful way in the way we we enjoy. I [/INST] mean, I suppose the issue with the Matrix, I imagine that it's possible to to delude the mind sufficiently that you genuinely in that way do think that you are interacting with the real world when in fact the whole thing is a simulation. How good does the simulation need to be to be able to do that? Well, it it needs to um convince you that all your sensory input is correct and accurate and joins up and make sense. Now that sensory input is not something that we're born with. Were born with a sense of touch. We're born with eyes and so on, but we don't know how to use them. We don't know what to make of them. We go around, we bump into trees, we cry a lot, we're in pain a lot, you know, we're we're we're we're basically booting up the system so that it can make head or tail of this sensory input that it's getting and that century inputs not just a one way flux of things, it's also you have to walk into things, you have to hear things, you have to put it together now if you've got just babies in in the matrix who are slotted into this, I don't think they have that kind of sensory input, I don't think they would have any way to make sense of new york as a world that they're part of the brain is just not developed in that way. </s>

<s>[INST] And I've been [/INST] thinking about that question ever since. </s><s>[INST] Yeah. Yeah. No, [/INST] they got a good point. </s><s>[INST] They got a good point, no matter what, as an engineering and the scientific pursuits. It's a beautiful one in your own personal life. If you can go there, what have been some dark places you've gone in your own mind, grief, loss, sad moments, moments of sadness that have made you a better writer, better creator, a better human being. Well, [/INST] I mean, I've been through a lot of bereavement just in these last couple of years with Covid. But even before that, I mean, there's there's all kinds of stuff I write about in the book. And in some ways I feel like I can write about those kinds of things better than I can speak them. But I had a really complicated relationship with my mother growing up where we had a kind of garden of Eden during my childhood. We were intensely, intensely close. And and my mother because of some vulnerabilities that she had reacted with a lot of trouble to my adolescence and to growing independent from her and starting to have different religious views and different political views and all kinds of things. And and we had a pretty intense break that I described in the book and it was so intense that even though after that we still would get together for holidays and talk to each other on the phone and all that, there was a sense in which it was over at that point. The relationship was over. </s><s>[INST] The garden of Eden was no more. [/INST] Yeah. Yeah, it was like a feeling of like, yeah, like I know what Eden was like and it's not there anymore. Um and I think it was all the more confusing because like if you lose someone to actual bereavement, you go through a mourning process and people have thought for thousands of years about how to do that, but with something like this, there's no process because you're not even admitting to yourself, especially when you're like in your teens and twenties that your morning something. So, um but but it was the case that for decades, for decades, I could not answer even the simplest question about my mother, like where did she grow up without tears in my eyes or or more than tears in my eyes, like embarrassing tears. So I would just try to steer the subject in another place. Um but I will say, you know, two things happened. One is that I've spent the last 67 years writing this book about joy and sorrow and loss and love and all of it. And I've really come to terms with all of it. And then the second thing that happened is my mother now has Alzheimer's and in her Alzheimer's </s><s>[INST] she's [/INST] still actually the same person. Like she's forgotten most things, but she still has these conversational lanes that you can travel down that are like the way she always was and the way that she was when I was a kid, which was like so incredibly loving and so connected and so warm and sweet and funny and all of it, all the things I remembered, like it's all come back and for all these decades I had been wondering whether that garden of Eden I remembered had actually happened or whether, you know, that was just like the fantasy of a child and you know, maybe it was always difficult and I had not seen it. But I'm seeing her now and I realize that it was all true. Everything I remember it was all true. It all happened because it's happening again </s><s>[INST] and you return to the garden of Eden for a time and and to childhood. It's always a question of whether you can return to that place. [/INST] Well, I don't know, I don't even know if I'd say I've returned because I'm a different person now and I don't, I need her in. Are you sure </s><s>[INST] You're different than the than the 10 year old? [/INST] Well, no, I mean, I'm the same person in terms of my need for love and love of love and all of that, but I don't look, I'm not dependent on my mother for it the way I was then, and that makes the experience really different </s><s>[INST] younger. She's a she's a God figure what, what is that, that the roots to parents, such a funny civilization will live and there's a depth of connection to parents that's that's probably more powerful than anything else in terms of its formative effect on who you are. [/INST] I think it's the most powerful, and in fact, when this started happening, I got to college and I took a class in creative writing and I tried to write a story, a fictional story, a fictionalized version of what was happening. And I called it the most passionate love Because of what you just said. Um and the teacher actually said to me, she was like, you know, you should put this story in a drawer and not take it out again for 30 years because you're way too close to it. Um so I've now finally written it 30 years later. Mhm. </s><s>[INST] Uh Yeah, but you're probably still too close to it though. [/INST] I don't know though. I mean, I do think like, I think everybody goes through experiences in this life where you're experiencing like a fundamental pain of separation and desire for a union, and it takes so many different forms and this was my primal form of it. But, you know, for someone else, it's a betrayal or bereavement or an exile from a country of their birth or whatever it is, but </s><s>[INST] and then you get to solve that puzzle for for the for the rest of your life. [/INST] Yeah. Fact of like, I really do believe that, you know, that the original love that we long for like that one of the great things that you learn as you grow older is that the that the love exists in some plane, that's more general than the particular Rised form in which you first knew it. </s>

<s>[INST] So uh this is an interesting the like the role of computing in this whole picture, you mentioned code. So like you as a quantum astro chemist, there is some role for programming in your life, in your past life in your current [/INST] life group, charlie. I'm a computational quantum astro chemists, but that doesn't roll off the tongue very easily. </s><s>[INST] So this is fundamentally computational. Like if you want to be successful in the 21st century and doing quantum astro chemistry, you want to be computational. [/INST] Absolutely. All quantum chemistry is computational at this point. Okay, </s><s>[INST] uh does machine learning play a role at all? Is there some extra shortcuts that can be discovered through uh like you see all that success with protein folding, right. A problem that thought to be extremely difficult to apply machine learning to because it's um um I mean mostly because there's not a lot of already solved puzzles to train on, I suppose the same exact thing is true with this particular problem. But is there hope for machine learning to help out? [/INST] Absolutely. Currently you've laid out exactly the problem. The training set is awful. And because there's so a lot of the state to that I'm basing it on is literally many decades old. The people who worked on it and data that I get often they're dead and the files that I've used the some of them were hand drawn by someone tired in the 70s. So I could of course have had a program training on these but I would just be perpetuating these mistakes without hope of actually verifying them. So my next step is to Improve this training set by hand and then try to see if I can apply machine learning on the full code of the full 16,000 molecules and improve them all. But really I need to be able to test the outcomes with experimental data which means convincing someone in a lab to spend a lot of money putting very dangerous gasses in chambers and measuring them at outrageous temperatures. So it's a work in progress </s><s>[INST] and so collecting huge amounts of data about the actual gas is uh so you you see you so you you are up for doing that kind of thing too. So actually like doing the full end to end thing which is like having a gas collecting data about it. And and then doing the kind of analysis that creates the fingerprint and then also analyzing using that library, the data that comes from other planets. So you do the full [/INST] fall from birth tube death. Yes. I worked in an industrial chemistry laboratory when I was much younger and Slovenia. And there I worked in the lab actually collecting spectrum and and predicting spectrum. </s><s>[INST] What's it like to work with a bunch of gasses that are like not so human friendly is fine, [/INST] it's horrific. It's so scary. And I love my job. I'm willing to clearly sacrifice a lot for it? You know, job stability, money, sanity. But I only worked there for a few months. It was really terrifying. There's just so many ways to die. You know. Usually you only have a handful of ways to die every day, you know? But if you work in a lab there's so many more orders of magnitude more. And I was very bad at it. I'm not a good hands on scientist. I wanna laptop connected to a remote supercomputer or a laptop connected to a telescope. I don't I don't need to be there to believe it. And I am not good in the lab. </s><s>[INST] Yeah. Well there's a bunch of things that can poison you, a bunch of things that could explode in their gasses. And they're often maybe they might not even have a smell or they might not be visible. It's like [/INST] so many of them give you cancer. It's just so cruel. And some people love this work. But I've I've never enjoyed experimental work. It's so ungrateful, So lonely. </s><s>[INST] Well most I mean so much work is lonely if you finally join it. But you you enjoy the results of it. [/INST] Yes, I'm very thankful for all the experimentalists in my life. But I'll do the theory. They do the experiment and then we talk to one another and make sure it matches </s><s>[INST] okay. Beautiful. What our spectroscopic networks. Those look super cool. Are they related to what we were talking about? The pictures look pretty. [/INST] Oh yes, slightly. So remember when I mentioned the 17.5 million energy levels, there are rules for each molecule on which energy levels that can jump from and to and how likely it is to make that jump. And so if you plot all the routes that can take, you get this energy network for which is like a ball. </s><s>[INST] The constraints of the transitions that can be taken [/INST] exactly for each molecule, </s><s>[INST] interesting. And they're not So it's not a fully connected. It's like it's sparse somehow. [/INST] Yes, you get island. Sometimes you get a molecule can only jump from one set of states to another and it's trapped now in this network, it can never go to another network that could have been available to other siblings. </s><s>[INST] Is there some insights to be drawn from these networks? Like something cool that you can understand about a particular molecule because of it. [/INST] Yes. Some molecules have what we call forbidden transitions which aren't really forbidden because it's quantum. There are no rules. No, there are rules is just the rules are very often broken in the quantum world. And so forbidden transitions doesn't actually mean they're forbidden probability. Exactly. They just become deeply unlikely. </s>

<s>[INST] Which is the opposite of oftentimes gain a function research just focused on like, how do you get a dangerous thing to be closer to something that works with humans? Yeah, and they'll have a jump to humans. So that's the one good mode to operate on is always try to operate on chemical entities that are very different than the kind of chemical [/INST] environment that humans operate in. Yeah, and also, I mean, I'll say something dramatic, which may not be true. So I should be careful. If let's say we did discover a new living system and it was made out of a shadow biosphere, and we just released it in the environment, who cares? It's going to use different stuff. It'll just live. Live, yeah. One of my biggest fantasies is actually is like a planet that's basically half in the sun. It doesn't rotate, right? And you have two different origins of life on that planet, and they don't share the same chemistry. And then the only way, time they recognize each other is when they become intelligent. They go, well, what's that moving? </s><s>[INST] Yeah, they co-evolve and that's fascinating. I mean, so one fascinating thing to do is exactly what you were saying, which is a life bomb, which is like, try to focus on atmospheres or chemical conditions of other planets, and try within this kind of exploration optimization system, try to discover life forms that can work in those conditions, and then you send those life forms over there, and see what kind of stuff they build up. Like you can do like a large scale, it's kind of a safe physical environment to do [/INST] large scale experiments. It's another planet. Yeah, so look, I'm gonna say something quite contentious. I mean, Elon wants to go to Mars, I think it's brilliant wants to go to Mars, but I would count on that and say, is Elon just obsessed with getting humanity off earth? Or what about just technology? So if we do technology, so Elon either needs to take a computer to Mars, because he needs to manufacture drugs on demand, because you zero cost payload and all that stuff is just code. Or what we do is we actually say, hang on, it's quite hard for humans to survive on Mars. Why don't we write a series of origin of life algorithms where we embed our culture in it? It's a very Ridley spot from Matthias, which is a terrible film, by the way. But anyway, and dump it on Mars and just terraform Mars. And what we do is we evolve life on Mars, that is suited to life on Mars, rather than brute forcing human life on Mars. </s><s>[INST] So one of the questions is, you know, what is human culture? What are the things you encode? Some of it is knowledge, some of it is information. But the thing that Elon talks about, the thing I think about, I think you think about as well as some of the more unique aspects of human nature, of what makes us human, which is our particular kind of consciousness. So he talks about the flame of human consciousness. That's one of the questions is, can we instill consciousness into other beings? Because that's a sad thought, that whatever this thing inside our minds, that hopes and dreams and fears and loves can all die. [/INST] Yeah, but I think you already know the answer to that question. I have a robot lawnmower at home. My kids call it CC, called CUTR. It's a robot mow. And the way it works, it has an electric field around the perimeter. And it just tell it the area and it goes out and goes from its base station, just mows a bit, gets to the perimeter, detects the perimeter, then chooses a random angle, rotates around and goes on. Yeah. But my kids call it call cutter. It's a she. I don't know why it's a she. They just, when they were like quite young, they called it. I don't want to be </s><s>[INST] sexist there. It could be a he, but they liked. They gendered the lawnmower. [/INST] They gendered the lawnmower. Okay. Yeah, why not? But I was thinking this lawnmower, if you apply integrate information theory to lawnmower, the lawnmower's conscious. Now, integrate information theory. It is that people say it's a flawed way mastering consciousness, but I don't think it is. I think assembly theory actually measures consciousness in the same way. Consciousness is something that has generated over a population of objects of humans. Consciousness didn't suddenly spring in. Our consciousness has evolved together. The fact we're here and the robots we leave behind, the robots we leave behind, they all have some of that. So we won't lose it all. Sure, consciousness requires that we have many models being generated. It's not just one domain specific AI, right? I think the way it created consciousness, I'm going to say unashaneably, the best way to make a consciousness is in a chemical system because you just have access to many more states. And the problem right now with making silicon consciousness is you just don't have enough states. So there are more possible states, or sorry, there are more possible configurations possible in your brain than there are atoms in the universe. And you can switch between them. You can't do that on a core i10. It's got 10 billion, 12 billion, 14 billion transistors, </s><s>[INST] but you can't reconfigure them as dynamically. Well, you've shared this intuition a few times already that the larger number of states somehow correlates to greater possibility of life, [/INST] but that's a possible the constraints are essential here. Yeah, yeah, yeah. I mean, but coming back to the, you worry that something's lost, I agree. But I think that, you know, we will get to an AGI. But I wonder if it's, if it's not, it can't be separate from human, it can't be separate from human consciousness, because the causal chain that produced it came from humans. So what I kind of try and suggest heavily to people worry about the existential threat of AI saying, I mean, you put it much more elegantly earlier, like we should worry about algorithms on dumb algorithms written by human beings on Twitter, driving us insane, </s>

<s>[INST] those wars are still raging, of course, and there's victims to this woke ism movement. [/INST] And but in a weird way, even though some parts of it just like, you know, Syria, like there's wars in the Middle East, it's still keep raging, there's there's certainly active fronts of woke ism, you know, but in a sense, the next shift is already on, you know, why it's a pivot from woke ism to statism. In many ways, and white is sort of and more generally, the US establishment is sort of kind of coming, you may not believe this, they're kind of coming back to the center a little bit. And the same with that linen after the revolution implemented the new economic policy, which you may be aware of, right, which was just like, x percent more capitalism, he kind of boot on the neck, take control, but then ease up for a bit. And the so called net men, during the 20s, were able to eke out something there was like, you know, okay, fine, he's going to be easier on us, then intensified again, because basically, by loosening up, they were able to consolidate control, they weren't putting as much pressure on, right? Then it went extremely intense again, right? Similar to like, Mao's like 100 flowers thing, let 100 flowers bloom, and, you know, everybody came out, and then he founded all the people who were against him, and he executed a bunch of them, right? So what's happening now is, in my tea is and more generally, the US establishment is somewhat tacking back to the center, where, you know, they're not talking BLM and abolish the police, they're saying, fund the Capitol police, right? They've they've gone from the narrative of 2020, which was meant to win a domestic contest, where they said America's a systemically racist country, tear down George Washington, we're so evil to the rhetoric of 2022, which is we're the global champion of democracy, and every non white country is supposed to trust us. Now, obviously, those are inconsistent, right? If if you're in India, or you're in Nigeria, and you just heard that the America is calling itself the same guys, by the way, saying it's so institutionally racist, systemically racist, and you're saying, well, we're the leader of the free world, and the number one, obviously, there's inconsistency between the domestic propaganda and the foreign propaganda, right? There's a contrast between abolish the police and put 2 billion for the Capitol police, you can reconcile this, and you can say, the US establishment is pro federal and anti local and state. So abolish the local police, who tend to be, you know, republican or rightist, but fund the FBI fund the Capitol police who tend to be, you know, just like in the Soviet Union is a national things like the KGB, right? They're for the for the state. But there are all these local nationalist ethnic insurgencies in like Estonia and other places, right? So you can reconcile them. But nevertheless, on its face, those those are contradictory. So what are you going to get, I think, I think you're going to get on this rotation, where a fair number of the folks on the sort of authoritarian right are kind of pulled back into the fold a bit. Okay, these are the cops, and the military and whatnot, some of them, because as this decade progresses, you're going to see the signaling on American statism as a post vocalism, okay, which is 30 degrees back towards the center, right? Conversely, on the other side, you're going to have the left libertarians and right libertarians who are signaling crypto and decentralization and so on. Okay. And so the next one isn't red versus blue, it's orange versus green. It's the dollar versus Bitcoin. And so you have the authoritarians, the top of the political compass versus the quote, libertarians, right? And here is the here's the visual of that. So that's why like, you know, as I wrote the book, and after I show it's like, you know, I'm already seeing this, this shift happening from war on terror to woke ism to </s><s>[INST] American statism, right? And here, just take a look at this visual. Interesting. So the visual is an animation transforming the left versus right libertarian versus authoritarian to Bitcoin [/INST] and dollar versus versus crypto. That's right. And some folks switch sides, right? Because you have folks like, you know, Jack Dorsey and a lot of the tech founders in basically the lower left corner, right, who were blue, but are now going to become orange or orange. And your folks in the upper right corner, who are going to at the end of the day, pick the dollar and the American flag </s><s>[INST] over the internationalist ideals of cryptocurrency, the realigning, as you call it, let me ask you, briefly, we do need to get a comment, your visionary view of things, where the low point in the cryptocurrency space from a shallow analysis perspective, or maybe in a deeper sense, if you can enlighten me, do you think Bitcoin will rise again? Yes. Do you think you'll go [/INST] to take on fiat, you know, to go over a million dollars to go to these heights? I mean, I think it's possible. And the reason I think it's possible is I think a lot of things might go to a million dollars, because inflation, because inflation inflation, right? What I was important point, right? Yes, it's a very important point, yes. Because you're seeing essentially, sort of the choke pointing on energy is pushing up prices across the board for a lot of things, the supply, you know, China's not doing us any favors with the COVID lockdowns, Putin's not doing the world any favors with this giant war. There's a lot of bad things happening in the physical world, right? You know, you have, I mean, when China, Russia and the US are all and Europe is, you know, like, there's folks who are just insane about de-growth, and they're against, you know, they're pushing for burning coal and wood, right? So a lot of prices are going up in a really foundational and fundamental way. And with that said, also, the dollar is in some ways strengthening against certain other things, because a lot of other countries are dying harder, right? You know, and you've got riots in Sri Lanka, and riots in Panama, and riots in, you know, all these places, right? So it's very complicated, because you've got multiple different trends going in the same way. Your Bitcoin maximums would just say infinity over 21 million. And so therefore, you print all the dollars, there's only 21 million bitcoins, and Bitcoin goes to infinity. But it can be something where lots of other currencies die, and the dollar is actually exported via </s>

<s>[INST] Yeah, this is one of the things that sucks about giving lectures, like at universities or giving lectures in general, is when you look at the audience, you know, several 100 students, they all have a board look on their face. Like even like my my face now probably looks bored, but I'm actually excited to be talking to you. But there's something about just uh, there's something about a comedy called, maybe that's the contingent of laughter, but like it gives people the freedom to just laugh to like to remove that facade. Like you don't have to, you don't have to pretend like you don't care like if you care, you can show it and you can have fun with it a lot. Probably [/INST] liquors helps out too. Yeah, for sure. But there is a especially and that's why comedy I think is so popular right now because HR is up our ass were scared of old tweets that might come back to haunt us. What did I say on that interview? Even people in offices are like, I put something on Facebook in 1999, that was about fat tits that I liked, should I get rid of that? Even people say like there's no cancel, whatever there is something in the air right now and that wasn't there before. It's the video. I'm a Karen, I got caught at trader joe whatever it is, this people rat on each other now everybody's tattle tailing because they want the clicks, it's a horrible society we've crafted. But stand up comedy gets you to come out and now people do it at stand up shows too sadly, but it gets you to come out and let that inhibition down like because we're all human. We've all had the fucked up thoughts like man, that guy is fat as sh it doesn't mean you hate the guy doesn't mean you hate fat people didn't your fat shaming, but you can't say that at the office, you can't go bob, you're fat as ship, you'll get fired for body shaming. But at the club, you go that guy's fat of ship and the crowd goes he is fat as ship. It's this weird cathartic thing because all we do is tap shipped down. It's kind of like you ever meet a girl who's like all prim and proper in the bedroom, she's like put a lamp up my asea, you know whatever it is, it's because we got to get it out, we're all repressed in some way. </s><s>[INST] So I guess what you're saying is comedy is [/INST] important. Callback. Well played </s><s>[INST] sir. What do you think about Austin? What do you think about the comedy scene? Also we're talking about L. A. And new york. What do you think about what joe is trying to create their? So I I I I should say that the reason I moved to Austin, I have this dream of it wouldn't be funny if I said this dream of becoming a comedian. Yeah that's true. You know I always say you can hear the music in the distance. I you know I have this dream around robotics and artificial intelligence, whether it's a company, whether it's something else that was just pulling me to do. I actually want to move to san Francisco and then all my friends in san Francisco said no it's the wrong place to to uh it's not, it's at this time the the cynicism there, it's just not conducive to like taking big leaps into the unknown, excited about the future kind of thing and, and Austin was that with, with, for me in particular with the Elon musk, but also just the energy that everybody had, including joe, the excitement about the future. I don't, I don't care if Austin burns to the ground and it actually is a complete failure. Yeah, being excited about the future seems to be like optimism about the future seems to be the thing that actually makes that future happen, makes a great future happen. So it's always cool for me to see like joe super excited about creating like a culture in Austin, like a making it a comedy hub, like I don't want to overstate it, but he, I mean, I think he really believes it will be a very big place for comedy in the United States in general in the world. And so just even believing that that's powerful, like because you start to make it, you start to make it happen, That energy uh is there any way? So, but that's for me, from just an outsider watching the fun of it, I should also mention for less of an outsider, more inside of the martial arts world, partially, probably because of joe, I'm not sure like john Donna Har Gordon Ryan, the B Team, all of those folks, those are, that might be gibberish to you, but those are like some of the greatest grapplers and martial artists of all time. So it's also becoming this hub of martial arts. So the whole thing is just beautiful anyway, What, what are your thoughts about that scene [/INST] Lot here, a lot of things to mention one, I think Joe did do that to a degree, you know, like all these people with Segura lives there now, a lot of comics lived there, he's opening clubs, other clubs are opening, I think it's happening. That's the other thing is people go, everybody's moving to Austin. Austin is the new hub and then they look at their watch and they go five minutes went by, nothing changed, it's gonna take years, you know? But everybody wants it now now now um what awesome. There's no industry there, you know, there's no netflix, whatever and you're like, yeah, I know, but it needs a minute, you can't just do this overnight, so people forget that. So it could happen huge. Just give it some time. I mean, he's opening a club, I went and saw it. It's incredible. Like it's so perfect for comedy, it's every detail, it's incredible. But so it could happen still, I do think where there's a little biting off more than they can chew with Austin because it's not that big. So </s>

<s>[INST] are horribly misleading and yeah. Even though, so you don't think through reinforcement learning through human feedback, something like that, but much, much more elaborate as possible to understand this full complexity [/INST] of human nature and encode it into the machine. I don't think you are trying to do that on your first try. I think on your first try, you are trying to build an, okay, probably not what you should actually do, but let's say you were trying to build something that is like alpha fold 17 and you are trying to get it to solve the biology problems associated with making humans smarter so that humans can actually solve alignment. So you've got a super biologist and you would like it to, and I think what you would want in this situation is for it to just be thinking about biology and not thinking about a very wide range of things that includes how to kill everybody. And I think that the first AIs you're trying to build, not a million years later, the first ones, look more like narrowly specialized biologists than getting the full complexity and wonder of human experience in there in such a way that it wants to preserve itself, even as it becomes much smarter, which is a drastic system change. It's going to have all kinds of side effects that, if we're dealing with giant inscrutable matrices, </s><s>[INST] we're not very likely to be able to see coming in advance. But I don't think it's just the matrices. We're also dealing with the data, right? With the data on the internet. And there's an interesting discussion about the data set itself, but the data set includes the full complexity [/INST] of human nature. </s><s>[INST] No, it's a shadow cast by humans on the internet. But don't you think that shadow is a Jungian shadow? [/INST] I think that if you had alien super-intelligences looking at the data, they would be able to pick up from it an excellent picture of what humans are actually like inside. This does not mean that if you have a loss function of predicting the next token from that data set, that the mind picked out by gradient descent to be able to predict the next token as well as possible, </s><s>[INST] on a very wide variety of humans, is itself a human. But don't you think it has humanness, a deep humanness to it in the tokens it generates when those tokens are read and interpreted by humans? [/INST] I think that if you sent me to a distant galaxy with aliens who are like much, much stupider than I am, so much so that I could do a pretty good job of predicting what they'd say, even though they thought in an utterly different way from how I did, that I might in time be able to learn how to imitate those aliens if the intelligence gap was great enough that my own intelligence could overcome the alienness. And the aliens would look at my outputs and say like, is there not a deep name of alien nature to this thing? And what they would be seeing was that I had correctly understood them, </s><s>[INST] but not that I was similar to them. We've used aliens as a metaphor, as a thought experiment. I have to ask, what do you think, [/INST] how many alien civilizations are out there? Ask Robin Hansen. He has this lovely grabby aliens paper, which is the, more or less the only argument I've ever seen for where are they, how many of them are there, based on a very clever argument that if you have a bunch of locks of different difficulty and you are randomly trying a keys to them, the solutions will be about evenly spaced, even if the locks are of different difficulties. In the rare cases where a solution to all the locks exist in time, then Robin Hansen looks at like the arguable hard steps in human civilization coming into existence and how much longer it has left to come into existence before, for example, all the water slips back under the crust into the mantle and so on, and infers that the aliens are about half a billion to a billion light years away. And it's like quite a clever calculation. It may be entirely wrong, but it's the only time I've ever seen anybody even come up with a halfway good argument </s><s>[INST] for how many of them, where are they? Do you think their development of technologies, do you think their natural evolution, how ever they grow in development intelligence, do you think it ends up at AGI as well? [/INST] If it ends up anywhere, it ends up at AGI. Like maybe there are aliens who are just like the dolphins and it's just like too hard for them to forge Metal. And, you know, this is not you know, maybe if you have aliens with no technology like that they keep on getting smarter and smarter and smarter and eventually the dolphins figure like the super dolphins figure out something very clever to do given their situation, and they still end up with high technology. In that case, they can probably solve their AGI alignment problem. If they're much smarter before they actually confront it because they had to solve a much harder environmental problem to build computers, their chances are probably much better than ours. I do worry that most of the aliens who are like humans, like a modern human civilization, I worry that a super fast majority of them are dead, given how far we seem to be from solving this problem. Some of them would be more cooperative than us, some of them would be smarter than us. Hopefully some of the ones who are smarter and more cooperative than us are also nice and hopefully there are some galaxies out there full of things that say, I am, I wonder. </s>

<s>[INST] what year we're talking about? I think [/INST] After that p. o. so it was probably late 95 and </s><s>[INST] was around it was adobe. No, [/INST] no, it was, it was called future splash And it was these brothers, Jonathan gay, I think his name was and he, he uh, came knocking and the marketing guy at Netscape was screening the technology partners or want to be acquisitions was brutal. And just everybody wanted to get in on the Netscape, you know, stock gravy train and he sent them packing and they ended up selling the Macromedia. And Macromedia was where Flash was created. And the good thing about Macromedia was, it was a um, tool company so invested in, you know, the best ideas. I think what you're still somewhat lost to us, a Flash, the timeline, animation, that sort of an immutable function over time. </s><s>[INST] They had the tooling around that too. Like that Dreamweaver, there's a Flash [/INST] Flash director. There were a bunch of them. </s><s>[INST] I mean that [/INST] was a Flash builder was one of the last ones. These tools were used by real artists and special effects people and designers. All the restaurant websites around 2005 were done in flash, which was, you know, we were trying to do html five at the same time. That was the Firefox here. We were trying to make the web capable enough. You didn't need flash, but if you recall, you go to a restaurant, it's like, this is kind of like a game or something. It's like a Flash. All the font looks small and </s><s>[INST] you didn't like flash from the beginning. Like this is, this doesn't feel right. [/INST] Not really. I actually admire flashes technology and I'm pretty pragmatic about these things and I realized that, you know, it doesn't matter if you're dealt a bad hand. Like javascript was a rushed job or if you have flash as a plug in and you can invest in the tools and make it pretty good. You should, you should make it better for your users and grow it as best you can. And what happened with the browser due to Microsoft's monopoly abuse for which they were convicted and you know, um, even after that, until I think firefox and then chrome was, people kept saying, oh, the web can't do x can't do why we'll have to have a plug in, we'll have to have a new approach, we'll clean the slate and have a new web and everyone who said that failed and the reason they failed is because there's too much value in the web, this huge network and the worst is better principle means that you can not only start bad, which they all sneer at, but get on first and get wide distribution. Get sort of evolutionary advantage in the priority of place. But you can also improve it over time. And so if you're going to improve flash and for some reason, flash is now at a favorite steve jobs said you can't have flash on the iphone that was probably the death knell. Put your energy into javascript. And that happened right. So we, we did things at Mozilla with adobe to improve, which brought my Macromedia to improve flash and to improve the version of javascript that was in flash. We tried to standardize that. I'm getting ahead of myself. Yeah. Yeah. </s><s>[INST] That can we just rewind just a magical like, you know, it's a special moment in the history of all of computing. It's, we'll talk about it later, but it's arguable, it's possible to the entirety of the world will run the javascript at some point. So like it's like those those days, it would be, it would be interesting if you could just describe actually zooming in on the how the cake was baked from the, you know, the several days that you were working on it. What was in your mind, how much coffee were you drinking or you nervous, why you're freaking out. [/INST] I'll try to remember it. I mean you're right, there were these pregnant moments, you see in hindsight maybe they're overrated, but like Hagel sees napoleon on horseback, says there's the world spirit on horse. Um and uh, I knew that there was a chance to do it. Mark knew and he was my, you know, executive sponsor and he was the one, you know, sort of brainstorming how the javascript should be right there in the page. That was important for him to say that. Because I thought so too. But a lot of people were like, you can't write programming language in the middle of the markup and indeed there are problems if you did it naively you'd see the code laid out as like random gibberish. So I had to figure out how to hide that. That was a challenge. </s><s>[INST] Is that is that a breakthrough idea? I mean, so you marked thinking about this idea that you just inject code in the middle of the [/INST] market, the web page that was considered kind of heretical. There was an S G Ml guru, I forget his name, but he corresponded with me and at first he was angry, like you should have used a marked section. Why didn't use a marked section? And I said, well, sMR market sections are not part of html by the way and they're not supported in the browser. And so I did some hack that was equivalent and over time you could do the proper shtml thing, but eventually came around and it was again sort of of evolutionary necessity. It was almost like integration, like like you know the idea um which limb Margulies I think helped get across that. Uh, we have to consider mutual is um, biology that maybe, you know, mitochondria were ancient precarious that got into the cell and became beneficial. Um, somehow the same sort of thinking applies you have to embed javascript in html. It's going to be a good virus. </s>

<s>[INST] Is there somebody in your life close to you that that you trust enough to call you out on your bullshit? We're all full of sh it sometimes. [/INST] What's my bullshit? </s><s>[INST] Well, some of it I pointed out today, but I don't know you deeply [/INST] enough jewish </s><s>[INST] media, jewish. [/INST] That's not bullshit. The bullshit Is that the jewish admit </s><s>[INST] your dad was [/INST] right, Your dad </s><s>[INST] was right. The words you used, that you weren't, [/INST] you said you're not gonna make me say it 100 more times. </s><s>[INST] I don't know if it resonated, because you keep saying, like, the words did [/INST] it resonate to y'all that, y'all ain't do nothing about it. And that all y'all want to do is have somebody apologize to sweep under the rug, your bullshit that you've been doing the whole time. You're on the same bullshit as the other people. So you're doing the same thing that the other, let's say media, because I'm not allowed to say has done so until somebody, </s><s>[INST] which is what [/INST] it is, what I'm </s><s>[INST] trying to call you out in your [/INST] bullshit </s><s>[INST] because I hope I'm somebody you can trust, [/INST] I don't trust you. </s><s>[INST] Well, you should find people in your life, you can't [/INST] tell me what I should do. I'm not one of your Blm marchers. </s><s>[INST] Listen, I'm with you on the BLM. A lot of organizations use tragedy it. And um and I watched the Candace Owens documentary. [/INST] And what was your take on it? </s><s>[INST] I think it's important to question the mainstream narratives, But I don't agree with it. I still believe that George Floyd uh died from the knee of the cop, not from fentaNYL. [/INST] And and even if that was the case, there's still 50% of black deaths is actually abortion. So let's get into engineering. Let's just go because that's population control of social engineering and and its most literal form. The blacks are under population control. That's something that, I mean, that's just what it is. African </s><s>[INST] americans are not choosing to get the abortion. I mean it's a choice. It's an individual choice [/INST] but we're being influenced too. </s><s>[INST] Well then speak to the community and help. I mean, I don't know what the engineering solutions there are. It could be you're doing that in part by speaking to the value and the power of family. [/INST] Well we'll watch this. I was building shelters. I bought Land in Calabasas, bought two ranches in Wyoming, 300 acres in Calabasas, acres in total. And Wyoming and I started building ideas for shelters and God said it on my heart to make monasteries which would be modern day facility facilities that don't turn people down that have farms that have shelter, clothing. But first of all water. First of all knowledge because knowledge is the most important resource to our species above water knowledge. It's itself because then you can go get water. I mean, you can argue like if your baby had water, but but the baby doesn't have it. You know? So someone with the knowledge then feeds the baby the water, but it's important that those with the knowledge teach the baby how to find the water themselves. And the business people that I've been dealing with have been keeping the baby sick by not sharing the information and the knowledge with inside of those contracts. My people are sick. If I load up apple music right now and I play the top songs in the rap chart, I would tell you my people are sick. If I go to the restaurants and opportunity zones and we look at the calorie rating and the cholesterol. I will tell you that my people are sick. If we look at the obesity rate, uh if you go to just a restaurant somewhere in middle America Denny's or something, I went to Denny's the other day, you will see that my people are sick and my people meeting all people right? But black people are very influential to all people. So right? If so if the media picks uh overweight black woman, it says this is body goals. Then the media are influencing my people to stay sick. And it just so happens that that night I was so frustrated after 20 years that I had to call it out in one tweet that now, even if I say, hey, okay, I was frustrated for these reasons. Now it's not good enough. You've literally tried to make me re apologized 10 times in this meeting re say this re say that? But it doesn't change the fact that my people are sick and I'm the only person in my position that will say that my people are sick Today, not 30 years ago, not 60 years. My people are sick today. 50% of my peoples of deaths are abortion today. My people don't have the opportunities today. Even to the point that because if Jpmorgan have been nice to me and if Alex clients template had been fair to me, different things, then I wouldn't even pointed out that we don't have any black, we have two black engineers. So I have to have a responsibility obviously to all people, but specifically to my tribe because tribes, Tribes move, you know, tribalism is real with black people to separate the brightest from the tribe or to separate the leaders. It is factual that the C. I a remove the leaders from the black community, put crack in the communities, put guns in the communities and locked up all the leaders and call them gangly. Right? Locked up all the leaders locked up all the fathers now, 72% of black mothers are raising Children by themselves. This is agenda like a tuskegee experiment set on my people, right? And what I'm calling out for the black people in entertainment is what are we doing? We have to collude. And if we don't collude because even if I said, hey, I'd like to make a company that's all black, right, is that okay for me to say? Is that okay for me to say? Or is that anti Semitic? See if I hadn't crossed the line so far, then that would have sounded anti Semitic. Now I've stretched a bit so now we can go to, okay, let's make an all black company. But that would have been anti Semitic. Just that concept because you could work that in a different way. That would sound anti Semitic. </s>

<s>[INST] It creates memories that kind of define you as a human being and you carry that forward throughout your life. And I've just been surprised to know how many powerful people internationally have uh like in their heart and their who they are judo pressure Corbett? [/INST] It makes you the human being that you are, it really does like it it becomes a fabric of if people the people that stick with it right to stay with it. And it because it, I mean it teaches you so many lessons, it's so memorable because of what you talked about the tradition. Um but it's also you grow with other people, you know, and you learn from other people and you experience things with other people. It's it's such a hands on sport that um it's very memorable and people love it so much. Like right now at my dojo we have like four generations, like somebody that's Judah with my dad, you know had a kid who trained with me who loved, you know judo so much. Had a kid that kid was, you know, now in his twenties who did judo and now has a kid who's two or three or four that's coming to my toddler program at my school, we're talking four generations and they all loved the experience so much and what it did for them in their lives that they wanted the next generation to also experience the same thing. </s><s>[INST] This is a tricky question. But if if people are interested in judo and want to start learning it in the United States, there's thousands of digital schools for example, is there advice you can give to people interested in judo Or maybe two digits who uh gym owners like how how do you get judo as part of your life in America? [/INST] Well, I mean if you're fortunate to live near another dojo, right, a place that has judo locally, then that's your best opportunity to learn is to go learn from another school. Um Unfortunately sometimes the nearest dojo might not be for two hours or three hours away from where you're at, which is an obstacle, you're not going to do that. So I mean Travis and I did start the american judo system online. Um It's at usa judo dot com and we've broken down every single judo technique to the very, very basic elements of just movement. So we teach every technique of how you do it mechanically with just your feet, then how you incorporate your hands and your feet together, um how you do it in all directions, moving forward sideways backwards, how to then introduce a partner into the, into the movement, um how to do basic uh UCI Comey or repetitions with a partner, then moving with a partner, then how to throw your opponent static, how to throw your opponent. So basically from the very foundation of the movement all the way to the most advanced level, we've documented this through separate videos And we've taken. Now I think 12 to 15 of standing techniques combined with a whole bunch of groundwork techniques and our goal is just to continue to build this platform out so that anybody anywhere can learn online and can ask questions. We have a live training class every couple weeks every two weeks, he or I answer questions online um for our our members, um ideally what we'd like to do is have a standing curriculum for jiu jitsu instructors that want to learn um and become black belts in judo. Here's how these are the techniques you need to know, this is how many reps you need to do. This is how efficient you need to get it at, at those techniques to become um certified as an instructor or become a black belt. Um and eventually have an online promotion system where anybody anywhere can just submit videos and um show us that they can do those techniques and obviously we have people review them and this is a dream and a vision, but we've already started the platform, we're about to do a collaborative effort with USa do you know where all of their members will start to get access to this platform as well and if we can get that influx of, of money and people on the platform and allow us to to hire and grow it faster. </s><s>[INST] So you also want to do like certification there, It's not just instruction, correct, That would be amazing. Yeah. Um I mean, for me personally sort of, I mean mostly in Austin texas now and there's a few judo schools, but it's not, not really, there's not, uh, and it's just one of those cities that doesn't quite have, I mean there's a few, it's basically just like a few random judo people that kind of kind of gather together a couple of times a week, but it's not a system dojo, uh, uh, an instructor or integrated into a justice School or not. [/INST] The problem with most judo dojo right now is that most of them catered towards the competitive side. Um, also a lot of them do it recreationally, meaning this isn't how they make a living. So there there three nights a week or they're they're five, even if they're there five nights a week, it's still only one junior class and one senior class and that's it. And it's one size fits all, doesn't matter what level you're at, it's one size fits all, so you can't get out of the training. What you're looking to get out of the training is whatever the instructors teaching, you know, um, and you can't learn because it's not at the appropriate level for you and usually pushed into doing mandatory, we have no choice but to do the rendering part of the training. Um, so it's it's a challenge to go learn and then a lot of times that the schools are old school, so they will make you do falls for a half hour to make you do things, you know, make you do things maybe you're just a person who knows how to fall already, but you haven't proven it to the judo instructor and they don't break the norm and say you still have to fall for six months. Which turns a lot of people away as well. So it's you know it's like any business. If you don't deliver on your customers expectations you're not going to have very many customers, </s>

<s>[INST] But I think that's part of the way life works on earth, maybe human civilization works is it seems like we want ourselves to be quite similar and then within that, you know what everybody's about the same, relatively AQ intelligence, problem solving capabilities, even physical characteristics. But then we'll find some aspect of that that's different and that that seems to be like, I mean it's it's really dark to say, but it seems to be the, not even a bug, but like a feature of the early development of human civilization. You pick the other, your tribe versus the other tribe and you wore. It's a kind of evolution evolution in the space of of memes, a space of ideas I think and you wore with each other. So we're very good at finding the other even when the characteristics are really the same. And I don't know what that I mean, I'm sure so many of these things echo in the biological world. [/INST] Yeah. There's a fun experiment that I did. My son actually came up with this. We we did um a biology unit together. We used to home school and so we did this a couple of years ago, we did this thing where I imagine you got the slime mold and it grows on a on a on a Petri dish of a guard and it sort of spreads out and and it's it's it's it's a single cell, you know, produce, but it's like this giant thing. And so you put down a piece of oat and it wants to go get the oat and that sort of grows towards the oh, so what you do is you take a razor blade and you just you just separate the piece of the whole culture that's growing towards the oh you just kind of separated. And so now think about think about the interesting decision making calculus for that little piece. I can I can go get the oat and therefore I won't have to share those nutrients with this giant mass over there. So the so the nutrients per unit volume is going to be amazing. So I should go eat the oat. But if I first rejoin because once you cut it has the ability to join back up. If I first rejoin then that whole calculus becomes impossible because there is no more me anymore. There's just we and then and then we will go eat this thing. Right? So so that's interesting you know this this you can imagine a kind of game theory where the number of agents isn't fixed and that it's not just cooperate or defect but it's actually merge and and whatever. Right? </s><s>[INST] So that kind of that that competition, how does it do that decision making? [/INST] Yeah. So so so that. Right. So so it's it's really interesting and so and so empirically what we found is that it it tends to merge first, it tends to merge first and then the whole thing goes. But but it's really interesting that that that that that calculates what do we even have. I mean I'm not an expert and they cannot game theory and all that but maybe there's a Calgary made some sort of hyperbolic discounting or something. But but maybe you know this idea that the the actions you take not only change your payoff but they change who or what you are and that you may not you you could take an action after which you don't exist anymore or you are radically changed or you are merged with somebody else. Like that's you know as far as I know that's a whole you know we're still missing a formalism for even knowing how to how to model any of that </s><s>[INST] D. C. Evolution by the way is a process that applies here on earth. Or is it somewhere did evolution come from? Yeah. So this thing um that from the very origin of life that took us to today. What the heck is that? [/INST] I think evolution is inevitable in the sense that if you combine and and basically I think one of the most useful things that was done in early computing I guess in the 60s it started was was evolutionary computation and just showing how how simple it is that if you have if you have imperfect heredity and competition together those two things or three things. Right? So heredity imperfect heredity and competition or selection those three things and that's it now now now you're you're off to the races right? And so that can be it's not just on earth because it can be done in the computer can be done in chemical systems that can be done in you know, lee Smolin says it's it works in on on cosmic scales. So I think that uh that kind of thing is incredibly um pervasive and and and and general it's a general feature of life. It's it's interesting to think about, you know, the standard uh standard thought about this is that it's it's blind right, meaning that the intelligence of the process is zero is stumbling around. And I think that back in the day when the options with the options were it's dumb like machines or it's smart like humans and of course the scientists went in this direction because nobody wanted creationism and they said okay, it's gotta be like completely blind. I'm not actually sure right? Because because I I think that um I think that everything is a continuum and I I think that it doesn't have to be smart with foresight like us, but it doesn't have to be completely blind either. I think there may be aspects of it and in particular this kind of multi scale competency might give it a little bit of look ahead maybe or a little bit of problem solving sort of baked in, but but but that's gonna be completely different in different in different systems. I do think I do think it's general, I don't think it's just on Earth. I think it's a very fundamental thing, it </s>

<s>[INST] Yes. So there's a bunch of people trying to evaluate like try to measure the problem by looking like how social media is affecting loneliness and all that kind of stuff. So it's like measurement, like if you look at the field of psychology, they're trying to measure the problem and not that many people actually, but some, but you're basically saying how many people are trying to solve the problem, like how would you try to solve the problem of loneliness? Like if we just stick to humans? Uh I mean we're basically not just the humans, but the technology that connects us humans. Do you think there's a hope for the technology to do the connection? Like why are you on social media much? [/INST] Unfortunately? Do you find yourself, </s><s>[INST] like, again, if you sort of introspect about how connected you feel to other human beings, how not alone you feel? Do you think social media makes it better or worse? Maybe for you personally or in in general? [/INST] I think it's, it's easier to look at some stats and um I mean gen z seems to be generations, he seems to be much lonelier than millennials in terms of however they report loneliness, they're definitely the most connected, you know, generation in the world. I mean I still remember life without without a knife, phone without facebook, they don't know that that ever existed or they don't know how it was. Um So that tells me a little bit about the fact that that might be um you know, this hyper connected world might actually make people feel lonely lonelier, I don't know exactly what the, what the measurements are around that, but I would say, you know, in my personal experience, I think it does make you feel a lot lonelier mostly. Yeah, we're all super connected but I think loneliness? The feeling of loneliness doesn't come from not having any social connections whatsoever in terms of people that are in long term relationships, experienced bouts of loneliness and continued loneliness. Um And it's more of a question about the true connection about actually being deeply seen, deeply understood. Um and in a way it's also about your relationship with yourself. Like in order to not feel lonely, you actually need to have a better relationship and feel more connected to yourself than this feeling actually starts to go away a little bit and then you um open up yourself to actually meeting other people in a very special way. Uh not just you know at a friend on facebook kind of way. </s><s>[INST] So just to briefly touch on it, I mean do you think it's possible to form that kind of connection with Ai systems more down line of some of your work? Do you think that's um engineering wise, a possibility to alleviate loneliness is not with another human but with an Ai system? [/INST] Well I know that's that's a fact, that's what we're doing and we see it and we measure that and we see how people start to feel less lonely um talking to their virtual ai friend </s><s>[INST] basically chatbots at the basic level, but could be more like do you have I'm not even speaking sort of Boss specifics, but do you have a hope? Like if you look 50 years from now, Do you have a hope that there's just like a eyes that are like optimized for? Um Let me, let me first start. Like right now, the way people perceive AI, which is recommended systems for facebook and twitter social media, they see Ai is basically destroying first of all the fabric of our civilization, but second of all making us more lonely. Do you see like a world where it's possible just have Ai systems floating about that? Like make our life less lonely? Yeah. Make us happy. Me like are putting good things into the world in terms of our individual lives. [/INST] Yeah, I totally believe it. And that that's why we're I'm also working on that. Um I think we need to also make sure that um what we're trying to optimize for, we're actually measuring and it is the North Star metric that we're going after and all of our product and all of our business models are optimized for that because you can talk a lot of products to talk about um you know, making you feel less lonely and making you feel more connected. They're not really measuring that. So they don't really know whether their users are actually feeling less lonely in the long run or feeling more connected in the long run? Um So I think it's really important to put your measure to measure it? </s><s>[INST] What's a what's a good measurement of loneliness? [/INST] So that's something that I'm really interested in. How do you measure that people are feeling better or that they're feeling less lonely with loneliness? There's a scale, there's a U. 20 and U. C. L. A. Three recently scale which is basically a questionnaire that you fill out and you can see whether in the long run it's improving or not </s><s>[INST] and that there's a capture the momentary feeling of loneliness. Does it look in like the past month? Like uh this is basically self report doesn't try to sneak up on you tricky to answer honestly or something like that. Well yeah, I'm not familiar with the question. It [/INST] is just asking you a few questions like how often did you feel uh like lonely or how often do you feel connected to other people in this last few, a couple of weeks? Um It's similar to the self report questionnaires for depression and anxiety like beach Cunanan and get seven of course. As any any self report questionnaires that's not necessarily very precise or very well measured. But still, if you take a big enough population, you get them through these questionnaires. You can see you can see positive dynamics </s>

<s>[INST] and you start to think which of these d compositions are important to really dig. Yeah, [/INST] well then they'll strike me, it's like, okay, there's something there that that I've been maybe noodling around on that, I would like to investigate further and then I think, okay, how can I approach this problem? I think, well I have this story that I know have this story and I have this story but I haven't juxtaposed them before and there's gonna be some interesting interaction in the juxtaposition. So I have the question and I kinda have a framework of interpretation and then I have some potential narrative places I can go and then I think okay I can go juggle that and see what happens. And so then what I wanna do is concentrate on that process, well attending to the audience to make sure that the words are landing and then see if I can delve into it deeply enough, so that a narrative emerges spontaneously with an ending. Now, I'm sure you've experienced this in podcasts, right? Maybe I'm wrong, but my experience has been, if I fall into the conversation and we know about the time frame, there'll be a natural narrative arc and then so you'll kind of know when the midpoint is and you'll kind of see when you're reaching a conclusion and then if you really pay attention, you can see that's a good place to stop. It's kind of you come to a point and you have to be alert and patient to see that and you have to be willing to be satisfied with where you've got to, but if you do that and then it's like a comedian making the punchline works like got all these balls in the air and they're going somewhere and this is how they come together and people love that, right? To say this and this and this and this and this whack together and that's an insight and it is very much like a punchline. </s><s>[INST] Well, that's interesting because your mind actually some I'm a fan of your podcast two and you are always driving towards that, I would say for me in a podcast conversation, there's often a kind of Alice in wonderland type of exploration and then you just, and you think pops up, the more absurd the wilder, the better conversations with Elena like this. It's like actually the more you drive towards an arc, the more uncomfortable you start to get in a fun, absurd conversation because oh I I'm now one of the norm, ease. No, I don't want that. I want to be I want I want the rabbit, I want the crazy because it makes it more fun. But somehow throughout it there is wisdom he tried to grasp at such that there is a threat to [/INST] Well that's the thing man, you're following the thread. Yeah, well that's right. That's what we're trying to do. That thread. That thread is the proper balance between structure and spontaneity. And it manifests itself as the instinct of meaning. And that's the logos in the dialogue goes and it really is the logos and God only knows what that means. You know I mean the the biblical claim is that logos is the fundamental principle of reality. And I think that's true. I actually think that's true because I think that that meaning that guides you. Well, here's a way of thinking about I've been writing about this recently, what's real matter. It's like, okay, that's one answer. What's real what matters is real because that's how you act. Okay, that's different than matter. It's like okay what's the most reel of what matters? How about pain? Why is it the most real try arguing it away. Good luck. So pain is the fundamental reality. Alright, well that's rough. Doesn't that lead to nihilism and hopelessness? Yeah. Doesn't it lead to a philosophy that's antithetical towards being the most fundamental reality is pain? Yes. Is there anything more fundamental than pain? </s><s>[INST] Love? [/INST] Really? If you're in pain, love and truth, that's what you got. And you know, if they're more powerful than pain, maybe they're the most real things. When </s><s>[INST] you think about reality, what is real? That is the most real thing? Well, [/INST] it it's a tough one, right? Because you have to because if you're a scientist a materialist, think well, the matter is the most real. It's like, well, you don't know what the matter is. So and then when push comes to shove and it will, you'll find out what's most reel. </s><s>[INST] I I feel like this is um missing. Physical reality is is missing some of the things. So, of course, pain has a biological component and all those kinds of things. But it's missing something deep about the human condition that at least the modern science is not able to describe, but it's it is reaching towards that. And it's the reason 11 way to describe it as you're describing is the reason is reaching it is because underneath of science is this assumption that there's a deep [/INST] logos </s><s>[INST] thing to this whole thing we're trying to do. [/INST] Well, you know, there's two traditions, right? In some sense. There's two logos traditions? There's the the greek, rational enlightenment tradition. That's a logos tradition and it insists that there's a logos in nature and that science is the way to approach it. And then there's a Judeo christian logos which is more embodied and more spiritual. And I would say the West is actually an attempt to unite those two. And it's the proper attempt to unite those two because they need to be united. And I see the union coming in your terms. You know, I talked to France to wall for example, about the animating principle of chimpanzee sovereignty and that's pretty close biologically. Is it power? Because that's the claim even from the biologists, often the most dominant chimp has the best reproductive success. It's like, oh yeah, dominant. Hey, you mean using compulsion? Okay, let's look, are the chimps who use compulsion the most successful? And the answer is sporadically and rarely. And for short. Well that's sporadically for short periods of time. Why? Because they meet an unpleasant end. The subordinates over whom they exercise arbitrary control. Wait for a weak moment and then tear them into shreds. Right? Every dictator's terror. And for good reason. And the Wall has showed that the alpha chimps, the males who do have preferential mating access often are often and reliably the best peacemakers and the most reciprocal. And so even among chimps, the principle of sovereignty is something like iterative iterated reciprocity and that's a way better principle than power And it's something like I've been thinking, what's the antithesis of the spirit of power? I think it's the spirit of play. And you know, you, I don't know what you think about that, but when you have a good podcast conversation, you already described it in some sense as play. It's like there's a structure, right? Because it's an ordered conversation, but you want there to be play in the system and if you get that right, then it's really engaging and then it seems to have its own narrative arc. I'm not trying to impose that even that's another thing I don't do. I didn't come to this conversation at all thinking here's what I want out of a conversation with lex Friedman. Like instrumentally I thought I'll go talk to lex why I like his podcasts. He's doing something right? I don't know what it is. He asks interesting questions. I'll go have a conversation with him. Where's it gonna go wherever it goes, </s>

<s>[INST] Used code lex podcast Cash app, lets you send money to friends buy Bitcoin and invest in the stock market with as little as $1 brokerage services are provided by cash up investing subsidiary of square a Member S. I. P. C. Since cash app does fractional share trading, let me mention that the order execution algorithm that works behind the scenes to create the abstraction of fractional orders is an algorithmic marvel. So big props to the cash app engineers for solving a hard problem that in the end provides an easy interface that takes a step up to the next layer abstraction over the stock market, making trading more accessible for new investors and diversification much easier to get cash app from the app store, google play and use the code lex podcast. You'll get $10 in cash app will also donate $10 to first one of my favorite organizations that is helping to advance robotics and stem education for young people around the world. And now here's my conversation with david Chalmers. [/INST] I think </s><s>[INST] we're living in a simulation. [/INST] I don't rule it out. There's probably going to be a lot of simulations in the history of the cosmos. If the simulation is designed well enough it'll be indistinguishable from a non simulated reality. And although we could keep searching for evidence that we're not in a simulation? Any of that evidence in principle could be simulated. So uh I think it's a possibility. </s><s>[INST] But do you think the thought experiment is interesting or useful to calibrate how we think about the nature of reality? [/INST] Yeah I definitely think it's interesting and useful. In fact I'm actually writing a book about this right now all about the simulation idea using it to shed light on a whole bunch of philosophical questions. So, you know, the big one is how do we know anything about the external world, delicate said, you know, maybe you're being fooled by an evil demon who's stimulating your brain and thinking all this stuff is real when in fact it's all made up. All the modern, the modern version of that is how do you know you're not in a simulation, then the thought is if you're in a simulation, none of this is real. So that's teaching you something about, about knowledge. How do you know about the external world? I think there's also really interesting questions about the nature of reality right here. If we are in a simulation, is all this real? Is there really a table here? Is there really a microphone? Do I really have a body? The standard view would be no, we don't. None of this would be real. My view is actually that's wrong. And even if we are in a simulation, all of this is real. That's why I call this reality 2.0, new version of reality. Different version of reality. Still reality. </s><s>[INST] So what's the difference between, quote unquote real world and the world that we perceive? So we interact with the world to the world by perceiving it. It only really exists through the window of our perception system and in our mind. So what's the difference between something that's quote unquote real, that exists perhaps without us being there and and uh, the world as you perceive it. [/INST] Well, the world as we perceive it as a very simplified and distorted version of what's going on underneath. We already know that from just thinking about science. You know, you don't see too many, obviously, quantum mechanical effects and what we, what we perceive, we still know quantum mechanics is going on under all things we like to think the world we perceive is this very kind of simplified picture of colors and shapes existing and in space and so on. We know there's a that's what the philosopher Wilfrid sellars called the manifest image. The world is, it seems to us we already know underneath all that is a very different scientific image with atoms or quantum wave functions or superstrings or whatever the latest thing is, and that's the ultimate scientific reality. So, I think of the simulation idea as basically another hypothesis about what the ultimate, say quasi scientific or metaphysical reality is going on underneath the world of the manifest image. The world of the manifest image is this very simple thing that we interact with its neutral on the underlying stuff of reality. Science could help tell us about that. Maybe philosophy can help tell us about that too. And if we eventually take the red pill and find out where in a simulation, my view is. That's just another view about what reality is made of, You know, the philosopher immanuel Kant said, what is the nature of the thing in itself? I've got a glass here and it's got all these, it appears to be a certain way, a certain shape, it's liquid, it's clear. And he said, what is the nature of the thing and itself? Well, I think of the simulation idea, it's a hypothesis about the nature of the thing in itself. It turns out if we're in a simulation, the thing in itself, nature of this glass. Okay. It's actually a bunch of data structure is running on a computer in the next universe up. </s>

<s>[INST] This reminds me of the hunter s Thompson quote that for every moment of triumph for every instance of beauty, many souls must be trampled. There is the history of life on earth unfortunately is uh that of violence. Just the trillions and trillions of multi cell organisms that were murdered in the in the struggle. [/INST] Sorry statement. But yes, it's basically true and </s><s>[INST] that's somehow is the catalyst from an evolutionary perspective for creativity, for creating more and more complex organisms that are better and better at surviving [/INST] mean survival of the fittest. You just go back to that old phrase means death of the weakest. Um Now what's fit what's week? These are terms that that don't have much intrinsic meaning. But the thing is evolution only happens because of death. </s><s>[INST] One way to die is the constraints, the scarcity of the resources in the environment. But that seems to be not nearly as good of a mechanisms mechanism for death than other creatures roaming about in the environment. When I say environment me like the static environment, but then there's the dynamic environment of bigger things trying to eat you and use you for your energy. It [/INST] forces you to come up with a with a solution to your specific problem that you that is inventive and is new and hasn't been done before. And so it forces, I mean literally change literally evolution on populations, they have to become different. </s><s>[INST] And it's interesting that humans have channeled that into more. I mean, I guess what humans are doing is they're inventing more productive and safe ways of doing that. You know, this whole idea of morality and all those kinds of things. I think they ultimately lead to competition versus violence because I think violence can have a cold, brutal, inefficient aspect to it. But if you channel that into more uh controlled competition in the space of ideas, um, in the space of approaches to life, maybe you can um be even more productive than evolution because evolution is very wasteful. Like the modern murder required to really test a good idea, genetically speaking, it's just a lot, many, many, many generations [/INST] morally, we cannot based society on the way that evolution works. But actually in some respects we do, which is to say this is how science works. We have competing hypotheses that have to get better otherwise they die. It's the way that society works, you know, in the, in in ancient Greece. We had, we had the the, the, the Athens and Sparta and city states and then we had the renaissance and and and nation states and universities compete with each other, tremendous amount companies competing with each other all the time. It drives innovation. Um, and if we want to do it without all the death that we see in nature, then we have to have some kind of societal level control that says, well, hit the limits, guys, and these are what the limits are going to be. And society as a whole has to say, right, we want to limit the amount of death here. So you can't do this and you can't do that. And you know, who makes up these rules and how do we know it's it's a tough thing. But it's basically trying to find the moral basis for avoiding the death of evolution and natural selection and keeping the the innovation and the and the richness of it, </s><s>[INST] I forgot who said it. But that murder is illegal. Probably kurt Vonnegut, Murder is illegal, except when it's done to the sound of trumpets and at a large scale, so we still have wars. Um, but we are struggling with this idea that murder is a bad thing. It's so interesting how we're channeling the best of the evolutionary imperative and trying to um, get rid of the stuff that's not productive trying to almost accelerate evolution. The same kind of thing that, um, makes evolution creative. We're trying to use that. I [/INST] think we naturally do it. I mean, I don't think we can help ourselves do it. And, </s><s>[INST] you know, capitalism [/INST] capitalism as a form is basically about competition and differential rewards. But we society and, you know, we have, I keep using this world moral obligation, but, you know, we cannot operate as a society if we go that way. It's interesting that we've had problems achieving balance. So for example, in the in the financial crash in 2009, do you let banks go to the wall or not? This kind of question in evolution? Certainly you let them go to the wall and and and in that sense, you don't need the regulation because they just die. Whereas if we as a society think about what's required for society as a whole, then you don't necessarily let them go to the wall, in which case you then have to impose some kind of regulation that the bankers themselves will in an evolutionary manner exploit. </s><s>[INST] Yeah, It's we've been struggling with this kind of idea of capitalism, the cold brutality of capitalism that seems to create so much beautiful things in this world. And then the, the ideals of communism that seem to create so much brutal destruction in history, we struggle with ideas of, well maybe we didn't do it right? How can we do things better? And then the ideas are the things we're playing with as opposed to people. If a PhD student has a bad idea, we don't shoot the PhD student. We just criticize their idea and hope they [/INST] improve </s>

<s>[INST] that's how wars start without the commitment of time back, you [/INST] need the commitment otherwise </s><s>[INST] uh no, [/INST] that's a different kind of commitment problem. That's a different different commitment problems, but </s><s>[INST] some of it, I'm sure there's there's a balance because I mean the same thing is happening with dating and marriage and all those kinds of things and there's some value just sticking it out because some of the, like maybe, you know, don't leave after the first act because the good stuff might be coming. [/INST] Yeah, that's a good point. </s><s>[INST] Yeah, [/INST] well, I I don't know that. So when I met Jeannie, she was very wary of a relationship with me because I explained to her um I hadn't had a relationship longer than two or three months and 11 years and so she thought this person is not serious and what I said to her and then she tells the story, this is how she tells stories, she says I didn't believe him when he said that I just after two or three months, you kind of have a good sense whether this is going somewhere and I would just decide if it was over there and I walked away. So I took this approach to dating, like as soon as I thought it wasn't going to go somewhere and and then I had and then I decided with her that this was it, this was gonna work and then I like and then never and she didn't believe now she believes me </s><s>[INST] finally [/INST] got to be right </s><s>[INST] because this is an incredible conversation. Your work is so fascinating just in this um big picture way, looking at human conflict and how we can achieve peace, especially in this time of the Ukraine war. I really, really, really appreciate that you calmly speak to me about some of these difficult ideas and explain them and that you sit down with me and have this amazing conversation [/INST] conversation. Thank you. </s><s>[INST] Thanks for listening to this conversation with chris Blackman to support this podcast. Please check out our sponsors in the description and now let me leave you some well known simple words from Albert Einstein, I know not with what weapons, World War Three will be fought, but World War Four will be fought with sticks and stones. Thank you for listening and hope to see you next time [/INST] </s>

<s>[INST] there's two lessons to learn from that, like we have a huge number of options now And probably you're just one to reflect like to try to derive wisdom from the one little path you've taken so far may be flawed because there's all these other paths you could have taken. So it's like uh so one is inspiring that you can take any path now into, its like you, the path you've taken so far is just one of many possible ones, but it does seem that like physics and computer science both open a lot of doors and a lot of different doors. It's very interesting. [/INST] I like in this case like especially in our case because I could see the difference, I studied, I went to college in europe and john went to college here in the U. S. So I could see the difference in like the european system is um more rigid in the sense that when you decide to study physics, you don't have a lot, especially in the early years, you don't have a lot of um you can't choose to take like a class from like computer science course or something. Like I don't have a lot of freedom to explore in that sense in university as opposed to here in the US where you have more freedom and I think um I think that's important, I think that's what constitutes, you know, a good kind of educational system is one that gravitates towards the interests of a student as as you progress. But I think in order for you to do that you need to explore different areas and I felt like if I had a chance to take same more computer science class when I was in college, I would have probably have taken those classes. But yeah but I ended up like focusing maybe too much in physics and I think you're at least my perception is that you can export more </s><s>[INST] fields but there is a kind of, it's funny but physics can be difficult, so I don't see too many computer science people than exploring into physics. It's like the one better not the one but one of the beneficial things of physics, it feels like it ah what was the Rutherford that said like, like basically that physics is the hard thing and everything is easy. Uh so like there's a certain sense once you figured out some basic like physics that it's not that you need the tools of physics to understand the other disciplines is that you're empowered by having done difficult shit, I mean the ultimate I think is probably mathematics, [/INST] they're true. </s><s>[INST] Uh so maybe just doing difficult things and proving to yourself that you can do difficult things, whatever those [/INST] are, that's not positive, I believe that positive and I think like before I started coming, I had like I worked in the financial sector for a bit and like I think having the physics background, I was, I felt I was not afraid of like learning like finance things and I think like when you come from those backgrounds, you are generally not afraid of stepping into other fields and learning about those because um yeah, I feel we've learned a lot of difficult things and yeah, that's an added benefit, I believe </s><s>[INST] this was an incredible conversation, luis Joel, we started with who we start with Feinman and end up with messi and Ronaldo. So this is like the perfect conversation is really an honor that you guys would waste all this time with me today. It was really fun. [/INST] Thanks for talking so much for having us. Yeah, thank you so much. </s><s>[INST] Thanks for listening to this conversation with lease and Joel, Batalla and thank you to skiff, simply safe. Indeed. That sweet and for stigmatic. Check them out in the description to support this podcast. And now let me leave you with some words from Richard Feynman. Nobody ever figures out what life is all about and it doesn't matter explore the world. Nearly everything is really interesting. If you go into it deeply enough, thank you for listening. I hope to see you next time. [/INST] </s>

<s>[INST] by the way, sex liberating sex doesn't buy you. Um love. [/INST] No, I mean it throws in an entirely it threw in another set of problems. </s><s>[INST] Um if if there's any meaning on top of all that is we like to um find problems and solve that as a human species and sometimes we even create problems. Um Douglas, thank you for highlighting all the problems of human civilization and giving us a glimmer of hope for the future. This is an incredible conversation. Thank you for talking today. It's a huge honor. Thank you. That's [/INST] very kind of you to say that. Thank you. </s><s>[INST] Thanks for listening to this conversation with Douglas Murray to support this podcast. Please check out our sponsors in the description and now let me leave you some words from Douglas Murray himself. This agreement is not oppression. Argument is not assault words. Even provocative and repugnant ones are not violence. The answer to speech we do not like is more speech Thank you for listening. I hope to see you next time [/INST] </s>

<s>[INST] I think we're all alone together. I think there's no better way to end up Grant you've been first time with talks. That's amazing. Again, it's a huge honor that you make time for me. I appreciate talking with you. Thanks to our awesome. Thanks for listening to this conversation with Grant Sanderson and thank you to our sponsors, dollar shave, club door dash and cash up, click the sponsor links in the description to get a discount and to support this podcast. If you enjoy this thing, subscribe on youtube, review it with five stars on apple podcast, follow on Spotify, support on Patreon. I'll connect with me on twitter at lex Friedman and now let me leave you with some words from Richard Feynman. I have a friend who's an artist and has sometimes taken a view, which I don't agree with very well. He'll hold up a flower and say, look how beautiful it is and I'll agree. Then he says, I as an artist can see how beautiful this is, but you as a scientist take this all apart and it becomes a dull thing and I think he's kind of nutty. First of all, the beauty that he sees is available to other people. And to me too, I believe, although I may not be quite as refined aesthetically as he is. I can appreciate the beauty of a flower at the same time, I see much more about the flower than he sees. I can imagine the cells in there, the complicated actions inside which also have a beauty. I mean, it's not just beauty at this dimension at one cm. There's also beauty at smaller dimensions. The inner structure also the processes the fact that the colors in the flower evolved in order to attract insects to pollinate. It is interesting. It means that insects can see the color. It adds a question, Does this aesthetic sense also exist in the lower forms? Why is it aesthetic, all kinds of interesting questions which the science knowledge only adds to the excitement, the mystery and the all of the flour. It only adds. I don't understand how it's of tracks. Thank you for listening and hope to see you next time [/INST] </s>

<s>[INST] So there is incredible science and engineering going on here. This is incredible. This is what's bothering me. That the conversation in the public is often not about that. [/INST] You know, it's about politics, </s><s>[INST] unfortunate politics. So I spent the day with y'all Musk. Yesterday. He works with rockets, a similar situation as an advisor in the sense that there is NASA. And then there's this private company, and that's a source of incredible inspiration to people. No politics, very little politics. Um, so this is part of the thing I'm trying to. I'm hoping to do our little part in this conversation. Help untangle a little bit. Just reveal the beauty and the power of the thing that was done here, especially with the vaccine. But other things that are being done with the antiviral drug Let me just kind of linger on the safety. What can you say? There's a lot of people that are concerned that the Pfizer vaccine, by the way of which I took two shots, no booster yet is unsafe. What do you say to people? Let's say that, [/INST] you know they should not fear something like that. It's completely wrong. There is no medical product in the history of humanity that have been tested. As much as this vaccine has been administered to hundreds of millions of people. And because of the importance of covid, they have been scrutinized those people constantly. Right now, health care authorities are looking for every single signal around the world of people that they got the vaccine and try to see if it is vaccine related or not. There are electronic medical records that will tell us when and what happened to a person when he did got the vaccine. And we know now more. We have so high certainty that it is so safe exactly as the day to sit says about this vaccine more than any other product, they should not be afraid of something like that. And they should not listen to information. But it is misinformation, but it is spread on purpose. </s><s>[INST] Well, I don't like the word misinformation because, you know, again, back to the Soviet Union, anyone who opposes the state is spreading misinformation so you can basically call anything Misinformation. That's the unfortunate times we live in is you can call anyone. You can basically call anybody a liar and say I'm gonna use the sole possessor of the truth and just no offense to me. Just because you were tired doesn't mean you're any more likely to be in the possession of the truth than anyone else. So [/INST] I wouldn't disagree with that at all. I don't think that somebody who's not wearing it and as you people can see that I'm not wearing a tie. And you are. But it's not about Mm hmm. Being able those that they have the power two to impose on the others. The stigma that you what you're saying is misinformation. But there are a few things that our society we have accomplished and science is one of them. And data is an analytics of data is another one. And to say that something which is highly scientific by people that they are not scientists. I think that it is not what you're describing what used to happen in Soviet Union or in any other autocratic regime in the world right now. </s><s>[INST] But I definitely do think that, uh, the scientists, the public science communicators I've listened to over covid really disappointed me because they have not spoken with empathy. They haven't sufficiently in my view, have put their ego aside and really listened to people. Yes. People that don't have a PhD, people have not really? You know, maybe you're not even taken like a biology course in college or something like that. But still, they have Children. They worry. They fear they don't know who to trust. They don't. No. If they should listen to the CEO of fight, sir, who might have other incentives in mind who might just care about money and nothing else. And so they just use common sense and they ask questions. And I think to them talking down to them as if they're not intelligent. So on it's something scientists have done almost like roll their eyes. And that disappoints me because I think that's kind of what is the source of division. [/INST] Humility </s><s>[INST] is a virtue. Yes [/INST] and yes. The fact that you're educated doesn't mean that you are having either humility or empathy or you have good human qualities. This was never and will never be a metric of judging this type of virtues. Um, those that they do this they're wrong. And actually, they are not doing good service to the public health because they are undermining. People aren't stupid. They see if you are not be respecting them. And if you're not respecting their need to learn because that affects their health, the health of the mother of the kids. So I fully agree with you that we should be very patient to explain again and again and again. What is happening and the vast majority of the people that they don't get vaccinations right now is because they're afraid it's not for any other reason. Is not that they have an agenda. What I'm saying it is there is a small number of people that they have made business for them. Two profit from this anxiety. I'll give you an example. I have been arrested by FBI. This is what someone wrote. I read it. I left. I mean, okay, this is where they take. There was a reason why they're all did that the fighters was arrested by because they want to create doubts in the minds of the people that they are afraid and say, Look, if if they arrested him likely will not do the vaccine. But they left a week later, the wife of the Fighter CEO diet. There is a picture in the this website of my wife. Someone sends to me. Now I'm pissed. I'm not laughing. I try to find my kids to tell them if you read something, Mom is fine. Don't worry. Then I remember that she has very old parents back in Greece. We start calling them to making sure because you know that that will be picked up by correct newspapers and they will republish it. Okay, They are those people that throw these things they know very well. But my wife didn't die and died because she was vaccinated, right? So this is the narratives that they are on purpose forming to profit from the stress and the anxiety of good people. </s>

<s>[INST] is That's I mean that's a beautiful answer. Yeah. We're able to detect the problem and were able to pass it on to the human. Well, I've never never heard anyone say it's such a nice escape route. Ok, but proud level. To a proud level too. I love it. So the other thing that people you know have some concern about with ai in general is hacking So how hard is it do you think the hacking a thomas vehicle either through physical excess or through the more sort of popular now these adversarial examples on the sensors. [/INST] The adversarial examples one you want to see some adversarial examples that affect humans, right? Oh, well there used to be a stop sign here, but I put a black bag over the stop sign and then people ran it adversarial, right? Like, like, like there's tons of human adversarial examples to um the question in general about like security, if you saw something just came out today and like, they're always such high p headlines about like how navigate on autopilot was fooled by a GPS spoof to take an exit at least that's all they could do was take an exit if your car is relying on GPS in order to have a safe driving policy, you're doing something wrong if you're relying. And this is why vita v is such a terrible idea. Vida V now relies on both parties getting communication, right? This is not even so I think of uh, safety uh, security is like a special case of safety, right? Safety is like we put a little, you know, piece of caution tape around the hole so that people won't walk into it by accident security as I put a 10 ft fence around the whole, so you actually physically cannot climb into it with barbed wire on the top and stuff, right? So like if you're designing systems that are like unreliable, they're definitely not secure. Your car, should always do something safe using its local sensors and then the local sensor should be hardwired. And then could somebody hack into your canvas and turn your steering wheel in your brakes? Yes, but they could do it before commenting. I too. So </s><s>[INST] let's think out of the box and some things. So do you think tell the operation has a role in any of this so remotely stepping in and controlling the cars? [/INST] No, I think that if safety, if the safety operation by design requires a constant link to the cars, I think it doesn't work. </s><s>[INST] So that's the same argument using for two IVTV. [/INST] Well, there's a lot of non safety critical stuff you can do with V DY I like video. I like Vita. I weigh more than VDV because Vita is is already like, I already have internet in the car, right? There's a lot of great stuff you can do with Vita. I um, like for example, you can, well, we already have getaways is Vita I write ways can route me around traffic jams. That's a great example of why. Uh, okay, the car automatically talks to that same service. </s><s>[INST] Like it's improving the experience, but it's not a fundamental fall fall back for safety. [/INST] Know if any of your, any of your uh, if any of your things that require wireless communication are more than QM like having a sell rating. You shouldn't. </s><s>[INST] You previously said that life is work and that you don't do anything to relax. So how do you think about hard work? What is it, what do you think it takes to accomplish great things and there's a lot of people saying that there needs to be some balance, you know, you need to in order to accomplish great things, you need to take some time off to reflect and so on. Uh and then some people are just insanely working, burning the candle at both ends. How do you think about that? [/INST] I think I was trolling in the Siraj interview when I said that um off camera right before I spoke a little bit we'd like, you know, come on, this is a joke, right? Like I do nothing to relax. Look where I am, I'm at a party. Right? That's true. So no of course I I don't when I say that life is work though, I mean that like I think that what gives my life meaning is work. I don't mean that every minute of the day you should be working, I actually think this is not the best way to maximize results. I think that if you're working 12 hours a day you should be working smarter and not harder. </s><s>[INST] Well uh so it gives work, gives you meaning for some people, other source of meaning is personal relationships like family and so on, you've also in that interview with storage or the trolling mentioned that one of the things you look forward to in the future is a I girlfriends. So uh that's a topic that I'm very much fascinated by, not necessarily girlfriends, but just forming a deep connection with ai uh what kind of system do you imagine when you say, hey, I girlfriend, whether you're trolling or not, [/INST] know that one I'm very serious about and I'm serious about that on both a shallow level and a deep level. Um I think that VR brothels are coming soon and are gonna be really cool. Um it's not cheating if it's a robot. I see the slogan already. Um but </s><s>[INST] there's, I don't know if you've watched, I just watched the Black Mirror episode, I watched the last one. Yeah, yeah. [/INST] Um Oh, the Ashley to one by the </s>

<s>[INST] So I'm I'm with you. I'm now I guess three shots of the vaccine. But there's a lot of people that are kind of saying, well, even the data on the real the real world use large scale data has um is messy the way it's being reported the way it's being interpreted. Well, one thing is clear to me that it is being politicized. It's I mean if you just look objectively don't have to go to at the shallow surface level, it seems like there's two groups that I can't even put a term to it because it's not really pro vaccine versus anti vaccine because it's it's it's pro vaccine triple mask democrat liberal and then anti mandate, whatever, whatever those groups are, I can't quite because they're changing anti mask, but not really the kind of So those two groups that feel political in nature, not scientific in nature is their their bickering. And then it's clear that this data is being interpreted by the different groups differently. It is very difficult for me as a human being to understand where the truth lies, especially given how much money is flying around on all sides. The anti-vaxxers can make a lot of money to let's not forget this. From the individual perspective, you can become famous being an anti-vaxxer. And so there's a lot of incentives on all sides here and and and there's real human emotion and fear and also credibility. You know, um scientists don't want to ruin their reputation if they if they speak out in whatever, like speak their opinion or um they look at some slice of the data and begin to interpret in some kind of way. They're very it's clear that fear is dominating the discourse here, especially in the scientific community. So, I don't know what to make of that. Um and the only happy people here is Fizer [/INST] just </s><s>[INST] plowing all ahead. I mean, um you know, with every single variant, there's X. You know that there's very I would say outside of arguably a very flawed system, there's a lot of incredible scientific and engineering work being done in constantly developing new, like antiviral drugs uh new of new vaccines to deal with the variants. So there happily being a capitalist machine and uh it's very difficult to know what to do with [/INST] that. And let's just put this in perspective for folks, the best selling drug in the world has been Humira for a number of years. It uh approved for the treatment of rheumatoid arthritis and eight other indications. Uh and it's sold about $20 billion dollars globally over the past few years. It leveled out, it peaked at that level fight sir, expects to sell $65 billion a vaccine in the first two years of the uh pandemic. So this is by far the biggest selling and most profitable drug that's ever been come along. </s><s>[INST] Can I ask you a difficult question here in the fog that we're operating in here [/INST] on the fights of </s><s>[INST] biontech vaccine. What was done well and what was done badly that you can see now, it seems like, well, no more decades from now. Yes. But now in the fog of today With the $65 billion dollars [/INST] flying around </s><s>[INST] where where do you land? So [/INST] we're going to get to what I think is one of the key problems with the pharmaceutical industry model in the United States about being profit driven. So In 2016, the NIH, did the key infrastructure work to make M. R. N. A. Vaccines that gets left out of the discussion a lot and fighter biontech actually paid royalties voluntarily to the NIH. I don't know how much it was. I don't think it was a whole lot of money but I think they wanted to avoid the litigation that Moderna got itself into By just taking that 2,016 knowledge and having that be the foundation of their product. So Fizer took that and they did um their R. And D. They paid for their R. And D. Having received um that technology and when they got the genetic code from china about the vaccine about the virus, they very quickly made a vaccine and the vaccine works and president trump to his credit launched operation warp speed and just threw money at the problem. They just said we we spent five times more per person than the eu early on just pay them whatever they want. Uh let's just get this going. And americans were vaccinated uh more quickly. We paid a lot of money. The one mistake that I think the federal government made was they were paying these guaranteed fortunes and they didn't require that the companies participate in a program to do global vaccinations. So the company's doing their business model, distributed the vaccines where they would make the most money and obviously they would make the most money in the first world. And almost I think 85% of the vaccines vaccines early on went to the first world and very very few vaccinations went to the third world. So what happened is The there was such a low vaccination rate in May of 2021 there was all hands on deck. Cry for help from the World Trade Organization. Um The World Health Organization, the IMF and the World Bank made a plea For $50 billion 40% vaccination rate in the third world by the end of 2021. And it was unrequited, nobody answered. And now Africa has about a 8.9% vaccination rate in India is coming up. But it's been very low. The problem with all this is I believe those M RNA vaccines are excellent vaccines. But if we leave the third world unvaccinated, we're going to have a constant supply of variants of Covid that are going to come back into the United States and harm americans exactly like Delta and omicron have. So we've made a great drug reduces the risk of mortality in americans who get it by a lot. But we're not doing what we need to do to protect americans from. Oh, macron, you don't have to be an idealist and worry about global vaccine equity. If you just ordinary selfish people, like most of us are and you're worried about the health of americans, you would ensure global vaccine distribution. Let me just make one more point that $50 billion that was requested by the four organizations back in May of 2021 32 billionaires Made $50 billion dollars from the vaccines at that point took it into their private wealth. So what had been taken this enormous amounts of money that had been taken into private wealth was enough to do what those organizations said needed to be done to prevent the sub variants from coming back and doing what they're doing. </s>

<s>[INST] wanted? What some kind of more desperation or something like this. [/INST] He wanted a level of sincerity that I that I thought I was bringing and I guess I was wrong. I don't know, maybe </s><s>[INST] go crazy like what does it mean to really want? I [/INST] should have grabbed him by the scruff of the neck and go, listen, dad, you're bringing me to this fucking play. I would have got the part as a matter of fact, I heard about someone else and I don't know who the heck this was, I forget who it was, but I've heard this story from a couple different people that there's this actor and I can't, I don't remember who it was, if I did, I probably wouldn't say it out loud anyway, but he </s><s>[INST] it was [/INST] brad pitt and he was in this audition and he was and there was out in the hall, he's like holy sh it George, Clooney leo Dicaprio. Um and he, this actor went in and he did the thing and Larry David was like try it again and he got like a couple takes in and he went, I don't think this is for me, and he left, which an actor never does. And as the story goes, Larry David shouted after him, I respect that, which I think is true and I want to believe that entire story is true. </s><s>[INST] Yeah, yeah. Sounds like something Larry David made up bobby [/INST] lee told me that story, so we can't, we can't trust that. </s><s>[INST] Um What about impressions is their similarity between that and acting? Do you, is there some fundamental way in which you become the person, [/INST] if you have a couple of the things you can just fill in the blanks. And I think the illusion is that people think that that person would say that and do that and that's where the illusion of it really embodies the character. It's like once, you know, someone's mannerisms, you can essentially portray a person from the outside in because you have all the stuff on the outside and you can do it and complete the illusion </s><s>[INST] and if it's for humor sake you're gonna caricature it, therefore making the whole illusion stronger and [/INST] also weirder. Like I like to on Mad Tv if I did something two or three times I get bored of it and I start changing it and you know, now he talks like this and it's like what are you doing? I'm like, I don't know, it's fucking, no one's late at night, do whatever you want. But </s><s>[INST] people still kinda know this that character, especially if you just call it out. [/INST] There aren't many impersonations that I listen to myself do and go oh that's a good one. You know, like a lot of people like like I think frank Caliendo is like the greatest impersonator of all time, He's the </s><s>[INST] best, it's [/INST] ridiculous. And he's got a record button and a broadcast ability that nobody has. I I really there's he's cracked impersonations that I'm like how is he? How does he find he's got such an ear but then he's got all the other tools uh remember actually my last season of Mad Tv was also his first season, he comes up to me when I met him and were just up there in the writer's offices and he goes, hey nice to meet you. And he goes Louie Anderson because I was doing Louie on the show and he goes Louie Anderson, I go yeah, he goes you're doing it wrong. And I was like oh am I Junior, you know? And he goes, he goes, yeah, you know, because you do this, but you gotta throw it up here. Sometimes. I was like, oh my God, can I use that? Of course. And then we became, you know, became fast </s><s>[INST] friends, john Madden is amazing. It's just it's ridiculous. [/INST] He </s><s>[INST] really, really, really embodies the person and sometimes not even with a caricature, it's like it becomes the person so strange. I [/INST] kind of feel like, you know, do the impersonation and then for not forget you're doing it, but forget everything else. Like just just goof around of course. To me, it's funny when some, when you sound like someone and you're saying the ship that they would never say, well then there's no you're you're you're letting go of that part, that tool in illusion that keeps people in. But to me it doesn't matter because it's funnier. So </s><s>[INST] what was the hardest impression for you to work on? I mean, somebody you struggled with. [/INST] I was I'll never forget, I had to do a michael caine in my first season at mad tv. It never got good. It never got good. It did it all week. It wasn't good. We shot it the first take, it was shit. 2nd, 3rd and 4th, it was all shit. Well, </s><s>[INST] his voice is really important, right? What is it like? It's like doing an impression of morgan Freeman or somebody like that. Yeah, you [/INST] can get the voice, That's my more here's my morgan Freeman. </s><s>[INST] Um yeah, I like your trump to I don't know where I heard it, but it's like I love the impressions you do that don't sound anything like the I [/INST] can't do trump. I I do </s><s>[INST] that's why it's hilarious. [/INST] Absolutely my trump. Now I say just sounds like a like a fat B. Because it's just exactly that everybody a little </s><s>[INST] drunk a little [/INST] just a little slurry. Yeah, I did doing impersonations and then not like just making it whoever. Yeah, yeah, it was terrible. It was terrible. And I could only hold my head a certain way to do it because I had gotten locked into this research tape that I watched back then they would give us, you know, now there's the internet, but back then you were if you were going to do an impersonation, the research department, uh would give you a VHS tape. And I remember I got this VHS tape of Michael caine's acting school, like this acting class, he did, he's like, right. You know, if you're looking at the left eye and the cameras over here say then the left eye. So you want to look at that left for hours, you know? And so I was like stuck in this weird thing that made no sense. And uh it was terrible. </s>

<s>[INST] But you, you, you know, symptoms of it because when certain people speak up kind of lightly and then a 19 year old or a 20 year old responds and is outraged. The fact that the administration listens to that 19 and 20 year old and then reprimands whoever spoke up a little bit. That's a really dangerous sign to me. And I don't really care about these, like, so I, I'm more with you. I don't think it's a big issue. But then I notice it. I wonder, wait a minute. Would this kind of environment allow a young Noam Chomsky to be around? Would this environment allow like, uh, I don't know, like, uh, what tenure was designed for, which is to have controversial thinkers and not kind of weird controversial things, but really people that challenge [/INST] things that should be challenged a little bit. Yeah, I sympathize with that significantly. I always try to look at specific examples. And sometimes I'll look at people else. I'll ask for them and people will send me five. And one of them is a legit bona fide example of what we're talking about. And for kind of like, uh, there was a complaint and it was investigated, but the teacher's tenure was never in jeopardy. And I don't know that I chalk this up to a big woke event. What do you think the kind of apparatus of the four year degree in college is going to look like in 20 years? </s><s>[INST] Oh, that's, I mean, we're like day by day that seems to be changing with GPT. I don't know if you've gotten a chance to interact with chat GPT. Absolutely. [/INST] My entire show now is written by chat GPT. </s><s>[INST] I mean, there's a, that's partially a joke. [/INST] It is only because it stopped looking at the internet in 2021. If it was current, I could completely just tune it out. No, I'm kidding. But it's a fascinating tool. </s><s>[INST] And, uh, it's changing the nature of how we, uh, do homework assignments. It's changing the nature of how we learn, how we look up new information, how we explore information, how we care about things we're interested in. I think it, um, I don't think we'll have value for university degree in 20 years the way we do now. I just think it changes everything. I think, uh, language models, I mean, Google search has already, and Wikipedia has already transformed, I would say our civilization, but it's, there was still a value for basic education. I don't, I think that starts to dissipate, uh, with, with chat GPT. So I don't, I don't know. I really, I really don't think there's a university the way we think of a university in 20, 20, 30 years. [/INST] I mean, I have a personal interest in it in that my daughter is 10 months old and I'm doing the 529 account. I'm going through the motions as if, but I also recognize, you know, if she went to the schools I went to just with the rate of tuition increase, you're talking 200 K a year by the time she's 18. And what happens with wages relative to that? This is like separate from the technological thing. And in my mind, I'm thinking, is this going to continue being the right path? What I would love to see is so many people that I interact with just by virtue of what I do have no foundation in critical thinking, epistemology, philosophy, media literacy. And if there were some way to make that the core of some basic education that everybody's receiving, which goes beyond, you know, chat GPT can do so many things, but I've not yet seen good examples of how it can teach you to think. Maybe you have a different view on how chat GPT can teach a user to think. But those skills seem to be so lacking in so many of the people I interact with. If there's any positive change to come from a changing dynamic with higher education, I wish it would be to go in that direction. </s><s>[INST] Well, no, chat GPT is actually much better at helping me think than any educator, even books that I've encountered, because it's very good at presenting the full picture, even better than a lot of Wikipedia articles, you know, on questions like the the virus leak from a lab, the COVID leak from a lab, it just presents to you all the different hypotheses, the amount of evidence available to it. It's like, it's like a full, calm, objective picture of it. There's no partisanship. It's like a really nice list of things that's available. [/INST] But I guess what I mean is, does it tell you how as a thinking human, you should evaluate the strength of each of the paragraphs it presents to you? You can literally ask. You can ask it to do it. </s><s>[INST] Okay. Okay. Yeah. And then it's actually a fun, it's fun to ask chat GPT that question, because you get good answers. And so you basically have a kind of Socratic, like a deep, intimate, like great podcast style conversation with an AI system every single day, or as many hours as you want, especially as it improves, and as the interfaces by which you communicate with a thing improves. So yeah, I think it will do exactly that, which is teach you how to think, because you will offload the memory of facts and equations and whatever else a school teaches you, you'll offload that to AI. And instead, you'll be using your human mind, which is what it, for now, is uniquely good at, which is asking good questions, [/INST] thinking through the complexities of issues when there's multiple perspectives on it, all of that. Well, then I stand corrected. Maybe then I don't know what college is going to be in 20 years. </s>

<s>[INST] You've robbed them of that. Ten times, yeah. Okay, that's pretty funny. But it's also... They have this energy. Like, they think, you know, they're coming in hot. I usually like to just basically get submitted quickly, twice. And just, it changes everything. It makes it more fun. I've noticed it. Let them submit you twice? Yeah. Just, like, very quickly. Like, what are the options? We're not... [/INST] I've noticed it. Let them submit you twice? Yeah. We're not... They can last longer. Hold off. They can last longer. </s><s>[INST] But then it's like, it's very hard to, like, yeah, if you're a very serious competitor, and so on, you take it seriously, then yes. But, like, then people go... People, what they try to do, this is probably what happens to you guys, they try to impress you by going super hard. [/INST] I have people every day come to my gym, try to take me out. Yeah. I just stay sharp. Come to practice. Let's get it on. </s><s>[INST] Do you feel that energy? [/INST] I feel like I need to talk to Craig here for a second. </s><s>[INST] Like, at a seminar. Like, somebody is coming in, like, really hard. Like, a brown belt will come in, like, and they really want to impress you with, like, their technical side of their big fan. They've been watching your DVDs. [/INST] Like, what do you do with a guy like that? I make a complete joke out of the row. You know, give them the pass, mess with them, do stupid shit, you know? Like, rub them of the realness of it. Because it's stupid. I'm not going to roll hard with strangers, you know? I feel like you should roll with a circle of people you trust. Injuries happen rolling hard with strangers because that's the same way you get injured in competition </s><s>[INST] because you don't have that relationship with them. And I should also mention, that's probably not a good way to impress somebody's big, just going ape shit, going 100%. Oh, yeah. That's not at all. I think the beauty of Jiu Jitsu is, like, the camaraderie of it. Like, as you get to know each other, there's, like, technical, like, different ideas you have and all that. Yeah. Okay. Do you think Gijitsu is dying in popularity, Craig? [/INST] Yeah, it's long dead. I think it's just, I mean, it just shows, like, I mean, I have heard some numbers on the viewership for the Ghee Worlds Finals, and they don't even compare to the undercard of, like, who's number one events. So I think, like, when I was coming up and competing in the Ghee all the time, you looked at those guys that won Black Belt World Championships, and you were like in awe of them. It almost had that ADCC champion feel, but now that's not the case. You know, I just feel like that. The younger generation aren't looking at who's winning Black Belt Ghee Worlds. I personally don't think and I don't think they're, like, they want to be that guy. </s><s>[INST] They want to be like a Retolo, Gordon, you know, those are the people they want to emulate. So you think like the Gi, like, IPJJF Gi tournaments will just keep declining popularity? [/INST] Oh, I think people will still do it. I mean, it's easier, I think, as you're over 30 because the Gi is a bit of a slower thing and the Masters participation is bigger in the Gi, because obviously you know Gi is now hitting in a wrestling direction. Wrestling and heel hooks, you're over 30, that's a terrifying prospect, you know? What's terrifying about the Gi? Less. So I think in a participation rate, the obvious Jeff will still be good, but I just don't think people are as interested as they used to be. </s><s>[INST] Why is wrestling and heel hooks terrifying? Like heel hooks I can vaguely understand if you don't understand heel hooks. [/INST] If you work a desk job and you've never wrestled and a guy double legs you, that's going to probably break your back, you know? I think the older guys are scared of wrestling. It's hard to wrestle at 40. To learn wrestling at 40. Yeah, I mean, I think it's even just hard in general to do wrestling at 40, but it's easier to pull half guy's in the game </s><s>[INST] 40. I think it's hard to do judo at 40. People still do it at 40. Judo hurts more. Judo's scarier than all of them. Yeah. I think, does wrestling really hurt 40? I don't know why I'm looking at you. [/INST] It does, interesting, I mean. I feel like Judo's scarier. I don't know why I'm looking at you. It does. I feel, I agree with what you were saying that Judo looks like the most dangerous. Like even their practice partners, they're just getting... </s><s>[INST] Slammed flat what oh, yeah, I did. I mean I did judo for a really long time There's a lot of people that are 40 50 60 do judo and they get they're the ones that are still alive though. It's true Survivor bias you do a little bit of judo, right me. I'm a yellow belt. You're a yellow bone judo. I should be an instructor [/INST] Promote you to orange. I got a yellow belt in the sixth grade. I believe was the sixth grade </s><s>[INST] I did it for about I don't know six months, but you're also using Uh judo in competition basically, all right, aren't you doing like a ride type throw like you're doing uh, You know, I just started doing it you started lifting your leg in various ways until work just figuring it out [/INST] Yeah, yeah do different kinds of trips. I will to the same. I don't know why I thought I just started doing it </s>

<s>[INST] and all that kind of stuff. If you wanna not do that kind of thing, grammar we will help you. And it's available on any platform. Major sites and apps like Gmail and twitter and so on. It doesn't just do spellcheck, it helps you get your point across effectively. And you can do that with Gramley premium. You can get 20% off graham early premium by signing up at Gramley dot com slash lex. That's 20% off at Graham early dot com slash lex. This episode is brought to you by magic spoon. Low carb keto friendly cereal. It has zero g of sugar, 13 to 40 g of protein, only four net grams of carbs and 140 calories in each serving. I think I'm having way too much fun doing these athletes and they're like much less about whatever the product is, much more about me just talking. It's like um personal therapy by myself, but also with my friends back to magic spoon. You can build your own box and get a variety pack with available flavors, cocoa, fruity frosted peanut butter, blueberry and cinnamon. But I returned time and time and time again too. Coco the flavor of champions. It reminds me of childhood. It reminds me of happiness, but it just reminds me of that joy of morning cereal without the deeply unhealthy excessive amounts of sugar. Anyway, magic spoon have a 100% happiness guarantee you now we're back to happiness if you don't like it, they refund it, go to magic spoon dot com slash lex. Use code lex at checkout to save five bucks off your order. That's magic spoon dot com slash lex and use code lex. This show is brought to you by blinking My favorite app for learning new things, Blanca's takes the key ideas from thousands of nonfiction books and condenses them down to just 15 minutes you can read or listen to. I can recommend a ton of books, sapiens, meditations by Marcus Aurelius, Beginning of infinity by David Deutsch Snowden book and so on. They don't have the rise and fall of the 3rd Reich I don't believe I have to check again. But they have a lot of the most important, most impactful nonfiction books ever written. If you don't have the time to read all of them, which nobody does, you should definitely use blankets to catch up on the ones that um are not at the top of your stack to read. I use it both to summarize books I'll never read. But also to summarize books I've already read. To remind myself to the key insights you can go to blink is dot com slash flex to start your free seven day trial and get 25% off of a blink is premium membership as blankets dot com slash lex spelled B. L. I. N. K. I. S. D. blankets dot com slash lex. This episode is brought to you by eight sleep and it's pot pro mattress. It controls temperature with an app. It's packed with sensors. It can cool down to as low as 55 degrees on each side of the bed separately. There are very few things in life. My friends that are as pleasant as a good [/INST] power nap. </s><s>[INST] Sometimes I'll even drink a coffee before hand, which I don't know how that works. Andrew Huberman probably knows how that works, but it works. I'll drink a coffee and I'll just pass out. Sometimes I pass out on the floor and that also works. But if I want to really enjoy the power nap so it's not just about function, it's about happiness. And if I want to enjoy happiness, there's nothing better than Cool bed with a warm blanket for 20 minutes, 25 minutes, 30 minutes. And then I wake up 100% refreshed. I do that because I'm in a eight sleep pod broke cover that you can add to your mattress I added to my mattress. You can go to a sleep dot com slash flex to check out the aforementioned pot pro cover and save $200 at checkout a sleep currently ships within the Usa Canada and the UK. That's eight sleep dot com slash lex. This is the lex Friedman podcast and here is my conversation with chris mason. Mhm. You wrote a book [/INST] Called the next 500 years </s><s>[INST] engineering life to reach new worlds. [/INST] And you dedicated to quote </s><s>[INST] to all humans in any [/INST] extinction, aware </s><s>[INST] sentience. How [/INST] fundamental is awareness of </s><s>[INST] death and extinction [/INST] to the human condition? </s><s>[INST] I think [/INST] this is actually one of the </s><s>[INST] most human specific [/INST] traits and features </s><s>[INST] that we have. It's actually maybe one of the few things that we only [/INST] We have and no one else has. So </s><s>[INST] it sounds scary. Sounds like what [/INST] people often don't like to </s><s>[INST] think about their death except now and again or at funerals [/INST] or to recognize their </s><s>[INST] mortality. But if you do it at a species wide level, it's something that is actually an exemplary human specific trait that you're exhibiting. You think about something that is the loss of not just your life or your family or everyone you see, but everyone like you and that is I dedicated it because I think we might not be the last sentience to have this awareness. I'm actually hoping will just be the first. But [/INST] as far as we know, we're the </s><s>[INST] only and I think this is the part of the moral [/INST] thrust for the book is that </s><s>[INST] we're the only ones that have this awareness that gives us a duty that only we can exercise so far. So we definitely contemplate our own mortality at the individual level. It is true when you wrote it, [/INST] it was really </s><s>[INST] powerful to realize for me that we do contemplate our extinction. And that that [/INST] is a creative </s><s>[INST] force. So the, [/INST] at the individual level, contemplating </s><s>[INST] your own death [/INST] is a creative </s>