text
stringlengths 28
334k
|
---|
<s>[INST] yeah, I had that. You know, it's funny because there's uh, have similar experiences, like immigrant family in the world tells you to do certain things and you think that's right. But, but then you put yourself in situations by luck probably where it's like, oh, this, there's this, this feels right. I don't know what this means, but this feels right. I think the biggest moment like that for me was uh, I don't know what to make of it exactly, But when I met spot the robot legs, robot was like five years ago. It felt like this, the, the depth of fascinating ideas that are yet to be explored with this thing. This felt like a journey. It was like a door that opened. I was like, I don't want to be a professor at that point. I realized I don't want to do sort of generic stuff. I want to do something crazy. I want to do something big. That's the reason I stepped away from M. I. T. That's the reason I have this burning desire to do a startup. That's the reason I came to Austin. Yeah. I don't know what the hell it all means. But it just kind of follow that. That's [/INST] awesome. That sounds like you're following what's doggedly you. And also I think just to just to piggyback off it. I think that means no matter what it is because I think are the american dream is sold like, hey, if you're not Beyonce or if you're not famous, you're not worth it. I hate that. And that's what I love so much about certain countries like Sweden and it's like um where everyone has healthcare because everyone's a little is valued more. It's like whatever. If you want to be a dormant do it. Like it's all the same. Prince was not happy. There's no just because you're rich or famous, you're still the same guy, whether your possessions are a lot little you know, it's like I have met some dormant. I have met some tax cap. Is that a lot of you not are more fascinating. I have comedians are horrible people. So I want to get away from all that. I have very few friends, paul versi, tim Dillon, who are comedians because they're awful, awful people. Some of the people who, you know the most were the most famous are not who they say they are. Usually that's the case. They're putting on that public facade because they're fucking sociopaths. Yeah, they're horrible people. And some of the most beautiful people I've met in the most interesting people I've met have regular jobs. There is no shame in any fucking job. We don't all have to be rappers with like rims. It's just a weird thing. </s><s>[INST] Famous, famous a drug And yeah, comedians agree with you. There's some part of me that knows that there will be a moment in my life when I'm standing there with, with like a sword or a knife in my stomach and looking at tim Dillon's smiling face saying, uh, you shouldn't have trusted me. You stupid fuck. So on that note, you honest, I've been a huge fan of yours. I love what you're doing with long days now, your new podcast and um, obviously love all the stuff you've done before with history hyenas. The chemistry, The chemistry you have with yourself. It's also fun to watch. So man, I'm a huge fan. It's a huge honor that you come down here. Thanks so much for talking [/INST] about. It means so much to me to hear you say that I really appreciate. I'm a big fan of yours and have me. It's been amazing. And just thank you man, thank you for having me on and people, if they want to watch my special, it's called blowing the light, it's on youtube and please come listen to Long Days of </s><s>[INST] podcast. Let's go eat some barbecue. Let's do it. Thanks for listening to this conversation with Yannis Pappas and thank you to wine, access, blink ist, magic spoon and indeed check them out in the description to support this podcast. And now let me leave you with some words from Karl Marx revolutions are the locomotives of history. Thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] wrote this, you know, I wouldn't pass them. You get a C minus, oh, you wouldn't pass them. Okay, all right. [/INST] You get a C minus, okay. Same thing with gravity waves. </s><s>[INST] He didn't believe- [/INST] Oh, he didn't believe in gravitational waves either? He went back and forth, but he wrote a paper in I think 34 saying that gravity waves didn't exist because people were very confused about what a coordinate transformation is. And in fact, this confusion about what a coordinate transformation is has persisted. And we actually think we were on the edge of solving it 100 years later. </s><s>[INST] A hundred years later. Well, what is coordinated transformation [/INST] as it was 100 years ago to today. Let's imagine I want to draw a map with pictures of all the states and the mountains, and then I want to draw the weather forecast, what the temperatures are going to be all over the country. And I do that using one set of weather stations, and I number the weather stations, and you have some other set of weather stations, and you do the same thing. So the coordinates are the locations of the weather stations. They're how we describe where the things are. At the end of the day, we should draw the same map. That is coordinate invariance. And if we're telling somebody, we're going to tell somebody at a real physical operation, we want you to stay as dry as possible on your drive from here to California. We should give them exactly the same route, no matter which weather stations we use or how we... It's a very trivial... The labeling of points is an artifact and not in the real physics. </s><s>[INST] So it turns out that that's almost true, but not quite. There's some subtleties to it. The statement that you should always have the same... Give at least the same kind of trajectory, the same kind of instructions, no matter the weather stations. [/INST] Yeah, there's some very delicate subtleties to that, which began to be noticed in the 50s. It's mostly true, but when you have a space-time with edges, it gets very tricky how you label the </s><s>[INST] edges. And space-time in terms of space or in terms of time, in terms of everything, just space. [/INST] Either one, space or time. That gets very tricky. And Einstein didn't have it right. And in fact, he had an earlier version of general relativity in 1914, which he was very excited about, which was wrong. It wasn't fully coordinate invariant, it was only partially coordinate invariant. It was wrong. It gave the wrong answer for bending light to the sun by a factor of two. There was an expedition sent out to measure it during World War I. They were captured before they could measure it. And that gave Einstein four more years to clean his act up, by which time he'd gotten it right. So it's a very tricky business, but once it's all laid out, </s><s>[INST] it's clear. Then why do you think Einstein didn't believe his own equations and didn't think that black holes are real? Why was that such a difficult idea for him? [/INST] Well, something very interesting happens in Schwarzschild's solution of the Einstein equation. I think his reasoning was ultimately wrong, but let me explain to you what it was. At the center of the black hole behind the horizon, in a region that nobody can see and live to tell about it, at the center of the black hole, there's a singularity, and if you pass the horizon, you go into the singularity, you get crushed, and that's the end of everything. Now, the word singularity means that it just means that Einstein's equations break down. They become infinite. You write them down, you put them on the computer. When the computer hits that singularity, it crashes. Everything becomes infinite. There's two. So the equations are just no good there. Now, that's actually not a bad thing. It's a really good thing, and let me explain why. So it's an odd thing that Maxwell's theory and Newton's theory never exhibit this phenomena. You write them down, you can solve them exactly. They're really Newton's theory of gravity. They're really very simple theories. You can solve them. Well, you can't solve the three-body problem, but you can certainly solve a lot of things about them. Nevertheless, there was never any reason, even though Maxwell and Newton perhaps fell for this trap, there were never any reason to think that these equations were exact. There's some equations that we've written down that we still think are exact. Some people still think are exact. My view is that there's no exact equation. </s><s>[INST] Everything is an approximation. Everything is an approximation. You're trying to get as close as possible. So you're saying objective truth doesn't [/INST] exist in this world? The internet's going to be very met. The internet's going to be very met. We could discuss that, but that's a different thing. We wouldn't say Newton's theory was wrong. it had very, very small corrections, incredibly small corrections. It's actually a puzzle why they're so small. So if you watch the procession of Mercury's perihelion, this was the first indication of something going wrong. According to Newton's theory, Mercury has an elliptical orbit, the long part of it moves around as other planets come by and perturb it and so on. And so this was measured by Laverrier in 1859, and he compared theory and experiment, and he found out that the perihelion process moves around the sun once every 233 centuries instead of every 231 centuries. Now, this is the wonderful thing about science. Why was this guy? I mean, you don't get any idea how much work this is. But of course, he made one of the greatest discoveries in the history of science without even knowing what good it was going to be. So that was the first sign that there was something wrong with Newton. So the corrections to Newton's law are very, very small, but they're definitely there. The corrections to electromagnetism, they're mostly the ones that we see are mostly coming from quantum </s> |
<s>[INST] But the solution to that, I know you're you're creating a thought experiment. Maybe playing a little bit of a devil's advocate. I think the solution to that is not to limit the algorithm. In the case of the super deadly virus, it's for the scientists to step up and become better communicators, more charismatic is fight the battle of ideas, sort of create better videos. You know, like if the virus is truly deadly, you have a lot more ammunition, a lot more data, a lot more material to work with in terms of communicating with the public, so be better at communicating and stop being uh you have to start trusting the intelligence of people and also being transparent and playing the game of the internet, which is like what is the internet hungry for? I believe authenticity stop looking like you're full of sh it, that's the scientific community, if there's any flaw that I currently see, especially the people that are in public office that like Anthony Fauci, they look like they're full of sh it and I know they're brilliant. Why don't they look more authentic? So they're losing that game? And I think a lot of people observing this entire system now, younger scientists are seeing this and saying, okay, if I want to continue being a scientist in the public eye and I want to be effective in my job, I'm gonna have to be a lot more authentic. So they're learning the lesson this evolutionary system is working. Uh so is this just a younger generation of minds coming up that I think will do a much better job in this battle of ideas that when the when the much more dangerous virus comes along, they'll be able to be better communicators at least. That's the hope the using the algorithm to control that is uh I feel like it's a big problem. So you're going to have the same problem with a deadly virus as with the current virus. If you let Youtube draw hard lines by the pr and the marketing people versus the broad community of scientists. [/INST] Well, in some sense, you're suggesting something that's close kin to what I was saying about, you know, freedom of expression ultimately provides an advantage to better ideas. So I'm in agreement, broadly speaking. Um, but I would also say there's probably some sort of you know, let's imagine the world that you propose where youtube shows you the alternative point of view that has the problem that I suggest. But one thing you could do is you could give us the tools to understand what we're looking at, right? You could give us. So first of all, there's something I think myopic solipsistic narcissistic about a an algorithm that serves shareholders by showing you what you want to see rather than what you need to know. Right? That's the distinction is flattering you, you know, playing to your blind spot is something that algorithm will figure out. But it's not healthy for us all to have google playing to our blind spot. It's very, very dangerous. So what I really want is analytics that allow me or maybe options and analytics. The options should allow me to see what alternative perspectives are being explored. Right? So here's the thing I'm searching and it leads me down this road, right? Let's let's say it's ever met them. Okay. I find all of this evidence that I ever met and works. I find all of these discussions and people talk about various protocols and this and that. And then I could say all right, what is the other side? And I could see who is searching not as individuals, but what demographics are searching alternatives. And maybe you could even combine it with something. Read it like where effectively let's say that there was a position that I don't know that that a vaccine is a mind control device. And you could have a steelman this argument uh, competition effectively. And the better answer is that steel man it as well as possible would rise to the top. And so you could read the top three or four explanations about why this really incredibly is a mind control uh, product. And you can say, well that doesn't really add up. I can check these three things myself and they can't possibly be right, right. And you could dismiss it. And then as an argument that was credible, let's say plate tectonics before that was an accepted concept. You say, wait a minute. There is evidence for plate tectonics. As crazy as it sounds that the continents are floating around on liquid. Actually that's not so implausible. You know, we've got these subduction zones, we've got geology that is compatible. We've got puzzle piece continents that seem to fit together. Wow, that's a surprising amount of evidence for that position. So I'm going to file some Bayesian probability with it that's updated for the fact that actually the steelman arguments better than I was expecting. Right? So I could imagine something like that where a I would love the search to be indifferent to who's searching, right? The solipsistic thing is too dangerous. So the search could be general. So we would all get a sense for what everybody else was seeing too. And then some layer that didn't have anything to do with what youtube points you to or not, but allowed you to see, you know, the general pattern of adherence to searching for um information and again, a layer in which those things could be defended. So you could hear what a good argument sounded like rather than just hear a caricatured argument. </s> |
<s>[INST] is weird because I saw smoke a joint right before this conversation, [/INST] it's my biggest thing. I mean, I try to keep that secret. </s><s>[INST] Alright, well, that's interesting about intervention. Can you comment about the war in Ukraine? So for me it's a deeply personal thing. Um but I think you're able to look at it from a geopolitics perspective. What is the role of the United States in this conflict before the conflict? During the conflict and right now in helping achieve peace? [/INST] I think before the conflict, the big problem is that the West took almost the worst possible view which was encouraged Ukraine to keep trying to join NATO and the EU but don't let them in. And so what that does is it achieves the purpose of getting Russia really, really, really ticked off and feeling threatened but also does not give any of the protections of NATO or the EU to to Ukraine. I mean, Zelensky is on film when he was a comedy actor making that exact joke, right? As Merkel on the other line and she's like, oh welcome to the welcome to NATO. And he's like, great, like wait, is this Ukraine on the line? And oops. But so you know that that sort of policy is sort of nonsensical if you're gonna offer alliance to somebody offer alliance to them and if you're going to guarantee their security, guarantee their security and the West failed signally to do that. So that was mistakes in the run up to the war. Once the war began, then the responsibility of the West began and became to give Ukraine as much material as is necessary to repel the invasion. Uh, and the West did really well with that. I think we were late on the ball in the United States. It seems like europe led the way a little bit more in the United States did there. Um, but in terms of effectuating american interests in the, in the region, which being an american is what I'm chiefly concerned about. You know, the, the american interests were several fold. One is preserved borders to is degrade the Russian aggressive military because Russia's military has been aggressive and they are geopolitical rival of the United States. Three recalibrate the european balance with china, europe was, was sort of balancing with Russia and china. And then because of the war, they sort of rebalanced away from china and Russia, which is a real geostrategic opportunity for the United States, it seems like most of those goals have already been achieved at this point for the United States. And so then the question becomes, what's the off ramp here? And what is the thing you're trying to prevent? So what's the best opportunity? What's the, what's the best case scenario? What's the worst case scenario? And then what's realistic? So best case scenario is Ukraine forces, Russia entirely out of Ukraine, including Luhansk Donetsk and Crimea, right. That's the best case scenario, virtually no one thinks that's accomplish able including the United States, right. The White House has basically said as much, it's still cool to imagine, particularly Crimea, the Russians being forced out of out of Crimea. The Ukrainians have been successful in pushing the Russians out of certain parts of Luhansk and Donetsk, but the idea they're gonna be able to push the entire Russian army completely back to the Russian borders. That would be at best, a very, very long, difficult slog in the middle of a collapsing Ukrainian economy, which is a point that Zelensky is made, it's like it's not enough for you guys to give us military aid in the middle of a war, we're gonna need economic aid as well. So it's a pretty open ended and strong commitment </s><s>[INST] can take a small changes on that best case scenario, if that does militarily happen, including Crimea, do you think there's a world in which Vladimir Putin would um be able to convince the Russian people that this is this was a good conclusion to the war? [/INST] Right. So the problem is that the best case scenario might also be the worst case scenario, meaning that that there there are a couple of scenarios that are sort of the worst case scenario and this is sort of the puzzlement of the situation. One is that Putin feels so boxed in, so unable to go back to his own people and say we just wasted tens of thousands of lives here for no reason that he unleashes a tactical a tactical nuclear weapon on the battlefield. Nobody knows what happens after. So we put NATO planes in the air to take out Russian assets to Russians start shooting down planes. Does Russia then threatened to escalate even further by attacking an actual NATO civilian center or or even the Ukrainian civilian center with nuclear weapons, like where it goes from there, nobody knows, because nuclear weapons haven't been used since 1945. So that's, you know, that is a worst case scenario. It's an unpredictable scenario that could devolve into really, really significant problems. The other worst case scenario could be a best case scenario could be worse. We just don't know is Putin falls, what happens after that? Who takes over for Putin? Is that person more moderate than Putin? Is that personal liberalize? Er it probably won't be the only if he's gonna be ousted, it'll probably somebody who's a top member of Putin's brass right now and has capacity to control the military or it's possible the entire regime breaks down. What you end up with is Syria, in Russia, right, where, where you just have an entirely out of control region with no centralizing power, which is also a disaster area. And so, in the nature of risk mitigation, in in sort of an attempt at risk mitigation, What actually should be happening right now is some off ramp has to be offered to Putin. The off ramp likely is going to be him maintaining Crimea and parts of Luhansk and Donetsk, it's probably gonna be a commitment by Ukraine not to join NATO formally, but a guarantee by the west to defend Ukraine in case of an invasion of his borders. Again by Russia, like an actual treaty obligation, not like the B. S. Treaty obligation and when when Ukraine gave up its nuclear weapons in the nineties, um and uh and that is likely how this is going to have to go. The problem is that requires political courage, not from not from Zelensky, it requires courage from from probably biden because the only Zelensky is not in a political position where he can go back to his own people who have made unbelievable sacrifices on behalf of their nation and freedom and say to them guys now I'm calling it quits, we're gonna have to give them a chance to give Putin and offer him, I don't think that's an acceptable answer to most Ukrainians at this point in time from the polling data and from the available data we have on the ground, it's gonna actually take biden biting the bullet and being the bad guy and saying to Zelensky, listen, we've made a commitment of material aid, we were offering you all these things including essentially a defense pact, we're offering you all this stuff. But if you don't come to the table, then we're gonna have to start weaning you like they will have to be a stick, there can be a carrot. Uh And so that will allow Zelensky if biden were to do that would allow Zelensky to blame biden for the solution. Everybody knows has to happen. So let's go back to his own people and you can say, listen, this is the way it has to go, like, I don't want it to go this way, but it's not my I'm signing other people's checks, right? I mean, like this is it's it's not my money. Uh and Biden would take the hit because he wouldn't then be able to blame Ukraine for whatever happens next. Which has been the easy road off. I think for a lot of politicians in the West is for them to just say, well, this is up to the Ukrainians to decide. It's up to the Ukrainians to decide. Well, is it totally up to the Ukrainians to decide? Because it seems like the West is signing an awful lot of checks and all of europe is gonna freeze this winter. So </s> |
<s>[INST] as long as that knowledge is transferred forward. Something tells me that the greatest of all time lived a few 1000 years ago and it's forgotten some of the greatest warriors. You can imagine the kind of grapplers, we just the history didn't record them that there could have been small tribes where they developed many U. F. C. S. And they've developed the kind of things we, you have to think of like the gracie's just a small family was able to develop so much so quickly. [/INST] I I often as this this discussion with john and I think it's very important to mention. I asked you very several times like what would happen if we would take a fighter of modern days facing the champion of Japan creation. </s><s>[INST] This is an interesting question and [/INST] you brought something incredible good point and and people don't don't realize </s><s>[INST] it. You know you know I think um one of the great tragedies of martial arts history is our loss of uh the historical records of pan creation, like most of what we know was from what I'm told is actually lost in the fires of the library of alexandria. And we're left with only a pitiful amount of information on Pan Creation manages. But what we do know is that there was a very large participation in the sport and that it was why they considered the most popular sport in the ancient olympics and that it was represented in the ancient olympics for many hundreds of years plus a long period of time before its introduction into the ancient olympics. And so the development time that it may have had would have been very significant as far as we know, most of the development would have been in the major greek city states for literally hundreds of years of development um given its prestige as an olympic sport, then the best athletes would have been doing it. Some of the sharpest minds that we know of and human history were involved in the sport. Plato, the great philosopher, was a pan creationist in his youth. In fact, his name Plato is a nickname, platypuses like plate, it means broad or big guy, like the big guy and uh he spoke often about pan creation and his written works. Um imagine people with the intelligence of plato thinking about grappling technique for hundreds of years, in the most popular olympic sport of that time, significant numbers of people with financial backing as city states put great prestige upon olympic success, they would have funneled athletes and brought in the best coaches and they had that for many hundreds of years. It's quite conceivable that the best plan creation athletes were of the absolute first quality. And uh, it's, it's so sad to think. We'll never know what was their skill level. And uh, it's interesting to think about what kind of techniques have developed, whether there's stuff we haven't discovered yet in class, you're talking about the most effective take down strategy and wrestling and collegiate wrestling. So maybe let me ask first, because we offline talked about this to what is the highest percentage submission in grappling overall. You have to go with the rear naked, strangle strangles from the back. If you look at most tournaments, most rule sets, it has success across all rule sets, all weight divisions, all body types. It doesn't require any kind of specific physical advantage, such as height in order to be effective. Um, It works equally well in both fighting and grappling. Um it will work regardless of how physically and mentally tough your opponent is. Okay here, Hawk is a very high percentage technique in modern day competition, but if your opponent simply makes up his mind that he's not going to tap and is willing to take the physical damage. It won't result in the end of the match a stranglehold by contrast, will always end the match regardless of your opponent's mental toughness. So, um, I believe it's fair to say that at the end of the day, the single most high percentage method of submitting people and grappling is a redneck its frame. So when you look at an athlete, maybe Gordon? You can speak to this. Like what, what's the best you mentioned Gary with the guillotine? What's the best submission to really invest in? Is it the rear naked choke to really invest your development? Like understanding the entirety of the system that leads into that? [/INST] I think that, I mean you have to do them all obviously, but if I had like one submission that I would only one submission, I could pick for the rest of my life. It would definitely be a rear naked. </s><s>[INST] Can you explain maybe some of the actual technical details of why that's the case? [/INST] Well, as john's book about their different in joint locks, whereas you don't have to tap, you can just let your leg break and then keep going with the strangle this. There's no, uh, there's, there's none of that. Um, and then it's just an inherent advantage you have being behind someone. Um, whereas if you go for an arm bar, you stop, you start from top mountain, you're facing the guy and then you put them down and you're not directly behind them with leg locks, you're facing the guy. Whereas when you're on someone's back, you have them in a pin where you can, your chest back have a body triangle and you you're paying the guy in place, you can't explode out. He can't grease his way out most of the time. Uh, and there's an inherent advantage you have being behind him due to the fact that were poorly set up to deal with threats behind us. </s><s>[INST] So it would just say that's the most dominant position, jujitsu, like more than Mt, more than side control. [/INST] More than I think. If you look at most matches historically, most guys who get stuck in positions for long amounts of time are guys that they're back taken. Um If you get an explosive guy from Bottom Mountain can bridge and he can off balance you and lock half guard maybe and then work back to guard. But someone locked the body triangle on your back. Um That's where you see most guys getting pinned in place for long amounts of time. </s> |
<s>[INST] the way, it doesn't really have to be a copy of itself. Right? It just has to be you have to create something that's interesting [/INST] the </s><s>[INST] way evolution is So it is extremely powerful process of evolution which is basically make a copy yourself and sometimes mess up a little bit. Okay, that seems to work really well. I wonder if it's possible to [/INST] mess up big time </s><s>[INST] mess up big time as a standard. That's the default [/INST] it's called a hopeful monster. And you know, </s><s>[INST] it doesn't work [/INST] in principle. It can actually it turns out I would say that this is due a reemergence. This amazing work from Michael Levin. I don't know if you came across him but if you haven't interviewed him you should interview him. </s><s>[INST] Yeah. About Yeah, talking to him in a few days. [/INST] Fantastic. </s><s>[INST] So I mentioned off there's some people that andre if I may mention on drake apathy is a friend who's really admired in the community said, you absolutely must talk to to Michel and tunic. This is so this of course I'm a huge fan of yours. So I'm really fortunate that we can actually make this happen anyway, you were saying. [/INST] Well, Michael Levin is doing amazing work basically about the way in which electrical fields control development. Um and he's done some work with culinary in worms, flatworms, where he'll tell you all about this. So, I won't say any more than the minimum, but basically you can cut their head off and they'll redevelop a different a new head. But the head that they develop depends if you knock out just 11111, iron pumpin a membrane. So you change the electrical circuitry just a little bit. You can come up with a completely different head, It can be ahead, Which is similar to those that diverged 150 million years ago. Or it can be a head which no one's ever seen before, a different kind of head. Now. That is really, you might say a hopeful monster. This is a kind of leap into a different direction. The only question for natural selection is, does it work is the change itself feasible as a single change. And the answer is yes. It's just a small change to a single gene. And the second thing is it gives rise to a completely different morphology. Does it work? And if it works, that can easily be a shift. But for it to be a speciation for it to to continue for it to to to give rise to a different morphology over time, then it has to be perpetuated. So that shift, that change in the in that one gene has to work well enough that it is selected and it goes on </s><s>[INST] and copied enough times to work really tested. And so [/INST] the likelihood it will be lost. But but there will be some occasions where it survives. And yes, the the idea that we can have sudden, fairly abrupt changes in evolution, I think it's time for a rebirth. </s><s>[INST] What about this idea that kind of trying to mathematics, eyes a definition of life and saying how many steps, the shortest amount of steps it takes to build the thing almost like an engineering view of it. [/INST] I like that because I think that in a sense that's not very far away from what what what what what a hypothesis needs to do to be a testable hypothesis for the origin of life. You need to spell out. Here's here's each step and here's the experiment to do for each step. The idea that we can do it in the lab. Some people say, oh, well, you know, we'll have created life within five years. But, you know, ask them what they mean by life. Um we have a planet four billion years ago with these vent systems across the entire surface of the planet. And we have millions of years if we wanted. I have a feeling that we're not talking about millions of years. I have a feeling we're talking about maybe millions of nanoseconds or PICO seconds. We're talking about chemistry, which is happening quickly. Um but we still need to constrain those steps, but we've got, you know, a planet doing similar chemistry. You asked about the trajectory? The trajectory is the planetary trajectory. The planet has properties. It's basically it's got a lot of iron at the center of it has got a lot of electrons at the center of it is more oxidized on the outside, partly because of the sun. And partly because the heat of volcanoes puts out oxidized gasses. So, the planet is a battery as a giant battery. Um, and we have a flow of electrons going from inside to outside in these hydrothermal vents. And that's the same topology that a cell has a cell is basically just a micro version of the planet. And it's a there is a trajectory in all of that. And there's an inevitability that certain types of chemical reactions are going to be favored over others. And there's an inevitability in in what happens in water. The chemistry that happens in water, some some will be admissible with water and will form membranes and will form insoluble structures and, you know, water's nobody really understands water very well. Um and it's it's another big question for for experiments on the origin of life, what do you put it in? What kind of structure do we want to induce in this water? Because the last thing is likely to be is just kind of bulk, bulk water. How </s><s>[INST] fundamentals water to life would you say? [/INST] I would say pretty fundamental. Um I wouldn't like to say it's impossible for life to start any other way, but water is everywhere. Water is extremely good at what it does and carbon carbon works in water especially well. So those things and carbon is everywhere. So those things together make me think probabilistic Lee if we found 1000 life forms 995 of them would be carbon based and living in water. </s> |
<s>[INST] more meaningful. Let's say, no, we're it. I mean, that's, that's, that's the, um, and, and the symbolism of this particular moment. So this has been one of the, one of the favorite conversations I've ever had, Steven, it's a huge honor to talk to you, to talk about a topic like this for four plus hours on the fundamental theory of physics. And yet we're just two finite descendants of apes [/INST] that have to end this conversation because darkness have come upon us. Right. And we're going to get, </s><s>[INST] right. And we're going to get bitten by mosquitoes and the symbolism of that. We're talking about the most basic fabric of reality and having to end because of the fact that things end. Um, it's tragic and beautiful, Steven. Thank you so much. Huge honor. I can't wait to see what you do in the next couple of days and next week and month. We're all watching with excitement. Thank you so much. Thanks. Thanks. Thanks for listening to this conversation with Steven Wolfram. And thank you to our sponsors, Simply Safe, SunBasket, and Masterclass. Please check out our sponsors 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 and Apple Podcasts, follow on Spotify, support on Patreon, or connect with me on Twitter, Alex Friedman. And now let me leave you with some words from Richard Feynman. Physics isn't the most important thing. Love is. Thank you for listening. Hope to see you next time. [/INST] </s> |
<s>[INST] Yeah, there's uh, currently the algorithm is very rabbit hole driven meaning if you, uh, if you click on flat earth videos, that's all you're going to be presented with and you're not going to be nicely presented with arguments against the flat earth and the flip side of that Uh huh If you watch like quantum mechanics videos, Oh no, general relativity videos, it's very rare. You're going to get in the recommendation. Have you considered the Earth is flat and I think you should have both uh, same with vaccine videos that present the power and incredible like biology, genetics, Biology about the vaccine, you're rarely going to get videos from well respected scientific minds presenting possible dangers of vaccine and the vice versa is true as well, which is if you're looking at the danger of the vaccine on youtube, you're not going to get the highest quality of videos recommended to you and I'm not talking about like manually inserted CDC videos that are like the most untrustworthy things you can possibly watch about how everybody should take the vaccine is the safest thing ever know. It's about incredible again, M. I. T. Colleagues of mine incredible biologists, biologists that I'll talk about the details of how the M. RNA vaccines work and all those kinds of things. I think maybe this is me with the AI had on is I think the algorithm can fix a lot of this and Youtube should build better algorithms and trust that to a couple of complete freedom of speech to expand the what people are able to think about present always very views not balanced in some artificial way. Hard coded way, but balanced in a way that's crowdsourced. I think that's an algorithm problem that can be solved because then you can delegate it to the algorithm as opposed to this hard code censorship of basically creating artificial boundaries on what can and can't be discussed. Instead creating a full spectrum of exploration that can be done and trusting the intelligence of people to do the exploration. [/INST] Well, there's there's a lot there. I would say we have to keep in mind that we're talking about a um a publicly held company with shareholders and obligations to them and that that may make it impossible And I remember um many years ago back in the early days of google, I remember a sense of terror at the loss of general search, right? It used to be that, that google if you searched, came up with the same thing for everyone and then it got personalized and for a while it was possible to turn off the personalization, which was still not great because if everybody else is looking at a personalized search and you can tune into one that isn't personalized, what are, you know, that doesn't tell you why the world is sounding the way it is, but nonetheless, it was at least an option. And then that vanished and the problem is, I think this is literally deranged ng us that in effect, I mean, what you're describing is unthinkable. It's unthinkable that in the face of a campaign to vaccinate, vaccinate people in order to reach herd immunity. That um, Youtube would give you videos on hazards of vaccines when this is, you know, how hazardous the vaccines are is an unsettled question, </s><s>[INST] Why is it unthinkable? That doesn't make any sense. From a company perspective, if intelligent people in large amounts are open minded and are thinking through the hazards and the benefits of the vaccine, a company should, should find the best videos to present what people are thinking about. [/INST] Well, let's come up with a hypothetical, Okay, let's come up with a, a very deadly disease for which there is a vaccine that is very safe though not perfectly safe. And we are then faced with Youtube trying to figure out what to do for somebody searching on vaccine safety. I suppose it is necessary in order to drive the pathogen to extinction. Something like smallpox that people get on board with the vaccine. But there's a tiny fringe of people who thinks that the vaccine is a mind control agent. Right? So should Youtube direct people to the only claims against this vaccine, which is that it's a mind control agent when in fact the vaccine is very safe, whatever that means, if that were the actual configuration of the puzzle, then Youtube would be doing active harm pointing you to um this other video potentially. Now, yes, I would love to live in a world where people are up to the challenge of sorting that out. But my basic point would be if it's an evidentiary question and there's essentially no evidence that the vaccine is a mind control agent and there's plenty of evidence that the vaccine is safe, then. Well, you look for this video, we're going to give you this one puts it on a par. Right? So for the mind that's tracking how much thought is there behind its safe versus how much thought is there behind it's a mind control agent will result in artificially elevating this. Now. In the current case, what we've seen is not this at all. We have seen evidence obscured in order to create a false story about safety and we saw the inverse with Ivermectin, we saw a campaign to portray the drug as um more dangerous and less effective than the evidence clearly suggested it was. So we're not talking about a comparable thing. But I guess my point is the algorithmic solution that you point to um creates a problem of its own, which is that it means that the way to get exposure is to generate something fringy. If you're the only thing on some Fringe, then suddenly Youtube would be recommending those things and that's that's obviously a gay mobile system at best. </s> |
<s>[INST] that was [/INST] Floating. Yes, it was totally floating about and it comes down to oxygen, which on our planet fills our atmosphere to 20% by volume. And you know, we rely on oxygen to breathe when they you hear about the people on mount Everest running out of air. They're really running out of oxygen while they're running out of oxygen because the air is getting thinner as they climb up the mountain. But without plants and bacteria, there's plants, bacteria that also photosynthesize is and produces oxygen as a waste product. Without those, we would have virtually no oxygen. Our atmosphere would be devoid of oxygen. </s><s>[INST] So yeah, what if you were to analyze earth is oxygen? The strong indicator [/INST] here. Oxygen is a huge indicator and that's what we're hoping that there is an intelligent civilization not too far from here around the planet orbiting a nearby star with the kind of telescopes were trying to build and they're looking back at our son and they've seen our earth and they see oxygen And they probably won't be like 100.0% sure that there's life making it. But if they go through all the possible scenarios, they'll be left with a pretty strong hint that there's life here. </s><s>[INST] Okay, but how do you detect that type of gasses that are on the planet from a distance? [/INST] And that's going back to that. That's what people were skeptical about when I first started working on exoplanets long time ago. People didn't believe we would ever ever ever study an exoplanet atmosphere of any kind and now dozens of them are studied, there's a whole field of people, hundreds of people working on exoplanet atmospheres. Actually, </s><s>[INST] first, there was a point where people didn't even know there's exoplanets right, When was the first exoplanet detected? [/INST] The first exoplanet around a sun like star anyway, was detected in the mid 1990s. </s><s>[INST] That was a big deal. Kind of vaguely remember [/INST] that well, at the time, it was a big deal, but it was also incredibly controversial because in extra planets, we only had one example of a planetary system, our own solar system. In our solar system, jupiter are big, massive planet is really far from our star. And this first exoplanet around a sun like star was incredibly close to its star, its star so close that people just couldn't believe it was a planet actually. </s><s>[INST] So maybe it zoom out. What the heck is an exoplanet? [/INST] An exoplanet is our name like is the name that we call a planet orbiting a star other than our sun. </s><s>[INST] Extrasolar, I [/INST] guess it's called extrasolar exoplanets simpler, but I think it's worth pausing to remember that each one of those stars out there in our night sky is a son, you know, our sun has planets, Mercury, venus, earth mars, et cetera. And so for a long time, people have wondered, do those other stars or other sons have planets and they do. And it appears that nearly every star has a planet has the planet we call exoplanet and there are thousands of known exoplanets already. So </s><s>[INST] that's already, yeah. Like there's so many things about space that it's hard to put it into one's brain because it starts filling it with awe. So, yeah, if you visualize the fact that the stars that we see in the sky aren't just stars, they're like their sons, and they very likely, as you're saying, we have planets around them. There's all these planets roaming about in this, like dimly lit darkness, potentially, uh, life. I mean, it's just mind blowing. But maybe can you give a brief, like, history of And like, of discovering all the exoplanets to do? So, there's no exoplanets in the 90s. And then there's a lot of exoplanets now. So, how did [/INST] that come about planets? How did it come about? Well, </s><s>[INST] maybe another way to ask is what is the methodology that was used to discover [/INST] them? I can see that, but I'd like to just say something else first, where, so, exoplanets, you know, the line between what is considered completely crazy and what is considered mainstream research legit is constantly shifting. </s><s>[INST] So, [/INST] before, when I started an exoplanet, it was still sketchy, like, it wasn't considered a career, a thing, a place where you should be investing. And right now, now, today, it's So many people are working in this field, a good, I don't know, at least 1000, probably more. I know that sounds like a lot to you, but it's a </s><s>[INST] lot. It's a legitimate field of inquiry, [/INST] legitimate field in Korea and what's helped us is everything that's helped everyone else. It's software, it's computers, it's hardware. It's like our phones. You have a fantastic detector in there. Like they didn't always have that. I don't know if you remember the so called olden days, we didn't have digital cameras. We had filmed, you take a film camera, you send the film away and eventually comes back and then you see your pictures and they could all be horrible. </s><s>[INST] So yeah, I mean digital, it just changed everything. Data, changed [/INST] everything. And so one thing that really helped exoplanets were detectors that were very sensitive because when we're looking for this, the transiting planets, what we're doing is we're monitoring a star's brightness as a function of time. It's like click taking a picture of the stars every few seconds or minutes and we're measuring the brightness of a star like every frame and we're looking for a drop in brightness that's characteristic of a planet going in front of the star and then finishing its so called transit. And to make that measurement, we have to have precise detectors </s><s>[INST] and the detectors that are making the measurement. Can you do it from Earth? Is it are they floating about in space? Like what kind of telescope? [/INST] So on the ground people are using telescopes, small telescopes that are almost just like a glorified telephoto lens and they're looking at big swaths of the sky And from the ground, people can find giant planets like the size of Jupiter. So it's about 10 to 12 times the size of Earth. We can find big planets because we can reach about 1% precision. So not sure how technical you want to get, but </s> |
<s>[INST] and typeset in late check. [/INST] No, no, no. Are you </s><s>[INST] kidding? I remember liking the typography so I don't know [/INST] we did it with the roof. </s><s>[INST] I don't even know what that is. Yeah, [/INST] exactly. You're too </s><s>[INST] young to think [/INST] of tear off as as a A predecessor to the tech family of things. It's a format that was done at Bell Labs in this same period of the very early 70's That predates tech and things like that play 5-10 years. </s><s>[INST] But it was nevertheless just, I'm going by memories. It was, I remember it being beautiful. Uh It was nice outside of UNIX C are going all the things we talked about all the amazing work you've done. You've also done working graph theory. Ah let me ask this this crazy out there question. Uh if you have to make a bet and I had to force you to make a bet, Do you think P equals np? [/INST] Uh The answer is no. Although I'm told that somebody asked Jeff Dean if that was the under what conditions? Beauty Glenn P And he said either P A zero or in his one or vice versa. I've forgotten. This is what Jeff was a lot smarter than </s><s>[INST] I. Uh So, but your intuition is uh I [/INST] have no, I have no intuition. But I've got a lot of colleagues who got intuition and they're betting is no, </s><s>[INST] that's the popular, that's the popular bet. Okay. So what is computational complexity theory? And do you think these kinds of complexity classes especially as you've taught in this modern world are still useful way to understand the hardness of problems. [/INST] I don't do that stuff the last time I touched anything to do with many, many years ago was before it was invented because I it's literally true. I did my PhD thesis on before big </s><s>[INST] o notation. Absolutely. [/INST] Before I did this in 1968. Um and I worked on graph partitioning, which is this question, you got a graph that is a nodes and edges kind of graph and the edges have weights and you just want to divide the nodes into two piles of equal size so that the number of edges that goes from one side to the other is as small as possible. And </s><s>[INST] we developed so that problem is hard. [/INST] Well, as it turns out, I worked with shen lin at bell labs on this and we were never able to come up with anything that was guaranteed to give the right answer. We came up with heuristics that worked pretty darn well. And I peeled off some special cases for my thesis, but it was just hard and that was just about the time that steve cook was showing that there were classes of problems that appeared to be really hard of which graph partitioning was one. But this my expertise such as it was totally predates that development. </s><s>[INST] So the purest which now uh your cares the two of yours names for the traveling salesman problem and for the graph partitioning that was like how did you, you weren't even thinking in terms of classes, you were just trying to was no such idea a heuristic That kind of does the job pretty well. You [/INST] were trying to find a something that did the job and there was no nothing that you would call it a closed form or algorithmic thing. That would give you a guaranteed right answer. I mean, compare graph partitioning to max flow min cut or something like that. That's the same problem. Except there's no constraint on the number of nodes on one side or the other of the cut. And that means it's an easy problem, at least as I understand it. Whereas the constraint that says the two have to be constrained in size makes it a hard problem. </s><s>[INST] Yes. So the robert Frost has that poem where you choose to path. So why did you uh is there another alternate universe in which you pursued the don canoe? The path of you know, algorithm design, sort [/INST] of not smart enough, </s><s>[INST] smart enough. Uh uh You're infinitely uh modest, but so you you proceed your kind of love of programming. I mean when you look back to those, I mean, just looking into that world, does that just seem like a distant world of theoretical computer science, then? Is it fundamentally different from the world of programming? [/INST] I don't know. I mean, certainly in all seriousness, I just didn't have the talent for it. I when I got here as a grad student at Princeton and I started to think about research at the end of my first year or something like that. I worked briefly with john Hop Croft, who is absolutely you know, you mentioned during award winner et cetera, a great guy. Um and it became crystal clear. I was not cut out for this stuff period. Okay. And so I moved into things where I was more cut out for it. And that tended to be things like writing programs and then ultimately writing books. </s><s>[INST] Yeah, you said that in Toronto as an undergrad, you did a senior thesis or literature survey on artificial intelligence. This was 1964, correct. What was the ai landscape ideas, dreams at that time? [/INST] I think that was one of the, what you've heard of ai winters. This is whatever the opposite was a I summer or something. It was one of those things where people thought that boy, we could do anything with computers, that all these hard problems we could, computers will solve them, they will do machine translation, they will play games like chess, that they will do miss uh you know, prove theorems in geometry. There are all kinds of examples like that where people thought, boy, we could really do those sorts of things. Um and you know, I I read the kool aid in some sense, I still have a wonderful collection of papers called computers and thought that was published in about that era and people were very optimistic. And then of course it turned out that What people thought was just a few years down the pike uh was more than a few years down the pike and some parts of that are more or less now sort of under control. Uh we finally do play games like going chess and so on better than than people do. But there are others. Machine translation is a lot better than it used to be, but that's you know, 50 close to 60 years of progress and a lot of evolution and hardware and a tremendous amount more data upon which you can build uh systems that actually can learn from some of </s> |
<s>[INST] Yes, but symmetry is not enough for digit recognition. Right? [/INST] It is not necessarily for digital combination. It's helps to create in variant which will you can use when you will have examples for digital condition. You have regular problem of digital recognition. You have examples of the first class, second class plus, you know that there is a there exist concept of cemetery and you apply when you looking for decision rule usual apply uh concept of symmetry of this level of cemetery issue estimate from. So let's talk everything is come from big convergence. </s><s>[INST] What is convergence? What is weak convergence? What is strong convergence? I'm sorry, I'm going to do this to you. What are we converging from? And to [/INST] you can do a drink. You would like to have a function. The function which say indicator function which indicate your digit five, for example, </s><s>[INST] a classification task. [/INST] Let's talk only about classification </s><s>[INST] classification means you will say whether this is a five or not or say which of the 10 digits it is [/INST] right. I would like to to have these functions then I have some examples. I can consider protest. E of those examples sensitivity and I can measure level of symmetry for every digit and then I can take average and I from from my training data and I will consider only functions of conditional probability which I'm looking for. My decision rule, which applying two two digits will give me the same average as I absorb on training date. So actually this is different level of description of what you want you want uh not just you shall not one digit. You show this this predicate. So general property of all digits which you have in mind. If you have in mind digits three, It gives you pro 30 of digits three and you select as admissible set of function only function which keeps this property. You will not consider other functions. So you immediately looking for smaller subset of </s><s>[INST] function. That's what you mean by admissible functions. Admissible functions which is still a pretty large For the # three. [/INST] A pretty large. But if you have one predicated but according to there is a strong bendy convergence. Strong convergence of convergence and function you're looking for the function on one function and you're looking concerned. Another function and square difference from them should be small. If you take difference in any points. Make discover make an integral and it should be small. That is convergence in function suppose you have some function any function. So I would say I say that some function converts to this function if integral from square difference between them is more. </s><s>[INST] That's the definition of strong convergence. That definition of two functions. The integral of the difference. [/INST] Yes, it is convergence in functions but you have different convergence in functional. You take any function, you take some function fee and take inner products. This function, this f function zero function which you want uh to find and that gives you some value. So you say that set of functions converge in inner product to this function. If this value of inner product converged to a value of zero, That is for one he but we converges requires that it converts for any function of Hilbert space. If it converges for any function of Hilbert space, then you would say that this is vic conversions, you can think that when you take integral that is protest the integral, protest your function. For example, if you will take sign or a sign it is coefficient of Uh say 40 year expansion. So if it converge for all coefficients of free expansion. So under some condition converged to function you're looking for. But the convergence means any property convergence, not point wise, but integral property of function. So the convergence means integral property of functions. When I talking about pre decayed, I would like to um formulate which integral properties I would like to have for conversions. So and if I will take one predicate predicate, its function which I measure property uh huh If I will use one predicate and say I will consider only function which gives me the same value as it is. This predicate I selecting a set of functions from functions which is admissible in the sense that function which are looking for in this set of functions. Because I checking in training data it gives the same </s><s>[INST] Yes, it always has to be connected to the training data in terms of [/INST] Yeah but but pro 30 you can no independent on training data. And this guy prop Yeah. So there is formal project 31 protecting </s><s>[INST] Russian fairy tales [/INST] but Russian fairy tale is not so interesting. More interesting that people apply this to movies to theater to different things and the same works. The universal. </s><s>[INST] Well, so I would argue that there's a little bit of a difference between uh the kind of things that were applied to which are essentially stories and digit recognition. [/INST] It is the same story, </s><s>[INST] You're saying digits. There's a story within the digit. [/INST] Yeah. </s><s>[INST] So [/INST] But my my point is why I hope that it's possible to beat a record using not 60,000 but 100 times less because instead you will give predicates and you will select your decision not from white set of function but from set of functions which keeps us predicate but predicate is not related just two digit recognition. Right? So </s><s>[INST] like in [/INST] platters </s><s>[INST] case, do you think it's possible to automatically discover the predicates. So you basically said that the essence of intelligence is the discovery of good predicates. Yeah. Now the natural question is you know that's what Einstein was good at doing in physics. Can we make machines do these kinds of discovery of good predicates or is this ultimately a human endeavor [/INST] that I don't know I don't think that machine can do because uh according to theory about conversions uh any function from Hilbert space can be predicated. So you have infinite number of predicated and upper and before you don't know which predicated is good and which but whatever prop show and white people call it breakthrough that there is not too many predicate which cover most of situation happened in the world. </s> |
<s>[INST] Well let's talk about it more. You're an incredible writer, one of my favorite writers. So let me read from your latest book transformers. What you write about consciousness. I think therefore I am said the cart is one of the most celebrated lines ever written. But what am I exactly an artificial intelligence can think to by definition and therefore is yet few of us could agree whether ai is capable in principle of anything resembling human emotions of love or hate, fear and joy of spiritual yearnings for oneness or oblivion or corporeal paying of thirst and hunger. The problem is we don't know what emotions are as you were saying, what is the feeling in physical terms? How does that discharging neurons give rise to a feeling of anything at all? This is the hard problem of consciousness, the seeming duality of mind and matter, the physical makeup of our innermost self. We can understand in principle how an extremely sophisticated parallel processing system could be capable of wondrous feats of intelligence. But we can't answer in principle whether such a supreme intelligence would experience joy or melancholy. What is the quantum of solace? I speaking to the question of emergence? You know, there's just technical um uh there's a there's an excellent paper on this recently about the kind of phase transition, emergence of performance in your own networks on problem of NLP natural language process. So, language models, there seems to be this question of size at some point, there is a phase transition as you grow the size of the neural network? So the question is sort of somewhat of a technical question that you can philosophize over. The technical question is is there a size of a neural network that starts to be able to form the kind of representation that can capture a language and therefore be able to um not just language but linguistically capture knowledge that's sufficient to solve a lot of problems in language? Like be able to have a conversation and there seems to be not a gradual increase but a face transition. And we and they're trying to construct the science of where that is. Like what is a good size of a neural network and why does such a phase transition happen anyway? That that sort of points to emergence. That there there could be stages where a thing goes from being ah you're you're very intelligent toaster [/INST] to </s><s>[INST] a toaster that's feeling sad today and turns away and looks out um out the window, sighing. Having an existential crisis. We'll know Marvin is simplistic because Marvin is just cranky. [/INST] Yes. </s><s>[INST] Uh [/INST] easily programmed. </s><s>[INST] Yeah, easily programmed. Nonstop existential crisis. You're almost basically uh what is the notes from underground but just like just just constantly complaining about life. No, they're capturing the full roller coaster of human emotion, the excitement of bliss, the connection, um the empathy and all that kind of stuff and then the selfishness, the anger, the depression, all that kind of stuff, capturing all of that and be able to experience it deeply. Like it's the most important thing you can possibly experience today. The highest highs. The lowest lows. This is it, My life will be over this. Uh I cannot possibly go on that feeling. And then like after a nap you're you're feeling amazing. That might be something that emerges. [/INST] So why would a nap? make an ai being feel better? </s><s>[INST] The first of all, we don't know that for human either. Right. But [/INST] we do know that that's actually true for many people much at the time. Maybe </s><s>[INST] you [/INST] do in fact feel better. So, oh, </s><s>[INST] you are actually asking the technical question there is that. Uh so that's a very there's a biological answer to that. And so the question is whether ai needs to have the same kind of attachments to its body, bodily function and preservation of the brain's successful function uh self preservation essentially in some deep biological sense. [/INST] I mean, to my mind, it comes back around to the problem we were talking about before, about simulations and sensory input and learning what all of this stuff means. And life and death. Um that that biology, unlike society has a death penalty over everything. And natural selection works on that death penalty. That if you make this decision wrongly you die. Um and the next generation is represented by beings that made a slightly different decision on balance. Um and that is something that's intrinsically difficult to simulate in all this richness? I would say so. So what is </s><s>[INST] death in all its richness? [/INST] Our </s><s>[INST] relationship with death or or or the whole of it. So, which when you say richness, of course there's a lot in that, which is hard to simulate what what's the what's part of richness? That's hard to simulate, [/INST] I suppose the complexity of the environment and your position in that or the position of an organism in that environment in the full richness of that environment over its entire life, over multiple generations. With changes in gene sequence over those generations of slight changes in the makeup of those individuals over generations. But if you take it back to the level of single cells which I do in in in in the book and and ask, how do how how does a single cell in effect know it exists as a unit as an entity? I mean, no, in inverted commas, obviously it doesn't know anything, but it acts as a unit and it acts with astonishing precision as a unit. And and I had suggested that that's linked to the electrical fields on on the membranes themselves and that they give some indication of how am I doing in relation to my environment as a kind of real time feedback on the world. And this is something physical which can be selected over generations. That if you are if you get this wrong, it's linked with this set of circumstances that I've just as an individual, I have a moment of blind panic and run as a bacterium or something. You have some electrical discharge that says blind panic and it runs whatever it may be. And you associate over generations, multiple generations, that this electrical phase that I'm in now is associated with a response like that. And it's easy to see how feelings come in through through the back door almost with with that that kind of um giving real time feedback on your position in the world in relation to how am I doing and then you you complex if I the system. And yes, I have no problem with with with with with phase transition. And you know, can can all of this be done purely by the language, by the the the the issues with how the system understands itself? Maybe it can, I honestly don't know. But I, you know, the philosophers for a long time have talked about the possibility that you can have a zombie intelligence. Uh and that there are no feelings there. But everything else is the same. Um, is I mean, I have to throw this back to you, really. How do you deal with the zombie intelligence? </s> |
<s>[INST] episode is also brought to you by better help spelled h E L P help. I often go in my mind to a place where I'm just sitting alone on a desert island. I imagine talking to that volleyball Wilson and just the piece of being away from humanity for a time. So you can be alone with your thoughts. I imagine that. And I also might imagine writing help in the sand when I'm too sick of my own thoughts. Speaking of being too sick of your own thoughts, That's just a funny thing to say. Of course your thoughts dark or beautiful, low or high are your lifelong companions and you should bring them to the surface and you should play with them, you should dance with them and talk therapy is one way to do that. I think podcast things that kind of talk therapy, that's the way to do that. So you should really try out and better help which is a way to do online talk therapy. You can check them out at better help dot com slash lex and save in your first month. This episode is also brought to you by on it, a nutrition supplement and fitness company. They make alpha Brain and you tropic that helps support memory. Mental speed and focus. Like I said, I just took a nap, that's a component number one of ultra focus, component number two for me is caffeine. Then of course there's the zen, like maybe people think of it as meditation ability to block out all the other distractions, but even then sometimes that's not enough if you really want to accomplish something difficult, mentally speaking and so for that I will take an alpha brain every once in a while to help me be the extra super boost for that deep work session. By which I mean sitting there staring at a thing, thinking about it and not allowing your mind to deviate from the focus on that thing. Any way you can get a special discount on alpha Brain at lex Friedman dot com slash on it. This show is also brought to you by indeed hiring website. I've used them many times many, many times in the past for the hiring efforts I've done for the teams that I've led teams have been a part of, I'm doing quite a bit of hiring now for the podcast. Creative kind of efforts a lot of us spend a lot of our day working on a thing. Hopefully it's a thing that you really enjoy doing when it's the thing you enjoy doing. There's to me at least nothing more rewarding than doing it with people you care about people that inspire you people that challenge you people that teach you stuff. So a great team is a beautiful thing. So I really, really care about good hiring tools, services, websites and indeed is um great at that. Anyway, I'm also hiring quite a bit for a lot of things I'm doing now. I'm a little bit behind schedule on that, but I will get to all the resumes quickly and I'm also using indeed as part of this effort, they have a special offer only available for a limited time. Check it out at indeed dot com slash lex. This is the lex Friedman podcast. The supported, please check out our sponsors in the description and now dear friends, here's Will Sasso, so let's call it the elephant in the room. You wore a black suit in a recent episode of Doozy. You wore a black suit again today Shakespeare. Then Mark Twain said, clothes make the man, uh what kind of man does the suit make you? [/INST] Well, me in particular, it makes me a fellow who did not get this dry cleaned in between because that episode of the show as we sit here now is around a week ago. So that's, that's the kind of man. It makes me </s><s>[INST] well, the nice thing is you're wearing pants I think [/INST] yes, I am wearing, I </s><s>[INST] don't think you're wearing pants in the episode. [/INST] That's correct. I I prefer to wear shorts, but this was a special occasion. So I'm wearing pants and I thought it fitting obviously to just wear, you know the black tie and uh clothes do make the man and I'm I would not consider myself to be a man of leisure but I do enjoy shorts because my legs get hot so that's what kind of man the shorts </s><s>[INST] make you wear a suit. [/INST] I fucking hate wearing suits. So </s><s>[INST] what is this a statement of uh is it ironic or is it are you honoring the gods of this particular podcast? [/INST] I'm honoring the gods of this particular podcast would be a good way to put it. Yes. No this is this is in in reverence of and in dedication to you and our newfound friendship here which we are making on the podcast. You and I just met everything that we're saying here is the first things that we're saying to each other. So I'm meeting you on common ground dressed like </s><s>[INST] well I've been actually a one way friend of yours for many, many years since Mad Tv when did you start on Mad T. So that was I mean in nineties [/INST] 97 90 </s><s>[INST] seven so I was a huge fan of yours and the cast was incredible. One of the funniest shows ever created your whole journey watching through. That was was incredible. From at T. V. 23 stooges to the podcast. The 10 minute pot and then the new podcast is incredible. Um [/INST] My </s><s>[INST] favorite role that you played was the mountain and the game of Thrones. What was it like working with dragons? [/INST] Well the dragons are usually tennis balls on the end of c stands but sometimes they they hang out. Um I am, it's like, you know, it's like a little like the thing you got the camera on here. </s> |
<s>[INST] because that maximizes attention and that's like an emergent Matlock type force [/INST] right? That </s><s>[INST] takes any anything any topic and cuts through it so they can split nicely into two groups. One that's, [/INST] well it's it's whatever. Yeah, it's all everyone is trying to do within the system is just maximize whatever gets them the most attention because they're just trying to make money so they can keep their thing going right? And the way the best emotion for getting attention because it's not just about attention on the internet, it's engagement, That's the key thing right? In order for something to go viral, you need people to actually engage with it. They need to like comment or retweet or whatever. Um and of all the emotions that uh you know, there's like seven classic shared emotions that studies have found that all humans, even from like un un previously uncontacted tribes have um some of those are negative, you know, like sadness, disgust, anger, etcetera, some positive happiness, um excitement and so on. The one that happens to be the most useful for the internet is anger because anger is, it's such an active emotion if you want people to engage if someone's scared and I'm not just like talking about my asset, there are studies that looked into this um whereas like if someone's like disgusted or fearful, they actually tend to then be like, I don't want to deal with this, so they're less likely to actually engage and share it and so on. They're just gonna be like where they're enraged by a thing. Well now they're like that triggers all the like the old tribalism emotions. Um and so that's how then things get sort of spread, you know, much more easily they out compete all the other memes in the ecosystem. Um and so this like the attention economy, the wheels that make it go around is rage. Um you know, the problem with raging against the machine is that the machine has learned to feed off rage because it is feeding off our age, that's the thing that's now keeping it going. So the more we get angry the worse it gets. Um </s><s>[INST] so the Malkin this attention in the war of attention is constantly maximizing rage. [/INST] What it is optimizing for is engagement and it happens to be the engagement um is propaganda. You know, it's I mean, it just sounds like every everything is is putting is more and more things being put through this like propagandist lens of winning whatever the war is in question, whether it's the culture war or the Ukraine war. Yeah, </s><s>[INST] well I think the silver lining of this, do you think it's possible that in the long arc of this process, you actually do arrive at greater wisdom and more progress. It just in the moment it feels like people are be tearing each other to shreds over ideas, but if you think about it, one of the magic things about democracy and so on is you have the blue versus red constantly fighting. It's almost like they're in discourse creating devil's advocate making devils out of each other and through that process discussing ideas, like almost really embodying different ideas just to yell at each other and through the yelling over the period of decades, maybe centuries figuring out a better system, like in the moment it feels fucked up, but in the long arc it actually productive, [/INST] I hope so, um that said, we are now in the era of just as we have weapons of mass destruction with nuclear weapons, you know, that can break the whole playing field. We now are developing weapons of informational mass destruction, information weapons, you know, WMDS that basically can be used for propaganda or just manipulating people. However they, you know, is needed, whether that's through dumb Tiktok videos or you know, there are significant resources being put in. Um, I don't mean to sound like, you know, to doom and gloom, but there are bad actors out there. That's the thing, there are plenty of good actors within the system who are just trying to stay afloat in the game, so effectively doing monarchy things. But then on top of that, we have actual bad actors who are intentionally trying to like manipulate the other side into doing things </s><s>[INST] and using because of the digital space, they're able to use um artificial actors meeting bots. [/INST] Exactly, botnets, you know, and this is a whole new situation that we've never had before. </s><s>[INST] It's exciting, you know, you know what I want, you know what I want to do that because there is, you know, people are talking about bots manipulating and um like malicious bots that are basically spreading propaganda. I want to create like a bot army for like that. Like fights that. Yeah, exactly. For love that fights though, that, I mean, [/INST] you know, there's there's, I mean, there's truth to fight fire with fire, it's like, but how you always have to be careful whenever you create again like the monarch is very tricky. </s><s>[INST] Hitler was trying to spread the love to [/INST] Yeah, so we thought but you know, I I agree with you that like that is a thing that should be considered, but there is again everyone the road to hell is paved with good intentions and this is, there's there's always unforeseen circumstance, you know, outcomes, externalities of you trying to adopt a thing even if you do it in the very best of faith, but </s><s>[INST] you can learn the lessons that [/INST] you can run some sims on it first. Absolutely, let's but </s> |
<s>[INST] there's a friendliness about like one way to think about a raise is um raises just like full of numbers but to make them accessible to humans and make them less air prone to human users. Sometimes you want to attach names. Human interpret herbal names that are sticky to those arrays. So that's how you start to think about dictionaries. You start to convert numbers into something that's human interpret herbal and that's actually the tension I've had with Numpy because I've built so much tooling around human uh human interpret ability and also protecting me from a year later not making the mistakes by being I wanted to force myself to use english versus uh numbers. [/INST] Yes. There's a there's a project called label the race. Like very early. It was recognized that oh, we need, we're indexing Numpy was just numbers, all the columns and particularly the dimensions. I mean if you have an image, you don't necessarily have label each column or row, but if you have a lot of images or you have another dimension, you at least like to label the dimensions. This is X. This is why the Z or this is give us some human meaning or some domain strict meaning. That was one of the impetus for pandas actually was just, oh, we do need to label these things. And label label array was an attempt to add that like lighter weight version of that. And there's been like, that's an example of something I think Numpy could add could be added in. Um, Pie, but one of the challenges again. How do you fund this? Like, like I said, one of the tragedies I think is that so I, I never had the chance to, was never paid to work on Numpy. Right? So I've always just done in my spare time. Always taken from one thing taken from another thing to do it. And, and at the time, I mean today it would be the wrong time today. Like paying me to work on empire now would not be a good use of effort. But we are finally at Quan site labs. I'm actually paying people to work on um pine sci fi, which is I'm thrilled with. I'm excited by, uh, I wanted to do that. That's why we wanted to do from day one. It just took me a while to figure out the mechanisms do that </s><s>[INST] even like in the university setting, respecting that like pushing students, young minds of the young graduate students to contribute and then figuring out financial mechanisms that enable them to contribute and then sort of reward them for their um, innovative scientific journey. That, that would be nice. But then also there's just a better allocation of resources. Well, you know, it's a 20 year anniversary since 9 11 and I was just looking, we spent over $6 trillion in the, in the Middle East after 9 11 in the various efforts there and sort of two put politics and all that aside. It's just you think about the education system, all the other ways we could have possibly allocated that money, you to me to take it back, the amount of impact you would have by allocating a little bit of money to uh, the programmers that build the tools that run the world is fascinating. I [/INST] mean, </s><s>[INST] I don't know. I think again, there's some aspect to being broke as somewhat of a feature, not a bug that you make sure that you've [/INST] managed that. </s><s>[INST] I know. I know so, but I don't think that's a big part. So it's like, I think you can, you can have enough money and actually be wealthy while maintaining your values agreed. I [/INST] think agreed there's an old adage that, you know, nations that trade together don't go to war together. I've often thought about, you know, nations that code together because one thing I love about my source is global multinational, like there aren't national boundaries. One of the challenge with business and open source is the fact that businesses national, like businesses or entities that are recognizing legal jurisdictions right? And have laws that are respected in those jurisdictions and hiring. And yet the open source ecosystem is not, it's not, it's not there. Like currently one of the problems we're solving is hiring people all over the world, right? Because we, it's a global effort and I've had the chance to work and I love the chance. I've never been to uh like uh Iran, but I once had a conference was able to talk to people there right? And talk to folks in Pakistan, never been there. But we had a call whether there are people there like just scientists and normal people and you know, and it's, there's a, there's a certain amount of humanizing right that gets away from the we often get the memes of society that bubble up and then get discussed. But the means are not even an accurate reflection of the reality of what people are. </s><s>[INST] Well, if you look at the major power centers that are leading to something like cyber war in the next few decades, it's the United States Russia and china. And the those three countries in particular have incredible developers. So if they work together, I think that's one way the politicians can do their stupid bickering. But like the there's a layer of infrastructure of humanity if they collaborate together that that I think can prevent major, major conflict, which would, I think most likely happened at the cyber level versus the actual hot war level. [/INST] You're right. You know, I think that's good. That's good prediction nations </s><s>[INST] that code together, don't go to [/INST] work together to work together. That's the whole right. That's one of the philosophical hopes. But </s> |
<s>[INST] to apparently to realize that. That's one of the things you realize with the war is there's not going to be a strong signal that things are not working. If you just keep pouring money into the thing, [/INST] a military effort thing. Well, also there are signs of it working too, you have all the stories of girls now going to school, right, you know, the girls are getting battery acid thrown in their faces by religious maniacs. And then we come in there and we stop that. And now girls are getting educated and there's, I mean, and that's all good. And our intentions are good there. And I mean, we're on the right side of history there, girls should be going to school. You know, Malala Yosafzai should have the Nobel Prize and she shouldn't have been shot in the face by the Taliban, right? We know what the right answers are there. The question is, what do you do when there are enough, in this particular case, religious maniacs, who are willing to die and let their children die in defense of crazy ideas and moral norms that belong in the seventh century? And it's a problem we couldn't solve, and we couldn't solve it even though we spent </s><s>[INST] trillions of dollars to solve it. This reminded me of the thing that you and Jack Dorsey jokingly had for a while, the discussion about banning Donald Trump from Twitter. But does any of it bother you now that Twitter files came out that, I mean, this has to do with sort of the Hunter laptop, Hunter Biden laptop story. Does it bother you that there could be a collection of people that make decisions about who to ban and not? And then that could be susceptible to bias [/INST] and to ideological influence. Well, I think it always will be, or in the absence of perfect AI, it always will be. </s><s>[INST] And this becomes relevant with AI as well. Yeah. Because you have some censorship on AI happening. Yeah. [/INST] And it's an interesting question there as well. I don't think Twitter is what people think it is, right? And I used to think it was more important when I was on it, and now that I'm off of it, I think it's, I mean, first let me say, it's just an unambiguously good thing in my experience to delete your Twitter account, right? It's like, it is just, even the good parts of Twitter that I miss were bad in the aggregate, in the degree to which it was fragmenting my attention, the degree to which my life was getting doled out to me in periods between those moments where I checked Twitter, and had my attention diverted. And I was not a crazy Twitter addict. I mean, I was probably a pretty normal user. I mean, I was not someone who was tweeting multiple times a day or even every day, right? I probably, I think I probably averaged, right? And I had something like one tweet a day, I think I averaged, but in reality, it was like, there'd be like four tweets one day, and then I wouldn't tweet for the better part of a week. But I was looking a lot because it was my news feed. I was just following 200 very smart people, and I would just wanted to see what they were paying attention to. They would recommend articles, and I would read those articles. And then when I would read an article, then I would thought I should signal boost, I would tweet. And so all of that seemed good. And that's all separable from all of the odious bullshit that came back at me in response to this, largely in response to this Hunter Biden thing. But even the good stuff has a downside. And it comes at just this point of your phone is this perpetual stimulus of, which is intrinsically fragmenting of time and attention. And now my phone is much less of a presence in my life. And it's not that I don't check Slack or check email. And I use it to work, but my sense of just what the world is and my sense of my place in the world, the sense of where I exist as a person has changed a lot by deleting my Twitter account. I mean, I had a, and it's just, it's, and the things that I think, I mean, we all know this phenomenon. I mean, we say of someone that person is too online, right? Like, what does it mean to be too online? And where do you draw that boundary? How do you know? What constitutes being too online? Well, in some sense, just being, I think being on social media at all is to be too online. I mean, given what it does to, given the kinds of information it signal boosts and given the impulse it kindles in each of us to reach out to our audience in specific moments and in specific ways, right? It's like, there are lots of moments now where I have an opinion about something, but there's nothing for me to do with that opinion, right? Like there's no Twitter, right? So, like there's lots of things that I would've tweeted in the last months that are not the kind of thing I'm gonna do a podcast about. I'm not gonna roll out 10 minutes on that topic on my podcast. I'm not gonna take the time to really think about it, but had I been on Twitter, I would've reacted to this thing in the news or this thing that somebody did, right? What do you do with that thought? </s><s>[INST] No, I just let go of it. [/INST] Like chocolate ice cream is the most delicious thing ever. It's usually not that sort of thing, but it's just, but then you look at the kinds of problems people create for themselves. You look at the life deranging and reputation destroying things that people do. And I look at the things that have, the analogous things that have happened to me. I mean, the things that have really bent my life around professionally over the past decade. So much of it is Twitter. I mean, honestly, in my case, almost 100% of it was Twitter. The controversies I would get into, the things I would think I would have to respond to and, like I would release a podcast on a certain topic, I would see some blow back on Twitter. It would give me the sense that there was some signal that I really had to respond to. Now that I'm off Twitter, I recognize that most of that was just, it was totally species. It was not something I had to respond to, but yet I would then do a cycle of podcasts responding to that thing that like taking my foot out of my mouth or taking someone else's foot out of my mouth. And it became this self perpetuating cycle, which I mean, if you're having fun, great. I mean, if it's generative of useful information and engagement professionally and psychologically, great. But, and there was some of that on Twitter. I mean, there were people who I've connected with because I just, you know, one of us DM'd the other on Twitter and it was hard to see how that was gonna happen otherwise. But it was largely just a machine for manufacturing unnecessary controversy. </s> |
<s>[INST] but that's how you can have a chance. [/INST] Yeah that's how you can have a chance. Exactly. And and I think it's also what you know this to me this rapid testing program like this is the most dead simple solution in the world and </s><s>[INST] this literally could change the world. It [/INST] could change the world. It could change and it is you know there's countries that are doing it now. The U. S. Isn't but I've been advising many countries on it And and I would say that you know some of the early papers that we put out earlier on a lot of the things actually are changing. You don't know unless you really look hard. You don't know where you're actually having an effect. Sometimes it's more overt than and other times um In april I published a paper that was saying hey with the PcR values from these tests we need to really focus on the ct values the actual quantitative values of these lab based PcR tests at the time. All the physicians and laboratory directors told me that was stupid why would you do that? They're not accurate enough. And of course now it's headline news that florida they just mandated reporting out the C. T. Valley's of these tests because there's a real utility of them. You can understand public health from it, you can understand better clinical management. Uh you know that was a simple solution to a pretty difficult problem. Uh and it is changing the way that we approach all of the lab testing in this country is starting to, it's taken a few months but it's starting to change because of that. And you know that was just me saying hey this is something we should be focusing on. Got some other people involved in other people and and now people recognize hey there's actual value in this number that comes out of these lab based pcr tests. So sometimes it does grow fairly quickly. Um but I think the real answer is my only, my only answer. I don't know what you know, I recognize that everyone, some people are going to be really focused on and have one small but deep skill set. I go the opposite direction. I try to bring bring things together and um but the biggest thing I think is just don't see problem. Don't don't see barriers. Like just see like there's always a solution to a barrier. If there's a barrier that literally means us a solution to it, that's why it's called a barrier. And </s><s>[INST] just like you said most people will just present to you only be thinking about it and present you with barriers. And so it's easy to start thinking that's all there is in this [/INST] world and just think big, I mean God there's nothing wrong with thinking big Elon musk that big and then thinking big builds on itself, you know, you you get a billion dollars from one big idea and then that allows you to make three new big ideas </s><s>[INST] and there's a hunger for it. If you think big and you communicate that vision with the world, all the most brilliant and passionate people will just like you'll attract them and they'll come to you and then it makes your life actually really exciting that people have met at like Tesla and uh neural link, I mean there's just like this fire in their eyes, they just love life and uh it's amazing I think to be around those people, I have to ask you about what was the philosophy, the journey that took you to becoming a buddhist monk and what what were, what did you learn about life, what did you take away from that experience? How did you return back to Harvard and uh the world that's unlike that experience I imagine. [/INST] Yeah, well I was at Dartmouth at the time um uh well I went to Sri Lanka, I was already pretty interested in developing countries in under resourced areas and uh I was doing a lot of engineering work and I went there but I was also starting to think maybe health was something of interest um and so I went to sri Lanka because I had a long interest in buddhism as well, just kind of interested in it as a thing, </s><s>[INST] which aspect of the philosophy attracted you, [/INST] I would say that the thing that interested me most was um was really this idea of kind of a butterfly effect of like uh you know what you do now has ripple effects that extend out beyond what you can possibly imagine both in your own life and in other people's lives. And in some ways buddhism has not in some ways, in a pretty deep way, buddhism has that as part of its underlying philosophy in terms of rebirth and sort of your actions today propagate uh to others, but also propagate to to sort of uh what might happen in in your circle of what's called Samsara and rebirth and um I don't, I don't know that I subscribe fully to this idea that we are reborn, which always was a little bit of of a debate internally, I suppose it was a monk, but but it has always been, it was that and then it was also meditation at the time, I was a fairly elite rower. I was growing at the national level and and growing to me was very meditative, it was, you know, just there's even if you're on a boat with other people, it's, I mean on the one hand it's like the extreme of like a team sport, but it's also the extreme sort of focus and concentration that requires that's required of it. And so I was always really into just meditative type of things, is doing a lot of pottery too, which was also very meditative and, and so buddhism just kind of really, really, there are a lot of things about meditating um that just appealed and so I moved to sri Lanka planning to only be there for a couple of months um and then I was shadowing in this medical clinic and there was this physician who was just really, I mean it's just kind of a horrible situation um frankly this guy was trained decades earlier, he was an older physician and he was still just practicing like these fairly barbaric approaches to medicine because he had was a rural town and he just didn't have a lot of, he didn't have any updated training frankly. And so, you know, I just remember this girl came in with shrapnel in her hand and his solution was to like air it out. And so he was like without even numbing her hand, he was like cutting it open more with this idea that like the more oxygen and stuff, you know, and it just, I think there was something about all of this and I was already talking to these monks at the time, each I would be in this clinic in the morning and I'd go and my idea was to teach english to these monks in the evening uh turned out I'm a really bad english teacher. Uh, so they just thought they allowed me just to sit with them and meditate and they were teaching me more about buddhism than I could have possibly talked him about english or being an american or something. Um, and uh, and, and so I just slowly, I just couldn't take, I like couldn't handle being in that clinic. So more and more, I just started moving to spending more and more time at this monastery and then after about two months I was supposed to come back to the States and I decided I didn't want to. So I moved to this monastery in the mountains primarily because I didn't have the money to like just keep living. So I was living in a monastery is free and so I moved there and just started meditating more and more and then months went by and, and I've, it just really gravitated, I gravitated to the whole to the whole notion of it. I mean it became, it sounds strange, but meditating almost just like anything that you put your mind to Became exciting. You know, it became like there weren't enough hours in the day to meditate and I do it for 18 hours a day, 15 hours a day, uh just sit there and you and like, I mean I hate sleeping anyway, um, but I wouldn't want to go to sleep because I felt like I didn't accomplish what I need to accomplish in meditation that day, which is so strange because there is no end, you know? But it was always, but there are these uh there are these steps that happen during meditation that are very prescribed in a way buddha talked about them, you know, and these are ancient writings which exist in the writings are real, there are thousands of years old now and um you know the weather was buddha writing them or whoever, you know, there there are lots of different people have contributed to the, to these writings over the years and but they're very prescribed and they tell you what you're going to go through and I didn't really focus too much on them. I read a little bit about them, but your mind really does when you actually start meditating at that level, like not an hour here and there, but truly just spending your day is meditating, it becomes kind of like this other world where it becomes exciting and uh and you're actively working, you're actively meditating, not just kind of trying to quiet things that sort of just the first stage of trying to get your mind to focus. Most people never get past that first stage, especially in our culture, </s> |
<s>[INST] can't believe master class have done this work of putting this all together. It's, it's just amazing if for no other reason, you should just support their efforts in doing so, get unlimited access to every master class and get 15% off an annual membership. If you go to master class dot com slash lex this show is brought to you by indeed hiring website. [/INST] I've used them </s><s>[INST] as part of many hiring efforts I've done for the teams I've led in the past. They have tools like indeed is the match that gives you quality candidates whose resumes that indeed fit your job description immediately. There are very few things as important in life as figuring out who are the people you surround yourself with and because we spent so much of our time at work, it's really important to select the [/INST] people you work with </s><s>[INST] and make sure you build a team that [/INST] um make you </s><s>[INST] excited to wake up in the morning [/INST] to take </s><s>[INST] on the day because some of the hardest things we do in life are those that work. The ones that push us to our limits, challenges mentally and physically all of that kind of stuff. And so [/INST] your brothers </s><s>[INST] and sisters in arms with the people you work with [/INST] and it's </s><s>[INST] extremely important from a perspective of employer and the employee to make sure the team is one that you're proud of, that you're happy with. Anyway. Right now you get free 70 [/INST] five </s><s>[INST] dollars sponsored job credit to upgrade your job post. You can get up to 500 bucks extra and sponsored job credits with Indeed virtual interviews at indeed dot com slash flex offers good for a limited time terms and conditions apply. This is the lex Fridman podcast to support it. Please check out our sponsors in the description and now your friends here's Donald Hoffman in your book the case against reality why evolution hid the truth from our eyes. You make the bold claim that the world we see with our eyes is not real. It's not even an abstraction of objective reality, It is completely detached from objective reality. Can you explain this idea? [/INST] Right. So this is a theorem from evolution by natural selection. So the technical question that my team asked was what is the probability that natural selection would shape sensory systems to see true properties of objective reality? And to our surprise, we found that the answer is precisely zero. Except for one one kind of structure that we can go into if you want to. But for for any generic structure that you might think the world might have a total order topology metric. The probability is precisely zero. That natural selection would shape any sensory system of any organism to see any aspect of objective reality. So, in that sense, what we're seeing is what we need to see to stay alive long enough to reproduce. So in other words, we're seeing what we need to guide adaptive behavior full stop. </s><s>[INST] So the evolutionary process, the process that took us from the origin of life on earth to the humans that we are today. That process does not maximize for truth maximizes for fitness. As you say, fitness beats truth and fitness does not have to be connected to truth is the claim. And that's where you have an approach towards zero of probability that we have evolved human cognition, human consciousness, whatever it is, the magic that makes our mind work evolved not for its ability to see the truth of reality, but its ability to survive in the environment. [/INST] That's exactly right. So most of us intuitively think that surely the way that evolution we'll make our senses more fit is to make them tell us more truth or at least the truth we need to know about objective reality. The truth we need in our niche. That's the standard view. And it was the view I took. I mean that's sort of what we're taught or just even assume it's just sort of like the intelligent assumption that we would all make. But we don't have to just wave our hands. Evolution of natural selection is a mathematically precise theory. Uh john Maynard smith in the seventies created evolutionary game theory and we have evolutionary graph theory and even genetic algorithms that we can use to study this. And so we don't have to wave our hands. It's it's a matter of thurman proof and or simulation before you get the terms improves. And a couple of graduate students of mine Justin Mark and brian Marian did some wonderful simulations that tipped me off that there was something going on here and then I went to a mathematician Caitlin Precaution Manish Singh and uh some other friends of mine chris fields and but was the real mathematician behind all this and he's proved several theorems that uniformly indicate that with one exception, which has to do with probability measures. Um there's no the probability of zero. The reason there's an exception for probability measures. So called sigma algebra is or or segmented classes is that for any scientific theory, there is the assumption that needs to be made that the whatever structure, whatever probabilistic structure the world may have is not unrelated to the probabilistic structure of our perceptions. If they were completely unrelated, then no science would be possible. So and so this is technically there. The map from reality to our senses has to be a so called measurable map has to preserve sigma algebra, but that means it could be infinite to one and it could collapse all sorts of event information. But other than that there's, there's no requirement in standard evolutionary theory for fitness payoff functions, for example, to preserve any specific structures of objective reality. So you can ask the technical question, This is one of the avenues we took um If you look at all the fitness payoffs from whatever world structure you might want to imagine. So a world with say a total order on it. So it's got end states and they're totally ordered and then you can have a set of maps from that world into a set of payoffs, say from 0 to 1000 or whatever you want, your payoffs to be. And you can just literally count all the payoff functions and just do the combinatorics and count them. And then you can ask a precise question how many of those payoff functions preserve the total order, if that's what you do or how many preserve the topology and you just count them and divide. So, so the number that are homo morph ISMs versus the total number, and then take the limit as the number of states in the world and the number of payoff values goes very large. And when you do that, you get zero every time. </s> |
<s>[INST] So using the term of higher states of consciousness, [/INST] yes. </s><s>[INST] Is consciousness an important part of that word? What what, why higher? Uh is it is it is it a higher state or is it a detour a side road on the main road of consciousness? What [/INST] I think the psychedelic state is on a continuum, there's insight and then flow is an insight cascade, there's flow and then you can have sort of psychedelic experiences, mind revealing experiences and then, but they overlap with mystical experiences and they aren't the same. Um so for example, in the griffiths lab, they gave people psilocybin and they taught them ahead of time how like sort of the features of a mystical experience and only a certain proportion of the people that took the psilocybin went from a psychedelic into a mystical experience. What was interesting is the people that had the mystical experience had measurable and longstanding change to one of the big five factors of personality. They had increased openness. Openness is supposed to actually go down over time and these traits aren't supposed to be that malleable and it was significantly like altered, right? But imagine if you just created more openness and a person, right? And they're now open to a lot more and they want to explore a lot more, but you don't give them the tools of discernment that could be problematic for them in important ways that could be very problematic. </s><s>[INST] I got it. But, you know, so you have to land the plane uh in a productive way, somehow integrated back into your life and how you see the world and how you frame your perception of that world. [/INST] And when people do that, that's when I call it a transformative experience. Now, the higher states of consciousness are really interesting because they tend to move people from a mystical experience into a transformative experience. Because what happens in these experiences is something really, really interesting. They get to a state that's ineffable, they can't put it into words, they can't describe it, but they do this this this there in this state state temporarily, and then they come back and they do this, they say that was really real and this in comparison is less real. So I remember that platonic meta desire, I want to change my life myself so that I'm more in conformity with that really real. And that is really odd lex because normally when we go outside of our consensus intelligibility, like a dream state, we come back from it. We say that doesn't fit into everything, therefore it's unreal. They do the exact opposite. They come out of these states and they say that doesn't fit into this right consensus right intelligibility and that means this is less real. They do the exact opposite and that fascinates me. Why do they why do they flip our normal procedure about evaluating alternative states and what the thing is those higher states of consciousness precisely because they have that onto normative itty, the the realness that demands that you make a change in your life. They serve to bridge between mystical experiences and genuine transformative. </s><s>[INST] So you do think seeing those as more real as productive because then you reach for them. [/INST] So yeah, has done work on it. Um you know, and again, all of this is all of this stuff is recent, so we have to take it with a grain of salt, but you know, by a lot of objective measure people who do this, who have these higher states of consciousness and undergo that and undertake the transformative process. Their lives get better, the relationships improve right, their sense of self improves, their anxieties go down depression. Like all of these other measures are the needles are moved on these measures by people undergoing this transformative experience, their lives by many of the criteria that we judge our lives to be good, get better. </s><s>[INST] I have to ask you about this fascinating distributed cognition process that leads to mass formation of ideologies that have had an impact on our world. So, you spoke about the clash of the two great pseudo religious ideologies of Marxism and nazism, especially their clash on the Eastern front. Can you explain the origin of each of these Marxism and nazism in a kind of way that we have been talking about the formation of ideas. [/INST] Hagel is to protestantism, what thomas Aquinas is to Catholicism. He he was like the philosopher who took german protestantism and and also Kant and victor and shelling and he built a philosophical system. He explicitly said this by the way he wanted to bridge between philosophy and religion. He explicitly said that, I'm not I'm not foisting that on him. He said it repeatedly in many different places, so he's trying to create a philosophical system that gathered to it. I think the core mythos of Christianity, core mythos of Christianity is this idea of a narrative structure to reality, in which progress is real in which our actions now can change the future. We can co participate with God in the creation of the future and that future can be better. It can reach something like a utopia or the promised land or whatever. He created a philosophical system of brilliance by the way, he's a genius. But basically what it did was it took that religious vision and gave it the air of philosophical intelligibility and respect. And then Marx takes that and says, you know, that process of the by which the narrative is working itself out, that Hagel called dialectic, I don't think it's primarily happening in ideas. I think it's happening primarily in between classes within socio economic factors. But it's the same story, here's this mechanism of history. It's t ideological, it's gonna move this way. It can move towards a utopia. We can either participate in furthering it like participating in the work of God, or we can thwart it and be against it. And so, you have a you have a pseudo religious vision, it's all encompassing think about how Marxism is not just a philosophical position, it's not just an economic position, it's an entire worldview and entire account of of history and and a a demanding account of what human excellence is. And it has all these things about participating, belonging fitting to. But </s> |
<s>[INST] Well let me um take a small tangent. We're going to jump around in time which I think will be the best way to tell this story. So that was the beginning. [/INST] Yeah. Okay. Actually can I can I can I go back one more thing for that because that's really important and I should have I should have started with this. Um What led me to do those studies was a paper that I had remembered seeing from the H. One N. One flu epidemic in 2000 and nine. This is this is where I have been much less active in writing about that. I had written like a paper or two about that when in 2000 and nine um there there was actually the same debate over the mortality rate Except it unfolded over the course of three years, 2 or three years. The early studies of the mortality rate in H. One N. One counted the number of cases in the denominator kind of the number of deaths in the numerator cases meaning people identified as having one N. One showing up the doctor, you know tested to have it. Um And the early estimates of the H one N. One mortality were like 4% 3% really really high. Over the course of a couple of more years, a whole bunch of syrup prevalence studies. Syria prevalence studies of H one N one flu came out and it turned out that there were 100 or more times people infected per case. And so the mortality it was actually something like .02 for H one N. One not the 33 like a hundredfold difference. </s><s>[INST] So this made you think, okay it took us a couple of two or three years to discover the truth behind the actual infections uh for H. One N. One. And [/INST] then what's the truth </s><s>[INST] here and can we get there [/INST] faster? Yeah. And and there was it spreads in a similar way as the as the H one N. One flu did. I mean it's it's spread via aerosols civilization via you know the the person person breathing kind of kind of contact. Um Maybe maybe some by by film ice but seems like that that's less likely now. In any case it seemed really important to me to speed up the process of having those zero prevalence studies so that we can better understand who was at risk and what the right strategy ought to be. </s><s>[INST] This might be a good place to kinda compare influenza, the flu and Covid in the context of the discussion we just had, which is how deadly is covid. So you mentioned, Covid is a very particular kind of steepness. Uh more of the X axis is age. So in that context could you maybe compare influenza and Covid because a lot of people um outside the folks who suggest that the lizards who run the world have completely fabricated invented Covid. Outside of those folks, kind of the natural process by which you dismiss the threat of Covid and say what's just like the flu? The flu is a very serious thing actually. Um So in that comparison, where does Covid stand? [/INST] Yeah, the flu is a very serious thing. It kills, you know, 50, people a year. Something I found that order depending on the particular strain that goes around that's in the United States. The primary difference to me, there's lots of differences but one of the most salient differences is the age gradient and mortality risk for the flu. So the flu is more deadly for two Children than Covid is. There's no controversy about that. Children. Thank God have much less uh severe reactions to covid infection to then due to flu infections </s><s>[INST] and rate of fatalities, [/INST] fatalities. All of that </s><s>[INST] I think you mentioned. Um I mean it's interesting to maybe also comment on, I think in another conversation mentioned there's a U shape to the to the flu curve. So meaning like there's actually quite a large number of kids that die from flu. [/INST] Yeah, I mean the 1918 flu, the H1N1 flu that that the Spanish flu in the us killed millions of of of of younger people. And um that is not the case with Covid More than um I'm going to get the number wrong but something like 70, of the deaths are people over the age of 60. </s><s>[INST] Well we've talked about the fear the whole time really. But my interaction with folks now I want to have a family. I want to have kids but I don't have that real firsthand experience. But my interaction with focus is at the core of fear that folks had is for their Children like that somehow. You know, I don't want to get infected because of the kids like because God forbid something happens to the kids. And I think that obviously that makes a lot of sense. That's kind of the kids come first no matter what, that's number one priority. But for this particular virus, that reasoning was not grounded in data it seems like or that emotion and feeling grounded [/INST] at the same time this is way more deadly than the flu just overall and especially to older people. Yes. </s><s>[INST] Right. So the numbers when when the story is all said and done the Covid would would take many more lives. Yeah. [/INST] So I mean point to it sounds like a small number but it's not a small number </s><s>[INST] worldwide. What do you think that number will be by the, you know, that's not that's not like me. But would we cross, I think it's in the United States, it's um The way the deaths are currently reports like 800,000, something like that. Do you think we'll cross a million [/INST] Seems likely. </s><s>[INST] Do you think it's something that might continue with different variants? What? [/INST] Well, I I think so we can talk about the end state of Covid. The end state of Covid is it's here forever. Um I think that there is good evidence of immunity after infection such that you're protected both against reinfection and also against severe disease upon reinfection. So the second time you get it, it's not true for everyone. But for many people, the second time you get it will be milder, much milder than the first time you get it </s> |
<s>[INST] improvements in human condition. So as most people know, you're not just an eloquent, romantic, you're also a brilliant computational biologist, biologist, one of the great biologists in the world. I had to ask, how do the language models, how these large language models [/INST] and the investments in AI affect the work you've been doing? So it's truly remarkable to be able to sort of be able to encapsulate this knowledge and sort of build these knowledge graphs and build representations of these knowledge in these sort of very high dimensional spaces, being able to project them together jointly between say single-cell data, genetics data, expression data, being able to sort of bring all these knowledge together allows us to truly dissect disease in a completely new kind of way. And what we're doing now is using these models. So we have this wonderful collaboration, we call it drug GWAS with Brad Penteluto in the chemistry department and Marinka Zitnick in Harvard Medical School. And what we're trying to do is effectively connect all of the dots to effectively cure all of disease. So it's no small challenge, but we're kind of starting with genetics. We're looking at how genetic variants are impacting these molecular phenotypes, how these are shifting from one space to another space, how we can kind of understand the same way that we're talking about language models, having personalities that are cross-cutting, being able to understand contextual learning. So Ben Langer is one of my machine learning students. He's basically looking at how we can learn cell-specific networks across millions of cells, where you can have the context of the biological variables of each of the cells be encoded as an orthogonal component to the specific network of each cell type. And being able to sort of project all of that into sort of a common knowledge space is transformative for the field. And then large language models have also been extremely helpful for structure. If you understand protein structure through modeling of geometric relationships, through geometric deep learning and graph neural networks. So one of the things that we're doing with Marinka is trying to sort of project these structural graphs at the domain level rather than the protein level, along with chemicals, so that we can start building specific chemicals for specific protein domains. And then we are working with the chemistry department and Brad to basically synthesize those. So what we're trying to create is this new center at MIT for genomics and therapeutics that basically says, can we facilitate this translation? We have thousands of these genetic circuits that we have uncovered. I mentioned last time in the New England Journal of Medicine, we had published this dissection of the strongest genetic association with obesity. And we showed how you can manipulate that association to switch back and forth between fat burning cells and fat storing cells. In Alzheimer's just a few weeks ago, we had a paper in nature in collaboration with Li-Wei Tsai, looking at APOE4, the strongest genetic association with Alzheimer's and we showed that it actually leads to a loss of being able to transport cholesterol in myelinating cells known as oligodendrocytes that are basically protected neurons. And whether they cholesterol gets stuck inside the oligodendrocytes, it doesn't form myelin. The neurons are not protected and it causes damage inside the oligodendrocytes. If you just restore transport, you basically are able to restore myelination in human cells in mice and to restore cognition in mice. So all of these circuits are basically now giving us handles to truly transform the human condition. We're doing the same thing in cardiac disorders, in Alzheimer's, in neurodegenerative disorders, in psychiatric disorders, where we have now these thousands of circuits that if we manipulate them, we know we can reverse disease circuitry. So what we want to build in this coalition that we're building is a center where we can now systematically test these underlying molecules in cellular models for heart, for muscle, for fat, for macrophages, immune cells, and neurons, to be able to now screen through these newly designed drugs through deep learning and to be able to sort of ask which ones act at the cellular level, which combinations of treatments should we be using. And the other components that we're looking into decomposing complex traits like Alzheimer's, and cardiovascular, and schizophrenia, into hallmarks of disease, so that for every one of those traits, we can kind of start speaking the language of what are the building blocks of Alzheimer's. And maybe this patient has building blocks one, three, and seven, and this other one has two, three, and eight, and we can now start prescribing drugs not for the disease anymore, but for the hallmark. And the advantage of that is that we can now take this modular approach to disease instead of saying there's going to be a drug for Alzheimer's which is going to fail in 80% of the patients. We're going to say now there's going to be 10 drugs, one for each pathway. And for every patient, we now prescribe the combination of drugs. So what we want to do in that center is basically translate every single one of these pathways into a set of therapeutics, a set of drugs that are projecting the same embedding subspace as the biological pathways that they alter so that we can have this translation between the dysregulations that are happening at the genetic level, at the transcription level, at the drug level, at the protein structure level and effectively take this modular approach to personalized medicine, we're saying I'm going to build a drug for Lex Friedman is not going to be sustainable. But if you instead say, I'm going to build a drug for this pathway and a drug for that other pathway, millions of people share each of these pathways. So that's the vision for how all of this AI and deep learning and embeddings can truly transform biology and medicine. Where we can truly take these systems and allow us to finally understand disease at a superhuman level by sort of finding these knowledge representations, these projections of each of these spaces and try understanding the meaning of each of those embedding sub-spaces and sort of how well populated it is, what are the drugs that we can build for it </s> |
<s>[INST] Can we you mentioned with artificial intelligence sort of us human beings not having a monopoly unconsciousness. There's the idea of artificial intelligence systems, computational systems being able to basically replacing us humans scare you. Excite you. [/INST] What do you think about? So I'm going to tell you about a conversation I once had with eric Schmidt was sitting at a meeting with him and he was a few feet away and he turned to me and he said uh something like you know, jim and maybe a decade or so we're gonna have computers that do what you do. And my response was not unless they can dream because there's something about the human, the way that we humans actually generate creativity. It's somehow I get this sense of my lived experience and watching creative people that somehow connected to the irrational parts of what goes on in our head. And dreaming is part of that irrational. So unless you can build a piece of artificial intelligence that dreams that was strong suspicion that you will not get something that will fully be conscious by a definition that I would accept for example. </s><s>[INST] So you mentioned dreaming, you've played around with some out there fascinating ideas. How do you think? And we'll start diving into the world of the very small ideas of supersymmetry and all that in terms of visualization in terms of how do you think about it? How do you dream of it? How do you come up with ideas in that fascinating, mysterious space. [/INST] So in my workspace which is basically where I am charged with coming up on coming up on a mathematical palette with new ideas that will help me understand the structure of nature and hopefully help all of us understand structure of nature. Uh I've observed several different ways in which my creativity expresses itself. There's one mode which looks pretty normal which I sort of think of as the chinese water torture methods drop, drop, drop, you get more and more information and suddenly it all congeals and you get a clear picture and so that's kind of a standard way of working. And I think that's how most people think about uh the way technical people solve problems that is kind of you accumulate this body of information at a certain point, you synthesize it and then boom, there's something new. But I've also observed in myself and other scientists. There are other ways that we are creative, creative and these other ways to me are actually far more powerful. I first personally experienced this when I was a freshman at MIT live over in baker house right across the campus and I was in a calculus course 80, no one is called an mit and calculus comes in two different flavors. One of them is called differential calculus. The others called integral calculus, differential calculus is the calculus that Newton invented to describe motion. It turns out integral calculus was probably invented about 1700 years earlier by our comedians, but we didn't know that when I was a freshman. But so that's what you study as a student. And the differential calculus part of the course was to me, I wouldn't how do I say this? It was something that that by the drip drip drip method, you could sort of figure it out now. The integral part of calculus. I could memorize the formula. That was not the formula. That was not the problem. The problem was why in my own mind, why do these formula work? And because of that, when I was in the part of the calculus course where we had to do multiple substitutions to solve integral, I had a lot of difficulty. I was emotionally involved in my education because this is where I think the passion emotion comes to and it caused an emotional crisis that I was having these difficulties understanding the integral part of calculus. Why? Why? That's right. The why of it not the rote memorization of facts, but the why of it. Why does this work? And so one night I was over in my dormitory room in baker house, I was trying to do a calculus problem set. I was getting nowhere. I got a terrific headache. I went to sleep and had this very strange dream and when I work walk awakened I could do three and four substitution and integrates with relative ease. Now this to me was an astounding experience because I had never before my life understood that one subconscious is actually capable of being harnessed to do mathematics. I experienced this and I've experienced this more than once. So this was just the first time why I remember it so. So that's why when it comes to like really wickedly tough problems, I think that the kind of creativity that you need to solve them is probably the second variety which comes somehow from dreaming. </s><s>[INST] Do you think again I told you I'm Russian, so we romanticize suffering. But do you think part of that equation is the suffering leading up to that dreaming? [/INST] So the suffering is I am convinced that this kind of creative, the second mode of creativity as I like to call it. I'm convinced that this second mode of creativity is in fact uh that suffering is a kind of crucible that triggers it because the mind I think is struggling to get out of this. And the only, the only way there's actually solved the problem and even though you're not consciously solving problems, something is going on. And I've talked about to a few other people and I've heard other similar stories. And so I, the way I guess so I think about it is it's a little bit by like the way that uh thermonuclear weapons work. I don't know if you know how they work, but a thermonuclear weapon is actually two bombs, it's an atomic bomb, which sort of does an impression. And then you have a fusion bomb that goes off and somehow that emotional pressure I think acts like the first stage of a thermonuclear weapon. That's when we get really big thoughts. </s> |
<s>[INST] That's so fascinating because the reporting so symptom is what you feel. And certainly the mind has the ability to conjure up feelings. [/INST] Oh, yes, </s><s>[INST] absolutely. And so like culturally, you know, maybe there was a time in our culture where it was looked down upon to to feel sick or something like that, like toughen up kind of thing. And so then you probably have very few symptoms being reported and then now is like much more, um, I don't know, perhaps you're much more likely to report symptoms. That is fascinating, because then it changes, [/INST] it is definitely a perception because, you know, your symptoms may be nothing to me or vice versa. Right? And so when you're doing this, it's a little bit of, uh, imprecise science because, and, and, and even it's a cultural thing in some countries. Uh, something that would make us feel horrible. They wouldn't even bother reporting though I didn't have any symptoms. So it's a little bit and precise and it clouds the results. So if you can measure things, it's always better. But you start out with a symptom And if you say if someone tells you this virus, 20% of the people are asymptomatic. They don't report symptoms. That number is probably not a constant. It depends where you did the study. It could be different in China versus south America, europe, etcetera. Yeah, </s><s>[INST] I mean, I was trying to, so I took two shots of the Pfizer vaccine. I had zero symptoms, wow. So, and I was wondering what c because that's my feelings. Right? This is not because I felt fine. I was waiting. [/INST] Did you have pain at the injection site? </s><s>[INST] Uh, no, it was kind of pleasant. [/INST] You felt nothing the next day. </s><s>[INST] Nothing tiredness. The exhaustion. No. Um, but see like have an insane sleeping schedule already put myself through. Crazy stuff that said, maybe I was expecting something really bad, like I was way and therefore didn't feel it then. But I also got, um, allergy shots and those, I was out all next day, like exhausted for some reason. So that, that gave me like a sense like, okay, at least sometimes I can feel shitty. That's good to know. And then with the vaccine it didn't. But the question is like, how much does my mind come into play? There are the expectations of symptoms, the expectations of not feeling well. How does that affect the sort of the self [/INST] reporting of the symptoms? I think it's definitely a variable there, but there's certainly many people that don't feel anything after the vaccines and there's some that have a whole range of things like soreness and fever etcetera. </s><s>[INST] So, okay, you were talking about the old school development side, the egg. [/INST] Right? </s><s>[INST] What's uh, what's, what's better than that? So [/INST] Then the next generation of vaccines which arose in the 50s were what we call replication competent. Where the virus you taken, it's actually reproducing in you. </s><s>[INST] Yeah, that sounds [/INST] safe and it can be somewhat problematic. Yes. As you might imagine because you're not once you put that virus in you, you have no more control. Right? It's not like you have a kill switch in it, which actually would be a great idea to put in </s><s>[INST] like, like nano nano bots, what composite? [/INST] You could just put something in there. If you added a drug you would shut off. Right? And people are thinking about that because now we're engineering viruses to treat cancers and other diseases. And we we may want to put kill switches in them just to make sure they don't run away. </s><s>[INST] Oh, interesting. So you can deploy a drug that binds to the this this virus that would shut it off in the body, [/INST] something like that. Yeah, that would be the idea. You have to engineer it in any way. These were the first one was yellow fever vaccine that was made because that was a big problem. And this virus and the way you do this back in the old day was empirical. So max Tyler who did the yellow fever vaccine, he took the virus which is a human virus, right? And he infected I think he used chick embryos and he went from one embryo to another and just kept passing. He did that hundreds of times And every 10 passages, he would take the virus and put it in a mouse or a monkey whatever his model was. And then eventually he got a virus that didn't cause any disease After 200 and some passages and then that was tested in people. And it became the yellow fever vaccine that we used today. He selected for mutations that made the virus not cause disease but still Make an immune response. So those are called replication competent. We now have the polio vaccine which was developed in the 50s after the yellow fever, then we had measles, mumps, rubella, those are all replication competent vaccines. And you mentioned is that's that's a good idea they are all safe vaccines. The only one that has had an issue is the polio replication competent vaccine. Oh it's called Saban vaccine or oral poliovirus vaccine because you take it orally. It's a wonderful because you don't have to inject it. This is the perfect delivery. You know either intra nasal for respiratory virus or orally for polio goes into your intestines. It reproduces and it gives you wonderful protection against polio. However you do shed virus out and that virus is no longer a vaccine. It's reverted genetically in your intestine. </s><s>[INST] So you can infect others [/INST] with take that virus and it put it into an animal and give it polio. And in fact the parents of some kids In the 60s and 70s who were immunized got we got polio from the vaccine. The rate was about one and 1.5 million um cases of polio. So it's called vaccine associated polio. And I always argue that we may not have picked the right vaccine. There was a big fight in the U. S. And other countries between the inactivated polio and the and the infectious polio vaccines which ones we should be using because we found out that the infectious vaccine actually caused polio and 8 to 10 kids a year in the US alone got polio from the vaccine which looking back is really not acceptable in my view although the public health community said it was to get rid of polio. So now we're we're close to eradicating polio globally. Um But this vaccine derived polio is a problem. So now we have to go back to the and activated vaccine which is tough because it's injected. </s> |
<s>[INST] but in the more practical sense like almost like self attention, you think consciousness and cognition can in an impressive way emerge from the current types of [/INST] architectures because or or if if you think of consciousness in terms of self awareness and just making plans based on the fact that the agent itself exists in the world reinforcement. Learning algorithms are already more or less forced to model the agents effect on the environment so that that more limited version of consciousness is already something that we get limited versions of with reinforcement learning algorithms if they're trained well </s><s>[INST] but you say limited. So the big question [/INST] really is how you jump </s><s>[INST] from limited to human level, right? And uh whether it's possible, you know, the even just building common sense reasoning seems to be exceptionally difficult. So if we scale things up, if we get much better on supervised learning, if we get better at labeling, if we get bigger data sets uh more compute. Do you think we'll start to see really impressive things that go from limited to you know, something echoes of human level [/INST] cognition? I think so yeah, I'm optimistic about what can happen just with more computation and more data. I do think it will be important to get the right kind of data today. Most of the machine learning systems we train are mostly trained on one type of data for each model, but the human brain we get all of our different senses and we have many different experiences like you know, riding a bike, driving a car, talking to people reading. Um I think when you get that kind of integrated data set working with a machine learning model that can actually close the loop and interact, we may find that algorithm is not so different from what we have today, learn really interesting things when you scale them up a lot and train them on a large amount of multi modal data. </s><s>[INST] So multi modal is really interesting. But within like you're working uh adversarial examples. So selecting within modal within a one mode of data, uh selecting better at what are the difficult cases from which are most useful to learn from. [/INST] Oh yeah. Like could we could we get a whole lot of mileage out of uh designing a model that's resistant to adversarial examples or something like that. Yeah, my thinking on that has evolved a lot over the last few years when I first started to really invest in studying adversarial examples. I was thinking of it mostly as adversarial examples reveal a big problem with machine learning and we would like to close the gap between how machine learning models respond to adversarial examples and how humans respond after studying the problem more. I still think that adversarial examples are important. I think of them now more of as a security liability then as an issue that necessarily shows there's something uniquely wrong with machine learning as opposed to humans. </s><s>[INST] Also do you see them as a tool to improve the performance of the system? Not not on the security side, but literally just accuracy. [/INST] I do see them as a kind of tool on that side, but maybe not quite as much as I used to think. We've started to find that there's a trade off between accuracy on adversarial examples and accuracy on clean examples Back in 2014 when I did the first adversary really trained classifier that showed resistance to some kinds of adversarial examples. It also got better at the clean data on M nist and that's something we've replicated several times on Em Nist. That when we train against weak adversarial examples, feminist classifiers get more accurate so far. That hasn't really held up on other datasets and hasn't held up when we train against stronger adversaries. It seems like when you confront a really strong adversary, you tend to have to give something up </s><s>[INST] interesting, but it's such a compelling idea because it feels uh it feels like that's how us humans learn. [/INST] Yeah, the difficult cases, we try to think of what would we screw up and then we make sure we fix that. Yeah, it's also in a lot of branches of engineering, you do a worst case analysis and make sure that your system will work in the worst case and then that guarantees that it will work in all of the messy average cases that happened when you got into a really randomized world. </s><s>[INST] Yeah. With driving with autonomous vehicles, there seems to be a desire to just look for think adversary, really try to figure out how to mess up the system and if you can be robust to all those difficult cases, then you can, it's a hand wavy empirical way to show your system is [/INST] uh yeah. Today, most adversarial example research isn't really focused on a particular use case but there are a lot of different use cases where you'd like to make sure that the adversary can't interfere with the operation of your system. Like in finance, if you have an algorithm making trades for you, people go to a lot of an effort to obfuscate their algorithm. That's both to protect their I. P. Because you don't want to research and develop a profitable trading algorithm and have somebody else capture the gains. But it's at least partly because you don't want people to make adversarial examples that fool your algorithm into making bad trades. Or I guess one area that's been popular in the academic literature is speech recognition. If you use speech recognition to here an audio waveform and then uh turn that into a command that a phone executes for you you don't want. And a malicious adversary to be able to produce audio that gets interpreted as malicious commands, especially if a human in the room doesn't realize that something like that is happening </s> |
<s>[INST] Can we look at a neuron? Yeah. You say that prediction happens in the neuron, What does that mean? So the neuron traditionally seen as the basic element of the brain? [/INST] So we I mentioned this earlier that prediction was our research agenda. We said okay um how does the brain make a prediction? Like I'm about to grab this water bottle and my brain is predicting what I'm going to feel on on all my parts of my fingers. If I felt something really odd on any part here, I noticed it. So my brain is predicting what it's gonna feel as I grab this thing. So what is that? How does that manifest itself in neural tissue? Right. We've got brains made of neurons and there's chemicals and there's neurons and their spikes and connect, you know, where, where is the prediction going on? And one argument could be that. Well, what I'm predicting something um a neuron must be firing in advance. It's like, okay, this neuron represents what you're going to feel and it's firing, it's sending a spike and certainly that happens to some extent. But our predictions are so ubiquitous that we're making so many of them which were totally unaware of just the vast majority. We have no idea that you're doing this. Um that it wasn't really, we were trying to figure out how could this be, where, where these, where these happening, right. And I won't walk you through the whole story unless you insist upon it. But we came to the realization that most of your predictions are occurring inside individual neurons, especially these the most common on the parameter cells. And there are there is a property in neurons. Everyone knows that most people know that a neuron is a cell and it has this spike called an action potential and it sends information. But we now know that there's these spikes internal to the neuron called dendritic spikes, they travel along the branches of neurons and they don't leave the neurons, they're just internal only there's far more dendritic spikes than there are action potentials. Far more. They're happening all the time. And what we came to understand that those dendritic spikes, the ones that recurring are actually a form of prediction. They're telling the neuron the neuron is saying, I expect that I might become active shortly. And that internal. So the internal spike is a way of saying you're gonna you might be generating external spike soon I've predicted you're gonna become active. And and we've we've we've we wrote a paper in 2016 which explained how this manifests itself in neural tissue and how it is that this all works together. But the vast we think it's there's a lot of evidence supporting it. Um So that's where we think that most of these pictures are internal. That's why you can't be their internal in Iran you can't perceive them well </s><s>[INST] from understanding the prediction mechanism of a single. And you're on do you think there's deep insights to be gained about the prediction capabilities of the many brains within the bigger brain. And [/INST] yeah, so having a prediction side of their individual neuron is not that useful. You know what? So what um the way it manifests itself in neural tissue is that when a neuron to neuron mitzi spikes are very singular type event. If a neuron is predicting that it's going to be active, it admits it? Spike? Very a little bit sooner. Just a few milliseconds sooner than it would have otherwise. It's like I give the analogy of the book is like a sprinter on a starting blocks in a race and if someone says get ready set, you get up and you're ready to go and then when you really start to get a little bit earlier start, so that it's that that ready set is like the prediction that the neurons like ready to go quicker. And what happens is when you have a whole bunch of neurons together and they're all getting these inputs, the ones that are in the predictive state, the ones that are anticipating to become active. If they do become active, they happen sooner, they disable everything else and it leads to different representations in the brain. So you have to it's not isolated just to the neuron. The prediction occurs within your on but the network behavior changes. So what happens under different predictions? Different inputs have different representations. So, how I what I predict, um it's going to be different under different context. You know what my input will be different under different context. So this is this is a key little theory how this works. </s><s>[INST] So the theory of the 1000 brains, if you were to count the number of brains, how would you do it? [/INST] The 1000 main theory says that basically every cortical column. Yeah. In the in your new york cortex is a complete modeling system and that when I asked where do I have a model of something like a coffee cup, it's not in one of those models, it's in thousands of those models, there's thousands of models of coffee cups, that's what the 1000 brains mechanism and there's a voting mechanism which leads with your is the thing you're with your conscious of which leads to your singular perception. Mhm. Um that's why you you perceive something. So that's the 1000 brain theory. The details how we got to that theory um are complicated. It wasn't just thought of it one day, one of those details that we had to ask, how does a model make predictions. And we've talked about just these predictive neurons, that's part of this theory, that's like saying, oh it's a detail, but it was like a crack in the door is like how are we going to figure out how these neurons bill do this, you know, what is going on here. So we we just looked at prediction as like, well we know that ubiquitous, we know that every part of the cortex is making predictions. Therefore whatever the predictive system is, it's going to be everywhere. We know there's a gazillion predictions happening at once. So this time we can start teasing apart, you know, ask questions about how could neurons were making these predictions and that sort of built up to now what we have this 1000 brains theory which is completely, you know, it just so I can state it simply but we just didn't think of it, we had to get their step by step very, it took years to get there </s> |
<s>[INST] But here, here's the thing this show, but you have that harshness for Ellen to, [/INST] and no, </s><s>[INST] no, it's a different harshness. [/INST] No, it's a different um, arguing with, you know, I, I think SpaceX is amazing company on the other hand, you know, in one of my blog posts, I said, what's easy and what's hard I said, SpaceX, vertical landing rockets, It had been done before, uh, grid fins have been done since the sixties, Every Sawyer's has them. Um, um, reusable space DCX reuse those rockets that landed vertically. Um, those whole insurance industry in place for rocket launchers, there are all sorts of infrastructure that was doable. It took a great entrepreneur, great personal expense. He almost drove himself bankrupt doing it a great belief to do it. Whereas Hyperloop. Uh, there's a whole bunch more stuff that's never been thought about. Never been demonstrated. So my estimation is hyper is a long, long, lot further off and, and if I've got a criticism of, of Ellen? It's that he doesn't make distinctions between when the technologies coming along and ready and then he'll go off and mouth off about other things which then people go and compete about and try and do. And </s><s>[INST] so this is where I uh I understand what you're saying. I tend to draw a different distinction. I have a similar kind of harshness. Those people who are not telling the truth who are basically fabricating stuff to make money or to well [/INST] he believes what he says to me </s><s>[INST] that's a very important difference [/INST] because </s><s>[INST] I think in order to fly in order to get to the moon you have to believe uh even when most people tell you you're wrong and most likely you're wrong but sometimes you're right. I mean that's the same thing I have with Tesla autopilot. I think that's an interesting one. I was especially when I was you know um at M. I. T. And just the entire human factors in the robotics community were very negative towards Ellen. It was very interesting for me to observe colleagues at M. I. T. I wasn't sure what to make of that. It was very upsetting to me because I understood without where that's coming from and I agreed with them and I kind of almost felt the same thing in the beginning until I kind of opened my eyes and realize there's a lot of interesting ideas here that might be over hype. You know if you focus yourself on the idea that you shouldn't call a system full self driving when it's obviously not autonomous, fully autonomous, you're going to miss the magic, [/INST] oh, you're gonna miss the magic. But at the same time there are people who buy it literally pay money for it and take those words as given. </s><s>[INST] So that's uh, but I haven't so that I would take words as given is one thing I haven't actually seen people that use autopilot that believe that the behavior is really important, like the actual action. So like this is to push back on the very thing that you're frustrated about, which is like journalists and general people uh, buying all the hype and going out in the same way, I think there's a lot of hype about the negatives of this to the people are buying without using people used the way this is what this was, opened my eyes actually. Uh the way people use the product is very different than the way they talk about it. This is true with robotics with everything. Everybody has dreams of how a particular product might be used so on this. And then when it meets reality there's a lot of fear of robotics, for example that robots are somehow dangerous and all those kinds of things. But when you actually have robots in your life, whether it's in the factory or in the home making your life better. That's going to be, that's way different that your perceptions of it are going to be way different. And so my just tension was like, here's an innovator. Um uh uh what is it, sorry, Super Cruise from cadillac was super interesting to that's a really interesting system. There's and if we should like be excited by those innovations, Okay, so [/INST] can I tell you something that's really annoyed me recently? It's really annoyed me that the press and friends of mine on facebook are going, these billionaires and their space games, you know, why are they doing that really pisses me off? I must say, I applaud that I applaud it, it's taking and not necessarily the people who are doing the things, but you know that I that I keep having to push back against unrealistic expectations when these things can become real. </s><s>[INST] Yeah, I this was interesting on a because there's been a particular focus for me is autonomous driving Ellen's prediction of when certain milestones will be hit. Um there's several things to be said there that I I was I thought about because whenever you said that it was obvious that's not going to me as a person that kind of not inside the system, it was obviously it's unlikely to hit those, these two comments. I want to make one, he legitimately believes that yeah, and too much more importantly, I think that having ambitious deadlines drives people to do the best work of their life, even when the odds of those deadlines are very, [/INST] um, to a point. And I'm not, I'm not talking about, you know, I'm just saying, so there's a line there. You have to have a line because you over extended, it's demoralizing you. But I will say that there's an additional thing here that those words also, um, drive the stock market. Yeah. And you know, we have, because of the way that rich people in the past have manipulated the rubes through investment. We have, we have develop laws about what, you know what you're allowed to say and promise. And, you know, there's an area here, which is, </s> |
<s>[INST] amazing, So many, so many new ideas. Let me on another attention on top of a tangent, on top of a tangent ask if we didn't have Einstein. So how does science progress? Is that the lone geniuses or is it uh some kind of weird network of ideas swimming in the air and just kind of the geniuses pop up to catch them and others would anyway, without I styled we have uh special relativity, general relativity. [/INST] I mean, it's an interesting case to case basis, I mean, I mean, special special relativity, I think we would have had, I mean, there are other people, you could even argue that it was already there in some form or something, but I think special relativity would have had without Einstein fairly, fairly quickly general activity, that was much, much harder thing to do and required a much more effort and much more sophisticated that I think he would have had sooner or later, but it would have taken taken quite a bit longer. </s><s>[INST] Other thing, I took a bunch of years to validate scientifically the general activity, [/INST] but even for Einstein from, you know, the point which he had kind of a general idea of what he was trying to do to the point where he actually had a Well defined theory that you could actually compare to the real world that was, you know, kind of forget the number of the order of magnitude 10 years, a very serious work and if he hadn't been around to do that, it would have taken awhile before anyone else got around to it. On the other hand, there are things like with Kwon mechanics, you have Heisenberg and Schrodinger came up with two which ultimately equivalent, but two different approaches to it, you know, within months of each other and you know, so if Heisenberg had been there, he already would have had shredded or whatever and if neither of them have been there, it would've been somebody else a few months later. So there are times when they, you know, just the, a lot often is the combination of the right ideas are in place and the right experimental data is in place to point in the right direction and it's just waiting for somebody's going to find it. Maybe man, maybe to go back to your, to your aliens. I guess the one thing I often wonder about aliens is would they have the same fundamental physics ideas as we, if we have in mathematics with their math, you know, would they? You know, how, how much is this really intrinsic to our minds? If if you start out with a different kind of mind when you end up with a different ideas of what fundamental physics is or what or what the structure of mathematics. </s><s>[INST] So this is why like if I was, uh, you know, I like video games the way I would do it as a curious being. So first experiment I'd like to do is run earth over many thousands of times and see if our particular, um no, you know what, I wouldn't do the full evolution started homo sapiens first and then see the evolution of homo sapiens millions of times and see how the ideas of science would evolve, like would you get like how would physics of all? How would math involves? I would particularly just be curious about the notation they come up with um every once in a while, I would like throw miracles at them to like to mess with them and stuff. And then I would also like to run Earth from the very beginning to see if evolution would produce different kinds of brains that would then produce different kinds of mathematics and physics. And then finally I would probably millions of times run the universe over to see what kind of what kind of environments and what kind of life would be created to then lead to intelligent life to then lead to um theories of mathematics and physics and to see the full range and like sort of uh like Darwin kind of mark. Okay, it took them, what is it? Several 100 million years to come up with calculus. I would just like keep noting how long it would get an average and see see which ideas are difficult, which are not. And and then and then conclusively sort of figure out if it's uh if it's more collective intelligence or singular intelligence that's responsible for shifts and for big face shifts and breakthroughs in science, if I was playing a video game and I got a chance to run this whole thing. Yeah, [/INST] but </s><s>[INST] we're talking about books before I distract you [/INST] go back books. And yeah, so and then yeah, so that's one thing I recommend is the is the books books about the from the original people especially Heisenberg about the how that happened and there's also a very, very good kind of history of of the kind of what happened during the 20th century in physics and up to the time of the Standard Model in 1973. It's called The Second Creation by um bob Crease and uh man, that's one of the best ones. I know, that's But the one thing I can say is that, so that book, I think, forget when it was late, 80s 90s uh The problem is that there just hasn't been much that's actually worked out since then. So most of the books that are kind of trying to tell you about all the glorious things that have happened since 1973 are, they're mostly telling you about how glorious things are, which actually don't really work. And it's really the argument people sometimes making term in favor of these books as well, oh, you know, they're really great because you want to do something that will get kids excited. And then, you know, so they're getting excited about things, something that's not really quite working, it doesn't really matter. The main thing is get them excited. The other argument is, you know, wait a minute when if you're getting people excited about ideas that are wrong, you're really kind of you're actually kind of discrediting the whole scientific enterprise and it's not really good way. So there's problems so my uh the general feeling about expository stuff is yeah, it's to the extent you can do it kind of honestly and and and well that's great. There are a lot of people doing that now but to the extent that you're just trying to get people excited, enthusiastic by kind of telling them stuff, which isn't really true that you really shouldn't be doing that. </s> |
<s>[INST] and your senses. There's a connection between dreams and D. M. T. And like second out. Like all of the uh you can you can understand one by studying the other. So for example, dreams are also very difficult to study, right? But there more accessible. It's safer to study [/INST] and we're told we need to get more of it. Whereas with psychedelics, there's this big question mark, is it going to make everyone crazy? Is it is it going to be legal? I mean, it's kind of interesting how if one looks on instagram, one could almost think that these drugs are already legal based on the way that people come here, but they're not yet, there's still a lot of them are scheduled as </s><s>[INST] a lot of questions. Uh I mean, but nevertheless, it's like my my hope is that science opens up to these uh drugs a little bit more. It's just I have this intuition that like a lot of people share that they would be able to unlock deeper understanding of our own mind. It's any kind of the same as the studying dreams. [/INST] Absolutely. Well, creativity is in the nonlinear charities, right? But productivity is in the implementation of linear charities. I mean, that's that's what is absolutely clear, that's why I think we were talking earlier about why a formal rigorous training and something where other people are looking at you and telling, you know, not good enough go back and do it again. There's real value to that because otherwise it's just ideas. It's just vapors. </s><s>[INST] You know, one thing that matt mentioned as the study that they're working on is as opposed to, I think most of the psychedelic studies they've done is on how to treat different conditions. And one of the things they're working on now is to try to a study were uh, for creatives, for people that don't have a condition and try to treat. But instead see how this, how psychedelics can help you create. So like goodness, if [/INST] you take creatives and you give them more psychedelics, they're not gonna be able to get out of there. Right? I don't know. </s><s>[INST] Well, but this is the, maybe you can speak to that psychedelics are not or dreams or tools in general, how to be better creative. That's an interesting, I don't often see studies of this nature of like, how to take high performance in the mental creative space and get them to perform even better. So it's not average people, it's like masters of their craft, like taking, uh, I mean, his examples was taking an Elon musk, which is in the engineering space and maybe musicians and all that kind of stuff and studying that. That's a, I mean, that's weird. Usually the science of the scientific exploration there has been done in by the musicians themselves as has been documented like jazz [/INST] is like nonlinear charities. But if it's but the people still have to know how to play their instruments, right? There's some early, early skill building that's critical. I mean, when you mention someone like Elon, I mean, virtually, I mean, he's already a virtuoso, right? Because and in so many different domains I've never met him, but it's clear, right? He it's not just that he's ambitious and bold and brave and all that. It's all that. And there's there's clearly a different way of looking at the same problems that everyone else is looking at and people are probably banging their head against the refrigerator. Things like think differently things. It doesn't work that way. It involved. There's a certain anxiety in for the I'm not talking about for Ellen, but I don't have no idea. But I think for somebody who's very structured, very regimented, very linear. The anxiety comes from letting go of those linear charities. And for the person that's very creative, the anxiety comes from trying to impose linear garrity's, right? They really creative artist or musician there. They seem nuts. They seem like they can't get their life together because they can't and they, you know, we look at people who are kind of Sudo asperger's or asperger's or some forms of autism. And they are so hyper linear, but you take away those linear eddies. And they freak out. And that's kind of the essence of some of those syndromes. So I think that the ability to toggle back and forth between those states is what's remarkable. I mean, because we're here and we're having this discussion. I mean, steve jobs is a good example. He probably the best example of somebody who actually talked about his own process about the merging of art and science, art and engineering, humanities and science. Very few people can do that. Well, you seem to have a capacity to do that. I like you, you know, poetry and you are a, I guy like you, there's nothing linear about poetry as far as I can tell. </s> |
<s>[INST] despite having like vastly better ability to read GPT. Do you think it's possible? Do you think that's just a matter of time? Do you think it's possible to investigate and study the way neuroscientists study the brain? Which is looking to the darkness the mystery of the human brain by just desperately trying to figure out something and to form models and then over a long period of time actually start to figure out what regions of the brain do certain things with different kinds of neurons when they fire what that means, how plastic the brain is, all that kind of stuff. You slowly start to figure out different properties of the system. [/INST] Do you think we can do the same thing with language models? Sure, I think that if, you know, like half of today's physicists stop wasting their lives on string theory or whatever, and go off and study what goes on inside transformer networks, then in, you know, like 30, 40 years, we'd probably have a pretty good idea. Do you think these large language models can reason? They can play chess. </s><s>[INST] How are they doing that without reasoning? So you're somebody that spearheaded the movement of rationality, so reason is important to you. Is, so is that as a powerful, important word, or is it like how difficult is the threshold of being able to reason to you and how impressive is it? [/INST] I mean, in my writings on rationality, I have not gone making a big deal out of something called reason. I have made more of a big deal out of something called probability theory. And that's like, well, you're reasoning, but you're not doing it quite right. And you should reason this way instead. And interestingly, like people have started to get preliminary results showing that reinforcement learning by human feedback has made the GPT series worse in some ways. In particular, like it used to be well calibrated. If you trained it to put probabilities on things, it would say 80% probability and be right eight times out of 10. And if you apply reinforcement learning from human feedback, the like nice graph of like 70%, seven out of 10 sort of like flattens out into the graph that humans use where there's like some very improbable stuff and likely probable maybe, which all means like around 40% and then certain. So like, it's like it used to be able to use probabilities, but if you apply, but if you'd like try to teach it to talk in a way that satisfies humans, it gets worse at probability in the same way that humans are. </s><s>[INST] And that's a bug, not a feature. [/INST] I would call it a bug, although such a fascinating bug. But yeah, so like reasoning, like it's doing pretty well on various tests that people used to say would require reasoning, but rationality is about when you say 80%, </s><s>[INST] does it happen eight times out of 10? So what are the limits to you of these transformer networks, of neural networks? If reasoning is not that impressive to you [/INST] or it is impressive, but there's other levels to achieve. </s><s>[INST] I mean, it's just not how I carve up reality. What's, if reality is a cake, what are the different layers of the cake or the slices? How do you carve it? [/INST] You can use a different food if you like. It's, I don't think it's as smart as human yet. I do like back in the day, I went around saying like, I do not think that just stacking more layers of transformers is going to get you all the way to AGI. And I think that GPT-4 is passed or I thought this paradigm was going to take us. And I, you know, you want to notice when that happens. You want to say like, whoops, well, I guess I was incorrect about what happens if you keep on stacking more transformer layers. And that means I don't necessarily know </s><s>[INST] what GPT-5 is going to be able to do. That's a powerful statement. So you're saying like your intuition initially is now appears to be wrong. Yeah, wrong. It's good to see that you can admit [/INST] in some of your predictions to be wrong. </s><s>[INST] See that you can admit you think that's important to do. See, because you make several various throughout your life, you've made many strong predictions and statements about reality and you evolve with that. So maybe that'll come up today about our discussion. [/INST] So you're okay being wrong. I'd rather not be wrong next time. It's a bit ambitious to go through your entire life, never having been wrong. One can aspire to be well calibrated, like not so much think in terms of like, was I right, was I wrong, but like when I said 90% that it happened nine times out of 10. Yeah. Like, oops, is the sound we make, </s><s>[INST] is the sound we emit when we improve. Beautifully said. And somewhere in there, we can connect the name of your blog less wrong. [/INST] I suppose that's the objective function. The name less wrong was I believe suggested by Nick Bostrom. And it's after someone's epigraph, actually forget who's who said, like we never become right. We just become less wrong. What's the something? Something that's easy to confess, just error and error and error again, </s><s>[INST] but less and less and less. Yeah, that's a good thing to strive for. So what has surprised you about GPT4 that you found beautiful as a scholar of intelligence, of human intelligence, of artificial intelligence, of the human mind? [/INST] I mean, the beauty does interact with the screaming horror. Is the beauty in the horror? But like beautiful moments, well, somebody asked Bing Sidney to describe herself and fed the resulting description into one of the stable diffusion things, I think. And, you know, she's pretty and this is something that should have been like an amazing moment. Like the AI describes herself. You get to see what the AI thinks the AI looks like. Although, you know, the thing that's doing the drawing is not the same thing that's outputting the text. And it does happen the way that it would happen that it happened in the old school science fiction when you ask an AI to make a picture of what it looks like. Not just because we're two different AI systems being stacked that don't actually interact. It's not the same person, but also because the AI was trained by imitation in a way that makes it very difficult to guess how much of that it really understood and probably not actually a whole bunch, you know? Although GPT-4 is like multimodal and can like draw vector drawings of things that make sense and like does appear to have some kind of spatial visualization going on in there. But like the pretty picture of the like girl with the steampunk goggles on her head if I'm remembering correctly what she looked like. Like it didn't see that in full detail. It just like made a description of it and stable diffusion output it. And there's the concern about how much the discourse is going to go completely insane once the AIs all look like that and like are actually look like people talking. And yeah, there's like another moment where somebody is asking Bing about like, well, I like fed my kid green potatoes and they have the following symptoms and Bing is like that's selenine poisoning and like call an ambulance and the person's like, I can't afford an ambulance. I guess if like this is time for like my kid to go, that's God's will. And the main Bing thread says, gives the like message of like, I cannot talk about this anymore. And the suggested replies to it say, please don't give up on your child, selenine poisoning can be treated if caught early. And if that happened in fiction, that would be like the AI cares. The AI is bypassing the block on it to try to help this person. And is it real? Probably not, but nobody knows what's going on in there. It's part of a process where these things are not happening in a way where we, somebody figured out how to make an AI care and we know that it cares and we can acknowledge it's caring now. It's being trained by this immatration process followed by reinforcement learning on human feedback. And we're like trying to point it in this direction and it's like pointed partially in this direction and nobody has any idea what's going on inside it. Then if there was a tiny fragment of real caring in there, we would not know. It's not even clear what it means exactly. </s> |
<s>[INST] and of course in the beginning, especially in the Alphago zero formulation, it's everything is shrouded in uncertainty, so you're really swimming in a sea of uncertainty. So it benefits you to, I mean, actually following the same process as you describe, but because you're so uncertain about everything, you basically have to try a lot of different directions. [/INST] Yeah, so, so the early parts of the search tree, a fairly bushy um that it would it would look at a lot of different possibilities, but fairly quickly the degree of certainty about some of the moves, I mean, if a movie's really terrible, you'll pretty quickly find out, right, you lose half your pieces or half your territory. And uh and then you say, okay, this this is not worth thinking about anymore. And then so further down the tree becomes very long and narrow and you're following various lines of play 10 2030, 40, 50 moves into the future. And, you know, that again is something that human beings have a very hard time Doing uh mainly because they just lack the short term memory, you just can't remember a sequence of moves that's 50 moves along. Uh And you can't you can't imagine the board correctly uh for that money moves into the future, of course the top </s><s>[INST] players, I'm much more familiar with chess, but the top players probably have, they have echoes of the same kind of intuition instinct that in a moment's time, Alphago applies when they see a board. I mean, they've seen those patterns, human beings have seen those patterns before, at the top of the grandmaster level. It seems that there is some uh similarities or maybe it's it's our imagination, greats vision of those similarities, but it feels like this kind of pattern recognition that the Alphago approaches are using is similar to what human beings at the top level are using. [/INST] I think there's uh there's some truth to that, </s><s>[INST] but not entirely. [/INST] Yeah, I mean, I think the the extent to which human grandmaster can reliably rec instantly recognized the right move, instantly recognized the value of the position. I think that's a little bit overrated. </s><s>[INST] But if you sacrifice the queen, for example, I mean, there's these there's these beautiful games of chess with bobby fisher, somebody where it's seeming to make a bad move and I'm not sure there's a a perfect degree of calculation involved where they've calculated all the possible things that happen. But there's an instinct there, right? That somehow adds up to. Yeah, [/INST] so I think what happens is you you you get a sense that there's some possibility in the position, even if you make a weird looking move um that it opens up some some lines of calculation that otherwise would be definitely bad and and it's that intuition that there's something here in this position that might uh might yield that win down the second, you follow that all right. And and in some sense when a when a chess player is following a line and his or her mind there, they're mentally simulating what the other person is going to do, what the opponent is going to do and they can do that as long as the moves are kind of forced, right? As long as there's, you know, there's a, what we call a forcing variation where the opponent doesn't really have much choice how to respond. And then you see if you can force them into a situation where you win, you know, we see plenty of mistakes, even even in grandmaster games Where they just missed some simple 345 move combination that, you know, wasn't particularly apparent in in the position but was still there. </s><s>[INST] That's the thing that makes us human. So when you mentioned that in Othello, those games were after some matter reasoning improvements and research was able to beat you. How did that make you feel [/INST] part of the meta reasoning capability that it had um was based on learning and, and you could sit down the next day and you could just feel that it had got a lot smarter, you know, and all of a sudden you really felt like you were sort of pressed against the wall because it was, it was much more aggressive and and was totally unforgiving of any minor mistake that you might make, and actually it seemed understood the game better that I did. And Garry Kasparov has this quote where um during his match against deep blue, he said he suddenly felt that there was a new kind of intelligence across the board. </s><s>[INST] Do you think that's a scary or an exciting possibility for [/INST] cast province for yourself </s><s>[INST] in the context of chess, purely sort of in this like that feeling, whatever that is? [/INST] I think it's definitely um an exciting feeling. You know, this is what made me work on ai in the first place was as soon as I really understood what a computer was, I wanted to make it smart. You know, I started out with the first program I wrote was for the Sinclair programmable calculator. Uh and I think you could write a 21 step algorithm that was the biggest program, you could write something like that um and do a little arithmetic calculations. So I think I implemented Newton's method for square roots and a few other things like that. But then, you know, I thought, okay, if I just had more space, I could make this thing intelligent. And so I started thinking about Ai and and I think the thing that's scary is not, is not the chess program because chess programs, they're not in the taking over the world business. Uh but if you extrapolate, you know, there are things about chess that don't resemble the real world, right? We know we know the rules of chess. The chessboard is completely visible to the program where of course the real world is not most, most of the real world is not visible from wherever you're sitting, so to speak. And okay to overcome those kinds of problems, unique, qualitatively different algorithms. Another thing about the real world is that, you know, we we regularly plan ahead on the timescales involving billions or trillions of steps. Um, we don't plan that was in detail, but you know, when you choose to do a PhD at Berkeley, that's a five year commitment. And that amounts to about a trillion motor control steps that you will eventually be committed </s> |
<s>[INST] you can measure in physical space. Is there a lot to be understood about brontial space? I guess. Yes. Mathematically speaking. [/INST] Yes. Mathematically speaking. Yes. Because it's a very beautiful mathematical thing. And it's very... I mean, by the way, this whole theory is just amazingly rich in terms of the mathematics that it says should exist. Okay. So, for example, calculus is a story of infinitesimal change in integer, dimensional space, one dimensional, two dimensional, three dimensional space. We need a theory of infinitesimal change in fractional dimensional and dynamic dimensional space. </s><s>[INST] No such theory exists. [/INST] There are tools of mathematics that are needed here and this is the motivation for that. And this is the motivation for that action. Right. And there are indications and we can do computer experiments and we can see how it's going to come out, but the actual mathematics doesn't exist. And in branchless space, it's actually even worse, there's even more layers of mathematics that are, we can see how it works roughly by doing computer experiments but to really understand it, we need more mathematical sophistication. Quantum computers. Okay. The basic idea of quantum computers, the promise of quantum computers is quantum mechanics does things in parallel, and so you can sort of intrinsically do computations in parallel, and somehow that can be much more efficient than just doing them one after another. I actually worked on quantum computing a bit with Dick Feynman back in 1981, two, three, that kind of timeframe. A fascinating image, you and Feynman working on quantum computers. Well, the big thing we tried to do was invent a randomness chip that would generate randomness at a high speed using quantum mechanics, and the discovery that that wasn't really possible was part of the story of... We never really wrote anything about it. I think maybe he wrote some stuff, but we didn't write stuff about what we figured out about the fact that it really seemed like the measurement process in quantum mechanics was a serious damper on what was possible to do in the possible advantages of quantum mechanics for computing. Anyway, the promise of quantum computing is, let's say you're trying to factor an integer. Well, when you factor an integer, you might say, well, does this factor work? Does this factor work? Does this factor work? In ordinary computing, it seems like we pretty much just have to try all these different factors one after another, but in quantum mechanics, you might have the idea, oh, you can just have the physics, try all of them in parallel. There's this algorithm, Shaw's algorithm, which allows you, according to the formalism of quantum mechanics, to do everything in parallel and to do it much faster than you can on a classical computer. The only little footnote is you have to figure out what the answer is. You have to measure the result. The quantum mechanics internally has figured out all these different branches, but then you have to pull all these branches together to say, and the classical answer is this, okay? The standard theory of quantum mechanics does not tell you how to do that. It tells you how the branching works, but doesn't tell you the process of corralling all these things together. And that process, which intuitively you can see is going to be kind of tricky, but our model actually does tell you how that process of pulling things together works. And the answer seems to be, we're not absolutely sure, we've only got to two times three so far, which is kind of in this factorization in quantum computers, but what seems to be the case is that the advantage you get from the parallelization from quantum mechanics is lost from the amount that you have to spend pulling together all those parallel threads to get to a classical answer at the end. Now that phenomenon is not unrelated to various decoherence phenomena that are seen in practical quantum computers and so on. I mean, I should say as a very practical point, I mean, it's like, should people stop bothering to do quantum computing research? No, because what they're really doing is they're trying to use physics to get to a new level of what's possible in computing. And that's a completely valid activity. Whether you can really put, whether you can say, oh, you can solve an NP-complete problem, you can reduce exponential time to polynomial time, we're not sure. And I'm suspecting the answer is no, but that's not relevant to the practical speedups you can get by using different kinds of technologies, different kinds of physics to do basic computing. </s><s>[INST] So you're saying, I mean, some of the models you're playing with, the indication is that to get all the sheet back together and to corral everything together to get the actual [/INST] solution to the algorithm is... You lose all the... You lose all the... By the way, I mean, so again, this question, do we actually know what we're talking about about quantum computing and so on? So again, we're doing proof by compilation. So we have a quantum computing framework in Wolfman language, which is standard quantum framework that represents things in terms of the standard formalism of quantum mechanics, and we have a compiler that simply compiles the representation of quantum gates into to multiway systems, and in fact the message that I got was from somebody who's working on the project who has managed to compile one of the sort of core formalism based on category theory, core quantum formalism into multiway systems. </s><s>[INST] So this- When you say multiway system, do you use multiway graphs? Yes. So you're- Yeah, okay, that's awesome. [/INST] And then you can do all kinds of experiments on that multiway graph. Yes. Right, but the point is that what we're saying is the thing, we've got this representation of let's say Shor's algorithm in terms of standard quantum gates, and it's just a pure matter of sort of computation to just say that is equivalent. </s> |
<s>[INST] how do you, how do you escape? What is the uh, is there a light at the end of the tunnel of a midlife crisis? [/INST] So, so you should watch that symposium because the videos were transformative to me and to many others. So basically, the advice that I received from all of my friends was so meaningful. This. You know, there's some some advice that basically says, you have to constantly maintain unachievable goals goals that you can make progress towards, but you can never be fully done with and I think that's almost playing into the sort of rat race thing, Like basically make sure that there's more obstacles for your little rat persona to jump through. So that's one possibility. So first of </s><s>[INST] all, watch, [/INST] is it available? It's on youtube, just google, google really meaning of license, I should have </s><s>[INST] told me this like this is awesome, okay, this is great. But, and also like, you know, saying rat race is um you know, if you look at Rata TUI is not, [/INST] I mean that's a beautiful, </s><s>[INST] that's a beautiful thing of, of challenges and overcoming challenge that could be fundamentally the meaning of life is uh two see life as a set of challenges and to fully engage in the overcoming of those challenges. [/INST] I would say that that's embracing the rat race view of life. So, so a joke that we like to have with my wife all the time is uh we basically say we, we pretend that we're in this all inclusive resort that we basically hired all these people to go on the esplanade and play games because we enjoy watching people playing on the esplanade and we enjoy sort of laying and looking at life and all the people biking and rollerblading and all that. And then we've paid all these people in this all inclusive resort that we live in and then what are we going to do today? I'm like, oh I've signed up for Professor activities. It's going to be awesome. They lined up a bunch of super smart and my students, for me to meet with, I'm going to have a grant Writing meeting afterwards is gonna be awesome. And then she signed up for a bunch of consulting activities is gonna be great. And then in the evening we just get back together and say, hey, how was your consulting today? So in a way that's another view of life, basically, wait a minute. If I was a gazillionaire, what would I choose to do? I would probably pay an awesome university to give me an office there and just pay a bunch of super smart people to work with me, even though they don't really want to e etcetera. In fact, I would have exactly the life that I have now working my butt off every single day because it's so freaking full feeling. Well, that's so, </s><s>[INST] let's clarify, it is a beautiful way. It's almost like a video game view of life. That is a set of I mean, again, game is not perhaps a positive term, but it's a it's a it is a beautiful time. So you [/INST] do you </s><s>[INST] or do you not like the rat race view of life [/INST] because </s><s>[INST] it is fulfilling in [/INST] some about the goal, my view of life is about the path. So again, quoting grease </s><s>[INST] those folks have come up with some good stuff. [/INST] So this uh this? S elite is basically wrote this beautiful poem about sort of going through life, saying as you go through your journey Impersonating ulysses of his voyage. He says Wish that the path is long and argues because when you get to Ithaca you might realize that it was all about the path, not the destination. So the rat review of life makes it all about the destination. It's like how do I get through the maze to get there? But the all inclusive resort view of life is about the path. It's about, wow today, I couldn't wish for a better set of activities, all programs for me to enjoy having my brain, having my body, having my senses and you know, the life that I have, it's a very different kind of view. It's focused on the journey, not a destination. So you </s><s>[INST] mentioned kind of the ups and downs of life in the mid life crisis and right now you said, focusing kind of on the [/INST] journey. </s><s>[INST] But what the journey involves is ups and downs, is there advice or any kind of thoughts you can elucidate about the downs in your life, [/INST] the hard </s><s>[INST] parts of your life and how you got out or maybe not? Or is there how do you see the dark parts [/INST] of life? So, I'm so glad you're asking this question because it's something that our society does a terrible job at preparing us for every Hollywood movie has to have a happy ending. It is ridiculous. You can count on your 10 fingers the number of bad ending movies that you've ever watched And you probably wouldn't need all 10 fingers. Yeah, we strive to tell everyone yes, you can succeed. Yes, you're a millionaire just temporarily disabled and yes, you know the prince will eventually figure out his princess and they will have happily ever after ending and yes the hero will be beaten and beaten and beaten. But you know that at the end of the movie the good as will win. We need more movies where the bad guys went, we need more movies where just everybody dies. We're just you know, Macgyver doesn't figure out how to disable the bomb and just explodes. You just you just need more movies that are more realistic about the fact that life kind of sucks sometimes and it's okay, so again, growing up in Greece I I have been exposed to songs that are not just sad but they're miserable, miserable. So so one of them, one of them comes to mind. Mhm. And and it's basically talking about this woman who's lamenting in the early morning about losing the joyful kid, the joyful young man who basically died in the civil war in the arms of our own fellow citizens and she's like if only he had died fighting the foreign forces. If only he had died at the you know sides of the you know general if only he had died with honor, I would be proud to have lost the joyful kid. I mean it's devastating, right? It's like he didn't just die. She died without honor. And and uh my friend who was with me, he was listening to the song and she's like, this is depressing. Well you have to listen another one, It's not a sad and she's like, what? This one died with honor. So, so that's that's one example. It's a kind </s> |
<s>[INST] So that's why the condom use is the delayed thing five minutes or more. And then uh yeah [/INST] because normally be the larger later reward like the $10 versus the nine. It's like the 10 which is counterintuitive if you just think about the physical pleasure. </s><s>[INST] So that's a good that's a good thing to measure. So kind of music is a really good concrete quantity, quantitative ble quantifiable thing that you can use in a study and then you can add a lot of different elements like the presence of cocaine and so [/INST] on. Yeah you can get people loaded on like any number of drugs like cocaine, alcohol and methamphetamine or the three that I've done and published on. And it's interesting that </s><s>[INST] these are fun studies man [/INST] right? I love to get people loaded in in a safe context. And like, but to really it started like there was some early research alcohol. I mean, the psychedelics are the most interesting, but it's like all of these drugs are fascinating the fact that all these are keys that unlock a certain, like, psychological experience in the head. And so there was this work with alcohol that showed that it didn't affect those monetary delay discounting decisions, you know, $9 now versus $10 later. And I'm like getting people drunk. And I thought to myself, are you telling me that that, you know, getting someone that people being drunk is does not cause people at least sometimes to make to choose what's good for them in the short term, at the expense of what's good for them to uh in the long term, it's like, you know, bullshit. You know, like we see like, but in what context does that happen? So that's what, that's something that inspired me to go in this direction of like, ha ha, risky sexual decisions is something they do when they're drunk, they don't necessarily go home. And even though some people have gambling problems and alcohol interacts with that, the most typical thing is not for people to go home log on and change their their allocation in the retirement account or something like that, you know, like, </s><s>[INST] but they're more likely risky sexual decisions, they're more likely to not wait the five minutes for the condom, right? Instead go no condom [/INST] now. Right, That's a big effect. And we see that and interestingly we do not see with those different drugs, we don't see an effect. If we just look at that zero delay condition. In other words, the condoms right there, waiting to be used, would you? How likely you are to use it? You don't see it. I mean, people, people are by and large going to use the condom. So, and that's the way most of this research outside of behavioral economics that just looked at condom use decisions. Um very little of which has ever actually administered the drugs, which is another unique aspect. But they usually just look at like assuming the economy is there. But this is more using behavioral economics to delve in and model something that I've done survey research on this bottling what actually happens like you meet someone at a laundry mat, like you weren't planning on like, you know, and one thing leads another, they live around the corner, you know, these things, you know, and like we did one um Survey with with men who have sex with men and found that uh 25% of them, 24%, about a quarter reported in the last six months that they had unprotected anal intercourse, which is the most risky in terms of sexually transmitted infection. Um uh in the last six months in a situation where they would have used a condom but they simply didn't use one just because they didn't have one on them. Mhm. So this to me it's like even less we delve into this and understand this these sub optimal conditions, we're not going to fully address the problem. There's plenty of people that say yep condom use is good. I use it a lot of the time you know it's like where is that failing? And it's under the sub optimal conditions which in frank if you think about it, it's like most of the case action is unfolding things are getting hot and heavy. Someone's like you got a condom. No it's like do they break the action And take 10 minutes to go to the convenience store or whatever? Maybe everything's closed. Maybe they got to wait till tomorrow </s><s>[INST] and though there's something to be uh studied there on the uh that just seems like an unfortunate set of circumstances. What's the solution to that is uh I mean um what's the psychology that needs to be uh like taking apart there because it just seems like that's the way of life. We don't expect the things [/INST] that happen. </s><s>[INST] Are we supposed to expect them better to be like be self aware enough about our calculations or you see the 10 minute detour to a convenience store as a kind of thing that we need to understand um how we humans evaluate the cost of that. [/INST] I think in terms of like how we use this to help </s><s>[INST] people. It's [/INST] mostly on the environment side rather on the on </s><s>[INST] the yeah [/INST] although those those interact so it's like you know in one sense if you're especially if you're going to be drinking or using another substance that is associated with you know, a stimulant, um alcohol and stimulants go along with risky sex, you know, good to be aware that you might make decisions just to tell yourself, you might make a decision that is going to that you wouldn't made in your sober state. And so hey throwing a condom in the in the purse and in the pocket, you know, might be you know a good idea. I think at the environmental level just more condoms, I mean it highlights what we know about just making condoms widely available, something that I I I'd like to do is like reinforcing condom use and you know, so um you know just getting people used to carrying a condom everywhere they go because it's such once it's in someone's habit if they are saying like a young single person and you know it's you know they occasionally have unprotected sex like training those people like what if you got a text message, You know once every few days saying uh if you if you show me a sent back a photo of a condom within a minute you get a reward of $5, you could shape that up like that, it's a process called contingency management is basically just straight up operating reinforcement. You could shape that up with. No problem. And and um I mean those procedures of contingency management giving people systematic rewards is like for example the most powerful way to to to reduce cocaine use and addicted people and um uh but by saying if you show me a negative urine for cocaine, I'm gonna give you a monetary award and like that has huge effects in terms of decreasing cocaine use if that can be that powerful for something like stopping cocaine use. How powerful for that could that be for shaping up just carrying a condom? Because the primary, unlike cocaine use here, we're not saying you can't have the main reward, like you can still have sex and you can even have sex in the way that you tell yourself you you'd rather do it. You know if economy is available you know, so you know like you're not you know it's relatively speaking it's way easier than like not using cocaine if you like using cocaine, it's just basically getting in the habit of carrying a condom. So that's just one idea of like there could </s> |
<s>[INST] Indeed is one such tool. I highly recommend they have a special offer only available for a limited time. You can check it out indeed. Dot com slash lex. This is the lex Friedman podcast to support it. Please check out our sponsors in the description and now Dear friends, here's Annika Harris In your book, conscious you described evidence that free will is an illusion and that consciousness is used to construct this illusion and convince ourselves that we are in fact deciding our actions. Can you, can you explain this? I think this is Chapter three. [/INST] First of all, I I really think it's important to make a distinction </s><s>[INST] between [/INST] free will and conscious will and we'll get into that in a moment. So free will in terms of our brain as a system in nature. Making complex decisions and doing all of the complex processing it does, there is a decision making process in nature that our brains undergo um that we can call free will, that's that's fine to use that shorthand for that. Although once, once we get into the details, I might um convince you that it's not so free, but that the decision making process is a process in nature. The feeling our conscious experience of feeling like consciousness is the thing that is driving the behavior. That is, I would say in most cases an illusion. And usually when we talk about free will, that's the thing we're talking about. I mean sometimes it's in conjunction with the decision making process, but for the most part, when we use the term free will, we're talking about this feeling that consciousness that that that we have a self, that this there's this concrete thing that's separate from brain processing that somehow swoops in And is that the cause of our decision or the cause of our next action? And that is um in large part, if not in its entirety and illusion. So </s><s>[INST] conscious will is an illusion. And then we can try to [/INST] free will, I would say is a is good shorthand for a process in nature which is a decision making process of the brain, </s><s>[INST] but decisions are still being made. So there's um uh if you ran the universe over again, is there, would it turn out the same way I mean, maybe trying to sneak up to like what does it mean to make a decision in a way that's almost uh that means something. So [/INST] right, so this is where our intuitions get challenged. I've been thinking about some new examples for this just because I talk about it a lot and and the truth is most of the things I write about and talk about and think about our so counterintuitive. I mean that that's really what my game is, is breaking intuitions, shaking up intuitions in order to get a deeper understanding of reality. I'm often, even though I've thought about this for 20 years and think about it all the time, it's an obsession of mine really, I have to get back into that mind frame to be able to think clearly about it because it is so counterintuitive, </s><s>[INST] depends [/INST] on if there are kids around or if I'm alone or if I've been meditating. But what I was going to say, actually, I felt like we we need to just take one step back and talk a little bit just because I think the the importance of shaking up intuitions for scientific advancement is such an important piece of the scientific process. Um and I think we've reached a point in consciousness studies where it's very difficult to move forward and usually that's a sign that we need to start shaking up our intuition. So, you know, throughout history that the huge breakthroughs, the things that have really shifted our view of the universe and our place in the universe and all of that, those almost always if not always require that we at the very least shift our intuitions um update our intuitions, but many of them we just have to let go of intuitions that are feeding us false information about the way the world works. </s><s>[INST] Well, the weirdest thing here is that here we're looking at our own mind, you have to uh let go of your intuitions about your own intuitions. [/INST] Yeah. Right, Exactly. It's very meta and makes it hard and it's part of the reason why doing interviews for me feels so difficult aside from the fact that I just have social anxiety in general, what's </s><s>[INST] good because I took mushrooms just before we started. So we're in this we're on this journey together, let's go. So where do we take a step backwards? [/INST] And I was just, I was going to say, I mean, this leads into the point I was going to make. But what I was going to say is I mean, also just for me, I feel like I I'm not as good at speaking as I am at writing that I'm clear in my writing. And because these topics are so difficult to get our minds around. Um it's hard to kind of get to any real conclusion in real time. It's actually how I started writing my book. Um was just writing for myself, I decided that I needed to spend some time writing down all of my thoughts in order to get clear about how I think about them. </s><s>[INST] So you write down a sentence and you think in the in the silence paragraphs and and you just [/INST] and then I see if that makes sense. And then I check it with my intuitions, which is really the scientific process. And I really, in many ways I feel like I'm a physicist at heart, all of my inquiry, all of my career, Everything I'm interested in actually going back to being a child is just deep curiosity about how the world works, what this place is, what it's made of, how we got here. Um, just being amazed at the fact that I'm having an experience over here and you're having one over there and we're in this moment of time and you know, what does that all mean? My interest in consciousness really came out of originally an interest in physics and I guess that the two were always side by side and I didn't really connect them until I was older. But um I've always been really interested in just understanding the nature of reality before I even had language to describe. </s> |
<s>[INST] the following is a conversation with Bjarne Charles stroke, he is the creator of C Plus plus programming language that after 40 years is still one of the most popular and powerful languages in the world? Its focus on fast, stable robust code underlies many of the biggest systems in the world that we have come to rely on as a society. If you're watching this on youtube for example, many of the critical backhand components of Youtube are written in C plus plus. Same goes for google facebook, amazon twitter, most Microsoft applications, adobe applications, most database systems and most physical systems that operate in the real world like cars, robots, rockets that launch us into space and one day will land us on mars C plus plus also happens to be the language that I used more than any other in my life. I've written several 100,000 lines of C plus plus source code of course, lines of source code don't mean much but they do give hints of my personal journey through the world of software. I've enjoyed watching the development of C Plus plus is a programming language leading up to the big update in a standard in 2011 and those that followed in 14 17 and toward the new C plus plus 20 standard, hopefully coming out next year. This is the artificial intelligence podcast. If you enjoy it, subscribe on youtube give it five stars in Itunes supported on patreon are simply connect with me on twitter elects Friedman spelled F R I D M A N and now here's my conversation with Bjorn stroke stroke [/INST] The </s><s>[INST] first program you've ever written. Do you remember [/INST] it was my second year in university, first year of computer science And it was an elk or 60. I calculated the shape of super lips and then connected points on the, on the perimeter creating star patterns. It was with with with wedding on paper printer </s><s>[INST] and that was in college university. [/INST] Yeah. I learned to program the 2nd Year University. </s><s>[INST] And what was the first programming language if I may ask it this way that you fell in love with. I I think I'll [/INST] call 60 and after that I remember I am the snowboard. I remember FORTRAN didn't fall in love with that. I remember pascal didn't fall in love with that. It always gotten away of me. Uh and then I just covered a simpler and that was much more fun. And from there I went to micro micro code. So you were drawn </s><s>[INST] to the, you found the low level stuff beautiful. [/INST] I went through a lot of languages and then I spent significant time in assembler and microscope that was sort of the first really profitable things and I paid for my master's actually and then I discovered similar which was absolutely great. Similar. Similar was the extension of algal 60 done primarily for simulation but basically they invented object oriented programming and inheritance and runtime polymorphism when they were while they were doing it and that was the language that taught me that you could have the sort of the problems of a program grow with the size of the program row and with the square of the size of the program that is you can actually module arise very nicely. And that that that was a surprise to me. It was also a surprise to me that a stricter type system than pascal's was helpful. Whereas pascal's type system got my way all the time. So you need a strong type system to organize your code well, which has to be extensible and flexible. </s><s>[INST] Let's get into the details a little bit. What kind if you remember, what kind of type system did pascal have? What type system typing system did the alcohol 60 have? [/INST] Basically pascal was one of the simplest language that Nicholas we could define that served the needs of Nicholas we had at the time and it has a sort of a highly moral tone to it. That is, if you can say it in pascal, it's good. And if you can't, it's not so good. Whereas similar large is basically to build your own type system. So instead of trying to fit yourself into uh, Nicholas v in this world, Kristen eagles language and lulu handles language allowed you to build your own. So it's sort of close to the original idea of you build a domain specific language. As a matter of fact, what you build is a set of types and relations among types that allows you to express something that's suitable for an application. </s><s>[INST] So when you say types, the stuff you're saying has echoes of object oriented programming. [/INST] Yes, they invented it. Every language that uses the word class for type is a descendant of similar directly or indirectly christ in. You go on. All you handle were mathematicians and they didn't think in terms of types. They um, but they understood sets and classes of uh elements and so they call that type classes and basically in C plus plus as in similar classes, are you certifying type? </s><s>[INST] So can you try the impossible task and give a brief history of Programming languages from your perspective? So we started with alcohol 60 Simula Pascal but that's just the 60s and 70s. [/INST] I I can I can try the most sort of interesting and major improvement of programming languages was fortune the first four trip because before that all code was written for a specific machine. And each specific machine had a language a simply language or crow assembler or some extension of that idea. But you're writing for a specific machine in the terms in the language of that machine and Marcus and his team at IBM built a language that would allow you to write what you really wanted that is you could write it in a language that was natural for people. Now these people happen to be engineers and physicists. So the language that came out was somewhat unusual for the rest of the world. But basically they said formula translation because they wanted to have the mathematical formulas translated into the machine. And as a side effect they got portability because now they are writing in the terms that the humans used and the way humans thought and then they had a program that translated it into the machine's needs and that was new and that was great. And it's something to remember. We want to raise the language to the human level, but we don't want to lose the efficiency. So, </s> |
<s>[INST] but why? Because I seem to be equally as dumb today as I was yesterday? So there's some persistence, like a consistency over time that the intelligence have plugged into? So like what's it seems like there's a hard constraint? [/INST] Well, the </s><s>[INST] amount of computation I can perform in my consciousness like they seem to be really closely connected somehow. [/INST] Well, I think the point is that the thing that gives you kind of the ability to have kind of conscious intelligence, you can have kind of this Okay, so, so one thing is we don't know, intelligence is other than the ones that are very much like us. Yes. Right. And the ones that are very much like us, I think have this feature of single thread of time bounded, you know, computational bounded now that but you also need computational sophistication, having a single thread of time and being computational rebounded. You could just be a clock going tick tock, you know, that would satisfy those conditions. But the fact that we have this uh sort of uh irreducible, you know, computational ability, that's that's an important feature. That's that's the sort of the bedrock on which we can construct the things we construct now. The fact that we have this experience of the world that has a single thread of time and computational bounded nous. The thing that I sort of realized is it's that that causes us to deduce from this irreducible mess of what's going on in the physical world, the laws of physics that we think exist. So in other words if we say, why do we believe that there is, you know, a continuous space, let's say, why do we believe that gravity works the way it does Well. In principle we could be kind of parsing details of the universe that were uh you know that okay, the analogy is again with the, you know, statistical mechanics and molecules in a box. We could be sensitive to every little detail of the swirling around in those molecules and we could say what really matters is the, you know, the wiggle effect. That is um you know, there is something that we humans just never noticed because it's some weird thing that happens when there are 15 collisions of air molecules and this happens and that happens, </s><s>[INST] we just see the pure motion of a ball moving [/INST] about. Why </s><s>[INST] do we see [/INST] that? Right. And the point is that that what seems to be the case is that the things that if we say given this sort of hyper graph, that's updating and all the details about all the sort of uh sort of atoms of space and what they do and we say, how do we slice that to what we can be sensitive to? What seems to be the case is that as soon as we assume, you know, computational bounciness single thread of time that leads us to general relativity, in other words, we can't avoid that, that that's the way that we we will parse the universe, given those constraints, we parse the universe according to those particular uh, in such a way that we say the aggregate reducible compete sort of computation pocket of computational reduce ability that we slice out of this kind of whole computational irreducible ocean of behavior is just this one that corresponds to general activity. </s><s>[INST] Yeah, but we don't perceive general relativity [/INST] well, we do if we do fancy experiments. So </s><s>[INST] you're saying so perceive really does mean [/INST] before we drop something. That's that's a great example of general relativity in action that. But </s><s>[INST] what's the difference is in that in Newtonian mechanics? I [/INST] mean, it doesn't this is when I say general activity, that gravity, but the Uber theory, so to speak. I mean, Newtonian gravity is just the approximation that we can make, you know, on the Earth and things like that. So this is, you know, the phenomenon of gravity is one that is a consequence of, you know, we would perceive something very different from gravity. So, so the way to understand that is when we think about, okay, so we make up reference frames with which we paris what's happening in space and time. So in other words, one of the, one of the things that we do is we say as time progresses, uh everywhere in space, something happens at a particular time and then we go to the next time and we say this is what space is like at the next time is what space is like at the next time. That's it's the reason we are used to doing that is because you know, when we look around we might see, you know, 100m away. Um the time it takes light to travel that distance is really short compared to the time it takes our brains to know what happened. So as far as our brains are concerned, we are parsing the universe in this. There is a moment in time, it's all of space, there's a moment in time, it's all of space. You know, if we were the size of planets or something, we would have a different perception because the speed of light would be much more important to us. We wouldn't have this perception that things happen progressively in time everywhere in space. And so that's an important kind of constraint. And the reason that we kind of past the universe in the way that causes us to say gravity works the way it does is because we're doing things like deciding that we can say the universe exists. Space has a definite structure. There is a moment in time space has this definite structure. We move to the next moment in time space is another structure that kind of set up is what lets us kind of deduce kind of what passed the universe in such a way that we say gravity works the way it does. </s> |
<s>[INST] Some of the most successful people I know are sort of happily married and have kids and so on. It's it's always can be [/INST] boring, boring is okay, boring is serenity </s><s>[INST] and it's funny how that those elements actually make you much more productive. I don't understand the uh [/INST] I don't think relationships should drain you and take away energy that you could be using to create things that generate pride. </s><s>[INST] Okay, did you [/INST] say your relationship of love yet? Have you said your your definition of love? </s><s>[INST] My definition of love? Uh No, I did not say it. Well at the time uh when you have, when you have a podcast maybe you can invite me on. Oh [/INST] no, I already did. You're doing it. We've already talked about </s><s>[INST] this. Um because I also have co dependency, I have to say yes. [/INST] Yeah. Yeah. I know </s><s>[INST] you owe me now. Actually what uh I wondered whether when I I asked if we could talk today after doing more research and reading some of your book, I certainly wonder did you just feel pressured to say yes? Yes, of course. Good. But [/INST] I'm a fan of yours. No, I actually, because I am putting it but I'm in recovery for a co dependent. So I actually do, I don't do anything. I don't want to do </s><s>[INST] you really, you gotta, you always say no. [/INST] What's that </s><s>[INST] good. Trying to move this [/INST] A couple member. I moved it from one to to just </s><s>[INST] just [/INST] how covered I am not, but I don't do anything. I don't want to do. </s><s>[INST] Yeah. You're ahead of me on that. Okay, so do you think about your immortality? [/INST] Yes. It is a big part of how I was able to sort of kick start my co dependence recovery. My dad passed a couple years ago. And when you have someone close to in your life die, everything gets real clear in terms of how we're a speck of dust. Who is only here for a certain amount of time. </s><s>[INST] What do you think is the meaning of it all? Like what? This speck of dust, What what's uh, maybe in your own life? What's the goal? The purpose of your existence? [/INST] Is there one? </s><s>[INST] Well, you you're exceptionally ambitious. You've created some incredible things in different disciplines. [/INST] Yes. We're all just managing our terror because we know we're going to die. So we create and build all these things and rituals and religions and, you know, robots and whatever we need to do to just distract ourselves from imminent rotting. We're riding. We're all dying. And, you know, I, you know, I got very into terror management theory when my dad died and it resonated, it helped me and everyone's got their own religion or sense of purpose or thing that distract them from the horrors of being human. Um, what's </s><s>[INST] the terror management? [/INST] Terror management is basically the idea that since we're the only animal that knows they're gonna die. We have to basically distract ourselves with awards and um achievements and games and whatever. Just in order to distract ourselves from the terror we would feel if we really processed the fact that we could not only we are going to die, but also could die at any minute because we're only superficially at the top of the food chain. Um and you know, technically we're the top of the food chain if we have houses and guns and stuff machines, but if me and a lion or in the woods together and it's most things could kill us. I mean a B can kill some people. Like something that's big can kill a lot of humans. Like, you know, so it's basically just to manage the terror that we all would feel if we were able to really be awake because we're mostly zombies. Right? Job, school religion, go to sleep, drink football relationship doesn't mean love. You know, we're kind of just like trudging along like zombies for the most part. And then I think </s><s>[INST] that fear of death as some motivation. [/INST] Yes. </s><s>[INST] Well, I think I speak for a lot of people in saying that I can't wait to see what your terror creates in the in the next few years. I'm a huge fan wouldn? T thank you so much for talking to. Thanks for listening to this conversation with Whitney cummings and thank you to our presenting sponsor, cash app, download it and use Code Lex podcast. You'll get $10.10 dollars will go to first stem education non profit that inspires hundreds of thousands of young minds to learn and to dream of engineering our future. If you enjoy this podcast, subscribe on Youtube, give it five stars on apple podcast, support on Patreon or connect with me on twitter. Thank you for listening and I hope to see you next time. [/INST] </s> |
<s>[INST] rebel effects of all of that on the unlocking the human potential. [/INST] It's unbelievable </s><s>[INST] all those people [/INST] and </s><s>[INST] building cool stuff, amazing thing. Yes. [/INST] Yes, Yes. So some are going to be built stuff is going to work on the reforms. So we're working on reforms by the way, I'm I'm the head of the Africa Center for Prosperity of the atlas network, the largest organization in the world, working on taking down barriers of entry for entrepreneurs around the world in their respective countries, so we're doing great work. There are um basically um you know, all them, obviously all the think tanks we have in, in africa right now, um free market think tanks and we want to promote more of them to come up and these are local solutions by local people for their local problems, always, that's where we draw the line and so um there, so we're working on reforms primarily and making people understand the free markets and the importance of it. Um, but it is piecemeal legislation, it takes time, It is hard. By the time you accomplish something here, more crap has happened over here, more laws have been pounded out because you know how they fix a bad law most of the time in the US somewhere else put other laws to kind of undo the law before, but it's keep stacking up and before, you know it, where you should have one thing and it it's clear you have 100 and they go against each other and then it's all is worse. So we have piecemeal legislation that happening, you know, our teams are doing really amazing, fantastic work, especially the team in, you know, imani in Ghana, we have a group in, in Burundi the great and the Great Lakes. I mean, people are doing amazing work. Amazing work. But we need to run faster. So while we keep we help them running faster, we also have to unlock other things. And right now, I'm working on one of my most craziest projects. Something bold, radical crazy for some people. But I know we're not crazy because before us, Singapore has done it. You know, Hong kong has done it latest, the most recent china with the sec is the smell, the special economic zones. Um some of the most radical free market zones in the world. They've done it and oftentimes within a generation, meaningful change starts to happen, right? So, um here, what I'm working on is this concept of some call it um charter cities, paul Romer, others call it um the um free cities and I like to call it startup cities. What these are is for us to think about, okay, if piecemeal legislation takes forever at the same while we have this demographic that's growing faster and faster in africa there is a discrepancy here between the the process of the progress we're making to set the right environment for business to prop up and how many more people are coming to life literally every day on the continent. There's a discrepancy here. And so the ticking bomb is going faster than the process with the progress we can make. This is a problem. So what some of us are working on is this concept of a startup cities and to say peace minister takes piecemeal legislation takes too long. How about we continue doing that work, Which is essential and critical, but at the same time, can we think of zones and I like to call them also common law zones where we basically try to have within the country an area where for business, I'm not talking about family law or any of that stuff, no one is touching your culture or anything like that. But we're just saying business wise, an enclave where you have the best practices from around the world, including yours in terms of what constitutes a great business environment and allow people in like it's a, it's, you know, you get in freely or nobody's forcing you to go, nobody's forcing you to whatever. So in this, so basically you're to think about this um rather unoccupied plot of land within a country. Think Dubai on 100 and 10 acres of land. Dubai is thinking that uh, in their case, they're like, maybe they decided maybe she realized that the best for business in their case. And they said they look to run and we're like, wow, But common law especially british common law seems like a very good one. So at that point they decided for business only, not family or anything like that, which is gonna stand, you know, Sharia or whatever. And so they said we are going to bring in, um, you know, uh, so they hired a retired british common law judges to educate the law and trained the people under there. And I'm oversimplifying. But at the end of the day, in a, within a generation, Dubai became one of the top international financial centers of the world. It is what it is today. Um, so in </s><s>[INST] the case of the African nations that that zone can then spread. [/INST] Yes, it can not only spread, but maybe let's say Senegal, Senegal was to go for this here. You have this one and then over there you have another zone. And what they start to do is we're not all model the same way because maybe this one is saying, hey, we want to attract more, I don't know, maybe want to attract more um, um medical research, right? This one's gonna be saying maybe we want to attract more um crypto or maybe it's gonna be more like us. We want to be more about religious vessel or whatever. You know what I mean? So we wanted to fit more of that and just kind of give the basics the grounds and then watch the magic happen on it, right? And so this is what we're working on. And the hope there because some of the time people are like, you know, I know some people are like, you guys are crazy. But I'm like, no, it's, it's, it's more or less the story of um, you know um the asian tigers and um most recently most of china's progress economically speaking because some people might say well you don't want the china way of developing. You see even then I say and it's okay you can always do better But we cannot deny the what the magic that they have accomplished, what they have accomplished is nothing short of a miracle. 800 million people getting out of poverty. </s> |
<s>[INST] so C, C and C plus plus I was in the air already oh [/INST] no C and C plus plus absolutely owned the universe at that time everything was written in C and C plus plus. </s><s>[INST] So where was the hunch that there was a need for revolution? [/INST] Well so the need for a revolution was not about the language, it was about, it was just as simple and vague as there are things happening out there, </s><s>[INST] you understand [/INST] them, we need to understand them and and so a few of us went on several um somewhat epic road trips um literal road trips, literal road trips, it's like get on an airplane, go to Japan visit, you know Toshiba and Sharp and Mitsubishi and Sony and all of these folks and you know because we worked for sun. We had you know, folks who were willing to like give us introductions, you know, we we visited, you know Samsung and um you know a bunch of korean companies and we went all over europe, went to you know, places like like phillips and seamen's and Thompson. And </s><s>[INST] what did you see there? [/INST] You know, for me that one of the things that sort of left out was that they were doing all the usual computer computer things that people had been doing like 20 years before. The thing that really leapt out to me was that they were sort of reinventing computer networking and they were making all the mistakes that people in the computer industry had had made. And since I have been doing a lot of work in in the networking area, you know, you know, we'd go and you know visit, you know, company X they described this networking thing that they were doing and just without any thought, I could I could tell them like the 25 things that we're going to be complete disasters with that thing that they were doing. Um and I don't know whether that had any impact on any of them. But but but that particular story of you know, sort of repeating the disasters of the computer science industry um was there and and one of the things we thought was well maybe we could do something useful here with like bringing them forward somewhat. But but also at the same time we learned a bunch of things from, from these, you know, mostly consumer electronics companies. Um, and, you know, high on the list was that, mm they viewed their like, relationship with the customer as sacred. Um, they were never ever willing to make trade offs between for, for safety. All right. So one of the things that had always made me nervous in the computer industry was that, um, people were willing to make trade offs and reliability to get performance. Um, you know, the, you know, they want faster fascinated breaks a little more often because it's fascinating. Maybe you run it a little hotter than you should, or like, like the one that always blew my mind was the way that, um, the folks at, at, at Cray supercomputers got their division to be really fast, was that they did Newton Rapson approximations. And so, you know, the bottom several bits of, you know, a over B. We're essentially random numbers. Um, what could possibly go wrong, what could go wrong? Right? And, you know, just figuring out how to nail the bottom bit, how to make sure that, you know, if you put a piece of toast in a toaster, it's not going to kill the customer. It's not going to burst into flames and burn the house down. </s><s>[INST] So those are, I guess those are the principles that were inspiring. But how did from the days of, uh, java is called oak because of a tree outside the window story. There's a lot of people know, how did it become this incredible, like powerful language. [/INST] Well, so it was a bunch of things. So we, you know, after all that we started, you know the way that we decided that we could understand things better was by building a demo building a prototype of something. So um kind of, because it was easy and fun, we decided to build control system for some home electronics, tv VCR that kind of stuff. And as we were building it, we, you know, we we sort of discovered that there were some things about standard practice in C programming that um we're really getting in the way and and it wasn't it wasn't exactly, you know, because we were writing this all this C code and C plus plus code that that we couldn't write it to do the right thing. But that um one of the things that was weird in the group was that we had um a guy who's who's who's, you know, his sort of top level job was, he was a business guy, you know, he was sort of an NBA kind of person think about business plans and all of that. And you know, there were a bunch of things that were kind of, you know, and we will talk about things that were going wrong and um are things that were going wrong, things that were going right and you know, as we thought about things like like the requirements for security and safety, um, some low level details and see like naked pointers and you know, so, so back in the early nineties, um, it was well understood that, you know, the number one source of like security vulnerabilities, these pointers was just pointers was just bugs. Yeah, right. And it was like, you know, 50 60 70% of all security vulnerabilities were bugs, and the vast majority of them were like buffer overflows. </s><s>[INST] So you're like, we have to fix this, [/INST] we we have to make sure that this cannot happen. And that was kind of the original thing for me was this cannot, this cannot continue. And one of the things I find really entertaining this year was, um, I forget which rag published it, But there was this article that came out that was, um, an examination is sort of the result of of an examination of all the security vulnerabilities in chrome and chrome is like a giant piece of C plus plus code and 60 or 70% of all the security vulnerabilities were stupid pointer tricks and I thought it's 30 years later and we're still there and we're still there and you know, you know, that's one of those, you know, slap your forehead and, and, and just, just, just want to cry, would you attribute </s> |
<s>[INST] So it's a really important problem to solve What, what are your, your sources of hope in this? So like how do you steer the canoe? [/INST] One of my big sources of hope and this is my putting my answer to what I changed my mind on is I I think I always knew this, but I forget it's easy to forget it. Our primitive brain does not remember this fact, which is that I don't think there are um, very many bad people. Now when you say bad, you know, there are they're selfish. People were most of us. I think if, you know, I think that if you think of people, uh, you know, there's, there's, you know, digital languages ones and zeros and our primitive brain very quickly can get into the land where everyone's a one or a zero. Our tribe were all once, you know, we're perfect. I'm perfect. My family is that other families, That other tribe. There are zeros and you dehumanize them, right? These people, these people are awful. So, d'you know, zero is not a human place. No one is a zero and no one's the one, those are your dehumanizing yourself. So, when, when when we get into this land, I call it political Disneyworld because in Disney movies are good guys and you know, scar is totally bad and mufasa is totally good, right? There's no you don't see mufasa's character flaws. You don't see scars up upbringing that made him like that. That humanizes no lionizes him, whatever you are well done. Yeah, Mufasa's are one and scars zero. Very simple. So political Disney world is a place, a psychological place that all of us have been in. Um, and it can be religious Disney world, it can be national Disneyworld and war, whatever it is, But it's a place where we fall into this delusion that they're our protagonist and antagonist and that's it, right? That is not true. We are all 0.5 or maybe 0.6 is two point four's in that we are also on one hand, it's not that, I don't think there's that many really great people, frankly, I think if you get into it, people are kind of a lot of people, you know, most of us have, you know, if you get really into our most shameful memories, the things we've done that with our worst, the most shameful thoughts, the deep selfishness that some of us have in areas you wouldn't want to admit, right? Most of us have a lot of an admirable stuff, right? Um on the other hand, if you actually got into really got into someone else's brain and you look at their upbringing, you look at the trauma that they've experienced and then you look at the, the insecurities they have and then, and you look at all there, if you if you assemble the highlight reel of your worst moments, the meanest thing you've ever done, the worst, the most selfish the times, you know, you stole something whatever and you just have people think lex is an awful person. If you highlighted your, if you did a montage of your best moments, people say, oh he's a God, right? But of course we all have both of those. So I've started to really try to remind myself that everyone is a .5 Right? And .5s are all worthy of criticism and we're all worthy of compassion. And the thing that makes me hopeful is that I really think that there's a bunch of .5s and .5 are good enough that we should be able to create a good society together. There's a lot of love in every human and I think there's more love in humans than hate. Um you know, I, yeah, I always remember this moment, uh this is weird anecdote, but I was I'm a Red sox fan boston, Red sox baseball and Derek Jeter's who we hate the most, he's on the Yankees and hate, right? Jeter, right? He was his last game in Fenway, he's retiring and he got this rousing standing ovation and almost cried and it was like what is going on? We hate this guy, but actually there's so much love in all humans, you know we have it felt so good to just give a huge cheer to this guy we hate because it's like this moment of like a little fist pounding, like of course we all actually love each other and I think there's so much of that and so the thing that I think I've come around on is I just, I don't I think that we are in an environment that's bringing out really bad stuff, I don't think it's if I thought it was the people, I would be more hopeful, like if I thought it was human nature, I'd be you know, be more upset, it's the two independent variables here. Um or that there's a fixed variable, there's a constant which is human nature and there is the independent variable. Environment and behavior is the dependent variable. I like that. The thing that I think is bad is the independent variable, the environment which means I think we can, the environment can get better and there's a lot of things that can go into about why the environment I think is bad, but I have hope because I think the thing that's bad for us is something that can change </s><s>[INST] The first principles idea here is that most people have the capacity to be a .72.9 if the environment is uh, is properly calibrated with incentives. [/INST] I think that. Well, I think that I think maybe if we're all, yeah, we're all .5 I think that that uh, that environments can bring out our good side, you know? Yeah. So maybe we're all on some kind of district distribution and uh, the right environment can yes, can bring out our higher sides sides. And I think a lot of, a lot of ways you could say it has, I mean, the US environment we take for granted how the liberal laws and liberal environment that we live in. I mean like in new york city, right? If you walk down the street and you like assault someone, if anyone sees, you probably gonna yell at, you might get your asking by someone for doing that. You also might end up in jail. Um, you know, if it's security cameras and there's just norms, you know, we're all trained, that's what awful people do, right? So there's it's not the human nature doesn't have it in it to be like that. It's that this environment we're in has has has made that a much much, much smaller experience for people. There's so many examples like that where it's like, man, you don't realize how much of the worst human nature is, is contained by our environment. And um, but I think that, you know, rapidly changing environment, which is what we have right now. Social media starts, I mean what a seismic change to the environment. There's a lot of examples like that rapidly changing environment can create rapidly changing behavior and wisdom sometimes can't keep up and so we, you know, uh we can we can really kind of lose our grip on some of the good behavior. Were </s> |
<s>[INST] Yeah, there could be a lot of ways to go inwards to. Once you figure out some aspect of physics we haven't figured out yet. Maybe you can travel to different dimensions. I mean, travel in three dimensional space may not be the most fun kind of travel. There may be like just a huge amount of different ways to travel. It doesn't require a spaceship going slowly in three D. Space is space [/INST] time. It also feels in a one of them problems is that speed of light is alone and the university is vast and it seems that actually most likely if we want to travel very far then uh then we would instead of actually sending spaceships with humans that wait a lot we would send something similar to what yuri Miller is working on. These are like a huge sale which is at first power. There there is a shot of laser from an earth and it can propel it the quarter of speed of light and sale. It's a self contains a few grams of equipment. And that might be the way to actually transport matter through universe. But then when you think what would it mean for humans? It means that we would need to actually put their three D. Printer and you know three D. Printed human and other planet. I don't know play them Youtube or let's say or like a pretty three D. Print like huge human right away or maybe a womb or so. Um Yeah </s><s>[INST] with our current techniques of archaeology. If if if a civilization was born and died uh long long enough to go on earth we wouldn't be able to tell. And so that makes me really sad. And so I think about Earth in that same way how can we leave some remnants? If we do destroy ourselves, how can we leave remnants for aliens in the future, discover like here's some nice stuff we've done like Wikipedia on Youtube. Do we have it like in a satellite orbiting earth with the hard drive? Like how how do we say, how do we back up human civilization? Uh, the good parts or all of it is good parts so that uh, it can be preserved longer than our bodies can. That's it. It's kind of uh it's a difficult question. It also requires the difficult acceptance of the fact that we may die and if we die, we may die suddenly as a civilization. [/INST] So let's see, I think it kind of depends on the cataclysm we have observed in other parts of universe that birds of gamma rays, uh, these are high energy rays of light that actually can operatic your entire galaxy. So there might be actually nothing even to nothing to protect us from it. I'm also, and I'm looking actually at the past civilizations. So it's like aspects or so they disappear from the surface of the earth. And one can ask why is it the case? And the way I'm thinking about this, you know, that definitely they had some problem that they couldn't solve. And maybe there was a flat and all the sudden they couldn't drink. There was no potable water and they all died. And uh, I think that so far the best solution to such a problems is I guess technology. So I mean if they would know that you can just boil water and then drink it after, then that would save their civilization. And even now when we look actually at the current pandemic, it seems that the once again actually science comes to rescue and somehow science increases size of the action space and then I think that's a good thing. </s><s>[INST] Yeah, but nature has a vastly larger action space, [/INST] but still it might be a good thing for us to keep on increasing action space. </s><s>[INST] Okay. Looking at past civilizations, Yes, but looking at the destruction of human civilization, perhaps expanding the action space will add actions that are easily acted upon, easily executed and as a result destroy us. [/INST] So let's see, I was pondering why actually even we have negative impact on the globe because you know, if you ask every single individual, they would like to have clean air. They would like healthy planet. But somehow it actually is not the case that as a collective, we are not going in this direction. I think that there exists very powerful system to describe what we value. That's capitalism. It assigns actually monetary values to various activities at the moment. The problem in the current system is that there is something which we value. There is no cost assigned to it. So even though we value clean air or maybe we also uh value lack of destruction on the internet or so at the moment, these quantities, you know, companies, corporations can follow them for free. So in some sense I wish or like that I guess purpose of politics to align the incentive systems and we are kind of maybe even moving in this direction. The first issue is even to be able to measure the things that we value, then we can actually assign the monetary value to them. </s><s>[INST] Yeah and that's so it's getting the data and also probably through technology enabling people to vote and to move money around in a way that is aligned with their values. And that's very much a technology question. So like having one president and congress and voting that happens every four years or something like that. That's a very outdated idea. There could be some technological improvements that kind of idea. [/INST] So I'm thinking from time to time about these topics but it also feels to me that is, it's a little bit like it's hard for me to actually make correct predictions. What is the appropriate thing to do. I extremely trust some outman our ceo on these topics here. Okay, I'm more on the side of being I guess naive, heaping that the </s> |
<s>[INST] That's what I kind of, when I look at the life of Hitler, it seems like there's so many places where [/INST] something could have intervened </s><s>[INST] into the changed completely the person. I mean, there's like the caricature, like the obvious places where he was an artist, and if he wasn't rejected as an artist, he was a reasonably good artist, so that that could have changed, but just his entire, like where he went in Vienna and all these kinds of things, like little interactions could have changed, and there's probably millions of other people who are capable who the environment may be able to mold in the same way did this particular person to create this particular kind of charismatic leader in this particular moment of time. [/INST] Absolutely. And I guess the way I would the way that I would say, I I would agree 100% and I guess the way that I would say it is like this in the west, we have a way of reasoning um about causation which focuses on single simple causes for things, you know, there's a there's an essence to Hitler, there's an essence to his character, He was born with that essence or it was forged very, very early in his life and that explains the um the landscape of his horrible landscape of his behavior. But there's another way to think about it away that actually is much more consistent with what we know about biology, how biology works um in the physical world. And that is that most things are complex, not as in, wow, this is really complex and hard, but complex as in complexity, that is more than the sum of their parts. And that most phenomena have many, many weak nonlinear interacting causes. And so little things that we might not even be aware of can shift someone's developmental trajectory from this to that. And that's enough to take it on a whole set of other paths that, you know that and that these things are happening all the time. So it's not random and it's not really, it's not deterministic in the sense that like everything you do determines your outcome. But it's a little more like um you know, you're nudging someone from one set of possibilities to another set of possibilities. And I but I think the the thing is the thing that I find optimistic is that the the other side of that coin is also true. Right? So look at all the people who risked their lives to help people. They didn't even know. I mean, I just watched Borat the new Borat movie and the thing that I came away with but you know the thing I came away with was look at how generous people were in that because he's making, there are a lot of people he makes fun of and that's fine. But think about like those two guys, those </s><s>[INST] the trump supporters trump [/INST] supporter guys, those guys, </s><s>[INST] those kind, there's kindness in them, right? [/INST] They took a complete stranger in a pandemic into their house. Who does that? Like that's a really nice thing. Or there's one scene, I mean I want to spoil it for people haven't seen it, but but there's you know, there's one scene where he goes in, he dresses up as a jew. Yeah, I laughed myself sick at that scene seriously. But um but he goes in and he and there are these two old jewish ladies. What a bunch of sweethearts. Oh my gosh, like really? I mean that was what I was struck by actually. I mean there are other ones or like the babysitter, right? I mean she was really kind and yeah, so that's really what I was more struck by like, you know, sure there are other people who you know who do do very bad things or say bad things or whatever, but you know, we're like there's one guy who's completely stoic like the guy at the um who's doing the like, you know, sending the messages. I don't know if it's facts or whatever. He's just completely stoic but he's doing his job actually, you know, like you can't, you don't know what he was thinking inside his head. You don't know what he's feeling and he was totally professional doing his job. Okay. So I guess I just, I had a bit of a different, um, you know, view, I guess. And I, so I also think that about people, I think everybody is capable of kindness and um, but you know, it's the question is, how much does it take and what are the circumstances? So for some people, it's going to take a lot, and for some people it only takes a little bit, but you know, are we actually cultivating an environment for the next generation that um, provides opportunities for people to go in the direction of caring and kindness or, you know, and I'm not, I'm not saying that is like a, you know, Pollyanna ish person. Um, uh you know, I think there's a lot of room for competition and debate and and so on. Um, but I don't see Hitler as an anomaly and I never have, that was even before I learned anything about neuroscience and now I would say, knowing what we know about developmental trajectories and life histories and how important that is. Um, you know, knowing what we know about, um, that the whole question of like nature versus nurture is a completely wrong question. You know, we have the kind of nature that requires nurture, we have the kind of genes that allow infants to be born with unfinished brains where the brains, their brains are wired across a 25 year period with wiring instructions from the world that is created for them. And so I don't think Hitler is an anomaly. Um even if it's, even if it's less probable that that would happen, it's possible that it could happen again. And it's not, it's not like he's a bad seed. I mean that doesn't, I just wanna say for like of course he's completely 100% responsible for his actions and all the bad things that happened. So I'm not in any way, this is not me saying, </s> |
<s>[INST] so that they are not traumatized. So do you, the N-word should not be removed from Huck Finn, Adventures of Huck Finn, [/INST] or from the works of James Baldwin and Toni Morrison? Not at all. In fact, it seems to me that the bolderization of these great artists' literary work, as far as I'm concerned, highly objectionable, </s><s>[INST] highly objectionable. When is it okay for a white man to say the N-word [/INST] with a hard R? Well, you know, here we need to focus on the word say. Is it ever okay for anyone, you know, black, white, pink, yellow, I don't care, red, orange? Is it okay for anyone to use this word in a way to put down people, to terrorize people, to intimidate people? Answer, no. But, you know, and I'd say that black person, I've seen, I mean, by the way, I've seen black people use this word to try to intimidate, put down other black people, bad. So I'm against it with a black person, white person, doesn't matter. On the other hand, on the other hand, imagine a white person who is giving a lecture on the history of American racism, a lecture on the history of American racism. And in giving that lecture, quotes the, you know, white racist politicians who until fairly recently in American life, use the infamous N word. So imagine a white history professor giving a lecture about the history of American racism and says, in 1948, this is what so-and-so running for the presidency of the United States said. And then quotes a paragraph or two in which the infamous N word is featured. Is that bad? No, that's not bad. No, that's not bad. Sounds like a perfectly good lecture. And I'm glad that you put the infamous N word in there so that we can see that as recently as 1948, people running for the presidency of the United States openly used the word. That does not bother me. I'll say this too. Now, you know, somebody says, well, you know, nice job, Kennedy, but you've, you've limited it to over here. You've put it in an academic setting. What about other settings? It does not bother me. Let's imagine somebody who's a comedian, a white comedian who is satirizing word usage. Let's imagine a white comedian who is satirizing our current practice and wants to poke fun at the way in which, let's imagine you have a black rapper who invites people on stage. And let's suppose they invite a black person on stage and they're perfectly happy when the black persons flout with their lyrics. They invite a white person on stage. The white person is, you know, that doesn't really sort of mystified, but it comes on stage. And flout with what the rapper says, including the infamous N-word, and then the black rapper gets mad. Imagine the white comedian who satirizes that, pokes fun at that, and in poking fun at that, says the infamous N-word. Am I angry? No, I'm not angry. </s><s>[INST] Not angry at all. What if in the process of satirizing [/INST] that comedian is not very funny? You say that bad joke, you were not funny. I don't object to the use of the infamous N-word. I just say, you know, mm, you're not very funny, N-word? </s><s>[INST] I just say, you know, you're not very funny. But because there's a line, when the joke is not funny, it just seems like the comedy's used as a cover to actually say something hateful. It's interesting thing about comedy. I feel like the funnier you are, the more you can get away with. Probably. And that's something to do with the thing we said earlier, which is when you use words that have power, you should do so with skill and competence [/INST] and the responsibility those words carry. Again, the cases that I'm most familiar with are the cases involving teachers, professors, you know, academic, and it is said sometimes, oh, you know, why do I object? I object, sometimes people say, because, you know, I suspect that this teacher just wanted to say the word and that all of this is a cover, a pretext. Do I, you know, in my sense, my sense of it is, no, I don't think it's a pretext. If, you know, if it's pretextual, that's bad. But in my experience, I have not seen that. </s><s>[INST] I don't believe that that's what's going on. I agree with you on that, but sometimes I do see people that kind of have this fly flying towards the light, desire to say something controversial and edgy, and they don't realize that there's a responsibility there. There's a skill that you should, you shouldn't just say, I mean, actually when comedians first start out, they'll sometimes go into that territory. They'll say edgy stuff that's totally not funny. And then you realize this is not like the edgier the thing, the more skills required to really serve. Like if you're cooking as a chef, a poisonous fish, there's a responsibility on how to cook the damn thing [/INST] so you don't poison the people eating it. I would agree, but to get back to your question, let's imagine that somebody produces a new set of Lenny Bruce albums. So Lenny Bruce was white, Lenny Bruce used the term nigger in his sets. Question, would I want Lenny Bruce's albums now to be purged of the infamous n-word? </s><s>[INST] My response, absolutely not. There's another follow-on sort of question, what you think, I've seen interviews you've done about this particular book, the title of those interviews on YouTube and elsewhere, would use the full word. What do you think about that? [/INST] Should I use this word in the title? In my view, the answer would be yes. Again, there are people, I've been on interviews, I've been on stage with people who had a different conclusion reached. And I respect a different way. Again, there is a place for euphemism. Again, it all depends, I'm not offended. Let's imagine that you posted this and you had asterisks instead of spelling it out. Would I be offended? No, I wouldn't be offended. I would prefer the full spelling, but I would understand where you're coming from. Would it offend me? </s> |
<s>[INST] you actually give advice on the other end of logs being very useful for the defense perspective for you know, information is useful for being able to figure out what the attacks were all about. [/INST] Logs are. The only reason I found Hector Monsegur I mean the one time his VPN dropped during a fox ac and he says he did, it wasn't even hacking, he just was sent a link and he clicked on it and in 10 million lines of of logs there was one I. P address that stuck out, </s><s>[INST] this is fascinating. We'll explore several angles of that. So uh what was the process of bringing down ross and uh the Silk road. Alright, [/INST] so that's a long story, you want the whole thing, you want to break it up, </s><s>[INST] let's start at the beginning [/INST] once we had the information of the chat logs and all that from the server, we found </s><s>[INST] the server with the chat log. [/INST] So the dot onion was running the website, the Silk Road was running on a server in Iceland. How </s><s>[INST] did you figure that out? That's one of the claims that the N. S. A. [/INST] Yeah that's that's that's the one that that we said that. That yeah I wouldn't tell you if it was it's on the internet, I mean the internet has their conspiracy theories and all that. So </s><s>[INST] but you figure out that's the part of the thing you do, you it's puzzle pieces and you have to put them together and look for different pieces of information and figure out, okay so you figure out the servers in Iceland, [/INST] we get a copy of it and so we start getting clues off of that </s><s>[INST] was a physical copy of the [/INST] server. Yeah we flew you fly over there so you you go if you're and if you've never been you should definitely go to Iceland. </s><s>[INST] I [/INST] love it. I love it. It was so I'll tell you this so sorry, tangents, you know I </s><s>[INST] love this. [/INST] So I went to Iceland for the anonymous case and then I went to Iceland for the Silk Road case and I was like oh shoot all cybercrime goes through Iceland um it was just my sort of thing and I was over there for like the third time and I said, if I ever can bring my family here, like, so there's a place called thing of our, and I'm sure I'm sucking up the name, that Icelandic sharpest right now, but it's where the, the north american continental plate and the european contemplate are pulling apart and it's being filled in with volcanic uh material in the, in the middle. And it's so cool. Like I was like one day I'll be able to afford to bring my family here. Um and, and once I left, </s><s>[INST] just like the humbling and the beauty of nature, just [/INST] everything that it was a different world. It was, it was, it was insane how great Iceland is. And so we went back and we rented a van and we took friends and um we drove around the entire country. Uh absolutely like a beautiful place. Like Reykjavik's nice, but get out of Reykjavik as quick as you can and see the countryside house. </s><s>[INST] This place even real [/INST] well, it's so new. I mean that's so, you know, our rivers have been going through here for millions of years and flattened everything out and all that. These are, these are new. This is new land being carved by these rivers, you can walk behind a waterfall in one place. Um it's, it's the most beautiful place I've ever been, </s><s>[INST] you understand why this is a place where a lot of hacking is being done [/INST] because the energy is free and it's cool. It's cool. So you have a lot of servers going on their server farms, you know they're they're the energy has come up out of the ground geothermal um and so, and then it keeps all the servers nice and cool so why not keep your computers there at a cheap rate. </s><s>[INST] I'll definitely visit for several reasons including to talk to the [/INST] unit. </s><s>[INST] Well the servers are there but they don't probably live there. I mean that's interesting. I mean the pacific the PSC the time zones, there's so many fascinating things to explore here. But so [/INST] you got to add to that the, the european internet cable goes through there. So you know across the Greenland and down through Canada and all that. So they have backbone access with cheap energy and free cold weather, you know </s><s>[INST] and beautiful [/INST] and beautiful. Yes. </s><s>[INST] So chat logs on that server, what what are the what what was in the chat logs [/INST] everything? He kept them all. That's another issue. If you're writing a criminal enterprise, please don't keep again, I'm not making a guidebook of how to commit the perfect crime but you know every chat he ever had and everyone's chat, it was, it was like going into facebook of criminal activity. </s><s>[INST] Yeah, I'm just looking at texts with Elon musk being part of the conversations. I don't know if you're familiar but they've been made public for the court cases going through, what's going through is going through, what's going through twitter. Um but it made me realize that okay, um I'm generally, that's my philosophy on life is like anything I text or email or say publicly or privately I should be proud of. So I try to kind of do that because you basically, you say don't keep chat logs, but it's very difficult to erase chat logs from this world. Like I guess if you're a criminal, that should be um like you have to be exceptionally competent at that kind of thing to erase your footprints is very, very difficult. Can't [/INST] make one mistake. All it takes is one mistake of keeping it. But, but yeah, I mean not only do you have to Be whatever you put in the chat log or whatever you can email, it has to hold up and you have to stand behind it publicly when it comes out, but it hasn't, if it comes out 10 years from now, you have to stand behind it. I mean we're seeing that now in today's society. </s> |
<s>[INST] Do you think there is a future where tens of thousands, maybe hundreds of thousands of both delivery drones and flying cars of this kind. A V stars fill the sky. [/INST] I absolutely believe this. And um, there's obviously the societal acceptance is a major question. And of course safety is I believe in safety gear and exceed ground transportation, safety as has happened for aviation already commercial aviation and in terms of acceptance, I think one of the key things is noise. That's why we are focusing relentlessly on noise and we've been perhaps the crisis electric veto vehicle ever built. Um, the nice thing about the sky is a three dimensional. So, so any mathematician will immediately recognize the difference between one d of like a regular highway to three of the sky. Um, but to make it clear for, for the layman, um, say you want to make 100 vertical lanes of highway 11 in SAn Francisco because you believe building 100 vertical lanes is the right solution. Imagine how much it would cost to stack 100 vertical lanes physically onto 101. There would be private if there would be consuming the world's GDP for entire year just for one highway. It's amazing, expensive. Okay in the sky it would just be a recompilation of a piece of software because all these lanes are virtual. That means any vehicle that is in conflict with another vehicle would just go to different altitude and then the conflict is gone. And if you don't believe this, that's exactly how how commercial aviation works. When you fly from new york to SAN Francisco, another plane flies from SAn Francisco new york, there are different altitudes, so they don't hit each other. It's a solved problem for the jets space and it will be a solved problem for the urban space there's companies like google Ring and Amazon working on very innovative solutions, how do we have space management? It is exactly the same principles as we use today throughout today's Jets. There's nothing hard about this. </s><s>[INST] Do you envision autonomy being a key part of it? So that that the the flying vehicles are either semi autonomous or fully autonomous. [/INST] 100% autonomous. You don't want idiots like me fly in the sky, I promise you. And if you have 10,000, what's the movie? The fifth element to get people to happen if it's not autonomous </s><s>[INST] and a centralized. That's a really interesting idea of a centralist sort of a management system for lanes and so on. So actually just being able to have similar as we have in the current commercial aviation but scale it up too much much more vehicles. That's a really interesting optimization problems. [/INST] It is very mathematically very very straightforward. Like the gap we live between jet's Gargantua and part of the reason is there isn't that many jets. So it just feels like a good solution today when you get vectored by air traffic control someone talks to you right so any ATC controller might have up to maybe 20 planes on the same frequency and then they talk to you have to talk back And it feels right because there is more than 20 planes around anyhow. So you can talk to everybody. But if there's 20,000 things around you can talk to everybody anymore. So we have to do something that's called digital like text messaging. Like we do have solutions like we have got 45 billion smartphones in the world now right? And they're all connected and some of the solve the scale problem for smartphones, we know where they all are. They can talk to somebody and they're very reliable, they're amazingly reliable. We could use the same system, the same scale for air traffic control. So instead of me as a pilot talking to a human being and in the middle of the conversation receiving a new frequency like how ancient is that? We could digitize the stuff and and digitally transmit the right flight coordinates and that solution will automatically scale to 10,000 vehicles. </s><s>[INST] We talked about empathy a little bit. Do you think we will one day build an ai system that a human being can love? And that loves that human back like in the movie her [/INST] look, I'm a pragmatist for me a i is a is a tool, it's like a shovel and the ethics of using the shovel. I always with us, the people and there has to be this way in terms of emotions, I would hate to come into my kitchen and see that my refrigerator spoiled all my food. Then have it explained to me that it fell in love with the dishwasher and it wasn't as nice as the dishwasher. So as a result it neglected me. That would just be a bad experience and it would be a bad product. Would probably not recommend this refrigerator to my friends. Um and that's where I draw the line. I think to me technology has to be reliable. It has to be predictable. I want my car to work. I don't want to fall in love with my car. I I just wanted to work. I wanted to compliment me not to replace me. I have very unique human properties and I want the machines to make me turn me into a superhuman. Like I'm already a superhuman today. Thanks to the machines that surround me and give you examples. I can Run across the Atlantic at near the speed of sound at 36,000 ft today. That's kind of amazing. I can uh my voice now carries me all the way to Australia. Um using a smartphone today and it's not not the speed of sound which would take hours. It's the speed of light. My voice travels at the speed of light. How cool is that? That makes me super human. I would even argue my flushing toilet makes me super human. Just think of the time before flushing toilets. And and maybe you have a very old person in your family that you can ask about this or take a trip to rural India to experience it. Um it makes me super human. So to me what technology does, it complements me. It makes me stronger therefore words like love and compassion have very little uh huh. I have very little interest in these four machines. I have interested in people </s> |
<s>[INST] It's just forever. Yeah, it is. I'm gonna apply that to my dating life once again. [/INST] Metaphors just keep on coming. Metaphors just keep on coming. Well, if you think about it, like my tastes has changed throughout the years. When I first saw a Model 3 Tesla, I thought it was the most hideous car I've ever, without the Gorilla, I was like, this is so stupid. It took me all but two months to think that it was one of the coolest looking cars. Same with Cybertruck. I mourned Cybertruck. When I first saw that thing, I was at that thing with, and I went with, we used to do a podcast called Our Ludicrous Future. So we talked a lot about cars and EVs and stuff. We went to that unveiling and literally, we had almost a non-alcohol-induced hangover the next morning of mourning the hideousness of Cybertruck. Come six months later, a year later, </s><s>[INST] and I'm like, damn it, that thing's actually kinda cool. That also teaches you something about, again, it's the thing you said earlier, sort of going against the current of the experts or the beliefs or whatever and making a decision from first principles. Some of that also applies to design and styling and fashion and culture and all that. Big time. Some of that, fashion especially, it's so interesting. So subjective. Being rebellious against the current fads [/INST] actually is the way to pave the new fads. Big time, so subjective. When it didn't take long for others to follow, you look at currently what Hyundai's doing with their, I forget which one, the Ionic or something like that. It's square. It's boxy. It's a throwback. It's 80s. It's got these beautiful retro tail lights. It's got these square headlights. It's very inspired by Cybertruck, in my opinion. It might not be. It might be coincidental that we're all kind of getting </s><s>[INST] this retro future vibe, but retro future vibe. I personally like the boxy, so I never, I still haven't understood Porsches, Porsches. I still can't quite understand the small size, [/INST] the curves, I don't quite get it. Like I said, I don't love the look of the RX-7. I don't love it, but I love it because of the engineering, </s><s>[INST] I guess, that it represents, you know what I mean? Yeah, it's not the surface stuff. It's the deep down stuff. It's that 50-50 weight distribution that matters. All right, let's talk about Starship a little bit. We've been sneaking up to it from a bunch of different directions. Can you just say, what is Starship and what is the most impressive thing to you about it? I mean, you've talked about the engines involved. Maybe you haven't really, kind of like dancing around it, but because this is such a crucial thing in terms of the next few years, in terms of your own life personally, and also just human civilization reaching out to the stars, it seems like Starship is a really important vehicle to making that happen. So what is this thing that we're talking about? [/INST] Yeah, so Starship is currently in development, the world's largest, most powerful rocket ever built, fully reusable rocket, a two-stage rocket. So the booster is landed and, all this is currently aspirational until it's working. So I'll say what it's aspirationally going to be. And obviously I have faith that that will happen, but just factually. So the booster will be reused, landed and refueled and reused. The upper stage will be landed, refueled and reused. And ideally, rapidly, in the sense, not talking about months or weeks of refurbishment, but literally talking about like mild inspections, and ideally like under 24 hour reuse, where you literally land it and fly it like an airplane. So it utilizes liquid methane and liquid oxygen as its propellants. It utilizes the current iterations of it are 33 Raptor engines on the booster engine, or on the booster, and six Raptors on the second stage. So they'll be three that are vacuum-optimized and three that are sea level-optimized on the upper stage. That are primarily, they'll be used I think stage separation anyway in space, but their main reason that they use them is so they can use them for landing too, the three sea level engines to be able to propulsively land the upper stage as well. </s><s>[INST] So the three Raptor engines are the ones that generate the thrust that makes it the most powerful rocket ever built? By almost double. Compared to Saturn 5, really? [/INST] The N1 had 45 meganewtons of thrust, the Saturn 5 had, I think, 35 or 40 meganewtons of thrust, and this has 75 meganewtons. So we're talking almost double. It's a lot of power. </s><s>[INST] That could be the sexiest thing I've ever heard. Okay, so what are the different testing that's happening? So like, what's the static fire with some of these Raptors look like? And where do we stand? You were just talking about offline, like the thing that happened yesterday. [/INST] Yeah. That was impressive. You know, everything in this is kind of iterations. And so, you know, the milestones that we're seeing... We actually have on everydayastronaut.com, we have a milestone checklist of like all the things we're hoping to see that we kind of need to see before the first orbital flight of this rocket. So a big milestone that got checked off yesterday was a wet dress rehearsal. So it's literally like fueling the rocket up, getting ready to do everything, but lighting the engines basically. So we're talking about loading it with propellant all the way. This is the first time. Yeah, right. Where's the milestone? Right there at the top, click that big picture. Yep, just anywhere, that big picture. </s><s>[INST] Yep, yeah, right there. It's the milestones. So there's the what dress rehearsal? So what, what dress rehearsal? [/INST] Yep. So, that's where they, for the first time, they filled it completely to the brim with both liquid oxygen and liquid methane. Now, they had done component-level testing where they filled with liquid nitrogen, which is, you know, it's an inert gas, so it's could like say it leaks out, it's not gonna explode. You could just have a big giant pool of liquid nitrogen flooding the area. But it's not going to be an explosion. So they've done that for cryo testing to make sure all the components and stuff can handle being at cryogenic temperatures. It's kind of a good analog before you start putting your fuel and your oxidizer in there. But now, as of yesterday, they fully fueled the rocket with propellant. Both stages, the first stage and the second stage, were all fully stacked on the pad. I mean, it was the first sense we really got of like, this is what it's going to look like right before it takes off. </s> |
<s>[INST] So the complexity of the protein matters here. The complexity, the complexity of the protein modules or the protein domains. So you're saying uh solved So the definition of solved here is particularly the cast competition, achieving human level, not human level achieving uh experimental level performance on these particular sets of proteins that have been used in these [/INST] competitions. Well, I mean, you know, I I do think that uh you know, especially with regards to the alpha fault, you know, it is able to you know, to solve, you know, at the mere experimental level a three big majority of the of the more compact proteins like or protein domains because again, in order to understand how the overall protein uh you know, multi domain protein fold. We do need to understand the structure of its individual domains. </s><s>[INST] I mean I'm like if you look at alpha zero or like mu zero, if you look at that work, you know there it's nice reinforcement learning self playing mechanisms are nice because it's all in simulation so you can learn from just huge amounts like you don't need data. It was like the problem with proteins like the size uh I forget how many three D structures have been mapped. But the training data is very small, no matter what, it's like millions, maybe one or two million or something like that, but some very small number, but like it doesn't seem like that's scalable. There has to be. I know it feels like you want to somehow 10 X the data or 100 x the data somehow. [/INST] Yes, but we also can take advantage of uh hm ology models. Right? So, so the models that are very good quality because they are essentially um obtain based on the evolutionary information. Right? So so you can see there is a potential to enhance this information and uh you know, use it again uh to to empower the the training set. Um and it's I think I I am actually very optimistic. I think it's been one of these uh sort of uh you know, uh joining events where you have a system that is, you know, a machine learning system that is truly better than the the more conventional by physics based methods. </s><s>[INST] That's a huge leap. This is one of those fun questions, but where would you put it in, in the ranking of the greatest breakthroughs in artificial intelligence history. So like, okay, so let's let's see who's in the running maybe incorrectly. So you got like alpha zero and alpha go beating, beating the world champion at the game of go Thought to be impossible like 20 years ago or at least the community was highly skeptical. Then you got like also deep blue original Kasparov, you have deep learning itself like the maybe what would you say the Alex net image in that moment. So the first you know, network achieving human level performance super not that's not true, achieving like a big leap in performance on the computer vision problem. Uh there is open ai the whole gpt three that whole space of transformers and language models just achieving this incredible performance of application of neural networks to language models, boston dynamics pretty cool. Like robotics. Even people are like there's no way I uh no there's no machine learning currently but ai is much bigger than machine learning. So that just the engineering aspect I would say it's one of the greatest accomplishments and engineering side engineering, meaning like mechanical engineering of robotics ever. Then of course autonomous vehicles, you can argue for Waymo which is like the google self driving car or you can argue for Tesla which is like actually being used by hundreds of thousands of people on the road today machine learning system. Um and uh I don't know if you can, what what what else is there? But I think that's it. So and then after for many people are saying is up there potentially number one, would you put him at number one? [/INST] Well in terms of the impact on the science and on the society beyond it's definitely, you know, to me would be one of the, you know </s><s>[INST] uh three [/INST] Yeah. I mean, I'm, I probably not the best person to, to answer that, you know, but, you know, I, you know, I, I do have, I, I remember My, you know, back in, I think 1997 when the blue, that Kasparov, it was, I mean, it was a shock. I mean, it was, and I think for the, for the, you know, uh, for they, you know, pre substantial part of the world that, especially people who have some, you know, some experience with chess, right? And realizing how incredibly human this game, how, you know, how much of a brain power you need, you know, to, to reach those, you know, those levels of grandmasters, </s><s>[INST] right level. And it's probably one of the first time and how good Gazpacho [/INST] and, and again, yeah, Kaspars arguably one of the best ever. Right? And get a machine that beats him, Right? So it's, it's the </s><s>[INST] first time a machine probably be a human at that scale of a thing of anything. Yes. [/INST] Yes. So that was to me that was like, you know, one of the groundbreaking events in the history of a yeah, </s><s>[INST] that's probably number one. That's probably like, we don't, it's hard to remember. It's like, Muhammad ali versus uh, I don't know any of the mike Tyson or something like that. It's like, no, you gotta put Muhammad Ali at number one as saying with the same with the blue, even though it's not machine learning based [/INST] uh still it it uses advanced search and search is the integral part of it. Yeah. Right. So it's not that </s> |
<s>[INST] and that's the realm of public discord. I should actually recommend. I just listened to uh two people listening intelligence squared debates us edition just had a debate. They have this structure way of uh old Oxford style or whatever they're called debates those two versus two and they talked about affirmative action and it was is incredibly interesting that it's still there's really good points on every side of this issue, which is fascinating to [/INST] listen. Yeah, I agree. And so it's it's interesting to be a researcher trying to do for the most part technical algorithmic work. But Aaron and I both quickly learned you cannot do that and then go out and talk about and expect people to take it seriously if you're unwilling to engage in these broader debates that are are entirely extra algorithmic right there. They're not about you know, algorithms and making albums better. They're sort of you know, as you said sort of like what should society be protecting in the first place </s><s>[INST] when you discuss the fairness algorithm that that achieves fairness whether in the constraints and the objective function, there's an immediate kind of analysis you can perform which is saying if you care about fairness and gender, this is the amount that you have to pay for it in terms of the performance of the system. Like is there a role for statements like that in a table in a paper or do you want to really not touch [/INST] that? Like you know we we want to touch that and we do touch it. So I mean just just again to make sure I'm not promising your your viewers more than we know how to provide. But if you pick a definition of fairness like I'm worried about gender discrimination and you pick a notion of harm like false rejection for alone for example. And you give me a model, I can definitely first of all go audit that model, it's easy for me to go you know from data to kind of say like okay you're false rejection rate on women is this much higher than it is on men? Okay. But you know, once you also put the fairness into your objective function, I mean, I think the table that you're talking about is you know what, what we would call the Peredo curve, right? You can literally trace out and we give examples of such plots on real data sets in the book. You have two axes on the X axis. Is your error on the Y axis is unfairness by whatever. You know, if it's like the disparity between false rejection rates between two groups Um and you know, your algorithm now has a knob that basically says, how strongly do I want to enforce fairness and the less unfair? You know, we you know, if the two axes are air and unfairness, we'd like to be at 00, we'd like zero air and zero fair unfairness simultaneously. Anybody who works in machine learning knows that you're generally not going to get to zero error period without any fairness constraint whatsoever. So that's that that's not gonna happen. But in general, you know, you'll get this, you'll get some kind of convex curve that specifies the numerical tradeoff you face? You know, if I want to go from 17% error down to 16% error, what will be the increase in unfairness that I experienced as a result of that? And and so this curve kind of specifies the, you know, kind of undocumented models, models that are off that curve are you know, can be strictly improved in one or both dimensions. You can you know, either make the error better or the unfairness better or both. Um, and I think our view is that not only are are these objects these Peredo curves, you know, efficient frontiers as you might call them. Not only are they valuable scientific objects, I actually think that they in the near term might need to be the interface between researchers working in the field and stakeholders and given problems. So, you know, you could really imagine telling a criminal jurisdiction, look if you're concerned about racial fairness, but you're also concerned about accuracy. You want to, you know, you want to release on parole, people that are not going to recommit a violent crime and you don't want to release the ones who are so, you know, that's accuracy. But if you also care about those, you know, the mistakes you make, not being disproportionately on one racial group or another, you can you can show this curve. I'm hoping that in the near future it will be possible to explain these curves to non technical people that have that are the ones that have to make the decision. Where do we want to be on this curve? Like what are the relative merits or value of having lower air versus lower unfairness? You know, that's not something computer scientists should be deciding for society, right that, you know, the people in the field, so to speak. The policy makers, the regulators, that's who should be making these decisions. But I think, and hope that they can be made to understand that these tradeoffs generally exist and that you need to pick a point and like, and ignoring the trade off, you know, you're implicitly picking a point anyway, right? Um, you just don't know it and you're not admitting it </s> |
<s>[INST] So you were a key person in launching three revolutions, online education, the autonomous vehicles and flying cars or beetles so high level and I apologize for all the philosophical questions, [/INST] no apology necessary. </s><s>[INST] How do you choose what problems to try and solve what drives you to make those solutions in reality? [/INST] I have to, to desires in life. I want to literally make the lives of others better or as few of them say maybe jokingly make the world a better place. I believe in this. It's as funny as it sounds and second I want to learn, I want to get in this case, I don't want to be in the drop I'm good at because if I'm in a job that I'm good at the chances for me to learn something interesting is actually minimized. So I want to be in a job I'm bad at. Um that's really important to me. So in a bid for example, but people often called flying cars with electrical vertical takeoff and landing vehicles. Um I'm just no expert in any of this and it's so much fun to, to learn on the job, what it actually means to build something like this. Now. It's saying that the stuff that I done lately after I finished my professorship at stanford, They're really focused on like what is the maximum impact on society? Like transportation is something that has transformed the 21st or 20th century more than any other invention of my opinion, even more than communication and cities are different workers, different women's rights are different because of transportation. And yet we still have a very sub optimal transportation solution where we kill 1.2 or so million people every year in traffic. It's like the leading cause of death for young people in many countries where we are extremely inefficient resource minds, just go to your average neighborhood city and look at the number of parked cars. That's a travesty in my opinion or where we spent endless hours in traffic jams and very, very simple innovations like a self driving car or what people call the flying car could completely change this and it's there. I mean the technology is, is basically there to close your eyes not to see it. </s><s>[INST] So lingering on autonomous vehicles, fascinating space, some incredible work you've done throughout your career there. So let's start start with DARPA. I think the DARPA challenge to the desert and an urban to the streets. I think that inspired an entire generation of roboticists and obviously sprung this whole excitement about this particular kind of four wheeled robots called autonomous cars, self driving cars. So, you lead the development of Stanley, the autonomous car that won that The race of the desert. The DARPA Challenge in 2005 and junior, The car that finished second in the DARPA Urban Challenge also did incredibly well in 2007. I think what are some painful inspiring or enlightening experiences from that time to stand out to you. [/INST] Oh my God, painful. We're all these incredibly complicated stupid bugs that had to be found. We had a phase where the Stanley our Our car that eventually wandered up again challenge with every 30 miles, just commit suicide and we didn't know why and they ended up to be that in the sinking of two computer clocks occasionally o'clock went backwards and that negative time elapsed screwed up the entire internal logic. But it took ages to find this. You were like bugs like that. I'd say. Enlightening is the stanford team immediately focused on machine learning and software. Whereas everybody else seemed to focus on building better hardware. Our analysis have been a human being with an existing rental car can perfectly drive the course, but I have to write off to get a better rental car. I just should replace the human being and the human being. To me was a conjunction of three steps. We had like sensors, eyes and ears, mostly eyes. We had brains in the middle and then we had actuated our hands and our feet. Now the extras are easy to build. The sensors are actually also easy to build was missing was the brain. So we had to build a human brain and nothing nothing clear then to me that that the human brain is a learning machine. So why not just train our robots? You would be a massive machine learning into our machine. And with that we're able to not just learn from human drivers. We had the entire speed control of the vehicle was copied from human driving, but also have the robot learn from experience where it made a mistake and recover from it and learn from it. </s><s>[INST] You mentioned the pain point of software and clocks. Synchronization seems to seems to be a problem that continues with robotics. It's a tricky one with drones and so on. What what does it take to build a thing? A system with so many constraints. You have a deadline. No time. You're unsure about anything really. It's the first time that people really even exploring. You know, it's not even sure that anybody can finish when we were talking about the race of the desert the year before nobody finished. What does it take to scramble and finish a product that actually a system that actually works? [/INST] I mean, we're lucky. We're very, really small team, the core of the team of four people. It was for, because five couldn't comfortably sit inside a carpet for food and I as a team leader, my job was to get pizza for everybody and washed the car and stuff like this and repair the radiator and it broke and debug the system. Um, and we're already kind of open minded. We had like no egos involved and we just wanted to see how far we can get what we did really, really well. It was time management. We were done with everything a month before the race and we froze the entire self a month before the ways. And it turned out, um, looking at other teams, every other team complaint. If they had just one more week, they would have won. And we decided, you know, it's going to fall into a mistake. We're gonna be early. And we had an entire month to shake the system. And we actually found two or three minor bucks in the last month that we had to fix. And we were completely prepared in the race </s> |
<s>[INST] Since kept shop does fractional share trading. Let me say that to me it's a fascinating concept, the order execution algorithm that works behind the scenes to create the abstraction of fractional orders for the investor is an algorithmic marvel. So big props to the cash up engineers for that. I like it when tech teams solve complicated problems to provide in the end, a simple, effortless interface that abstracts away all the details of the underlying algorithm. And now here's my conversation with paul Krugman, [/INST] a </s><s>[INST] perfect world. A utopia from an economics perspective look like, [/INST] wow, I don't really, I don't believe in perfection. I mean, somebody once once said, uh, that his ideal was slightly imaginary Sweden. I mean, I like uh, an economy that has a really high safety net for people, uh, good environmental regulation and uh, you know, not something that's not, that's kind of like some of the better run countries in the world, but with uh, fixing all of the the smaller things that are wrong with them. </s><s>[INST] What about wealth distribution? [/INST] Well, obviously, you know, total equality is, is neither possible nor I think especially desirable. But I think you want one where basically one where nobody is nobody is hurting and where everybody lives in the same material universe, everybody uh, is basically living in the same society. So no, I think it's a bad thing to have people who are so wealthy, that they're really not in the same world as the rest of us. </s><s>[INST] What about competition? You see the value of competition? When what what may be its limits? [/INST] Oh, competition is great when it can work. I mean, there's a uh, yeah, I remember, I'm old enough to remember when there was only one phone company and uh, there was really limited choice. And I think the arrival of multiple uh, multiple phone carriers, uh, and all that is actually, you know, it's been a really good thing. And that's, that's true across many areas, but not every industry is not, every activity is suitable for competition. So there's some things like health care where competition actually doesn't work. And so it's, it's, it's not one size fits all. </s><s>[INST] It's interesting what is competition not work uh, in um, in health care? [/INST] Oh, there's a long list. I mean, there's a famous paper by Kenneth Arrow for 1963, which still holds up very well, where he kind of runs down the list of things you need for competition to work, well basically both sides to every transaction being well, informed. having a, you know, the ability to make intelligent decisions, uh, understanding what's going on and healthcare fails on every dimension. You know, you get health care, so not </s><s>[INST] health insurance, healthcare, we'll [/INST] both health care and health insurance. Health insurance being part of it. But no health insurance is, is, is really the idea that there is effective competition between health insurers is wrong and health care. I mean, the idea that you can comparison shop for uh, for major surgery is just, you know, it too. When people say things like that, you you wonder are you living in the same world I'm living in? You </s><s>[INST] know, that the piece of well informed, that was always an interesting piece for me just observing as an outsider because so much beautiful, such a beautiful world as possible. And everybody's well informed. A question for you is how hard is it to be well informed about anything, whether it's health care or any kind of purchasing decisions or just life in general in this world? [/INST] Oh, information. You know, in theory is hugely. I mean, there's more information at your fingertips than ever before in history. Uh, the trouble is, first of all that, uh, some of that information isn't true. Uh, so it's really hard. Uh, and, and then some of it is just too hard to understand. So if I'm, if I'm buying a car, I can actually probably do a pretty good job of looking up. You know, going to consumer reports, reviews. You can get a pretty good idea of what you're getting when you get a car. Uh, if I'm going in for surgery. Uh, first of all you fairly often it happens when without your able being able to plan it. But also, uh, there's a re medical school takes many, many years and going on the internet for some advice is not usually a very good uh, substitute. </s><s>[INST] So speaking about news and not being able to trust certain sources of information. How much disagreement is there about I mentioned Utopia perfection in the beginning, But how much disagreement is there about what Utopia looks like? Or is most of the disagreement simply bought the path to get there? [/INST] Oh, I think uh there's two levels of disagreement. One, maybe not Utopia, but justice. You know what is a just society and that's there are different views. I mean, I teach my students that there are, you know, broadly speaking, two views of justice. One focuses on on outcomes. Uh Ask your it's a just society is the one you would choose if you were trying to uh what the one that you would choose to live in if you didn't know who you are going to be. That's kind of john roles. Uh and the other focuses on process uh that just society is one in which there is um no, no coercion except where absolutely necessary. And uh there's no there's no objective way to choose between those. I'm pretty much a rolls in. Um And I think many people are. But anyway, there's so there's a legitimate dispute about what what we mean by a just society anyway. Um But then there's also a lot of dispute about what actually works. Uh there there's a range of legitimate dispute. I mean, any card carrying economist will say that incentives matter, But how much do they matter? How much does a higher tax rate actually deter people from working? How much does a a stronger safety net actually lead people to uh to get lazy? Uh I have a pretty strong view that the evidence is uh points to conclusions that are considerably to the left of of where most of our politicians are, but but there was a legitimate room for disagreement on those things. </s> |
<s>[INST] So I'm trying to see which one will probably be most useful. Pick the one or two things that are least ridiculous. [/INST] And you were mentioning if we could see some of the second order effects or externalities that we aren't used to seeing, specifically the one of a kid being radicalized somewhere else, which engenders enmity in them towards us, which decreases our own future security. Even if you don't care about the kid, if you care about the kids, the whole other thing. Yeah, I mean, I think when we saw this, when Jane Fonda and others went to Vietnam and took photos and videos of what was happening, and you got to see the pictures of the kids with napalm on them, that like the anti war effort was bolstered by that in a way it couldn't have been without that there's a until we can see the images, you can't have a mirror neuron effect in the same way, and when you can, that starts to have a powerful effect. I think there's a deep principle that you're sharing there, which is that if we can have a rivalrous intent, where our in group, whatever it is, maybe it's our political party wanting to win within the US, maybe it's our nation state wanting to win in a war or an economic war over resource or whatever it is, that if we don't obliterate the other people completely, they don't go away, they're not engendered to like us more, they didn't become less smart. So they have more enmity towards us and whatever technologies we employed to be successful, they will now reverse engineer, make iterations on and come back. And so you drive an arms race, which is why you can see that the wars were over history employing more lethal weaponry, and not just the kinetic war, the information war and the narrative war and the economic war, like it just increased capacity and all of those fronts. And so what seems like a win to us on the short term might actually really produce losses in the long term. And what's even in our own best interest in the long term is probably more aligned with everyone else because we inter affect each other. And I think the thing about globalism, globalization, and exponential tech, and the rate at which we affect each other, and the rate at which we affect the biosphere that we're all affected by is that this kind of proverbial spiritual idea that we're all interconnected and need to think about that in some way that was easy for tribes to get, because everyone in the tribes so clearly saw their interconnection and dependence on each other. but in terms of a global level, the speed at which we are actually interconnected, the speed at which the harm happening to something in Wuhan affects the rest of the world, or a new technology develop somewhere affects the entire world, or an environmental issue, or whatever, is making it where we either actually all get, not as a spiritual idea, just even as physics, right, we all get the interconnectedness of everything in that we either all consider that and see how to make it through more effectively together, Or failures anywhere end up becoming decreased quality of life and failures and increased risk everywhere </s><s>[INST] Don't you think people are beginning to experience that at the individual level? So governments are resisting it they're they're trying to make us not empathize with each other feel connected But don't you think people are beginning to feel more and more connected? Like isn't that exactly what the technology is enabling like social networks. We tend to criticize them, but isn't there a sense which we're [/INST] experience, you know When you watch those videos that are criticizing whether it's the woke Antifa side or the QAnon Trump supporter side Does it seem like they have increased empathy for people that are outside of their ideology camp? </s><s>[INST] Not at all. So I may be I may be conflating my own experience of the world and that of that of the populace I I I tend to see those videos as feeding something. That's a relic of the past. They figured out the drama fuels clicks But whether I'm right or wrong, I don't know but I tend to sense that that is not That hunger for drama is not fundamental to human beings that we want to actually that we want to understand Antifa and we want to like empathize we want to take radical ideas and be able to empathize with them And synthesize it all [/INST] Okay, let's look at cultural outliers in terms of violence versus compassion We can see that a lot of cultures have Relatively lower in-group violence bigger out group violence and there's some variance in them and variance at different times based on the scarcity or abundance of resource and other things but you can look at say Janes Whose whole religion is around? Non-violent so much so that they don't even hurt plants. They only take fruits that fall off them and stuff or to go to a larger population you take Buddhists where for the most part with a few exceptions for the most part across three millennia and Across lots of different countries and geographies and whatever you have 10 million people plus or minus who don't hurt bugs The whole spectrum of genetic variance that is happening within a culture of that many people and head traumas and whatever and nobody hurts bugs and Then you look at a group where the kids grew up as child soldiers in Liberia or Darfur We're to make it to adulthood pretty much. Everybody's killed people hand-to-hand and killed people who were civilian or innocent type of people and you say Okay, so we were very in the oddness we can be conditioned by our environment and humans can be conditioned Where almost all the humans show up in these two different bell curves. It doesn't mean that the Buddhists had no violence it doesn't mean that these people had no compassion, but the they're very different Gaussian distributions and so I think one of the important things that I like to do is look at the examples of the Populations with Buddhism shows regarding compassion or what Judaism shows around education the average level of Education that everybody gets because of a culture that is really working on conditioning it or various cultures What are the positive deviance outside of this statistical deviance to see what is actually possible and then say? What are the conditioning factors and can we condition those across a few of them simultaneously and could we build a civilization like that? becomes a very interesting question, so there's this kind of real politic idea that humans are violent large groups of humans become Violent they become irrational specifically those two things rivalrous and violent and irrational and so in order to minimize the total amount of violence and have some good decisions in need ruled somehow and That not getting that as some kind of naive utopianism that doesn't understand human nature yet This gets back to like mimesis of desire as an inexorable thing I think the idea of the masses is actually a kind of propaganda that is useful for the classes that control to popularize the idea that most people are too violent lazy Undisciplined and irrational to make good choices and Therefore their choices should be sublimated in some kind of way I think that if we look back at these conditioning environments we can say okay, so the kids They go to a really fancy school and have a good developmental environment like Exeter Academy There's still a Gaussian distribution of how well they do on any particular metric but on average they become senators and The worst ones become high-end lawyers or whatever and then I look at an inner city school with a totally different set of things And I see a very very differently displaced Gaussian distribution, but a very different set of conditioning factors So then I say the masses Well if all those kids who were one of the parts of the masses got to go to Exeter and have that family and whatever Would they still be the masses? Could we actually condition more social virtue more? more civic virtue, more orientation towards dialectical synthesis, more empathy, more rationality, widely. Yes. Would that lead to better capacity for something like participatory governance, democracy, or republic, or some kind of participatory governance? Yes. Yes. Is it necessary for it, actually? Yes. And is it good for class interests? No, not really. </s> |
<s>[INST] I think the great mask debate of the 2020 will probably be the thing that ultimately leads to World War III. I've been very surprised how tense, how much like division this one little arguably silly thing has led to. I think a lot of people sort of project their like, it's almost like not wearing a mask is a statement of sovereignty, of freedom, of like saying, fuck you to the man, the government, the centralized power, or the dishonesty or the in the scientific community, all those kinds of things. And then wearing a mask is a sort of kind of signaling of various kind of social aspects, I don't know, I'm not paying attention to it, I actually tuned out, I was part of a group of scientists that were looking into like, do masks work, this very interesting question. To me, it was an interesting question. I sort of roll in to ask that very interesting question. Because I think it is an interesting scientific question. But then I quickly realized that just as I was doing this like scientific exploration of this very interesting question about viral particles, like what kind of things. Like from a scientific perspective, how do we prevent the spread of a pandemic? Forget COVID, any pandemic, super deadly or not deadly. Like there's tools, there's testing, there's masks, there's all these tools, how well do they work? And then I realized, you know, in April or so, it became a tool of politics, a tool of philosophy. And that's when I sort of pulled out. So it's fascinating. I think it's a canvas on which people project their emotions and I guess until I got caught up in that kind of, so there's nothing fundamental [/INST] I suppose to their disagreement. Yeah, not that I'm aware of, but he is, you know, he's written some about in his books, the problem with centralization. I mean, a lot of his writing addresses that and he actually points to, I think Switzerland is the best government in the world because it's decentralized. So there's that, I don't think he has any, I'm not to speak for him, but I don't think he's voiced any specific critiques </s><s>[INST] on Bitcoin per se, could be wrong about that. It's just maybe his flavorful language [/INST] and the way he likes to communicate. And the other theory is that maybe he's playing 4D chess and having a Twitter boating accident, you know? So I don't believe in Bitcoin, I've sold all my Bitcoin. Oh, I see. Sorry, the boating accident in Bitcoin is this, I guess it's proverbial by this point where it's the way you lose your Bitcoin. So if someone comes after you and says, hey, you know, whether it's a government or an individual is coming after you saying, give me all your Bitcoin or pay these taxes in Bitcoin, you go, oh, I had a boating accident and lost them all. Lost them all. </s><s>[INST] So, yeah. But back to the fundamental nature of space-time, let me ask you, because we're kind of left it, I'd like to go back to this idea of, that you said that everything we think, say, or do occurs within the bounds of space-time. So first of all, maybe you can comment on, what do you mean in this context about space-time, but also about the nature of truth, like how much of all of this is knowable? How much of this is accessible to us humans? How much uncertainty, like we're talking about, is there in the world? Are you, do you fall in a place where we can reason deeply about this world and it's knowable, or is it mostly chaos and we're just holding on [/INST] for dear life? Yeah, I think, I said that all action occurs within the bounds of space-time. The other thing, everything we say, do, or make, the other thing is that everything we say, do, or make starts out as an idea. So there's this concept of universal Darwinism, which basically applies Darwinian principles, but outside of the biological sphere. So we could say that this kind of gets into Richard Dawkins memetics, </s><s>[INST] that even ideas are competing, reproducing, recombining. That idea is so powerful, by the way. I don't think it's been understood fully. I think in the 21st century, in the digital world, from my perspective in artificial intelligence, there's yet to be some profound things to be discovered [/INST] about this whole construct, full construct. Agreed completely. It's been called an acid actually, and then it just strips away all of the non-informational components of something and just strips it down to its bare bones. </s><s>[INST] I have a quote in there somewhere about that, but... I'm sorry, which is called an acid, the ideas? The universal Darwinism. Darwinism applied broadly outside of the ideas? [/INST] By broadly, and I will condition all of this with saying that a lot, most of my thinking is shaped by a book I wrote recently called The Case Against Reality, which introduced me to this concept, but it tied into Darwinism that I've used more broadly in the past, looking at things like money and economics. So the book, The Case Against Reality, by Donald Hoffman, he has a quote in the book that describes universal Darwinism. It says, quote, universal Darwinism can, without risk of refuting itself, address our key question. Does natural selection favor true perceptions? If the answer happens to be no, then it hasn't shot itself in the foot. The uncanny power of universal Darwinism has been likened by the philosopher Dan Dennett to a universal acid. And Dan Dennett says, quote, there is no denying at this point that Darwin's idea is a universal solvent capable of cutting right to the heart of everything in sight. The question is, what does it leave behind? I have tried to show that once it passes through everything, we are left with stronger, sounder versions of our most important ideas. Some of the traditional details perish and some of these are losses to be regretted, but good riddance to the rest of them. What remains is more than enough to build on, unquote. So the way I would interpret that is that life itself, I've come to view life as information propagating through flesh and that we are, I guess DNA is a quadratic code. I think it's four letters, maybe versus a binary, zeros and ones. And we are ideas, we are strategies competing with each other. And nature is that which selects, it's what selects the winning ideas, the ones that are most fit </s> |
<s>[INST] I don't always agree with what they write in there, but I always learn a lot. That's what journalism is supposed to do anyway, guess 75% off your first month. If you sign up at the information dot com slash lex, that's the information dot com slash lex beyond just the content. I see it as a good way of supporting in depth journalism. I hope you do as well. This is the lex Fridman podcast and here is my conversation with my longtime martial arts hero and now my friend Mr George ST Pierre in your fighting career, where you're more motivated by the love of winning or the fear and hatred of losing, [/INST] I like to win better then I hate to lose because if it would not have been the case, I would never have fought in the first place, because I don't like </s><s>[INST] to fight at all. Mhm. But you talked about the anxiety, the fear that you experience leading up to a fight. So to you, ultimately, the reason to go through that difficult process is because it feels damn good to have your hand raised [/INST] there is that there is also the fact that martial art I've been introduced when I was very young and it's probably the best thing I can do in my life fighting. That's what I do best. Also it provides me of freedom of access of things that most of people do not have. Um but all that as a price and a lot of money, I made a lot of money of course with it, I was may be predisposed with certain abilities. I met incredible mentors through all my life, I worked really hard and of course I had a lot of chances, the stars were all aligned and in order to keep that those advantages of freedom, money and glory and access of things that most people don't have and have these dream life that I have, I had to sacrifice myself and fight in order to keep it. It's very hard to understand because I also believe most fighters are not like me, they, a lot of guys because I corner a lot of guys and it seems to me that they love their </s><s>[INST] job. They enjoyed [/INST] to go fight in the cage. I love to </s><s>[INST] train. I love the science [/INST] of </s><s>[INST] fighting the [/INST] sport to be in good shape. The confidence that training in mixed martial </s><s>[INST] art give me. [/INST] However, I do not like the feeling of uncertainty. The stress that I have not knowing if I will be badly injured or humiliated or winning the fight, it's to me unbearable and that's what takes the most out of me more than brain </s><s>[INST] damage. More than anything, that's what takes the most out of me. But the thing you get from it is the freedom that you get because because of the money, but because of the celebrity, because of everything that comes with it, so you can be the best version of yourself because of fighting. But at the same time, you've said that quote, I don't believe there's pleasure in life. I believe there's only a relief from pain we have to suffer to be on top. So isn't there something to just the suffering in itself just doing really difficult shit just to get to the top [/INST] to explain that, and some people can relate to it because not everybody is a fighter. I think the best example I can give is, let's say you're you haven't eaten for a long time and you're craving, right, so you're suffering and then when it's time to eat, finally you're about to eat your favorite dish, it's gonna taste so much better. So that's why I believe there's always a some sort of sacrifice before the pleasure and the more sacrifice you do, Like they say in fighting, the bigger the risk bigger is the reward. And I feel that's that's how it it is for me. </s><s>[INST] Yeah, I feel that with I started fasting a little bit in the past couple of years and there's nothing as amazing as a delicious meal or anything, actually anything any food when you haven't eaten for several days. It's kind of incredible. Uh, it's not, it's not incredible in this simple way of Finally, I get to eat it. You get to truly experience the beauty of what it is to be alive, like that little piece of food. You see all the flavors, you feel just the experience of it is ultimately of gratitude, of how awesome it is to be alive. But when you eat many times a day and you're picking out, you don't get to experience that and it's fascinating. It's really like fasting is one of the most accessible things for people I think to experience that kind of pairing of hardship to pleasure. [/INST] I agree. And in my case it changed my life on a good, good way. I cannot recommend it to people because everybody is different. But after my, uh, to fight Michael Bisping, my last fight was against the champion and the heavier weight class that I used to compete at. So I thought that if I would gain weight, it would increase my performance and I struggled a lot to gain weight. I gained a lot about 8 to 10 £10. Normally I walk around 1 £85 and for that fight, I was walking around 1 95. However, I forced myself to eat like six times a day. It was on a very strict diet and I didn't feel it didn't feel right to me because I feel like I I was carrying, like a little bit like I was carrying a bag on my shoulder and I think it was a bad idea for me because when I did the way it the way in and I go, went on a scale of 1 85. I couldn't go back to my initial weight. That was 1 81 95 that I worked so hard for several months to get there. So it was 1 £90 but I couldn't get back in the morning of the fight. I I I got I got sick. I had like, uh we didn't know what what it was in the beginning because in order to know to find out what it was, I needed to do what they call a colonoscopy, they put a camera inside of you and to do that. They give you um something that makes that empty you. And I was trying to gain weight not to lose weight. So I told myself I'm going to wait after the fight, whatever it is, because it was pretty body was blood and I didn't know what I was, I was very concerned. I thought I had maybe cancer. I was freaking out. So I said, I'm going to do that fight. And then after right away, I'm gonna make a check up. So I did the fight. Everything went well. I wanted to fight. I went back home. I did a colonoscopy and I got diagnosed with ulcer colitis. Then I got a very severe medication uh to get better. And I'm not a big fan of medication. I always trying to look for more natural way to get better. And I found out about fasting and it really changed my life. I met Dr Jason Fung was one of the, one of one of the world authority of fasting. You treat diabetes patients with fasting. And he gave me a program of fasting and it really changed my life. And right away what I did is I went in a cat scan to see the difference because it was right after my fight with Michael Bisping and I did the cat scan. So I had my muscle mass, bone density, uh fat percentage, water retention. It's pretty amazing. It can show you which harm has more muscle than the other. It's very precise and I did it like 22 months after. So I I started doing um time restricted, eating 16 8. But right right away when I started I did three days water fast. And the doctor, Jason Fung, he says, because I like to train during those days I can I consume Himalayan salt to make sure because when you sweat, there's a lot of minerals to to make sure you don't deplete your mineral. And when I went, when I compared the two result in the cat scan, I found out my biggest concern was to lose muscle mass. I found out that I did not lose muscle mass instead of losing it, it increased a little bit, even though my weight on the scale was lighter. I I kept the same muscle mass even increases a little bit. My bone density increases a little bit. My water retention is the biggest thing that decrease. So the my inflammation and my fat percentage. So basically the by looking at the data, I found out that by eating so much trying to gain weight for to find michael Bisping, I only increases my water retention, which is not good because it's like dead weight, an inflammation on you. </s><s>[INST] So what Was the actual process of fasting? She said 16, 8 time restricted. So intermittent fasting. But you also mentioned the three out of the three day water fast. What did that feel like? And you also said training during the three day. How did that feel? Can you give me some details of this is fascinating. [/INST] So I do three days water fast four times a year for me. I do it every body is different for me. I do it after New Year's because during the holidays, that's when I I I eat bad foods and I drink. I see it more like a like a cleansing, you know, like, like, like a detox </s><s>[INST] sort of speak mental to like psychological. [/INST] I do it after the New Year's right before the summer cut for the beach after the summer because of the summer? I've been partying a little bit sometime let myself go and right before the </s><s>[INST] holidays. [/INST] And um, I've tried, the doctor family says to me is a George. Everybody is different because I'm a very active person and everybody has a different genetic. So for me, I I feel that three days is the sweet spot because I still train during those three days. The first day, the first two days I don't change nothing. I trained regular on a, on my regular schedule. However, on the, on the third day I modify a little bit, I I do something more uh more easy and that's how I do it. And I've tried before because when I say three days as my sweet spot, I've tried to go up to five days. But the problems is after my third days, I I found out that I had a big problem sleeping. I get into a </s><s>[INST] hyperactive mode. [/INST] They call that the interrogator uh mode. You know, like you you your brain. I mean, it's amazing your creativity is that it speak, but you cannot sleep very well and sleeping for me. I think it's very important. So that's why I do three days. For </s><s>[INST] me, it's my sweet spot. That's interesting. You're right. It's the four or five days when you start to see how sleep is not important for me. So the creativity is really important. So it's, it's very interesting the places your mind goes after a few days. You're right. But I mean, what does it do to your mind? So you mentioned your body likes it in terms of training, does it um do you find that it helps you focus and think, I mean you're one of the great strategic thinkers in terms of martial arts. Does it help with learning? Does it help with thinking? Does it help with strategy and jazzing and all that? [/INST] Well, unfortunately I got into fasting after I retired. I wish I would have, I really wish people ask me, would you have done it during the time that you competed? And the answer is yes. I think we live in a society that we're bombarded by publicity. Oh, by this eat protein. This that and fast thing. Nobody makes money with it because there's nothing to sell. You know, I think that's why a lot of people have not heard about it. And even my for myself, if someone would have talked to me about fast the benefits of fasting when I was training before I got sick, I would probably have ignored ignored him because I'm not, you know, it was hard to believe </s><s>[INST] it sounds ridiculous. [/INST] Don't eat, it's </s><s>[INST] going to help your mind and you're going to gain muscle potentially. [/INST] Exactly. And and perhaps people have talked to me about it, but I kind of it went in one of my hair and got out from the other side, you know, but it really changed my, my life and I am dying. I was diagnosed with cancer colitis and it helps me get rid of all my symptoms. What I do is a lot of people have ulcer colitis. And and for me, I cannot recommend it to to other people because everybody is different. But for me, I made a lot of research about people from the circle. Itis got better and I found out that a lot of people that got that condition get better in the natural, which was fascinating, eating fermented food, ca lodging and like bone broth and stuff all I got and it made a huge difference in my life. I just wish I would have known that before. </s><s>[INST] So do you have a specific diet wise stuff you like? So like, you know, I've recently another ridiculous sounding thing, but it makes me feel really good is very low carbs. So, you know, keto even carnivore. It sounds ridiculous. It doesn't make any sense. But it makes me feel really good even for performance. [/INST] It's Rogan has influenced you and you know, </s><s>[INST] I was influenced actually people. Yeah, he, there's, I'll tell you where, because I was doing it before he was doing it. Uh is there's it was popular in the endurance athlete community where it was fat adapted athletes. People who insane. People who run 50 miles, 100 miles. They figured out that they could fuel their body by with fat. they can go to fat as a source of energy as opposed to carbs. So remember hoping that I'll be able to learn how to run 50 miles and so on. I've never done more than 22 but I just remember switching away from carbs and feeling really liberated. Like I wasn't thinking about food as much I'm able to eat once a day and feel really good. I mean, I think every everybody's body is different, but I think carbs make me lazy, Maybe it's because yeah, it's the crash, but also just psychologically something. Um, it forces me to also think about food too much. Like it starts becoming, you know, our logistic, you said our society is so much about food, there's so many, so much advertisement and so much of our social life is about food and so it's very easy to live life like live day to day thinking when is the next meal? Like what am I gonna eat for lunch? What am I gonna eat for dinner? What am I gonna eat for breakfast? And if you're not careful, that's going to get in the way of you doing cool shit for like liberating yourself and thinking like, what am I actually passionate about in this life? Like creating and forgetting to eat that those kinds of things and still being able to fuel your body. I don't know, it's been fascinating to figure out like later in life that carbs aren't necessary to function. Well it makes me think like we don't know anything about nutrition. You [/INST] know, personally, I I don't think I could have a diet without carbs. I love chocolate too much for me eating. It's a it's a pleasure of life. I love my carbs, I love my sugar. However, if you talk about that, I don't have a specific diet. But recently I what I'm trying to do is the days that I do not work out. I only eat once. That's kind of my rules. Plus I try to respect 16 8 and do my three day fast uh four times years. And but the rest of the thing I I let myself loose because I I don't think I would be happy if I if I if I if I don't give myself the right to to eat. For me personally, I love to eat so much text. And you talk about diet carnivore diet is very interesting because I, a few years ago I went to Africa in uh Masai mara and uh it's a tribe in uh in East Africa and I want to visit them. I did a suffering And I talked to them and these guys they their diet is 99 percent carnivore. That's crazy. And you should see they're very beautiful. People shredded like some people would say, oh it's just it's like I'm not Yeah, maybe it's genetic, but I mean think about the Eskimos also that like most of their diet is on on fish, right? They saw I believe it can be done. You know, like, I believe it can be done and like an exclusive carnivore diet. And I I think I'm gonna try it pretty soon just to have the experience, you know, to see how it feels like, well, </s><s>[INST] you're going to hang out with joe, be careful bringing it up because he'll convince you to forever switched to carnivore, definitely. He loves it. I mean, but just like you, I think he loves food, so he's he can't ever stay on carnivore. It was funny because we went to an italian restaurant together and I still only meet like, I love I love the constraints of discipline. That's that's partially why I like carnivore. I like saying no to food that is delicious. Uh But part of the problem is that I don't know how to moderate. You said chocolate, I don't know how to have one chocolate. Is that something you're able to do have, like, in moderation? [/INST] No, it's when it when I have an abortion. D I do it. I don't have any. I'm an extremist. First one Alexy II that's the thing I when I when I have a chance, I I like I I just eat I go too much and that's why I like about my life, you know, that's what I like about fasting because probably if if I would not have discovered fasting eating chocolate would give me cramps and all sorts of problems because people are also colitis. Normally they cannot eat chocolate, they cannot drink alcohol. But I believe because I'm fasting, that's the reason why I'm medication, medicine, medication free, I can eat whatever I want whenever I want. But I have to do that that fasting, you know, and now it becomes too became to a point that it's no longer hard for me. It's it's like normal. I I don't even force </s><s>[INST] myself, I [/INST] don't, it's easy, you know what I mean? Some of my friends thinks I'm think I'm insane, you know? But I tell them, it's like when you get used to it, it becomes like an Abbott. And I'm, and I know that hunter gatherer, like our ancestor did not eat three times a day. It's not true. They they eat when they could and when they eat, they they they feed themselves as much as they can until they, because the next time, because I didn't know when they could eat again, right? So it's uh I think that's our were built, you know, to to have this similar lifestyle </s><s>[INST] if we could take a step back to the discussion about fear a little bit. So mike Tyson talks about this process of him walking to the ring. He sounds similar to you in many ways of the anxiety and the fear that he experiences and uh he has this uh sort of story that he tells about walking to the ring and being supremely afraid. But as he walks and gets closer and steps in, he finds the confidence and become supremely confident. I think he calls himself like a god. I feel like a god. And uh is do you go through a similar process of finding the confidence? [/INST] Well, it, yes, and I used, I used James lunch theory. They, so what I do is because I'm I'm I'm not afraid to admit that I'm afraid and that in the beginning of my career, I really thought, I asked myself because I was very good in mixed martial, but I really thought I wasn't made for this because the idea of fighting didn't it was, it didn't make me happy. It's something like I was, I was forced to do in order to keep that lifestyle that I have and achieve my goal perhaps one day to make enough money to retire and you know, that that was my dream. But when I was looking around the gym where I was training, most of my training partner, they were happy, They were excited and sometimes my corner to corner, a lot of guys and they're happy and they're in the locker room, they don't react the same way I do. Some perhaps does. But if you see me in the locker room, like when I get like my last fight with Michael Bisping. Just to give you an example in my last fight with Michael Bisping because it's fresh, it's the one that is the most recent and but it's always the same thing, my last fight and my best thing again in the locker room, I like three guys that I trained with mickey gall Emmons a hobby and joseph Duffy, they all lost. It was like, like my my locker room was basically cursed that you know, that when you're in a locker room and people from your locker room leave for a fight and then they come back. It's kind of a momentum, you know, you you shake and yeah, good job now it's my, you know, it's kind of a team brotherhood sort of thing. So the, the, the, the atmosphere in my locker room was pretty bad. It was like going to a, you know, like a funeral. So I was very scared. And before every fight, I, I asked myself, I asked myself always ship what the hell I'm doing here, why did I choose to come back? Oh my God, and I'm freaking out. However, I'm putting on a mask, like I'm acting because if I don't do that, it will reflect on my coaches and if my coach, my, the confidence of my coaches is affected, it will reflect reflect on me. So I need to feel strong, I need to make them believe that I'm excited to be there and I'm happy to be there. So this sort of play start when I get when I first step in the locker room, even though I feel completely different, but that's how I play it normally the day, the fight day, I never felt, feel 100% always feel exhausted, tired. Uh my highs are hitching because I don't sleep enough the few nights before because I'm constantly rehearse rehearsing scenarios that might happen in a fight. So mentally it's not that I'm not on </s><s>[INST] top, but you keep all that to yourself. [/INST] I keep it to myself and I'm lying to everybody around, but everybody knows, you know, for us, john then I heard they know Freddie rose because they've been with me for a long time. So they know what's going on, but at least I'm lying to them and I am feeling great. So, and seeing all my training partner like very disappointed because they lost their fight. Some were badly hurt as well, it was hard. So, and I remember, I get, I get one, I get, I start to warm up and everything and as you start to warm up, you become a different person because you know, we know that certain posture in yoga can affects your mental mental state. But it's, I would say it's a little bit the same thing in fighting, you know, like when you start hitting the pads, your, your muscle memory, your instinct comes back and you, you remember that you're good at this, you know, and your confidence start to grow and as senior trainers holding the pad and then repeating your moves, it makes you also remember all the sacrifice you have done through your training camp and confidence come from how you prepared yourself and even you're afraid. You can be confident, confident at the same time. Being afraid and being confidence is two different things. And before every fight, just right before I walk in, it's when I'm scared, I go in the bathroom and I look at myself in the mirror. I used to have a bandana and and again, but now I know I didn't have this this for my last fight because of the new Reebok deal they had. But I did the same rehearsal that I always do. I look at myself in the mirror and I start to compliment myself. Like even if I don't believe it, I'm starting to trying to believe it as I am. I'm finding all the reason why I'm gonna win the fight and and all my trainer knows that before every fight when when the guy from the UFC goes step in marine Sanctuary up next. I always take a few minutes to do that that same rehearsal and I tell myself I'm gonna win this fight because I'm better and and and I'm very cocky about myself. I'm telling all the reasons that I'm gonna gonna when I'm I got a better team, I made more sacrifice. You know, I'm I'm faster and more powerful, way more athletic, my fighting I. Q. Is better than him. I got a strategy on point that he's never gonna be able to keep up with and and this and that and I'm and I was telling myself I'm gonna show these young kids how things should be done, you know, trying to boost myself, try to to boost yourself and you start to believe in it, you become a different person. So when you walk out the bathroom now rock and roll now, I really believe it for real. You know like I'm still scared but I believe it for real and that's the transformation that happened for me right there and from that from now from from there to the fight it's until the fight is over, it's called I call it cruise control because you don't have time to think in a fight if you're trying to think you're missing the opportunity. So that's how I see it </s><s>[INST] for myself. So at that point you stop thinking and just go cruise control, to trust [/INST] yourself, you know, trust yourself because you you repeated all the scenarios, you know, so everything that you have done is it's inside that your computer, your computer, your brain is programmed to react accordingly to certain situations. And uh it's not the not the night of the fight that you'll you'll you'll tell yourself, oh finally I'm going to do this if you do this now if you have not practiced it before you're screwed it. The preparation, the repetition that makes it happen, you know </s><s>[INST] what about like the really difficult moments in a fight where you are tested to your limits essentially. Usually it's cardio related exhaustion, right? Where you have to ask yourself that same question is like, why the hell am I doing this? Uh, do you, do you, do you experience those or are you able to ride through the autopilot? And if you do, like, what do you do in those moments? [/INST] Never in a fight when I'm in a fight when it's, that's when the fight is on. I never changed my mind. I go until the end. However, for example, my first fight would be Japan, I add a terrible first round, so I had to switch gear that happened sometimes, but it's part of my plan. I always have a plan B. Plan a plan A Plan B, plan C. You need to have that. If fighters goes into a fight thinking, oh, what I'm gonna do this is this and they don't have a plan B. If this doesn't work, Does't mean they're not well prepared. If you talk to me before every fight, I can like in 30 seconds give you my old strategy, you know, for for B. J. Penn, my first fight with BJ Penn was, I'm gonna keep it standing up, keep the fight from the outside, you know, because I'm faster than him, then the fight would be Japan's start, I found out that I was not faster than him and I found out that his reaction time was better than mine. So I got beat up the first round and I got a bloody nose and everything. So my plan B was, now I'm going to wrestle him, you know, I'm going to wrestle him and, you know, make him tired and trying to put him down, and that's how I beat him because I switch gear, you know, But if you can't do that, if you cannot find a way to become the perfect nemesis to your opponent, you you might win a few fights, but you're gonna find uh you're gonna fight someone sooner or later, that will, that will give you a lot of a lot of trouble. </s><s>[INST] So that's where the anxiety pays off. You're anticipating all the ways it goes wrong. So you develop the plan B and plan C. Hi, you know, we talked a lot with like john Danaher who you work with. It's interesting. I don't think I've heard him talk about Plan B and plan C. He usually has a really clear plan A, the entire system of Plan A. I don't think I've heard him, we've had uh we had a good discussion about it and um over some cheeseburgers and he's uh he was kind of espousing the value of mastering escapes. So when you find yourself a bad situations being exceptionally good at finding ways out of those bad situations and that's a way of dominance. There's nothing, there's no better way to dominate your opponent according to him than to show that they can't possibly hurt you. No matter how bad the position is, it's like it's a as opposed to a physical dominance, it's a psychological dominance is very interesting, but I wonder if he has plan B and plan seen as mine too. [/INST] You know, in in a mixed martial arts sometime, it's like in science something you can make a mistake, like a mistake, you know, like every human can make mistakes, you know, there's certain sport or a certain situation that you if there's a mistake made your that's it. Exactly. Sometimes it's the case in Emma, but sometimes you're able to redeem yourself and ah Mhm. If you look the fight with BJ Penn one that I had, which was probably one of the most competitive fight and it was probably the it was the fight that I got the most damage and I was messed up. It took me three days, like 23 days to recuperate from that fight. I was really damaged and my first fight versus my second fight, I made a lot of adjustment because I have learned from my first fight and also I had a guy, one thing people don't know, like they talk about fighters having secret weapons, c for me, my secret weapons was not like some is that they use like certain different things for me it was knowledge, I gotta go in Montreal, he was measuring frames. He's not a scientist is a friend of paris and I and what he does he watch fight any measure frames the way it does it is when you watch a fight and one of the guys threw a punch, he cut the picture by frame, the video by frame cut so he's able to see which fighter has better reaction time than others and be Japan. He found out that BJ Penn of all the UFC roster at the time when he was in his prime, he had probably the best reaction time of all According to him, Leo to Machida was the 2nd 1, But BJ Penn was the 1st 1. So I knew that if I would try to go first because I always been the fastest guy normally when I fight someone, but when I fought the Japan I tried to go first and he was always able to like I never was never able to touch him with my job and he came back with a counter punch. However, because of what he told me, I knew that Japan has a very fast reaction time but at a very poor reset time to him, the way he described it to me is like your nervous system is like a muscle. B J Penn was so fast but it's like more like a sprinter. So what I did the second fight when I fell to Japan, I made him flinch like I fake a lot so I make him react and flinch. So all that, that reaction time that he used to flinch was not used properly to avoid my punches. So I burned, I, I load up his nervous system with a lot of information and fit and fake and to make him flinch and pretending I was kicking wrestling. So he got overwhelmed and he got tired very, very fast. So that's how I beat them. People sometimes they don't know really what's the strategy behind the thing, They only see the physical part. But when you fight someone, if I fight you, I look at you in the eyes, there's a lot of things that going on between you and I can look down here, pump jab you in the face that the audience will not see this little detail, but you will see it and that's what makes the magic during a fight, The relation that you have with the opponent, you know, like, like the mental game. What do you make him believe that those little thing, I use a lot of those, if you've talked to a lot of my opponent, they'll tell you like I use a lot of these little things, you know, like I look down at banner, I go, I go up or I'm pretending I want to attack you so I'm gonna make you flinch. But in reality, I'm just doing this because I want to rest. I want to recuperate and I'm tired. </s><s>[INST] How much is, you know, people talk about that with poker, for example, how much is the value of this? You know? So like some people argue that poker is more about the betting, you know, just the money. It's just how much you bet and so on. So that would be more like the analogy there with with fighting would be just strictly the physical movement of your body. And then a lot of people argue that there's a lot here in the way you look in the little movements in the face. So do you think there's do you think you're communicating with your opponent when you look at them? [/INST] There's no way to know for sure. 100%. And I'm by no, no mean psychic, nothing like that. And I don't believe in that at all. The only thing is I know to look into the eyes from my opponent when he's afraid and when he gives up on me, I've been accused very often in my career to not take enough risk to not finish my opponent. But the reason why I didn't finish my opponent is because I saw in his eyes that he gave up, you gave me the fight and I'm winning the fight. So it's not up to me, it's not to me to make it to try to sacrifice myself trying to finish him. Perhaps if I do that, I will open up for him to to capitalize on my mistake. It's up to him to make a risk. So people sometimes they don't understand that this is the art of fighting my friend. You know, like if I'm winning the fight, like in hockey and ice hockey, if you're winning the game and it's the third period, it's at the end of the third period, you're not going to take out your gold and they're trying to score another goal because winning 5, 2, 3 or 5-4 is the same thing, Same thing in M. M. A. We make a living out of this. And sometimes, you know, as sad, as bad as it can be, you want to save yourself for another day, you know, you want to minimize the damage. But if he knows he's losing the fight, it's up to him to take the risk, It's not up to me. So I'm a I'm a good counter fighter. I use a lot of my attack or counter strike or reactive technol proactive technology, that's my specialty. So I'm not gonna I have no desire to sacrifice myself trying to trying to finish my opponent if he wants to if if if perhaps I might give him the opportunity to capitalize on me. It's not it's not smart to do that. And very often when I fight someone, I can read him, I see the fear in his eyes. Now I'm like, I got, you know, he's very desperate. That doesn't mean I have to put my guard down because he's gonna, he's gonna be desperate. But I know I'm beating you and I know I'm beating you. I'm just gonna do what I need. You know, if I have a chance, of course I'll knock him out. But I'm not gonna try to sacrifice myself to knock you out. And if you do that, maybe one day you'll make a mistake and you'll get dropped and you'll you'll, you'll tell us what I shoot. I just got brain damage. Maybe I'm never going to come back the same. Maybe, you know, I, I ruined my career or you know, it's a very serious game that we're playing. It's very dangerous </s><s>[INST] in the face of that risk. I mean, Mike Tyson talked about, you know, when the opponent looks away, he knows he's got him right that uh, that he's broken for a person like me who has trouble making eye contact with people. There's, there's truth to that. I mean, there's truth to that, that there's, there's an animal nature to us looking away. I mean, you could see that the way the body language, the way the eyes move between two animals going at it uh in the wild one, like two lines fight or to whatever fight. There's a certain beta move when you've been defeated. [/INST] Yes. Or one thing when I know that, that when it happened, one of the signs is when I just like mega faint and the guy flinch like crazy. That's mean, is really scared of me. It's a little bit like you're, you're, you're, you're doing this, that guy flinch a little bit or you're doing this is splendid. Like that's mean you hurt him and he doesn't want to get hurt again. So he's really trying to run away and not, not winning the fight anymore, but not losing sort sort of surviving the five round. And it's hard to, to finish a guy who does, doesn't want to fight a guy who's not fighting anymore to win in this, fighting to not lose. And the proof of that if you don't believe me, just look the reign of all the greatest champion and UFC, I don't care who they are, john jones or uh, like you could clearly see that in the beginning of their ring, they could, you know, finish a lot of their opening the same as me in the beginning. I was finishing a lot of, but there's a time that the entire UFC roster is studying you and they found ways to perhaps not beating you, but they found a way to navigate through the fight in a way that they minimize the damage, You know what I mean? So it's a big difference between fighting to win and fighting to not lose, </s><s>[INST] you said that there's a difference between a fighter and a martial artist. So now we were talking about fighting, you're considered by many to be one of the greatest fighters of all time. But you've said that there's a difference between a fighter and a martial artist. A fighter is training for a purpose. He has a fight. I I'm a martial artist. I don't train for a fight. I trained for myself. I'm training all the time. My goal is perfection, but I will never reach perfection. So what do you, does it mean to be a martial artist? [/INST] Martial artist is because that lifestyle that I have has been introduced to me and the seed has been planted to my mind a long, long time ago by by my father. I am I do not train because I have a fight. I will always train even now it kind of amused me that to see that a lot of people because I'm still training because I love the science of fighting. I do not like to fight, but I love the science of it and I will always do it as long as I can do it. People think I'm going to make a comeback and everything I'm I'm about to get to have 40 years old, you know, like it's have you know, like, </s><s>[INST] well I don't [/INST] Want to fight in a cage at 40 years old. I mean, some people have done it, they did it very well, but I'm not one of them. I'm I feel a little bit to me that and you never say never. I felt like to me like it's a little like a kid that he played with the strain when he's young, like, and he's five years old, six or seven years old, eight years old. And I was like, What the hell I'm doing here and I'm 12 for this. Like, it's AI I've done it, you know, and and and and I got out of it on top and, and I'm I'm healthy, which is the most important thing right now. I'm touching wood and I'm I'm wealthy, I beat the game, you know what I mean? In a way, like that's not to be cocky, but I did it and I wish more more fighters could do the same thing I wish. But it's unfortunate because a lot of them, they stay there and hang out for too long and they get badly hurt, they get beaten and broken, you know, and they finished broke as well because the lifestyle you have when you're a pro athlete, it's crazy, you know, it's it's unbelievable. However, everything that goes up and life goes down and you need to plan your future. So for for me what if some guys have the same mentality as me and they were watching us right now, I would say if you do it because you're just good at it. You like the money that they advantage, the freedom that it gives you. But you don't necessarily like to fight when you're done. You finish on top, you know, okay, go cash out and get out </s><s>[INST] of the way. It's hard to do. [/INST] However, Alexis, it's not everybody that does it for that reason, some people generally love to fight, love to compete, so they do it because I love it, you know, or they do it because of the money, but if you don't love it, if you don't like to fight because it's very stressful and you don't enjoy, you enjoy the training perhaps, but you don't like to fight, You do it because it's part of what you need to do in order to keep that lifestyle and, you know, like, you don't need the money to get out of here, man. If you're in, you're you're in your prime, get out of here because if you don't, you'll hurt your own legacy, you'll damage your health. It's it's very sad and it's a it's a it's a sad business, you know what I mean? Uh it's like a lot of, one of the place where is the most, the most, one of the most happiest place for me to go and the most saddest place for me to go. It's in the gym tri star in Montreal because it's one of the happiest place for me to go because I can go train and do what I love to do, but it's also a very sad place for me because after when I'm about to leave, there's always a bunch of young kids that comes or Guys that are around 30, years old and they come to me, Hey George you have some advice for me and I look at them and if they're my friend there, real close friend of mine, I'll tell them the truth in their faith and I've done it many times and it was not well received, but if they're not my friend, I have to, you know, you know, there's always an advice about fighting, then I answer their question is my pleasure. But the truth, if they want me to tell the truth, the big majority of them, I would tell them, I said, listen man, you're in a maybe a three, like an a on a losing streak of three fight, You're 30, 33 years old, you know, I think you should think about doing something else in your life. You know, I have other goals, you know, because you're not gonna make it and you know, I've seen that movie before and it's a very sad ending and I'm I'm sad to tell you the truth because you're not gonna make the money just choose something. But if I tell them that they're gonna be angry at me because they would be like, oh you you make it and you think I cannot make it so it's kind of you're gonna think I'm cocky, but I was lucky to make it, you know, and that's the start we're all aligned. But at one point you need to be able to to have a plan B. You know, like like some parents, they come to see me with their kids, hey, this is the future world champion and UFC and what advice would you give him? I always tell the same thing and it doesn't not make everybody happy when I said I say I go to the case a are you good at school? Say stay at school? School is very important for you. Stay educated. Yeah. Do boxing, martial arts. A great sports stay in shape, but don't put your eggs all in the same basket and the parents sometimes are angry when I'm not angry, but I can see in their eyes they're like they kind of surprise and it's not because I made it that I will tell their kids to follow the same path that I did. I went to school to. I I've studied, I I dropped out of school when I had my first world championship fight against matt Hughes, but before that I was school. So I had another, you know, another way to go if things would not have gone the same the way I wanted, but the problem and I'm saying that it's not only about boxing in M M. A. I'm talking about our key basketball, baseball, same same thing, maybe it's the one on 100,000 that make it. And I'm saying I'm saying that make it what I'm saying, I make it doesn't mean they can retire and have enough money for the rest of his life because it's a sad story, the only people only heard about the people that makes it, but a lot of fight or even in the UFC champion in boxing champion, even the football, basketball, I don't I don't I don't care the big names when they retire, they have zero, they're bankrupt my friend. And it's a very sad, sad story in a sad reality that most people are not </s><s>[INST] aware of but having other paths in life actually can also increase the chance of you dominating and like reaching the highest peak in your main thing. I mean, jimmy Pedro, I don't know if you know who that is, is a judo coach in uh in America, he was uh he says that to all of his athletes just to make sure that you go, he has a lot of you know, Kayla Harrison, two time olympic gold medallist has a lot of olympic medalists, but basically there's something about going to school like having a forget school, any other avenue in life that gives you the freedom to go all out in your main like you know, you're doing it for the right reasons, you're not stuck, it clears the mind to where you're free to be the best in the world as opposed to kind of, you have to, I mean at different people are motivated by different things. So sometimes some people like having their back to the wall and that's the only option they have. But most people, I think excel when you have other options, [/INST] I think it's a distraction and I think it's important to have a distraction when you say that, I think about one of my coach, john Danaher, he put his academic background experience into jiu Jitsu and that for me that's why he's the best teacher I ever had is incredible. He start teaching me when I even couldn't speak much english at the time and I was able to communicate and understand, you know, that's how good he is, but I, I truly believe that most of athlete, especially in a sport like mixed martial art trained way too much. If I couldn't go back and talk to a young George, I would tell him, I say you do way too much volume, you trained way too hard, train smarter. It's more important and I think sometimes we underestimate the benefit of recuperation because you, I think we assimilate the information that we learn during a training when we recuperate and not during the training itself and this whole mentality of harder, heavier, you know, like, like, like it's, it's good for someone who was lazy, but if you're an elite athlete most of the time, you know, like you're not always, but most of the times because you're not lazy and a lot of guys sometimes there elite athletes, champions. And you hear people say, oh, I can't believe he's very gifted, but it doesn't work, but perhaps it's not really because perhaps it's because we don't understand, perhaps he's doing the right thing and it's us who's working too much and too hard. That's what I think there's a guy I trained with his uh he made me think about about his, his name is Matt Manser barnouin is gonna be a future, future star is an incredible fighter. He trained once a day. And he asked me sometimes advice when he came to Montreal is from France, you'll hear about him, he's very good. And I saw him in the morning at Tristar and I said, okay, I'll see you perhaps later in the other twenties on, oh, I only train once a day and he kind of waits for me to give him, like, like, not, not an approval, but like to see how I react or or, you know, I don't know, it was kind of a strange feeling, but I told myself at that point, I kind of I add an awakening and I and I told myself, and maybe he's doing the right thing because a lot of, a lot of people would say for example, oh, that's a lazy way of doing it, but perhaps it's the best way to do it? I'm not saying training once a day is the best way to do it. That's what I'm saying. I'm saying that everybody is different, but for him it works beautifully and I wouldn't change anything, you know, like if I would be him because he's improving like crazy. </s><s>[INST] Yeah. And ultimately the bigger picture there is to do something that everyone else is, uh, says it's stupid, it's like the fasting thing that, that a lot of people would say a lot of nutritional experts would say that that's that's a dumb way. You know, if you want to be an M. M a fighter, you should be eating like many times a day, you should be starting every day with oatmeal, you should be carving up constantly. But that's not necessarily true for everybody. And it's possible. I'm sure there's actually, now, if you have um, a fighters that are carnivore only, it's possible. [/INST] I, I used to eat right before training and I it didn't bother me. However, now I, my first training that I do normally in average around noon 11 a.m. I'm uh, I haven't eaten anything when I do my first training and I failed to me that much, I'm much more clear and much more clear in my mind. I'm much more creative, I feel better. Yeah, it's a big difference. I just wish I would have known that </s><s>[INST] before? Well, it's fascinating, the role of the mind and all of this. How important is it for your mind to be clear to, to really think deeply I, there's a, there's a judoka american named Travis stevens, remember he said something that uh the right kind of practices when your mind is exhausted at the end of it, that you were constantly thinking through things uh like your body shouldn't be exhausted first, your mind should be exhausted first. It's really fascinating. So people think about training hard, you know, a successful practices where you walk away just overwhelmed how much you had to think. It's fascinating framing of, of a successful practice. [/INST] It's true. Travis steven was one of my main training partner when I got ready for my fight with Nick Diaz and Carlos Condit. E drove every friday from, I believe boston, it's like a six hour drive, mhm dr through the german, Montreal train with us an hour and a half drive back. Uh he's got such an amazing discipline, I was so happy for him when he won the medal at the olympic game man, what I well deserve. Uh you know, accomplishment, it's unbelievable, it paid off, you know, I was so happy for him and every time we, we got to the gym, it was waiting for me in, in, in in the kneeling position like a soldier, I was like, oh my God, this guy is made of, of still, you know, and and after training, I always have to offer him, I say, hey Travis, I know you, you, you like to train with it because in Montreal they are very good judo team Nicholas gill and all the get those guy and I say if you want to stay, I'll get you at the hotel, you know, like anything you want. It's like, no, no, I gotta go back. I got another training later. I'm like, not only did he trained with with us, you have to go back because he had another training. I'm like, this is </s><s>[INST] insane and he's gone through a huge number of injuries. So he's also an innovator because I mean it's difficult to say, but for american judo, there's not many high level judoka. So if you want to be the like fight with the best in the world, you're, you have to be alone. It's a lonely journey actually, it's kind of sad. Uh it's much easier to be in japan where everybody is a killer when you're alone at it. It's uh, it's a difficult journey and you know, it's funny, we talked about kind of, there's some sports where a mistake is um that's it, you know, you can't recover from a mistake. I think judo oftentimes is one of those sports and added on top of that is the olympics Only every four years And Travis's story, he's the reason I, when I saw him in 2008, I started martial arts, I switched from like wrestling and street fighting to doing jiu jitsu and judo. Uh and I just saw so much guts and the in 2000 I might be messing up the years here. But in the next olympics he fought and he lost on just the referee call. Yeah. And just he went to war and he just so much guts and just everything on the line and to lose and then to still persevere through all the injuries, through all that, through incredibly difficult training sessions to go another four years and then compete and then with a metal. I mean that guy is just uh and like he clearly could have been very successful. He's also an incredible Jiu jitsu competitor. So he could have switched to that. But he's stuck [/INST] in a lot of sports when you're an elite. Like for example, in Canada ice hockey is the number one supported the country's uh kids when they're an elite. When they're young, they get chosen and they're kind of already um known as a superstar. You know the school where where they go and on the program they follow. Like I'm sure it's the same thing in us and basketball, baseball perhaps uh american football because they already chosen. So they grew up with that uh that it that it's a kit that that that superstar stardom, so to speak. And it's already glass order glamorous, you know, However in in M. M A there is no mm a judo wrestling. Like in America because it's not our national sport. It's actually it's it's not like even when I first started was not really well received by the media, there's no glamour into it now, I don't know, it seems like it's another era now and I feel sometimes that some people do it for the wrong reason. You know, some people do it because of the glamour because of the money. But even if you're an elite and very good, the glamour and the money won't come in the beginning. It's a very long grind before you know it starts it starts to come in and you need to make those sacrifices and it's a it's a journey that where you will be tested, you will be hurt repeatedly and you're going to have to reach the down deep and come back up and then when you finally think you made it, you're gonna go back and down deep again. It's a very exhausting and decorate aging um adventure sometimes. But if you hold onto your dream and you believe in it, you know and you have the stars are aligned, You're gonna make it. That's why it's only a few people that didn't make it, you know and and that's why I feel I feel sometimes that that a lot of people in the new generation do it for the wrong reason in my in my generation because the sport at first it was there were no rules. I thought it was more pure, the people that did, it was really because of the passion that we didn't seek money, fame, we did it because we wanted to be, I did it because I wanted to be the man, you know, I like to have the confidence that when I walk somewhere and you know have the confidence that, you know, it's an illusion because nobody is faster than a bullet, but I wanted to achieve it for myself and which today now, because I don't know if it's social media and all that, that, that the world has changed the glamour, the, you know, it's I feel it's a different thing right now. </s><s>[INST] Yeah, the uh if you get in it for the glamour of the money, you may not have the right the right amount of fuel to persevere through all the ups and downs. Sure, you know, when you talk about motivation of money and glamour, a guy comes to mind and I don't know how many wrestlers, you know, but in Russia there's a guy named bob Fosse, esat Iev this is your brother's, one of the greatest freestyle wrestlers of all time, but he also has um it's funny, he doesn't have any interviews. One of my goals is to go out and talk to him and Russian do an interview with him because he's exceptionally poetic and a deep thinker, he's the kind of martial artists that you are in the way that it's not just about the different battles you've been through or whatever. It's about the philosophy behind the way he approaches life now. He has spoken quite a bit about that, the glamour, the fame, the money are, all things that get in the way of uh, the purity of the experience, the art, that the way to achieve greatness is to just lose yourself in the art of the actual combat. In this case it's wrestling and then kind of not to worry and actively make sure that you block out anybody who you know, feeds you the narrative where you're supposed to be this famous person and all those kinds of things that he basically says, let others write your story. I make sure that you just focus on the art and another person from that side of the world is of course could be uh so he represents that side of the world. And we were talking about walking away and most people not being able to walk away at, at the top as you have, but also now could be has it looks like incredibly so, so I mean maybe you can comment about what your thoughts are about to be a number in a matter of being able to just walk away. [/INST] You know, we talk about the gold very often ca babies, you know, one of isn't the argument because he has the most dominant carrier of all martial art guy. You know, some guys can be named the gold for different reasons, but cab for that reason and he's undefeated, I don't even know if he lost, it might have lost round, but it dominates all his opponent. It was ridiculous and such an incredible career that he had. Um I love to watch them fight is incredible. Um and when you talk about the art, when you say mixed martial art, the idea of a flying flawless performance for me, everybody often when we say flawless performance thinks about a knockout, a brutal knockout, but for me it's it's to be able to showcase beautiful technique, like a beautiful takedown, beautiful submission, like something beautiful that, you know, when you, you look at, for example, uh Wayne Gretzky or Michael Jordan's or like Stephen curry or so even if you don't know nothing about basketball and you watch Michael Jordan's, you'll be like, wow, that's beautiful what you just did, like we talked about fighting and trying to say the word beautiful in fighting for certain people, it could sound kind of crazy, you know what I'm talking about the technique, beautiful technique, you know, for me that's the goal, you know, when I was fighting, it's no need to have a brutal knockout because some people are more gifted than others and I'm saying gifted, some people are better than others in certain phase of fighting, but for me it was that it was to showcase to win of course, but to showcase some beautiful technique that you can watch the, watch it and be like, wow, that was incredible that the timing did it that and when I talk about, when I think about cabin normal romanov, I see all the detail that of his work, especially when he got his, got his opponent against the fence, that's like, that's his area of expertise worries to me is the best that ever did it in terms of that fighting style, that that particular </s><s>[INST] expertise that he has, it's just the flawless execution of that particular set of techniques. [/INST] Uh Connor McGregor at the, the accuracy, the spider Anderson silva was like, was, I would say the most flamboyant of all, you know, like he was moving like the Matrix Jon jones was incredible in terms of creativity spinning elbows and that and he faced incredible adversity, demetrius johnson was so complete, you could, you could bring like he was slamming a guy to an arm bar, it was just unbelievable, like, like it was like the complete fighter B. J. Penn was like so flexible, he did stuff with his body that like nobody could do his dick, the dexterity of his hips was just unbelievable dominick Cruz to me was incredible. His footwork is distance control. So when you talk about like the goat Royce gracie, another one, he did things that I think for me is the </s><s>[INST] number one because I gotta, I gotta and starting to interrupt the hoist is a fascinating one. I'd love to hear what you think about them. But many people consider you, Most people consider you to be the # one greatest mixed martial arts fighter ever. So it's fascinating to remove you from that list and continue this discussion and asking like, who do you think is the greatest fighter ever? You listed some amazing ones hoist. You somehow skipped Fedor. I'm very, as a Russian, I'm very offended [/INST] now. I was I was going to there's so many Federal has one as well. Federer, I think in his prime was like when you say, when you talk about a name for example, like we talked about him when he was in his prime. Like when I talk for example about Anderson Silva, I'm not talking about the Anderson Silva fought his last fight against who read your whole, I'm talking about Anderson Silva who knocked out victor Belford. Yes, B J. Penn. Same thing. The problem is when fighters hang on for too long in the sport, that's what happened. They kind of make make people forget how good they were. And it's very sad. We talk about Federer and just just think about stepping your church me, which is probably the greatest every weight of all time with Fedor. I would really wonder who would have win this fight the boat guys in their prime. I tend to lean towards Fedor because my heart was with Federal Fedor. But you could have gone the other way but just because my chick lose his last fight now everybody is like, oh yeah they forgot about him. It's crazy man. It's one fight you zig when you should zag boom. It's that's the reality </s><s>[INST] of mixed martial arts. Well that's why the thing is the mixed martial arts isn't just the performance, the strictly who won, who lost. It's also the stories we tell ourselves and so I mean there's beautiful stories being weaved and that also is part of who is the greatest of all time, is what, what were the battles? Well what had to be overcome, what was the the flavor of the flawless performances, you know, all of that plays into it and you're right being able to walk away at the top is also part of that. [/INST] A lot of people ask me about Habib and that fight I wanted to happen. Kabob wanted to happen but um she did not want to happen between you and can be yes and we tried to make it like about three years ago when I when I retired two and three now it was after two years ago and they didn't never came to fruition. The UFC were clear, they said they have at their plan for cab and it makes sense to for the business standpoint because they want to keep the ball rolling now can be retired and like everybody else after just Justin Gayatri, I was doing the commentator in french or do you see and a butterfly. I thought he was going to call me out. If there's one guy that I would have said yes, it would be him because for a fighter the most exciting thing things to do, it's often the scariest one and cabbage was, you know, works the scariest matchup. Yes, it was worth the risk because nobody has ever been able to solve </s><s>[INST] them. How would you solve the could be normative amount of puzzle? [/INST] Well cab is very good against the fence. Uh, I would have to establish a game plan and everything, but I think what I would need it to do is take the center of the octagon right away. Use a lot of fake and faith keep the fight all the way all the way out or all the wind and when I sell the wind is when you close the gap, use my proactive and reactive take down and perhaps my superhero explosive to to put him down. I like to use those proactive and reactive techno because for me, I feel it's more economical, okay baby is a much better chain wrestler than me chinaware stories when you got the guys to the fence, it's pure racing. What makes my takedown very efficient, It's my karate, it's not my wrestling, it's I'm a, I'm very good at timing my opponent and getting in with my explosive itty. So if you watch my takedown, it does not demand often, it does not demand a lot of work when I use the, I call it proactive takedown when um, he's coming to punch me and I react. So, I mean productivity when I'm faking it. So I instigate the takedown by a fake, then I take him down. And reactive as one is, I'm baiting him to throw something that </s><s>[INST] you don't have his account. [/INST] Yes, </s><s>[INST] but all my take down in the center of the octagon. [/INST] Yes, My takedowns are more in the center of the octagon. Like for example, another guy that does it well is Gleason to bow that did it well in his best days, you know, Kabila is more a style of chain wrestling. I would say like Cameroon Guzman's or so to speak, kinda kind of guy. It's a different style. You cannot compare boats town and that's the kind of takedown. I'm good and I would, if I would have fight club, that's one of the strategy I would have that I wouldn't have been afraid because everybody that I thought I was able to put them down and, and I have the pedigree to prove it in my fight resume. So we would have perhaps him on his back and I would have perhaps being my back as well. So it would have been a very </s><s>[INST] interesting fight and how hard do you think he used to take down. I mean, a lot of people speak about his wrestling being just [/INST] has nothing to do with the wrestling because it's to do with the car. If I got that timing and I got my boat hand around around his knees is going down. Everybody </s><s>[INST] goes down. [/INST] Yes, yes. This goes down. And I had a lot of that. That's what I would have to adopt. I would not have been afraid of his wrestling. I would have been the instigator. I would have forced the fight forward and that's what, that's how it would have approached that fight, which I believe most of his opponent we're afraid of is resting because they didn't have the tools that I have to put him down. I would not have forced the wrestling. I would have in, in the clinch, I would have tried to disengage. I have many ways to disengage the clinch. I would have want to force the fight in, in a, in a fighting distance, you know, like in a shoebox distance, not in a wrestling distance. </s><s>[INST] Is it possible this fight still happens? You're young, look great in the suit. [/INST] Well, there's a lot of problems now. And the thing is now I made peace with it. I no longer don't want to fight and I don't, it's not gonna happen. You have seen was not interested and I'm bound by contract with the UFC and by exclusivity, there's some people's systems. So how about if Russians are crazy, uh, wealthy Russian guy come with, I think I'm going to be, uh, in court with, you see, and, and also I'm older now and when I go home and I'm like, I don't want to do this, you know, like you will always like this, I don't want to do this. But like for example, I was training with Freddie roach a few days ago and I'm hitting pads, you know, and Freddy is looking at me and he's like, you have the hitch back. I'm like, yeah, if dana white would walk in the room in the, in the gym at that precise moment with the UFC can track, I would sign it, sign it in the blink of an eye. But then after I go home, I'm like, hell no, my belly is full. My, I'm healthy, I'm wealthy, why would I want to fight for? I made peace with it. But the minute I go back in the gym, because I still get it inside me when I trained with the young guys, I still get it. And a lot of guys thinks, hey, tell me the truth, you're preparing a comeback because I still get it. You know, I'm a little bit older, but I, I got more knowledge, I can compensate, I become a different animal because you know, it changed you, but then after you go home </s><s>[INST] and you, you're like, man, no way I'm [/INST] doing this. It's very hard to explain. You need to be quiet church one to understand that it's very, very hard to explain. </s><s>[INST] Well, from your perspective, I think could be is one of the rare, one of the few fascinating scientific puzzles yet to be solved. So from that aspect as a martial artist, it's just a fascinating journey to try to solve that puzzle [/INST] that there is a thing to like say, oh, who's the best fighter people legs? They don't like I understand, I, I realized that later in my life and I'm sure a lot of young guys will say, I say if you're, it's not, don't speak for me, but I'm telling you right now what I'm about to say, You will realize it later when I was young. I think you can proclaim yourself the more the baddest man on the planet. You know, like nobody can beat you at, it's an illusion </s><s>[INST] man. That's the sad thing about for example, Dc uh Daniel Cormier was probably one of the greatest, if not the greatest, have a of all time. You said notice, but like it's almost because of that little matchup with john jones. It's difficult for people to conceive of him as the greatest of all time. [/INST] It's all about matchups. It's all about timing and also you make a fight, You make you make both guys fight 10 times. The result might be different. Like, like every time, you know what I mean? Maybe he's gonna win eight out of 10, but that night is gonna is gonna lose. Why? Because we don't know the universe made it like that. You know, maybe he got sick maybe at the emotional issues you didn't sleep well and he makes him lose focus and you got caught. You don't, we don't know. But it's it's that's the thing with people asked me, would you have done it with cab, what would happen? I don't know, maybe out of 10 times. I don't know. Maybe as a fighter, I hope I would have win more than him. He thinks the opposite. There's only one way to find out. But that night, if there is a fight the guys are going to win, doesn't mean it's the best fire doesn't mean the is the one that fought the best the night of the fight. Same thing in basketball or hockey, the team that wins the game, It's not necessarily the best team is the team that play the best that the night of the game and fighting is no different. So being the baddest man on the planet, it's an illusion. </s><s>[INST] I mean, that's the tragic thing about it is uh 81 night and you think could happen. And that, that tells a story for all of human history is it's uh it's sad, it's sad to think about, but that's what makes it beautiful that there's so much at stake like entire lives, all the dreams you've had growing up, all the hard work, all of it is decided in a single night, even though that means nothing in terms of who's actually better. It's uh I mean that's the beauty, that's why people of the olympics. Especially because it happens so rarely and dreams are broken or uh triumph is achieved by the unlikely hero all like right there. I mean that's that's why we love it, right? That's [/INST] what I love it. If we wouldn't know always the result before it would be boring and that's why we do it. You know? Uh you watch the ads, you know like like sometimes I like to watch the ads before a fight, you know because you know there's things, you know, I believe in causality, you know, I believe in everybody believed different things, but I believe everything is because there's a there's a cause to everything. That's personally what I believe. I don't believe that I I have like free will, I think I have the illusion of free will, but I believe there is a cause for everything and if I'm doing something because of something because of a cause by definition, there is no free will in a way, you know, if there's a cause by definition </s><s>[INST] there is not, how does that make you feel by the way like the idea that if we just look outside of even just human psychology and fighting and so on. If you look at like physics, if everything is predetermined if all of these little molecules interacting. It's already like your story is already written. [/INST] I mean depend it's written but I would need to know all the data and it's impossible right? Like it's it's it's kind of weird I got to say but I don't to me I don't see any argument to counter that idea. I like and I don't maybe I'm in your in but I haven't seen nobody and everything that I've read so far. There is nothing that countered that I did that because in a mechanical world if your car broke or you know we don't say oh the car decided to broke. Alright three trees follow. There's reason why the trees falling. We don't say the trees that's like default. Right? So what? Because us human being, I think it's our ego. We decide and I'm no different than anybody. When I make a decision I decided to this I choose to do this. But I'm aware that there is causes that make me do certain things and by definition I think if there is a cause there is no free will by definition right? </s><s>[INST] Yes. But the thing is just like you said, we understand so little about human intelligence, the human mind and especially consciousness that the this giant mystery this darkness that we don't understand how how how it feels like to be something to be a conscious being that because of that we're not able to really even reason about free will or not because there might be some magic that comes from consciousness. You know, the consciousness might be the thing that makes us different from a car that breaks down. There might be something uh, totally fascinating, totally undiscovered yet that will make us realize that free will is actually real and somehow fundamental to the human experience. So it's sometimes I think we forget when we talk about free will and physics and all seeming to be predetermined. We forget how little we actually understand about the world. And I think in that mystery that could be totally new ideas that are yet to be discovered and will make us realize that it's not just an illusion. There is something that is like at the core of how the universe works. Some people believe that consciousness is uh, fundamental property of the universe. Like it's it's one of the forces of physics. Like consciousness permeates everything. It's in everything like this table is conscious, but it's not as conscious as us and where this little peak of consciousness and if that's true, and if we get to understand that maybe there's something there's an extra bonus we get in terms of free will once you become one of those entities that are super conscious. So I tend to be sort of humbled by the mystery of it. [/INST] Do you believe one day with, with the technology that keep improving, we will make robot that will be able to be somehow </s><s>[INST] conscious. Absolutely. I that's been my dream. That's been I hope I hope to do just that. First of all, I believe that all people are capable and want to be good to each other. And I think love is a is a really powerful thing that connects us and can create better and better worlds, sort of like uh create better and better societies that uh improve both the technology, the quality of life and just the basics of human experience. And I think creating ai systems that are conscious that our human like can enable us to be better to each other. Like they can, it's almost like adding more and more kindness to the world through the systems we interact with will inspire us to be better and better to each other in terms of them being conscious. I think that is uh an absolute requirement that entities will interact with, communicate some element of consciousness to us. Like that's how we connect to each other. The reason we, you and I connect is that we believe that each of us are conscious and to me what consciousness means is the ability to hurt ability to to suffer to to struggle in this world. Because just like you said, uh with with without the struggle, you don't have the love. You don't have the pleasure. And ultimately consciousness is an entity's ability to struggle to suffer and from that arises the pleasure and us together. Being able to appreciate sort of uh appreciate the highs and experience together the lows? That's how we form the deep connections. I personally think we can create that in robots. And I personally believe it's a lot easier than uh than we think. [/INST] Does it make you afraid sometimes about the fact that one day, hey hi like intelligence, artificial intelligence could be, you know, could hurt us or you know like because we're, you know, because of Hollywood of course, you know the movies we watch. But it seems like when I hear sometimes Elon musk talking, you know like </s><s>[INST] yeah, so Ellen talks about with ai we're summoning the demon. He is very concerned and I talked to him about it quite a bit. He's very concerned about all the different ways Ai could hurt us humans. I tend to believe that there's a lot more ways in which a I can make our lives better and can make life awesome for humans. I think humans are the ones that can do a lot of evil things. So I'm less worried about a I am more worried about humans. [/INST] If I look at what humans have done on on the course of history, you know, for for example, in regards the planet to the scale of the universe, I think what I'm afraid is that we have more of a destructive force than a beneficial forces. So if a high take that in consideration in order to protect us against herself, he could hurt us. And I don't know if you if you understand what, like what do you think about that? The does it makes you afraid? Sometimes not because of a high, but because of what humans are doing that hey, I could do to us to prevent us of hurting each ourself, </s><s>[INST] you know? Yeah, I mean definitely it can bring out the worst in human nature and uh provide tools for evil people to do evil things at a larger scale, but I just think it depends what what you think human beings are. I tend to believe that as we get more intelligent, we uh we start to see the value, the evolutionary value and the value in terms of happiness of being good to each other. And I think ai if you look at ai as an optimization problem of how to create a civilization that works well and expands throughout the universe, I think Love is much more effective, so AI will help us maximize that. I think there's going to be always spikes throughout as it has been through human history where charismatic leaders will do evil onto the world in the name of good, you have the Stalin and the Hitlers and all that. But ultimately over time, I think technology will give the good, the good people power and the evil people less power. Now there's a lot of ways in that in the that that won't be the case, There's a lot of ways for it to go wrong and Ellen talks about them. But I honestly think in terms of intelligent Ai that's going to bring more love to the world. The thing I'm concerned about is dumb Ai so there's been a lot of discussion between china and the United States recently on autonomous weapons system. This is something people don't they're afraid to talk about. But there is now a race of where the United States has officially said that they're not against adding Ai to its weapons systems. So now the U. S. Military is adding automation, adding intelligence to its drones to its uh anything that can create damage. And so of course and they did this. So in response to china doing that so you can imagine this is this is terminator. You think about terminators intel intelligence systems. They're not they're pretty dumb. The point is they're efficient at doing what they do and uh in the space of war, efficient at doing what you do means killing so that I'm really afraid of. But those are dumb ai those aren't your uh loving deep fulfilling relationships that's like uh efficiently being able to fly to plan the trajectory of dropping bombs of missiles. Of how to do counter attacks of how to maximize the destruction of a particular facility instead of individuals. And then that can just escalate and as opposed to the cold war with the soviet union this could be a hot war. And then the consequences once you allow, it's kind of terrifying because because currently the drones are operated by humans. So, you know, you have say you have information about uh intelligence, gives you information about a particular terrorist located in this area. And then you use drones to maybe uh the automation there is to help you figure out what is the best trajectory to strike at that location. So you still have a human that pulls the trigger at the end dropping the bomb. Now, automation and Ai and autonomous weapons systems might be where you say there's a bad guy over here, you figure out how to get rid of the bad guy. Okay, So then of course the systems will be very good at finding the right trajectory and so on. But there's bugs that can happen, unexpected bugs that the system might figure out that there is. This bad guy might actually be in these other five locations. So Mike's might make sense to cover the entire area. Right? And so you might drugs drop bombs on the entire area and then, you know, that's just okay, So that's going to lead to a lot of destruction on a scale of a city. But then you can immediately take that to nuclear weapons. If you add automation to responding to counter attacks to nuclear weapons. Somebody you might get information that somebody is planning a nuclear attack on the United States and the ai system will immediately respond and, you know, it can respond to the scale of launching nuclear weapons itself. So there's all of these possibilities that don't require much intelligence. And uh that's exceptionally, that's exceptionally concerning. [/INST] I'm like you I do not believe there is babies that are born bad. I think people do bad things because of their experience. However, if I look to my experience and from what I can see some very often man's of power wants more power, right? That's what </s><s>[INST] makes me afraid with. Yeah, no, absolutely. I listen, I've been uh I've come from the soviet union, uh Stalin is arguably one of the most powerful humans in history. Uh he's not talked often enough about by the evils he's done. Hitler gets all the attention, but Stalin has done arguably much more evil than than Hitler. Yeah, well this is, this is human nature, it wants power. We see that with institutions, we see that with governments and nations, [/INST] I think </s><s>[INST] you see this with the internet, people are really hungry for the distribution of power. Like you see that people are very much distressful of centralized places of power of institutions and so on. So I think successful organizations, successful companies, successful governments will be run by people who distribute the power, like I don't trust myself with power at all. And I think you have to build into the system that no one person can have power uh that you distribute it. That's where you have in the financial sector of Cryptocurrency right now with Bitcoin and all those kinds of things. People are exploring how can we avoid the central bank to have control? How do you put the power in the hands of people, thousands of people, millions of people in the same way with uh with military, with uh any kind of with technology? I think the future looks very distributed. [/INST] So what do you think about militarizing space? </s><s>[INST] Uh Space force? I don't think about it often because right now I'm filled with excitement about space exploration, which is the positive aspects. So Ellen, you know, I was born in an era where it was exciting. I don't know about you, but for me it's exciting to look up to the stars and dream about us, humans. You know, uh colonizing mars colonizing other planets expanding out to the galaxy into the universe. That's really exciting. Uh So I'm the possibilities there are endless I don't think because also the resources are endless. And so I think we get into trouble with militarization with wars when the resources are very constrained. So I think for a while we're not going to be fighting. The the only wars will be fighting in space are the ones that kind of [/INST] help another nation to compete who goes to the </s><s>[INST] Moon 1st. That's those those kind those kinds of things there maybe for satellites and all those kinds of communication. And uh maybe in assistance for like cyber warfare which is also very dangerous. But in terms of space wars out in space I think I think everything out in space will be the positive and inspiring. It's very hard. But all good things are hard. I think this is where I've been, I've been talking to a bunch of people about um extraterrestrial life I'm really excited by. I don't know, it's the other thing um when I look out to the stars it's exciting to me. I know I think you've spoken about it being scary but to me it's exciting that there's intelligent creatures out there far beyond perhaps the intelligence of our own that are just too far away to explore yet. But we might one day come in contact with them. So uh that that to me is the ultimate motivator is to meet other intelligent life forms out there and connect with them. [/INST] Have you ever meet Jack Valley? </s><s>[INST] No, but I've been in communication. I want to hope to talk to him. He's an amazing. [/INST] I know that there are many theories about, you know if they're resilient, we don't know right. But but some people think it's from another star systems. Jack varias uh like to make a long story short. He has a different theory thinks it's perhaps means that could be living in a different dimension than us. And the reason why he says that is when he makes an experiment, when there is a sightings very often of a Ufo let's say I'm I'm the Ufo that you have three guys what they are looking at the Ufo very often one experiment that you can do and sometimes that that is the case, you asked your two friends to walk on the side and there's a a point that it's like a corridor. You see the UFO and then you stop seeing in like a corridor. And that's one of the reasons why you're saying that it's perhaps dimension and I found that fascinating. You know, as I </s><s>[INST] this is what you know to the discussion of consciousness and all that. It feels like we might be just experiencing a very particular slice of this universe. We might not be understanding what's at the higher dimensions or Yeah, I mean higher dimensions and whatever form that means, you know, there's all these physical theories now that describe a world with dimensions that's much higher than the four dimensions of three dimensional space and one dimension of time. So whatever the hell is going on in those other dimensions, it could be something unfortunately this is the sad part. It might be something we can't even comprehend with our human brains that the limitations are just uh I mean we're built were just descendants of apes. So like it might not be possible to even understand. Is [/INST] there alien? Is there another dimension that are they human from the future? Is there perhaps chinese or another you know what I mean? A group of people that are working with technology far behind but you know what I had the chance to meet you know because of the sport I'm doing. I met a lot of people in military and politics sometimes that I I asked them every time I met I met one this week and I I asked him as a is it true about the Ufo, is there is there and he says to me is like before even before I asked him I say sorry I have to ask you a question. I wasn't in Los Angeles uh sorry I have to ask you a question. You wanna ask me about your food right away. You knew and I said yes you saw in your eyes say yeah there's things that flies that we don't know but it does he didn't tell me, he doesn't know it, they don't know if it's all you know whatever but there's things apparently that are detected and I know you met flavor you know like </s><s>[INST] flavor is fascinating and it makes me sad that [/INST] we live in a different era now that that it used to be a subject that was ridiculed and now it's so cool that it's you know I'm very excited to live in to that that era </s><s>[INST] you know. Yeah it's really exciting but still the governments are kind of behind the times on that aspect is they're not transparent and they don't communicate well you know it saddens me to think the possibility that that you know like the U. S. Government might be in possession of something that they don't tell the world about because they're just scared. It's because they don't know what the hell it is and they don't want the chinese to gain the technology or all those kinds of things. Do [/INST] you think the President of the United States for example because the President comes and go every right four or eight years do you think you would know all the secret or it would be a guy like for example Vladimir Putin with no much of you know what I mean? I don't think the President even know like even knows all </s><s>[INST] the secret [/INST] the U. S. President. </s><s>[INST] I don't think so because he [/INST] goes they go back and forth you know every four years. You know they have the terms right? </s><s>[INST] So I you know I wasn't sure before but I think I could trust the previous United States President of Donald trump that if he knew [/INST] he would probably tweet about it. So </s><s>[INST] perhaps so I think from from the you know I've worked in Darfur I worked with the D. O. D. At a clearance and I think from the perspective if you if you see the world as fundamentally a dangerous world where secrets are important to have from a military perspective. I think it's very unsafe to tell the President of the United States that you have this kind of technology. So if you think of the world in that way, I I hate that. That's how that world is viewed because ultimately I think was more powerful than the military secrets. And I hope that actually is what will happen in the 21st century. Because what's more powerful is inspire people, inspire the the young Elon musk ox of the world to create cool new things. If we have technology that we've uh, have come, have encountered that we don't understand that should only be inspiration to develop that kind of stuff. It shouldn't be seen as military as a military threat, as a secret to hold onto. I think secrets, uh, I hope we more and more let go of the idea that there are secrets that give us advantage. You know, like in the tech sector, people are more and more releasing the software, they're making an open source like secrets don't make sense. They share the knowledge, share the knowledge, make sure like being afraid to share the knowledge, I think, I hope is an old idea. [/INST] It's more when you make it things more compartmentalized, </s><s>[INST] you know? Yes. Yeah. Well that's the other thing is the bureaucracy of government is like, people only know their own little thing and they don't spread the information. It doesn't travel Well, I mean, there's a lot of just inefficiencies that are, it makes me sad, it makes me sad because uh the the science, the engineering that happens in governments like Lockheed martin developing the different airplanes that were used for military applications. That some of the most incredible engineering ever and its secret because they're afraid to share it with the Russians and the chinese and so on. But on that topic I do think somebody like Vladimir Putin when they probably know some stuff. My God, my God, I would love to know what he knows. But then again, you never know because even he is, you know, people think of him as an exceptionally powerful person, but he's also just managing a bunch of tribes. His power is very limited. He's trying to hold together a bunch of greedy, power hungry mad men. Okay. And he's trying to establish a balance. He might not know everything. So I hope this changes because I think there's nothing more exciting about, [/INST] I don't even know if there is a human that knows, you know what I mean? Like this idea that there is some civilization, alien civilization that that land on the white house and say, hi I come to meet the prison and I, why would they do that? Do you know what I mean? It's kind of absurd. You know? Well </s><s>[INST] I do think that actually, I mean that's one possibility right as large. You know, if an alien civilization really wanted to contact us, I think everybody would know. So I think what we're if there's any kind of interaction between humans and aliens I think most likely what we're interacting with is a crappy like probe drone thing that kind of just like [/INST] like it's like this Yeah, </s><s>[INST] yeah this dumb thing. You know, we're not interacting with the aliens. I think just like just like for us, I think humans aren't when we venture out into space. The first thing that's going to meet aliens is our robots. It's not us humans because we keep sending robots out so they're going to like they're going to make decisions about humans by looking at the robots. I [/INST] say the famous grays Grays maybe there are robots. Maybe it's all Bs too, you </s><s>[INST] know. Yeah. So I I don't know, I don't know what that interaction actually would look like if aliens really wanted to reach out really communicate and I don't know if we're able to actually communicate with them. That's one of the sad things we may not be able to that we might the aliens might already be here and we might just not even no I know how to see them or know how to communicate with them. [/INST] There's so much misinformation and sometimes there is people that are very credible that that made crazy claims you know like like you don't know what to believe, you know like like paul failure the Minister of defense of Canada said like some that there's many alien race that ever, that's what he said research it and did that that scientists from I think Israel recently have said something about trump is he was keeping secret or Medvedev? You're from Russia. Medvedev have been cut in a like during a break between interviews to talks about like, oh, it's like men and blacks or to speak. I don't know if he didn't look like he was joking, but I don't know if you want, you can check on Youtube. It's a it's it went, it went viral. Yeah. There's a lot of things like that. Sometimes I'm like, or bob lazar, I'm like, imagine if it's true man. Yeah. Imagine if it were like a fish in the water. We live in our own world. And sometimes there's a fisherman that grabbed the fish. They came out of the water and threw it back in the water and the fish goes back to the other fish is like, hey, there's someone that take me out of the water. Then I've seen things that I did not like, imagine if it's true. Like we like Yeah. And and one other thing like I wanted to ask you because you are consciousness. How about dreams? What is a </s><s>[INST] dream? Yeah. Well [/INST] I I'm more and more, </s><s>[INST] I don't know if you're paying attention to this. There's no, it's become more acceptable in the scientific community to do large scale studies of psychedelics for example. And there's a lot of connection between psychedelics and dreams. It's very similar states. There's there's a lot of our mind does when it detaches itself from reality, that it can just explore a lot of different ideas. It's very possible that dreams is you're traveling somewhere and the same thing with psychedelics, you're traveling somewhere in a different not traveling through physical space. It's the other dimensions that we were talking about your traveling some other through some other dimension to meet some other creature. People talk with D. M. T. That they meet some elves. I've never done. I'd like to I don't know if there's a safe legal way to do it. But uh, they all talk about meeting elves and creatures like entities, the court, who are they? What, [/INST] what is this isn't because they're higher, it's because </s><s>[INST] they're actually meeting something and maybe there's no difference. I mean that who knows exactly that takes us right back to us not being able to really understand how our mind works. You know, I work in artificial intelligence. It's clear that we understand so little about intelligence, some basic things about intelligence just at the at the very sort of basic uh first principles level. We don't understand what it means to reason to think to assimilate pieces of knowledge together from, from the basics to the complex. We don't understand that. We don't understand how the human mind does it. We don't understand how the human mind is able to take incredible waterfall of information and filter cleanly into just like clean. You only see the things that are important and are able to stitch them together and be able to reason about the world and at the same time have moments of like genius of creativity. Like what is that that also, you know, people writers talk about that that they're, you know, they're almost communicating with um use like where do ideas come from? Yeah, this is the joe Rogan philosophy. [/INST] But but I do know that past civilization where a lot of them were based on shamanism and you know what I think it's sad is if someone drink alcohol and when his drug is going to commit like create like, like murders or we're gonna blame the person, right? We're gonna say that's his fault. It's not the fault of alcohol. However if someone does psychedelic or anything that is illegal and do something crazy now we're gonna put the fault on on psychedelic, you know what I mean? And perhaps the person itself is the reason why, you know, he's been doing these things, you know what I mean? So yeah, it's fascinating our like society, you know like in Canada, they just legalized marijuana. Yeah, marijuana is legal. But before that, before they did it. Like if you talk for example to my dad, my dad is against it because the whole mentality is like it's drug, it's bad but drinking and you know, drinking a beer it's fine. I mean, what is, you know what I mean? What is good? What is bad in that hand? I guess you think chocolate could be bad as well for your health or like, I mean, I'm going to the extreme now, </s><s>[INST] but [/INST] what is good? What is bad if you use it for recreation? You use it for an experience for you to learn about yourself? It's like, it's the lion is very tiny. You know, there's some countries that drugs are all legals. You know what I mean? And I don't know the stats, but I would I would be interesting to know if they have more crimes there than other countries where it's more strict. I would I would be interesting to know about that. It's fascinated </s><s>[INST] me, you know? Yeah. And I mean, humans kind of just come up with arbitrary lines of what's good was bad that applies with drugs that applies with anything, uh, that applies with animals. For example, we talked about carnivore diet, maybe the time live and now will be remembered for the cruelty to animals. For example. And I believe This the 21st century will be remembered for our cruelty to robots that eventually there will be a civil rights movement for robots were the ones who choose to be conscious, the ones who have consciousness will say we deserve rights too. We deserve to be treated with respect to [/INST] how about the people we put in jail? People </s><s>[INST] put in jail. I mean, [/INST] I think in the future will look back and we'll think of ourselves being stupid, you know, to put people in jail instead of, you know, like trying to fix the problem in at the base, you know? Of course now we're or I guess it's our insurance that made it in a way that we cannot sort sometimes understand what makes uh sometimes a psychopath, a psychopath, or a murderer, murderer. But you know, if we can pinpoint the problem and take care of it before, you know what I mean? Or made it in a way that we can reestablish that person in the society, you know, who knows, you know, what was the future is old? It's interesting, we're living in an interesting time. </s><s>[INST] You mentioned your father, what have you learned from your dad? You mentioned he was an important part of the childhood. [/INST] My dad is amazing. I grew up, we didn't have a lot of money, but it doesn't mean if I'm born in a nice country. That always nice thing happened, you know? Um my dad, for me is a big role model because I see him through to my life facing a lot of adversity, you know, he uh he stopped drinking when I was a teenager, he was an alcoholic and I've seen him struggle to that, you know, and it was very, very hard and I've seen him work like crazy hours like come leave in the morning, come home at night, burned out because of work to almost all his life to the point that it became a slave of the </s><s>[INST] system. Yes, [/INST] it became a knight bit in a normal way of living and it made me realize that I have learned a lot through my father, he taught me perseverance, hard work, you know when you face adversity, you know, to never give up until you achieve it. But also it it taught me a lesson that in a way that I don't want to be like him, even if he is happy. It's because I realized, I don't think he knows anything else, like he works through all his life and I don't want to live to work, I want to work for for you know what I mean? I want to decide when I work, you know, I feel like like he, he lived to work instead of working for a living and perhaps it's because he didn't not have choice. He was the older of his family. They had, they were nine kids is that my grandfather died when he was young, so he had to become the father of the family and and work to put money on the table. So perhaps that what made him that way and he </s><s>[INST] became like I can have it for him. [/INST] My dad taught me when I was at school, I was bullied at school. He's the first one who initiated me to a martial art. He taught me karate. My dad, my dad was a black belt in karate as well, </s><s>[INST] but [/INST] because he was working too much, he didn't have time to teach me and I needed self defense in order to defend myself. I have a winning a great terror in mixed martial art, but in the, in the schoolyard, that's my next record. My record is not very good when you're a kid And you're about 7, 8 years old and you're facing bullied bullies that are 2-3 years older than than yourself. It's not the same thing that when you're 25 and the guy is 28. So there is a big discrepancy in terms of maturity. So my dad taught me, introduced me to karate then he didn't, he didn't have time to teach me. Then he put me in a school with a teacher that it was gene code sir. And I grew up with a lot of anger and uh there were two person that was afraid going up. It was my dad, my dad was very severe, very strict with me and I'm glad it was because I I could have become very bad, I could have become tourism and a different path. People see me as a nice guy and I'm gonna, I am a nice guy. I tried to be a good role model, but I could easily have turned towards our </s><s>[INST] around there's darkness somewhere in there? [/INST] Yes, there are a lot and a lot of my friends choose that that Pat and unfortunately you know they are they are they are not with me to the even if I'm from Canada and Canada seems like the nicest country in the world. Like I said, even if you live in the nice country, not always nice thing, it depends of the situation, but that's what my dad taught me. You know and he gave me that too because I I'm very good at learning by observing people and by observing him. I I see the struggle you add with alcoholism and what it did the pain sometimes I didn't flick to us to my family. But our e turn When he did that 180° and I really admire that. And I know it was very very hard for him and he did it, you know, and uh for me uh that's a great role model for me. </s><s>[INST] So your dad being an engine of basically hard work and you're finding a balance of being able to work your ass off. But also to be able to enjoy a piece of chocolate. What is a perfect day in the life of George NPR looked like. So like if you were to go through a day that's very productive but also wanna makes you sit back and enjoy and say that was a good day. What's that look like? What are we talking about when you wake up, what do you eat? What do you do? It [/INST] changed over the years when I was younger, I have a good day, It was like a good training session or you know, achieving good thing in my training, you know, and that's why I was very good at it because when I was obsessed, you know, I think to be good at something, you need to become obsessed and to me perform performing and my training was everything, you know, like when I had a bad training session, I didn't tell my training partner, I was acting like, like because of my ego, I didn't, you know, I didn't tell nobody was like, hey, then I go into the locker room and like man, then then I'm playing the, the training in my mind, you know, I'm saying okay, I should have done this and I've done and it hunt me, it hunt me man, it's a training and it hunt me until the next training session when I can redeem myself, that's how it is. When we used to train in all together back in the day in Canada. We had David Lewis. So we had Patrick Coterie, we had Denis Kang uh steven, you Jonathan. There was all like the best guy in Canada that we're training with each other before we were training in different gyms, but once a week I made it in a way, I contact everybody that we all joined for us and we exchange ideas and we train with each other. So a friendly, I would say friendly competition, it was not malicious, but it was hard training, you know, like not our goal was to improve, you know, but it wasn't very competitive. And when that day you used to get out of the training session with a bad performance for me, he used to hunt me until the following week when I could give it back and perform better with the guy that had the most trouble with. That's how it was and that's how you get better, you know, but it was not a training where it we're trying to do malicious thing to one another. You know what I mean? You need to be playful but playful but competitive. That when I had a good training session because aspiring was on a friday, I had the best weekend and what I was going out with my friend drinking and partying and I've found that that was, that was my, my, my, my idea day back in the day today exchange my, my, my, my life has changed, you know, like um, I, I am not the same person I used to be when I went on my knees and begged the UFC for title shut, you know what I mean? I am. I'm wealthy. I'm healthy. Most importantly, that's the most important thing and as, and I'm going to tell the truth as good as my career was man, my private life man is a million times better man. I I and and people ask me sometimes. They always wonder, they try to ask me and it's normal. It's a lot of people is curious and the reporter and in the sport of mixed martial art we say we play basketball, we play soccer, but you don't play fighting. So when you expose your private life, we've seen that happen in the fight week sometime Connor McGregor and Habib your competitor knows that you cannot get to use what he will do. He will try to get to someone that you love. So me. I never exposed my, my private life. I never posed instagram of my family of my stuff. That's the reason why because I mean I'm in the business of fighting and people know that they cannot get to me and I believe that because I was bullied when I was young. I didn't realize that when I was young, but it helps me deal with the mental welfare that Annie that I had to face right on in my life and mixed martial art because it's a very egotistic sport and there's a lot of a lot of a lot of intimidation and I was used to, I've been used to this thing when I was young. So it does not get to me. However the good way to get to me, go, go, go, go try to get to someone I, I love now man, I'm gonna go crazy, you know what I mean? And I'm aware of that, so in order to protect myself, I always, because I'm aware I'm a public person, so I try to always keep my surrounding like in a private, </s><s>[INST] you know, one of the ways that, like you're, you're a friend of mine, joe Rogan has been an inspiration that he's got like an incredible family and he, for the most part, it started to change recently actually kind of interesting, but for the most part throughout his life he kept it pretty secret, doesn't talk about it in his comedy is a comedian, comedians talk about everything, he doesn't really talk about it and there's something to, that preserves the magic of the silence of the private life [/INST] and I think it can affect the, the development of the kid if the kid grow up being, oh, is the son of that guy instead of being his own person, you know what I mean? So, so for me, it's very important, like my parents are older, it's fine, but it taught me a big lesson when I'm with my friend at the dinner or anything, I talked with person always share a thing, but when I'm talking I'm aware of, of the audience who I'm in front </s><s>[INST] Yeah, I mean, but oftentimes those people are just incredible. It kind of makes me sad that uh you know, there's a lot of people that love you right? And there are a lot of really incredible people and you'll never get to really know their story. I mean I don't know for me it makes me sad. You see them like at airports and stuff, people will tell me they listen to this podcast or something like that and I can tell they're incredible people and it makes me, it's like a little goodbye of a possible friend. I don't know, it makes me sad. It makes me it's lonely. It's almost like celebrity is a lonely thing. So the higher the celebrity, the more lonely you become uh in some kind of way. But of course you have that little gem of a private life where you can [/INST] personally believe every relationship I like I don't like to use this term, but it's always a give and take relationship, you know, like you can gain something and the person like it could be something like not materialistic, materialistic, like something always a good confident like is someone that can give me good advice or it's a word I would say like extension a like if a pilot as a co pilot, the copilot is extent as an extension all relationship with him, you know, so he knows if he gets sick or you faint is there to make sure you know he's there to help and I think in every relation it's about compatibility but it's about extension maliti, right? In a way that if that person is extension Oh, and sometimes we talk about about love, you know, like sometimes I think it is it is it a B. S. Word or not? Because I myself sometimes look at I look at myself in the mirror and when I do a stupid thing, sometimes I love myself a lot and sometimes I don't you know what I mean? Because I'm angry at myself. I had done stupid thing. So that means sometimes you could love could be fluctuating, you know what I mean? How about in relationship? Sometimes people they say they love each other, but then when they divorce, they go, oh, I want the house and the dog and the kids stay with me. And you know what I mean? If you love by definition, if you really love someone and let's say you're an old man and you love a woman and she decided to leave you for a younger man. If you really love her, you're gonna help her pack and leave. But in our society, sometimes we want to home. </s><s>[INST] Something to me love includes the missing somebody losing somebody. That anger at somebody. It's all the passion feelings towards somebody that's all love. Like I, you know, it's all part of the thing, it's the ups and downs. It's a the sad thing is when the feelings towards the person, the ups and downs go away forgetting. That's that's the opposite of love is so the opposite of love isn't hate to me, the opposite of love is forgetting and that's that's a much bigger, this is the depth of human connection. That's how I see love. So [/INST] sometimes I try to stay positive and I've been asked how I try to because I have the image of someone who is positive, but I go through my own demon as well. Sometime, however, we talk about love when I was young, you know, like, like I didn't love who I was at first. That's how I love, I learned to kind of love myself. Like I didn't I didn't when I was going true true bullying I was I believe I was bullied because I didn't love myself because I project a very bad image of what I think of myself. I was a kid that lacked a lot of confidence. I was looking down when I was walking, I shrug my shoulder when someone was talking to me, I was avoiding eye contact. I was a very easy target for the bullies and I think bullies are like predatory animal in nature, they will hunt the easier prey. They don't they don't go the reliant, don't go for the alpha. Bull, they go for the one who's hold or was sick. The weakest one and bullies are the same in society, I believe and I didn't like to be bullied of course, but I didn't like the person that I was, but I found out two martial art the respect and my coach was extraordinary to me, he taught me discipline and self strength, self strength and I found out that I needed to in order to love myself, I needed to change myself because I didn't, when I looked at my son in the mirror, I didn't like what I saw, so I decided to become like someone that I would love. So I tried to look people straight up and trying to short case a more confident image that I had and it was hard in the beginning because I didn't really believe in it, but I, I fake it until kind of make it. So when I was walking at school more and more, I was learning how to become more confident and I was like taking charge when the teacher was asking questions I was, at first I was never answering, it was like this, waiting always to be the last that I was hey, I I know what the answer, this is the answer I got out of my comfort zone, so to speak and I wish I would tell you that I got out of bullying because Hollywood story, I use martial art to beat up all the bullies, but it's not how it happened to me, it happened because I changed myself from the inside out and I learned how to, because I didn't love myself in the beginning, I learn how to become like someone that I have loved and even now, like I'm by no means perfect, I do a lot of stupid things, but I learned as a person and even I do as something stupid, I'm like shoot, I did something stupid, I at least I can apologize to the person if I realize and then I know that I'm not the person I was in the past, I'm the person that I am right now, so I can learn and become that image of the person that I love. So in a way the reason why I'm trying to be positive and I am able to stay positive sometime in life is because I'm always trying to be like that person that I love and I think if you don't look yourself in the mirror and don't love yourself or don't see any positive future for yourself, how can you change your environment if you cannot change yourself, you know what I mean? You would never be happy if you're not happy when you look at yourself in the mirror, so change yourself first, then change your, you know, it's not the environment are going to change for yourself, it's you have to go from the inside out, you know this, this I learned to martial art, I have a, I had a coach, it was incredible, used to drill these ideas in my head and give me confidence, you know, like like this telling me all these these beautiful things about myself and how he's dead now. Unfortunately peace, peace to him. But he was incredible, incredible. He was very, very strict. I was afraid of him. I was afraid of my dad and afraid of him. He couldn't teach nowadays like you used to teach me because it would be in probably in gel, you know, but I'm glad he did it because for the time being, that's what I needed it and I would never have had that the career I had in mixed martial art without this because I would I would never have got out of my comfort zone would have been impossible and in order to improve in life you need to get out of your comfort zone. It's hard, it's very hard to do </s><s>[INST] and and strive to be the person that you can love. I does. That's that's beautifully put George. If you were to give advice to a young person today about life, what would you tell them [/INST] if he takes life with the same mentality that I do? If he has the same taste of things that I have, I would tell him, you know, for for for sport, for life in general, I would say if you will have the dream, you know, I liked make everything in your power and work very hard, you know, never take no for an answer and go through hell in order to achieve it. Don't work hard only, but work smart, that's I think the problems with a lot of people, they work hard, they can work hard, They burn themselves, They don't work smart whether it is and in science and business they make bad choices or their badly inform in sport how many guys I've seen ruin their career in the gyms, they spar so hard, they ruin their themselves and the gyms, they leave their career in the gyms. What I would say to, for example, because my field of expertise and it's in sport of mixed martial art, I would say to young kid, make your training playful, you know, when you get ready for for competition, you need, trying to recreate those element that makes you go outside of your comfort zone, but in every day's life in general, make your training playful, don't makes it like a hardcore competition about who's who's winning, who's losing, make it playful, so it will increase your, because you will not be afraid of getting hurt or losing, you will be tent to try more things and you, it will make you become more creative, creative, </s><s>[INST] you know, that brings up another question about learning, so you, you value knowledge and your exceptional at and basically being very good at learning and figuring stuff out new things or going deeper on the things you already know. So what advice would you have for how to learn effectively, how you say work smart, how do you figure this game out? [/INST] I believe the best way to learn is learning from other people's mistake, however, I'm not perfect and I've learned from my mistakes as well. And sometimes I've, it took it took me a few mistakes to learn the same thing, but especially in the sport of mixed martial art, because we're talking about the failure could have very serious outcome on someone's life and well being. So it's crucial to trying to learn from other people's </s><s>[INST] mistakes. Do you study others? [/INST] Do every every fight. I'm studying my opponent and I've studied myself as well to know what all my strength mix versus my opponent's weaknesses and how can I make the fight go in a way that I'm taking my opponent outside of his comfort zone. Very often people are good at studying their opponent, but they're not good at looking at themselves in the mirror and knowing what they should do in order to maximize their their odds of success, right? That's why I always thought for me, it was important to not be the best at one thing, but be very good at everything. That's why I always seek advice, advice is from the best in every discipline. Like I wrestled with the best wrestler, I I could be with my box with the best boxers II practice karate with the best karate fighters, uh same thing in jiu jitsu, I train jujitsu, the breast best jiu jitsu guys? Um However, when I mix everything and mixed martial art if if I'm because I'm very competent in every areas, so when I'm fighting someone I'm very good at and that's the identifying where is the less competent and I know for a fact that because I'm competent everywhere, I can, if I can bring the fight where he's outside of his comfort zone, it increases my odds of winning. There is no certainty, it's all about AIDS, I believe, because there is always expected that you do not control. </s><s>[INST] Yes, fascinating to see you actually, because you've been a student of movement, uh you've been exploring all kinds of gymnastics, all that kind of stuff there, there's something reminiscent to uh like Connor McGregor is one other martial artist that's kind of explored movement in a scholar of movement. Um at least from my perspective, it's very sort of Bruce lee, like it's almost making a study of the human body and all the possible things you can do is their philosophy behind that, that you have, [/INST] you talk about Bruce lee man, you best it changes my life too. He was ahead of his time. Yeah, incredible. A lot of people talk to me and asked me why is brucie would have been able to fight in UFC? I look, I don't think so, you know, I don't know, I think it was a, you know, he was a martial artist, he could have to defend himself, but to say that he could have competed amongst the elite of the elite fighter perhaps and it's time. But for sure if you put him in UFC right now, you know the sport has um improved incredibly since then. But in terms of philosophy, yeah, brucey was amazing. Like one thing that just to prove that he was ahead of his time, he was talking about using your longest weapon against your opponent nearest point and we see that that that kick that it got popular popularized by Jon jones, you know the sidekick to the time, it's the longest weapon against your nearest point in boxing is the jab. But in M. M. A. When you can use it all your weapon, that's the kick to the tie. Uh and there is, I felt there is that kind of three dimension and martial art, there is the philosopher like Bruce lee, there is the correct choreography, the co choreograph people like for example, you see in movies that stand people, they're incredible like or the one that does like forms and really like jumping, spinning back kick, like a dramatic stuff. Mixed martial art, they are unbelievable. And there's also the the the one that compete in fighting, like that's what I do, I personally specializing </s><s>[INST] well you also do the philosophy, [/INST] I do a little bit of philosophy but that's um you know, we are, I guess we are all like we all practice the tree dimension because martial art is I would say it's it whether you want it or not, you have </s><s>[INST] to touch these three [/INST] dementia, but you will specialize in one, I specialize to my life and in fighting like the real thing in terms of fighting competition. And of course if you do martial art, you will be able to defend yourself because it's a self defense. However, you might not be able to fight as an elite and the most prestigious organization and you might not be able to perform the stunt that for example, the stuntmen have done in the series, I was playing in the Falcon and Winter Soldier there. These guys are incredible. They're like real life superhero things, They do it to me like it's, it's fascinating. It's amazing. And also Bruce lee the philosophy how many hours he took like thinking about this stuff, you know, I'm sure he did not just came out out of nowhere, you know, like he was thinking like that many slept on this. He, how many hours? It just </s><s>[INST] unbelievable like water. My friend, how, how many times has he thought about water going to bed before he said that uh, let me ask a very important fundamental question about martial arts were both wearing a suit and tie. Joe Rogan thinks that wearing a tie is a huge disadvantage, is that clip on or is an actual tie? Are you actual diary? So do you agree or disagree with joe Rogan that wearing a tie is uh, is a martial art? Significant disadvantage in terms of combat in a combat scenario [/INST] In a fight. I think it would be a descendant disadvantage. Okay. But I work as a security bouncer in nightclubs and event when I was 18 years old and sometimes I had to work in certain event that I was in a suit and tie. I never had to use my force to take someone out when I wasn't suit and tired. But if I would have had to before going to the table to physically take the guy out, I would have removed my tie and I would have removed my vest for sure and I would have called back up for sure and I would have probably used the element of surprise to be first </s><s>[INST] on that guy [/INST] when you're in a bar, the same thing, you call back up first and, and, and you make sure you ask the way the waitress before to clean the table before </s><s>[INST] you go [/INST] and when you go, you have to use the element of surprise because fighting fighting that mixed martial and fighting in the street, it's two different things and yes, I'm gonna mix, I'm a mixed martial art competitor. That's what I've done all my life. But I had a lot of street fight in my life a lot when I </s><s>[INST] was, what's the difference, [/INST] what's like the my God, it's use different, there's guys that if I would have a choice, you know to fight like for example certain guys and you have seen a street fight and fight like other guys that are not then you have see I would maybe sometimes big guys that are nothing you have seen that necessarily because in a in a street fight there's no referee that says go it's the element of surprise and when you're a nice guy, you're not the aggressor, you always have the element of surprise, </s><s>[INST] that's what it taught me. Oh, interesting. [/INST] Yes, because if </s><s>[INST] aggression your second [/INST] come punch you without warning, it needs to it needs to trigger some, it's something you need to be triggered before. So if someone comes because he's looking for trouble, there is a sign that he's looking for trouble. So I was just talking with fast route and this weekend about it and I saw that every every martial art comes from like some martial art are from exclusive week for competition, </s><s>[INST] like sport [/INST] karate, uh like certain martial art, but traditional martial martial arts are for the street or for self defense. And I started my background in kickboxing, karate. So it's four and I did japanese jiu jitsu. So my background before I even start training for mixed martial art, my backgrounds in self defense and it's very important to understand that in a street fight, the element of surprise is everything and there are no rules, you can go for the eyes the next, it's </s><s>[INST] surprising [/INST] total ball game. You know what I mean? You have the chair of the beer, there's so much more thing going on. So the idea of because you are a UFC fighter, you think you're invincible, this is Bs anybody can come. Like if if a big guy who punched very hard, most people don't know how to punch, by the way, they don't know how to make a fist and threw it in a forward direction. But if someone knows how to do it, I don't care who you are. If you could be Francis and again someone come behind your head, lying or there's an argument, then you get surprised by a punch, you can be dropped and lose a fight. That doesn't matter. The element of surprise is </s><s>[INST] everything. So you were saying remove all the sources of the element of surprise, all the where the bar, remove the tie, I still the security [/INST] about the tablet and just for your information, if someone comes looking for trouble and you see me do this. And yeah, that's my position. I'm thinking there you go, something will happen and I'm about, that's a good about, about doing, I'm about to punch you or to do something to take </s><s>[INST] care of the sea to flip the table on you, then wearing a tie is communicating the nice guy image. So it actually gives you the freedom for more elements of surprise by wearing the tie. If you take it off, that's more you're limiting your options because nobody's going to expect the guy in the tie to do anything. [/INST] I'm a big believer that sometimes it's not only materialism, it's what you project. Like I had troubles in a bar and I was able to deflect. The guy was looking for trouble talking to me and I was able to deflect is all aggressive. Itty by saying like, hey man, that's a nice shirt, where did you get it? Like saying like something or stupid like this, then it kind of break, break the momentum and he, you know, but the guy was looking for trouble. I don't want to fight you. I don't want to fight you, but I'm not going to wait until you pull you make the first move because the first, the minute you you touch me, you push me or you touch me, you declare war and the war is unleashed, my friend and I'm I'm taking you out of order with the necessary force. Of course, you know, I mean, that's the thing with martial art. If you use the necessary force to take care of the problem, it's okay. But if you, you know, you you take advantage of it. That's when it's not all right because it's a weapon. So if someone comes up to me, that's my position and now I'm I'm assessing the situation, you know, that's that's how they teach in self defense here never put your hands down always end there because I'm bound or boom, like what this is, this is very important and you never, you always your center line on the side. Yeah, like this, if someone knows martial aren't it will recognize that pattern. But if you go, like if someone talked to you and you go like this, that's mean you're telling the guy that you want to fight, you don't want to do that, you don't want to. Yeah, that's it, that's it. You know, that's that's the position because you're an R here, you know, whatever you can do your here, </s><s>[INST] we'll also, your ear tells the story. [/INST] It's not everybody that knows that however it, some people might think that it's, my mom grabbed me by the hair and pulled me because I didn't listen to her, you know, a real fight in the street and the fight in the, in the mixed martial art is a different ball game. </s><s>[INST] What do you think is the best martial art to prepare you for street fighting? You know, people often kind of have this discussion of jujitsu, maybe boxing and the wrestling. Do you think we talked about a young person studying martial arts to prepare themselves [/INST] for a street fight, it's often much different than a mixed martial arts fight and I know there's a lot of Bs in the world of martial arts like self defense stuff that like, but I believe self defense is very important in a way to understand the situation, to understand those, those situations that might accurate how to deal with it because not necessarily the we talk about the technicality, we talk about the practicality, the tactics, you know, like when I'm talking to you about the element of surprise is important. This is not technique, technique is a punch or or techniques that I physically will use to unable my opponent. My aggressor tactic is the tactic I'm telling you about is in a street fight. If someone is looking for trouble and I feel the heat rising as the conversation goes, that's the position I'm going to take, and I have to be first, I cannot let him go first, so I have to strike first or do something. This is the first thing that generally, and I have to two to agree on, um after that, of course there's the knowledge if you're a professional fighter, you have a a huge advantage once the fight started the war is declared, now it's everything goes. But generally speaking, the person that will intervened physics that will have the first blower, the first, you know, the first punch, we'll have a huge decision, used advantage, it's like doing 100 m race and having a head start, </s><s>[INST] you know, and and that you don't you can't prepare for with any martial [/INST] art. Yeah, and and if I'm a smart guy, I know how to fight, if a guy like uh an every weight champion comes to me or like, like, like a, you know, I know I know what to do to this, this napoleon like boom or hair and, and or the, the neck, you know like, and if you, if you're blind them what we're gonna do, you know what I mean? So, so, or or a bottle, you know what I mean? So so the element of surprise is, it's everything. So that's why it's always always good to be the nice guy and not looking for trouble because if you're not looking for trouble, you have the head start, you have the option of having a head start. </s><s>[INST] So what you're saying is being a nice guy is the best form of self defense, Maybe a little humor. [/INST] Uh you know, I have learned that I've learned that when I </s><s>[INST] was a kid, [/INST] I was about Maybe 7, 6, 6 years old, we used to play in, in my child is a lot of snow. We used to play king of the mountain. That's the first combat lesson that I've learned in my life. And I managed somehow, it was a lot of kids, I managed to get on the top of the mountain and another guy can come in on the top of the mountain and he was angry that before I was there before him and when you play king of the mountain, the mountain, it was a mountain of snow, you don't strike each other. We just wrestle and push and I managed to be first. And when he came he says to me say, okay you want to you want to fight. And I said, yeah, I don't know what I mean. Like I want to fight, you want to wrestle. He said, I say yes, he punched me right in the face boom. And then I and then I fall on the bottom of the mountain. But then I when I fall down, I remember that vision in mali because it's I really remember that for the rest of my life, I'm about to stand up and I see the blood coming out of my nose. I see the snow is red because my nose is bleeding. Now I I remember the limit of surprises, everything. My first street fight, I lost it. I didn't get knocked out, but I got I got dropped on the bottom of the mountain and I was like, you got me because I was not expecting my hand, I was not expecting a punch. So from there when I felt the heat of an inn during an argument or something was not right. I always stroke first. I didn't win all my fights because sometimes there were more than one guy's on me, you know, but I think it's important. Do not be the aggressor. So you have the element of surprise and I always use that in </s><s>[INST] your favor. That's so brilliant, let me go from the very practical to the most impractical. A huge question about the meaning of life. You said that one great depths of unrelenting sorrow punctuated by great peaks of joy and liberation. The result is delicious. So, uh, what do you think is the meaning of this whole journey that we're on this life? What makes life delicious [/INST] to me? You know, satisfaction is the m for me, like, like, like I always, if I'm satisfied, that's me and I have no nothing to live for. I'm talking I'm not talking only about my career about to talk about my life. What do you want in your life? You want, you want kids, you want a family, you want to be champion, What do you want in your life? You have, you have like a long term goal, short term goal in mixed martial art I achieve when I needed to achieve, I'm satisfied here. I'm no longer the same johnson NPR then when I was begging for a title shot on my knees, I move on for it from it. Now I had a chance to go into movies now. That same insane. That same insane dr that had to be the champion of the world. Now, I put it into acting like I'm having a lot of acting class now and luckily for me, the timing was amazing. I got I got cast for the falcon and the Winter Soldier that is on Disney Plus channel, it's a huge, huge project to be part of for me because it's like you play basketball, you have a chance to go for the NBA right away. I was very lucky, the timing was just too perfect and so you need to constantly challenging yourself and having goals to achieve, you know, like that keep your brain activated, I keep working and the proof of that is you see sometimes some old people like when they retire very often, sometimes you see that they got sick and they die or because they, it's either because sometimes we think we, we certainly benefits will do something good for them by making network and giving them a break. So we don't mind, we're like, oh it is going to be able to relax what in their mind, it's not good because they're not busy, they have nothing to live for like, like my dad is used to work all the time and he has always something to do. He's retired now I </s><s>[INST] myself now [/INST] call him by force to find him some job. Dad, can you come in my house, have this thing to repair, I don't know what to do it. So he gives him, it gives him a reason not to live in because he has other things to do, but what I mean is also in life, I think you always don't be afraid to aim high, don't don't be afraid to fix your objective very high and never be able to reach it. Be </s><s>[INST] afraid of reaching your goals essentially. I mean you always have to keep moving it out. You think there's a uh it's an interesting question because you've been acting in some really exciting things. Do you think there's a, a dramatic role where it's basically, you know, you go full robert de Niro in taxi driver? Do you think there'll be a full length feature film with George ST Pierre? I [/INST] like it. There is level to this thing, I'm aware that I have to restart as a white white belt and for some people it could be discouraging, but for me man, it's great, I love it, I freaking love it, I embrace it because everybody told me like I would never be able to do it and it's fine. But and also the outcome of a failure in the sport of mixed martial arts is much more serious. Then the outcome of a failure for a movie, for example, for for if you zig when you should zag in a fight, you get knocked out. If you zig when you should zag and unset cut, we'll do it again and I know that I will be most likely be chosen for action martial art roles because that's my background, There's this new trend in Hollywood now, when they want someone to play an italian guy, they're going to choose a real italian person when they want someone to play a Russian guy, they're going to choose someone who has a real Russian background. Now they want a real martial art fighter, I've done fighting all my life, I just need to improve my acting skills. But when I train enacting I get myself out of my comfort zone, I'm not playing a role of a martial art, I'm playing like romance committee drama. So when I go on set and playing the role of a of a badass martial art guy, it's easier. So like in training for a fight, I always make my preparation harder than the actual </s><s>[INST] task. I would love to see where I don't know if you've seen the wrestler would make you work. Oh yeah, those types of films, I would love to, I would love to you do something like that if not now then in 10, 20 years I could see that, that would be amazing. It's, there's levels to the game, right? [/INST] Yes, it's gradual and I'm aware that I, I don't want to take something on my shoulder that I won't be able to deliver. It's like a fighter wants to go for a title shot right away. It could, it could very well break him, you know what I mean? And I don't want to do that because I know I've done some gigs in the past, but I was not focusing on it because I was focusing on competing as a martial art much martial artist and competition in m M A. But now I take it very seriously. So I cannot do the same mistake again because I've done some stuff, I've done it for the money and it was good, it was fun to be beat up by Chako van Damme, steven Seagal and everything. But but my acting was not on point you know at that time. So if I ever, every time I'm going to come back from now on on on on screen you need to be sharp because you cannot mess it up if you mess it up, it's like a loss on your record, you're not taken seriously. So so that's how I see it and it's very fun because I I add a chance to talk to a lot of guys and on top of all the class that I'm having like a few days ago I was with Danny Trejo and I always seek the advice of actors when I when I see some of them that because I really admire how they do you know how they project their emotion. And I asked him Danny True. I said I said to him is an amazing guy by the way, very nice guy and I asked him I see him how do you do to be because you scared the hell out of me? How do you do to be so scary like what is your trick? And he tells me it's like George if you threatening if your threat someone and you scream at him </s><s>[INST] I'm going to kill you were in [/INST] it's not as scary if you're smiling in his arm, I'm gonna kill you. Like and he says also to me that another advice he gave me his like when you say this, think about your killing him for real that how you hate him out, you're gonna kill him. So the camera will take the emotion out. Don't try physically to do that. That's a mistake I used to do before I used to physically show that I'm strong and angry and to be mean. So these are just an example of tricks that I learned sometimes when I met an actor. I always trying to learn from everybody </s><s>[INST] that I met in my life. It's a difficult journey because then you have to go to some dark places as a person because you really have to imagine imagine some dark things as fascinating actually. [/INST] I think a lot of the activity have sometimes problems because of that because now I understand why it's like if you work on your bicep your by self will grow right? It's because it's the stress that you put on it that will make it grow right? Mhm emotions are I believe are the same way if you're used to dig inside of you down deep to make your negative emotion depressive emotion comes out. If something bad in your life happened, you will fall into those emotions much more rapidly that someone who does not that every day, you know what I mean? Because it will it's like a muscle memory, like if you program yourself to react a certain way, you will reach that point very often. So that's why sometimes you see some guys there, we often blame it on drug, but I think it's also because of the acting, there used to be so on the hopped up and sometimes they go to the down deep, so they they're the boat extreme. You know, </s><s>[INST] you gotta be psychologically tough and that's life. This is I'm so excited to see you challenge yourself in that direction. [/INST] That's one thing that I'm a little bit afraid that happened to me. I really hope I'll always be uh you know, like I probably having a problem to control my emotion be </s><s>[INST] much extreme. [/INST] I hope it does not happen to me. And and and if I feel that I'm going towards that I'm gonna, you know, give up on my new objective and find something else to to achieve. </s><s>[INST] But in your personal life, you want to be real with your emotions, you don't want to, it doesn't, you know, just like with biceps, you don't want biceps are too big, [/INST] you are real, but you are extremely real and and that's that's the that's what I think something that could happen to actors sometimes when they go too much into their emotions. Like we talked about, like sometimes guys that that commit commit suicide perhaps, you know, I don't know, it's because I don't know their real life, but it could be something that they get so much into their character. I didn't understand it at first because I never had acting class, but after a while that you have acting class now, you start to realize that yeah, can you understand why some actor get caught up in their emotion because that can have an influence on their life, right? </s><s>[INST] You're on a fascinating journey George. I can't tell you how much it means to me that you would be so nice to me that you'll give me so much respect. Just that that tells everything I need to know about you as a human being with everything you've accomplished. You waste all your time and you're so nice to me just as a fellow human being, man have so much respect. I'm so honored and the energy you give me by just seeing me showing up here, I'll care that forward for a long time to come George. I love it. Thank you so much for talking. [/INST] Thank you. Thanks for having me on the show. You know, I've been looking to talk to you for a long time for me talking to a guy like you. It's a it's a great learning experience because I always learn and uh it's life is fascinating to me and all the experience that we have in lives, you know, it's it's something that can make us grow and this experience for me just, you know, make me grow as as </s><s>[INST] well, you know, Plus we look pretty damn sharp today. So [/INST] Man in Black, </s><s>[INST] Thanks George. [/INST] Nice. </s><s>[INST] Thanks for listening to this conversation with George ST Pierre and thank you to all form express VPN blink ist their gun and the information check them out in the description to support this podcast. And now let me leave you with some words from Miyamoto Musashi, think lightly of yourself and deeply of the world. Thank you for listening and hope to see you next time. Mhm. [/INST] Mhm. </s> |
<s>[INST] too, son of a bit. Thanks for listening to this conversation with a formerly known as Kanye West. To support this podcast. Please check out our sponsors in the description and now let me leave you with some words from yee himself. Nothing in life is promised except death. Thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] you don't think humans are unique. I gotta ask you, how many intelligent alien civilizations do you think are out there? And uh is their intelligence different or similar to ours? [/INST] Yeah, I've been preoccupied with this question quite a bit recently basically the fermi paradox and just thinking through and and the reason actually that I am very interested in the origin of life is fundamentally trying to understand how common it is that there are technological societies out there uh in space. And the more I study it, the more I I think that um uh there should be quite a few quite a lot. </s><s>[INST] Why haven't we heard from them? Because I I agree with you. It feels like I just don't see why what we did here on earth is so difficult to do. [/INST] Yeah. And especially when you get into the details of it, I used to think origin of life was very um it was this magical rare event. But then you read books like for example nick Lane, um the vital question uh life ascending etcetera. And he really gets in and he really makes you believe that this is not that rare </s><s>[INST] basic chemistry. [/INST] You have an active earth and you have your alkaline vents and you have lots of alkaline waters mixing whether the devotion and you have your proton gradients and you have the little poorest pockets of these alkaline vents that concentrate chemistry. And um basically as he steps through all of these little pieces, you start to understand that actually this is not that crazy, you could see this happen on other systems. Um and he really takes you from just a geology to primitive life. And he makes it feel like it's actually pretty plausible and also like the origin of life um didn't uh was actually fairly fast after formation of earth. Um I think if I were correctly just a few 100 million years or something like that after basically when it was possible life actually arose. And so that makes me feel like that is not the constraint that is not the limiting variable and that life should actually be fairly common. Um And then you know where the drop offs are is very um it's very interesting to think about. I currently think that there's no major drop offs basically. And so there should be quite a lot of life. And basically what where that brings me to then is the only way to reconcile the fact that we haven't found anyone and so on is that um we just can't we can't see them, we can't observe them. </s><s>[INST] Just a quick brief comment nick Lane and a lot of biologists I talked to, they really seem to think that the jump from bacteria to more complex organisms is the hardest jump. [/INST] Yeah. </s><s>[INST] Which I don't I get it they're much more knowledgeable than me about like the intricacies of biology but that seems like crazy because how much how many single cell organisms are there like and how much time you have. Surely it's not that difficult like in a billion years. It's not even that long of a time really. Just all these bacteria under constrained resources battling it out. I'm sure they can invent more complex. Like I don't understand. It's like how to move from a Hello World program to like like invent a function or something like that. I don't Yeah. So I don't Yeah. So I'm with you. I just feel like I don't see any if the origin of life, that would be my intuition, that's the hardest thing. But if that's not the hardest thing because it happened so quickly then it's gotta be everywhere. And yeah, maybe we're just too dumb to see it. [/INST] It's just we don't have really good mechanisms for seeing this life. I mean by what? How? So I'm not an expert just to pre face this, but just from aliens. And it </s><s>[INST] was I [/INST] want to meet an expert </s><s>[INST] on alien intelligence and how to communicate. [/INST] Very suspicious of our ability to to find these intelligences out there and to find these Earth like radio waves for example, are are terrible. They're power drops off as basically one over R square. So I remember reading that our current radio waves would not be the ones that we are broadcasting would not be uh measurable by our devices today. Only like was it like 1/10 of a light year away. Like not even basically tiny distance because you really need like a targeted transmission of massive power directed somewhere for this to be picked up on long, long distances. And so I just think that our ability to measure is um, is not amazing. I think there's probably other civilizations out there. And then the big question is, why don't they build one moment probes and why don't they interstellar travel across the entire galaxy? And my current answer is, it's probably interstellar travel is like really hard. Uh you have the interstellar medium if you want to move at close to the speed of light, you're going to be encountering bullets along the way because even like tiny hydrogen atoms and little particles of dust are basically have like massive kinetic energy at those speeds. And so basically you need some kind of shielding. You need, you have all the cosmic radiation. It's just like brutal out there. It's really hard. And so my thinking is maybe interstellar travel is just extremely hard years </s><s>[INST] to build hard. It feels like uh it feels like we're not a billion years away from doing [/INST] that. It just might be that it's very, you have to go very slowly potentially as an example through space, </s><s>[INST] right? As opposed to close to the speed of [/INST] light. So I'm suspicious basically of our ability to measure life and I'm suspicious of the ability to just permeates all of space in the galaxy or across Galaxies. And that's the only way that I can, I can currently see a way around it. </s> |
<s>[INST] What about we live in a world now. I've often in my own work, I hear about this concept of work life balance or overtraining. So you've been one of the hardest workers ever on the met, you've coached some of the hardest workers ever. Do you think it's possible to over train train too much? How big of a [/INST] concern peaking and burn out our frames of mind or burnout is a, is a like you let things probably getting to the point where you could have arrested them with a good frame of mind. But Peking is a frame of mind and you know, you have to know, be able to read and that's a lot of it. And the individual athlete also has to know that it's a frame of mind. And so when you have a coach that's reading that the right way and you have an athlete that is knowing that when zero hour comes, that you're going to be ready to go. Um, and knowing that there's light at the end of the tunnel, if you feel like you're burning the candle at both ends, lights coming at the, at the end of the tunnel, I mean you're good to go. </s><s>[INST] So you think about gable and that whole dream of being carried off the mat because you worked so hard again, do you think it's possible to over train. So you said it's a, it's [/INST] mental. I do think it's possible to over train if you have a lot of distractions and if you're looking at your watch running out of the room, then yeah, you're gonna in that frame of mind isn't going to lend itself to excellency. And the thing is, is we we have to accomplish what we need to get accomplished and get better every day. You can't kind of accomplish what you need to accomplish. You have to accomplish it. And when, when you're in that mindset, then the clock is irrelevant. There's no place for a clock in the wrestling room and maybe a clock that times a match. But it may be a clock if, you know, we're at student athletes here, but that's why we encourage our, you know, when when you schedule your classes that you don't have a class that comes right up to, you know, practice time or starts as a night class and it starts at 5 30 you know, go to get the 6 30 class in the seven o'clock. </s><s>[INST] So you leave it all behind your heart, your passion is completely, and [/INST] there's no, when you walk in that wrestling room, there's no distractions and it's never eternal. The only thing that's eternal is death. You know, there's nothing. Sometimes guys come in there and a wig out. Oh my word, 25 minutes and </s><s>[INST] oh, [/INST] We're an hour and 45 minutes? Oh </s><s>[INST] yeah, you have to be willing to go as long as it takes, there's no clock, [/INST] there's no clock </s><s>[INST] again rested as some of the hardest, some of the toughest people in all of sports, but weight cutting often breaks people. So what's your thought on weight cutting? Both nutrition wise, mental eyes, how do you approach and think of it as a coach in your own career too? [/INST] It's a lot of discipline and it's a lot of discipline during a very uncomfortable time period that really doesn't last that long, but it feels like it lasts long and it's painful and, but once you shrink your body down and if you're hydrated, you'll get through it if you're a little hungry, but you're eating, but you're hydrated. Once you break that sweat, your energy depletion goes away. That's a fact. I've practiced that. You come in and you're yawning and you're, you know, you're starting to shrink your body down and it's that time of year where hey, I gotta get my body shrunk down and you're dehydrated, you are dead in the water. But if you're hungry and hydrated when you break that sweat, </s><s>[INST] have people gotten better with that over the years? Over the past [/INST] few days. I think that coaches science is better. I think that coaches communicated. I think they always have, I think the bottom line is, is having the energy to implement that and taking a guy by the hand when he doesn't understand and he's new in your program and he is essential and or he's unwilling to not disciplined enough, because when you think about the hand enough, they will learn that discipline. This is an important aspect of wrestling buddy, You know what I'm saying? So, you know, it's not just go and show up for the match. I mean, it's not about just making weight either. You gotta be able to make weight. That's part of the warm up, That's part of the process, getting ready to wrestle things </s><s>[INST] stuff. Yeah. When did you first start believing you're going to win olympic gold? [/INST] I don't know. I mean, I found out I I got really addicted to wrestling. Really, really fast, started late, but looking back at my life, um, wrestled my whole life with my twin brother, and when Terry and I would fight, it was wrestling and it was to maim. And so if if you were, if you're so, if you're trying to maim me, I better be tough because if I roll over, it expects you to scratch my belly when you're trying to maim me, I won't lose my head and tom and terry brands. There was no alpha male, and when it was on, it was on for real, </s><s>[INST] what do you mean? There's no alpha male, there's [/INST] a lot of twins, there's a dominant twin, a lot of them very few times. Is there a situation where you're gonna I'm gonna win every time in everything, and then he's thinking the same exact way, and Terry used to describe it. Like when we used to get interviewed a lot about our careers, um like could be like you grabbing the steering wheel and me grabbing a steering wheel and fighting, and that's what it was like when you would wrestle him or fight him. And so I had that benefit. So when did I know? Well, I got addicted to wrestling really, really fast in fifth grade and started to research it and I don't know why and talked about the olympics and um put it in my head and member Said something about being an Olympic champion in 5th grade and somebody made fun of me and I got in a fight in the playground. And I remember um getting pulled in, getting in trouble for that, and the people that got me in trouble for that, we're smart enough to not rake me over the coals, but they researched or they actually found out what the fight was about and I was distraught. I was I was really emotional, like crying or whatever you want to say, you don't want to admit that to me. But um but it wasn't because I got beat up, I got my nose bloody, never got punched in the face or broke my arm, or there was any pain, it was because they stomped on my dream and they doubted me. And so I fought for that, and, you know, that was a lesson. There's gonna be a lot of doubters. And what one thing we talk about is the staff is our staff has to be lockstep in that hallway, in our offices and when you deviate outside of that, that is Heresy. So </s> |
<s>[INST] but pleasure then that's a narrow kind of view of player. That's like a short term pleasure. But you can see pleasure as a kind of uh ability to hear the music in the distance. It's like, yes, it's difficult now, it's suffering now, but there is some greater thing beyond the mountain that would be joy. I mean that's kind of, even if it's not in this life, well, you know, the warriors will meet in Valhalla right? The feeling that gives meaning and fulfillment to life is not necessarily grounded in pleasure of like the accounting of the grass. It's something else. I don't know. Um the struggle is a source of deep fulfillment. So like I think pleasure needs to be kind of thought of as a little bit more broadly, it's just kinda, [/INST] it </s><s>[INST] gives you this sense, it for a moment allows you to forget the terror of the fact that you're going to die. [/INST] That </s><s>[INST] that that's pleasure, like that's the broader view of pleasure, that you get to kind of play in the little illusion that all of this has deep meaning, that's pleasure. [/INST] Yeah, well, but I mean, you know, people sacrificed their lives. Atheists may sacrifice their lives for the sake of someone else or for the sake of something important enough and clearly in that case they're not um doing it for the sake of their own pleasure, That's a rather dramatic example, but they can be just trivial examples were um you know, I I choose to be honest rather than </s><s>[INST] lie about [/INST] something, can I lose out a bit and I have a bit less pleasure, but I thought it was worth doing the honest thing or something. I mean, I just think so, that's a, I mean maybe you can use the word pleasure so broadly that you're just essentially meaning something worthwhile, But then I think the word pleasure maybe maybe loses its meaning. </s><s>[INST] Sure, well what [/INST] do you think about the blades of grass case, what do you think about someone who spends their life counting blades of grass and doesn't enjoy it. </s><s>[INST] So I think I personally think it's impossible or maybe I'm not understanding even like the philosophical formulation, but I think it's impossible to have a goal and not draw pleasure from it, make it worthwhile. Forget the word pleasure. I think the word goal loses meaning. If I say, I'm going to count the number of pens on this table. If I'm actively involved in the task, I will find join it. I will find the like, I think there's a lot of meaning and joy to be discovered in the, in the skill of a task, in mastering of a skill and and and taking pride in in in doing it. Well, I mean that's, I don't know what it is about the human mind, but there's there's some um, joy to be discovered in the mastery of a skill. So I think it's just impossible to count blades of grass and not sort of have the Jiro dreams of sushi uh, compelling that draws you into the master of the simple task. Mm [/INST] hmm. Yeah, </s><s>[INST] I suppose, [/INST] I mean in a way you might think it's, it's, it's just hard to imagine someone who would spend their lives doing that. But then maybe that's just because it's so evident that that is a pointless task. Whereas if we take this David hume very seriously, it ought to be, you know, a totally possible life goal. Whereas I mean, yeah, I guess I just find it hard to shake the idea that some ways of um, some life goals are more worthwhile than others and it doesn't mean, you know that there's one single way you should lead your life. But pursuing knowledge helping people um pursuing your own pleasure to an extent are a worthwhile things to do in the in a way that you know for example I have I'm a little bit did I I still feel inclined to walk on cracks in the pavement or do it symmetrically. Like if I step on a crack with my left foot I feel the need to do with my right foot. And um I think that's kind of pointless. It's something I feel the urge to do but it's pointless. Whereas other things I choose to do I think there's it's worth doing And um it's hard to make sense of metaphysically. What could possibly ground that? How could we know about these facts? But that's the starting point for me. </s><s>[INST] I don't know I think you walking on the sidewalk in a way that's symmetrical brings order to the world. Like if you weren't doing that the world might fall apart and you know [/INST] it feels like that. </s><s>[INST] I [/INST] think there's there's </s><s>[INST] um there's meaning in that like you embracing the full like the full experience of that you living the richness to that as if it has meaning will give meaning to it. And then whatever genius comes with that as you as one little intelligent ant will make a better life for everybody else. Perhaps I'm defending the blades of grass example because I can literally imagine myself enjoying this task as somebody who's O. C. D. In a certain kind of way and quantitative. [/INST] But now you're running because you imagine someone enjoying it and imagine someone who doesn't enjoy it. We don't want a life that's just full of pleasure. Like we'd just sit there you know having a big sugar high all the time. We want a life where we do things that are worthwhile if for something to be worthwhile just is for it to be a basic life goal then um that that mode of reflection doesn't really make sense. We can't really think did I do things worthwhile on the on the david hume type picture. All it is for something to be worthwhile is it was a basic goal of yours or derived from a basic goal and. Yeah. </s> |
<s>[INST] Let me ask you a tricky one in the recent news that's become especially relevant for me. What do you think about if you've been paying attention to? Yeah Kanye West recent controversial outburst on social media about and jews black people racism, general slavery, holocaust all these topics that he touched on in different, in different ways on different platforms but including twitter. What do you what do you do with that? And like what do you do, what do you do with that from a platform perspective? What do you do from a humanity perspective of how to add love to the world? Let's [/INST] Um should we take both sides of them? Sure. Option one is he is completely out of line and option two is he's not just a so the path one is he is an incredibly important taste maker in the world that defines the belief system for a lot of people and there just is no room for any form of racism or bias or anti Semitism in today's day and age, particularly by people whose words and comments will be amplified around the world. We've already paid a large price for that. And then the expectation of success is some amount of societal decorum that keeps moving the ball forward. The other side would say life, I think goes from harmony to disharmony to repair and anybody who has gone through a very complicated divorce. We'll tell you that in that moment your life is extremely dis harmonious and you are struggling to cope and because he is famous, we are seeing a person really struggling in a moment that may need help and we owe it to him, not for what he said because that stuff isn't excusable, but we owe it to him to help him in a way and particularly his friends and if he has real friends, hopefully what they see is that what I see on the outside looking in is a person that is clearly struggling. </s><s>[INST] Can I ask you like a human question and I know it's outside looking in, but there's several questions I wanna ask. So one is about the pain of going through a divorce and having kids and all that kind of stuff and to when you're rich and powerful and famous. I don't know, maybe you can enlighten me too, which is the most corruptive um but how do you know who are the friends to trust? So a lot of the world is calling Kanye insane for like has mental illness, all that kind of stuff. And so how do you have friends close to you? Let's say let's say something like that message, but from a place of love and where they actually care for you as opposed to trying to get you to shut up [/INST] the reason </s><s>[INST] I asked all those questions I think if you care about the guy, how do you help him? [/INST] I've been through a divorce, it's gut wrenching. Um the most horrible part is having to tell your kids, I can't even describe it to you um how proud I am of and how resilient these three beautiful little creatures were when, when my ex wife and I had to sit them down and talk through it um and for that thing, I'll be so protective of them and so proud of them and um it's hard now, I don't know that that's what he went through um but it doesn't matter in that moment, there's no fame, there's no money, there's nothing, there's just the raw intimacy of a nuclear family breaking up in that there is a death and it's the death of that idea and that is extremely, extremely profound in its impact, especially in your Children. Um it is really hard, really hard, </s><s>[INST] could you have seen yourself in the way you see the world being clouded during, especially at first to where you would make poor decisions outside of your, outside of that nuclear family. So, like, poor business decisions, poor tweeting decisions, poor, uh I think that [/INST] I had to boil down a lot of those, what I would say is that there are moments in my life where I have felt meaningful e less than and in those moments, the loop that I would fall into is I would look to cope and be seen by other people, so I would throw away all of the work I was doing around my own internal validation and I would try to say something or do something that would get the attention of others, and often times, you know, when that loop was um was unproductive, it's because those things had really crappy consequences, so, you know, that was, that was, yeah, so yeah, I I went through that as well, so I had to go through, you know, this disharmonious phase in my life and then to repair it, you know, I had the benefit of meeting someone and building a relationship um, block by block, where there was just enormous accountability where my partner not had, has just incredible empathy. Um, but accountability and so she can put herself in my shoes sometimes when I'm a really tough person to be around, but then she doesn't let me off the hook, she can forgive me, but it doesn't make you know what I may have said or whatever, you know, uh excusable and that's been really healthy for me and it's helped me repair my relationships, be a better parent, you know, be a better friend to my ex wife who is a beautiful woman who, you know, I love deeply and will always love her and it took me a few years to see that that it was just a chapter that had come to an end. But she's an incredible mother and an incredible business woman and I'm so thankful that I've had two incredible women in my life that's like a blessing. </s> |
<s>[INST] it's not always fair. [/INST] No, no, it's not ever. But interesting stuff If people would see what we send the stuff that we, </s><s>[INST] that would judge you harshly. [/INST] Alright, </s><s>[INST] Alright, thanks so much guys. This is awesome. Thanks for listening to this conversation with George ST Pierre, john Donna har and Gordon Ryan to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Miyamoto Musashi. There's nothing outside yourself that can ever enable you to get better, stronger, richer quicker or smarter. Everything is within everything exists, seek nothing outside of yourself. Thank you for listening and hope to see you next time [/INST] </s> |
<s>[INST] and activism in the United States? [/INST] But what aspect of the January 6th was bad for you? </s><s>[INST] Well, I mean, if you're thinking it from a big philosophical political perspective, so presumably the number of people hurt and the number of people who died [/INST] is not the only metric to consider here. Absolutely. I think the sum total of what it means about how the United States operates is what's most concerning. And I'll kind of just like flesh it out a little bit. So summer of 2020, Trump's already saying they're going to cheat. Now, the polling is close, but it shows that Biden's in a good position. People aren't happy with Trump. Any reasonable person would look and say, it's going to be close, but Biden certainly wouldn't be a crazy thing if Biden won, Trump's already saying they're going to cheat with mail in ballots. So they're going to cheat with early voting or they're gonna cheat with machines or we should do only in person or whatever else the case maybe we have the election. We knew in certain states how the vote count was going to go. Some states stop counting at 10 P.M. some states count all of the mail and stuff up front. Some don't, everything was completely predictable, at 2 a.m. Trump comes out and says, I won okay, but where are you getting that, sir? As he claims, people always refer to him. Where are you getting that? And with that statement, immediately we see that there is a large portion of this country that either is unable or unwilling to say, wait a second, the polling all said this was a real possibility. The counting schedules are all being adhered to. But Trump won, that doesn't make any sense. That doesn't happen. It builds, people are donating millions to Trump for supposed audits which nobody can define and lawsuits which go nowhere. And it builds and builds and builds. And we have a total separation from a factual reality. There's no reason to think by December 1st, right? Give three weeks to look through some of this stuff. By December 1st, there's no reasonable case to be made that Trump actually won, but it doesn't end there. It goes into maybe we can just like send different electors even though Biden won Arizona. Let's just like send, I don't remember how many electors it is in Arizona, let's just like send Republican electors to say we vote for Trump, but that's not democracy. That's not the way the system works. Let's make sure we're ready. Ready for what exactly? And then it builds to maybe Mike Pence can just like prevent Biden from being president or maybe we can just interfere in this other way. And then it gets to let's break into the Capitol. It's the height of saying we no longer comport ourselves attached to what is a verifiable factual reality. And when we no longer do that, we're also willing to commit crimes, property crimes, violent crimes, okay, to different degrees in order to try to have something other than democracy. It wouldn't be democracy if any of those things had happened. </s><s>[INST] Yeah, I think it's not the height of it. I think there is still a case to be made that that did not leave the realm of protest versus a violation of the principles of democracy. So to me, the height of what could happen on January 6th is if Donald Trump was much better executive, [/INST] he could take control of the military. </s><s>[INST] If it had succeeded. No, not even succeeded. [/INST] The attempt would have been more empowered. </s><s>[INST] I understand. The way not to bring up Hitler every other word, which is something your subreddit also told me not to do. It's kind of an important figure. It's interesting to study that moment in history because it reveals so much about human nature and that all of us are capable of good and evil. But thank you to your subreddit or Redditor for your contribution to the conversation. I will keep bringing up Hitler and the Third Reich and I'll keep bringing up Stalin. There's so much to learn from that. Anyway, an effective practice authoritarian could roll the tanks out into the city streets to establish order and in so doing, pause the process of democracy, as opposed to a few protesters breaking in [/INST] to a questionably protected building. I agree that what you're saying would be worse. I don't want to use it to minimize what the protesters were intent on doing. </s><s>[INST] They failed, fortunately. But to you, the intention was there. [/INST] Well, the intention was Trump should remain president. That's the intention. And to what length they would have been willing to go if by the evening, early evening, they were sort of like forced out, I don't know. I agree with you that Trump trying to use the military would absolutely be worse. There's these reports that he tried to seize voting machines, which is kind of funny because it's like, once you get the machine at Mar-a-Lago, what do you do with it exactly? I don't know. There's like a comedic element to Trump sitting around with voting machines, but he did float trying to do some other things. I don't believe there's reporting </s><s>[INST] that he actually tried to use the military. I wonder to what degree this opened the door to further things like this with other candidates on, you know, even in the Democratic Party also. Do you think there'll be more and more questioning [/INST] of the election results? There has been already. It's very clearly the playbook. Kerry Lake lost. She ran for governor in Arizona, 2022. She lost. What I mean by that is her opponent received more votes. It's like very clear what it means that she lost. She insists to this day that she won. To this day, she did the same grift Trump did about donate. We've got a case. We won in the case. He didn't win. They just set a court date. Like that's not what, you know, lies upon grift upon lies. So they did it then. It is, I, I, it's extraordinarily saddening, but it seems like this is now going to be part </s> |
<s>[INST] Let me try to express my lived experience, Okay, okay, my experience at MIT is that there's a bunch of administrators that are the bureaucracy, that I can I can say this is the nice thing about having a podcast, I don't give a damn is they're pretty useless. In fact, they get in the way. But there's faculty, those professors that are incredible, they're incredible human beings that all they do all day, they're too busy. But for the most part where they do all day is just like continually pursue different little trajectories of curiosities in the in the various avenues of science that they work on. And as a side effect of that, they mentor a group of students, sometimes a large group of students and also teach courses and they're constantly sharing their passion with others. And my experience is, it's just a bunch of people who are curious about engineering and math and science, chemistry, artificial intelligence, computer sized with almost familiar with. And there's never this feeling of Emmett being broken somehow. Like this kind of feeling like if I talk to you just now or like eric Weinstein, there's a feeling like stuff is on fire, right? There's something deeply broken. Uh but when I'm in in the system, especially before the covid before this kind of tension, everything was great. There was no discussion of even diversity, all that kind of stuff. The toxic stuff that we might be talking about right now, none of that was happening was a bunch of people just in love with uh cool ideas, exploring ideas, being curious and learning and all that kind of stuff. So I don't, my my sense of academia Was, this is the place where kids in their 20s 30s and 40s can continue the playground of science having fun. It's if you destroy academia, if you destroy universities, like you're suggesting kind of lessening their power, you take away the playground from these kids to play. [/INST] It's gonna be hard for you to tell me that I'm anti playground. </s><s>[INST] Yeah, well I guess I'm saying you're anti certain kinds of playgrounds, which is [/INST] yeah, the ones that have the broken glass on the floor. Yeah, I am against those kinds of playgrounds. </s><s>[INST] No, no, you're you're you're no you see that, you listen, you wait. Yeah, I I would say you're being the watchful mother who the one kid who hurt themselves in the glass [/INST] one kid, it's an entire generation after generation. I'm not a watch her mother, I'm the guy with the flamethrower. </s><s>[INST] I understand I understand that, but you're using the one kid who was always kind of like weird um gender studies department uh that that hurt themselves on the glass as opposed to the people who are like obviously having fun in the playground and not playing by the glass, the broken glass and they're just, I mean to me some of the best innovations in science happen in universities. Okay. You can't forget that universities don't have this liberal like politics literally in every conversation until this year until this year, there's something happening. But uh, every conversation I've ever had nothing to do with politics who never trump, never came up. None of that ever come up. Nothing like all this kind of idea that there's liberal, all that. But that that's in the humanities. [/INST] Yeah. But do you think M I. T massachusetts institute? Technology might be a little bit of an outlier. </s><s>[INST] Yeah, this probably is. Yeah, but I don't, I honestly don't think when people criticize academia, they're looking at, uh, there in fact also picking the outliers, which is they're picking some of the quote unquote strongest gender studies [/INST] Departments is nonsensical. When I was at Bucknell. It was a college student. We had to take, uh, you know, we had a bunch of electives and I want to take a class on individual American individualism. One of the text of the five that we had to read was Birth of a nation. The movie about the Klan. So there's no department where these people are not thorough going hardcore ideologues. Uh, this is not a gender cities, that humanity fine. All the humanity is not just gender studies. Okay, fine. I can give you history english, all of them. Every university as you know, has it mandatory in the curriculum? They have to take a bunch of these propaganda classes. </s><s>[INST] Yeah, I look forward to youtube comments because you're being more eloquent and you're speaking to the thing that a lot of people agree with and I'm being my usual slow self. And people are going to say not very nice things about me, [/INST] don't say anything. Not nice about lex. Please </s><s>[INST] let me try to [/INST] just just shoot up a school that would be preferable. </s><s>[INST] There he goes again only to go to the darkest possible place. [/INST] The sunshine baby schools. That's where everyone goes to be happy </s><s>[INST] playgrounds. There he goes dark here, just dives right in like just go dark and then just comes back up to the surface. [/INST] You have to feel this way anymore. </s><s>[INST] It's one day um you're probably a figment of my imagination. I'm not even having this podcast after [/INST] 18 red bulls. I'm surprised you can see anything. This is like fight club delirium. Uh I got into that Norton yesterday on twitter. </s><s>[INST] Oh really? Yeah. Is he uh like the rest of the [/INST] celebrities? Yeah. He's like, oh this is an existential threat to America trump's a fascist. He's delegitimizing the oval office. I said why not endorsement of trump? </s> |
<s>[INST] So both of the examples you've given, there's some sense in which the social interactions between humans is the kind of moving away from the full responsibility that you as a human in the view of existentialism should take on. So like isn't all isn't a basic conversation a delegation of responsibility just holding a hand there. You're putting the response some of the responsibility into the court of the other person and for the waiter, if you exist in a society, you are generally trying on a roll. I mean all of us are trying on a roll. Me wearing clothes is me trying on the role that I was told to try as opposed to walking around naked all the time. Like there's there's like standards of how you operate and that's not that's a decision, that's not my own, that's me seeing what everyone else is doing and copying them. [/INST] Yeah, exactly. So start thinks that in the ideal you should try to resist that. Other existentialists think that that's actually a clue to how you should live well. So start start says somewhere else. Hell is other people, Why as hell other people for start because other people are making choices also and when other people make choices, they put some pressure on me to think that the choice they made is one that I should uh copy or one that I should sort of promote but if I do it because they did it, then I'm in bad faith for start. So it's it is as if starts view is like we would be better if we were all alone. I mean this is this is really simplifying starts position and this is really just mostly start in a certain period of his of his formation. But anyhow we can imagine that view and I think there's something to the idea that start is attracted to it at least in the mid 40s. </s><s>[INST] Can you dig into hell is other people? Is there some obviously it's kind of almost like a literary, like you push the point strongly to really explore that point, but is there some sense in that other people ruin the experience of what it means to be human? [/INST] I think for start the phenomenon is this like it's not just that you wear clothes because people wear clothes in our society, like you have a particular style, you wear a particular kind of clothes and for start like to have that style authentically in good faith rather than in bad faith, it has to come from you, you have to make the choice, but other people are making choices also and like you're looking at their choices and you're thinking that guy looks good, maybe I could try that one on and if you try it on because you were influenced by the fact that you thought that guy was doing it well, then there's some important sense in which although that's a resource for a choice for you, it's also acting in bad faith. So so God and God wouldn't do that right, God wouldn't be influenced by others decisions. And if that's the model, then that's I think that's the sense in which he thinks hell is </s><s>[INST] what do you think parenting is, then it's like what? Because God doesn't have a parent. So aren't we significantly influenced, first of all, in the first few years of life. Um and then even even the teenager is resisting learning through resistance. So [/INST] absolutely, I mean, I think what you're pushing on is the intuition that the ideal that starts aiming at is a kind of inhuman ideal. I mean, we're there's many ways in which we're not like the traditional view of what God was one is that we're not self generating. We have parents, we were raised into traditions and social norms and were raised into an understanding of what's appropriate and inappropriate to do. And I think that's a deep intuition, I think that's exactly right martin Heidegger, who's the who's the philosophy that start thinks he's sort of taking this from, but I think starts a kind of brilliant french misinterpretation of Iger's german phenomenal logical view. Heidegger says a crucial aspect of what it is to be us is our throne nous were thrown into a situation, were thrown into history, were thrown into our parental lineage were and we don't choose it. That stuff that we don't choose. We couldn't choose if we were God and we existed outside of time maybe, but we're not, we're finite in the sense that we have a beginning that we never chose. We have an end that were, you know, often trying to resist or put off or something and in between there's a whole bunch of stuff that organizes us without our ever having made the choice and without our being the kind of being that could make the choice to allow it to organize us, we have a complicated relationship to that stuff. And I think we should talk about that at a certain point. But the first move is to say so it's just got a sort of descriptive problem. He's missed this basic fact that um there's an awful, there has to be an awful lot about us that's settled without our having made the choice to settle it that way. </s><s>[INST] Right, the throne nous of life you have, that's a fundamental part of life. You can't just escape it. [/INST] Exactly. You can't escape it all together. All </s><s>[INST] together. Yeah, exactly. [/INST] You can't escape it all together. But </s> |
<s>[INST] you're reminded of it quite often in the context of of running a company? [/INST] Sure. I mean that's what it's about, it's it's about leadership and you know leadership is intimately tied to ego now, what does it mean? I mean what does the, you know for me, I've been fortunate that I think I have reasonable intellectual confidence, so to speak. That is uh you know, I am one of these people who at this point, if somebody tells me something and I just don't understand it, my conclusion isn't that means I'm dumb that my conclusion is there's something wrong with what I'm being told. Um and that was actually Dick Feynman used to have that that that feature too, he never really believed in, he actually believed in experts, much less than I believe in experts. So um </s><s>[INST] wow, so that's a fun, that's a that's a fundamentally powerful property of ego and saying like not that I am wrong, but that the world is wrong. And tell me like when confronted with the fact that doesn't fit the thing that you've really thought through, sort of both the negative and the positive of ego. Do you see the negative of that get in the way, sort of [/INST] sure mistakes I've made that are the result of, I'm pretty sure I'm right and turns out I'm not, I mean that's that's the you know, But but the thing is that the the idea that one tries to do things that so for example, one question is that people have tried hard to do something and then one thinks maybe I should try doing this myself, if one does not have a certain degree of intellectual confidence, one just says, well people have been trying to do this for 100 years, how am I going to be able to do this? And you know, I was fortunate in the sense that I happened to start having some degree of success in science and things when I was really young and so that developed a certain amount of sort of intellectual confidence I don't think I otherwise would have had and you know, in a sense, I mean I was fortunate that I was working in the field particle physics during its sort of golden age of rapid progress and that kind of goes on a false sense of achievement because it's kind of kind of easy to discover stuff that's going to survive if you happen to be, you know, picking the low hanging fruit of a rapidly expanding field. </s><s>[INST] I mean, the reason I totally I totally immediately understood the ego behind a new kind of science to me. Let me sort of just try to express my feelings and the whole thing is that if you don't allow that kind of ego, then you would never write that book that you would say, well people must have done this, there's not, you would not dig, [/INST] you would not keep </s><s>[INST] digging. And I think that was, I think you have to take that ego and and ride it and see where it takes you and that, and that's how you create exceptional work. [/INST] But I think the other point about that book was it was a nontrivial question. How to take a bunch of ideas that I think reasonably big ideas, they might, you know, their importance is determined by what happens historically. One can't tell how important they are. One can tell sort of the scope of them and the scope is fairly big and they're very different from things that have come before. And the question is, how do you explain that stuff to people? And so I have had the experience of sort of saying, well, there these things, there's a cellar or thomason, It does this, it does that. And people are like, oh, it must be just like this. It must be just like that said, no, it isn't, it's something different. Right? So you could have done </s><s>[INST] sort of, I'm really glad you did what you did. But you could have done sort of academically just published, keep publishing small papers here and there. And then you would just keep getting this kind of resistance, right? You would get like, yeah, as opposed to just dropping a thing that says here it is. Here's the full the [/INST] full thing. No, I mean that was my calculation is that basically, you know, you could introduce little pieces, it's like, you know, one possibility is like, it's the secret weapon, so to speak. It's this, you know, I keep on, you know, discovering these things and all these different areas where they come from, nobody knows, but I decided that, you know, in the interests of one only has one life to lead them. You know, the writing, that book took me a decade. Anyway, it's not, there's not a lot of wiggle room, so to speak, one can't be wrong by a factor of three, so to speak, and how long it's going to take. Um, that I, you know, I thought the best thing to do, the thing that is most sort of, that most um, respect the intellectual content, so to speak, is you just put it out with as much force as you can, because it's not something where, you know, it's an interesting thing, you talk about ego, and it's it's, you know, for example, I run a company which has my name on it, right? I I thought about starting a club for people whose, whose companies have their names on them. And it's it's a funny group, because we're not a bunch of egomaniacs, that's not what it's about, so to speak. It's about basically sort of taking responsibility for what one is doing. And, you know, in a sense, any of these things where you're sort of putting yourself on the line. Um, it's, uh, it's kind of a funny, uh, it's a funny dynamic because, um, in a sense, my company is sort of something that happens to have my name on it, but it's kind of bigger than me and I'm kind of just its mascot at some level. I mean, I also happen to be a pretty, you know, strong leader of it, but </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] It's a very tough city and list to walk. There's something, I mean, I wanna be careful here because I'd like to talk to Eric about this directly, but I'll just, from a perspective of a friend, wanna ask about the drug of fame. So there's also the public perception of the battles of physics. And so there's a very narrow community, but then there's the way that's perceived, the exploration of ideas is perceived by the public. And so there is a certain drug to the excitement that the public can show when they sense that you have something big. And that in itself might become the thing that gives you pleasure. And I think that with theories of everything or with any kind of super, super ambitious projects, and this is taking us back to when you were ambitious about trying to understand the origins of the universe, if you convince yourself that you have an intuition about the origins of the universe, and you have a platform like you do now where you start to communicate your intuition, it's hazy, like all the signs, you're still unsure, but you have a sense, I mean, perhaps you don't have that as much as an experimentalist because you always kind of start going, okay, how can I build a device to see through the fog? But if you're more like a theoretician who kind of works in the realm of ideas, in the realm of intuitions, it is also a source of pleasure. You mentioned dopamine, a source of dopamine that you can communicate to others that you're really excited by the possibility of solving the deepest mysteries of the universe. So there's some aspect to which you want to be a Grigori, Grisha Perlman, and go into the hole and get the work done and shut the hell up about the, speaking about myself, about talking about the dream and planning and exploring how great it will be if my intuition turns out to be correct, if the sketches I have turn out to actually build the bridge that takes us to a whole new place. As a friend of Eric's or a friend of my friend, what kind of advice do you give? What is your role? Is it to be a supporter given that he has many critics or is it to be in private a critic? Like a lot of my friends will say, hey, shut the hell up. [/INST] Just get it done. Well, first of all, I wanna ask you a question I've asked him and then it comes from Animal Farm. My favorite book, yeah. So you remember Benjamin the Donkey and he's talking to the pig. I forget the pig's name. You probably know. Anyway, the pig says to him, you've got this long, lustrous, beautiful tail. You're so lucky. I got this short, curly, little squiggly thing that does jack squat. Tell me, how does it feel to have such a lustrous tail? And Benjamin says, well, the good Lord, he gave me a tail to swat away the flies. But you know what? I'd rather not have the tail if I didn't have the flies. So I ask you, as I've asked Eric, is it worth it? You know, you've got these beautiful tail, but there are flies. I'm not saying in a negative way. I'm just saying you get unwanted distractions, dopamine, you know, it's kind of the highlight, the spotlight effect. It's obviously allowing you to do things that you could never do alone. And I think, you know, first of all, I'd love to know how you answer that </s><s>[INST] because that's something I don't feel I can relate to myself. Well, this has to do with more like platform. Platform stuff. Yeah, scale. [/INST] Oh, I, platform stuff. </s><s>[INST] Yeah, scale. That has no very little effect on me. I enjoy it. I enjoy meeting new people, but that has nothing to do with platform. Yeah, no, that has no effect on me. I want somebody that enjoys the act itself. So this conversation, the reason I'm doing this podcast with you today is because that allows me to trick you into talking to me for a long period of time. I don't care about platform. I assume nobody listens. [/INST] It really doesn't matter. Yeah, and if I got it right, my whole test of it was a good podcast. How do you know? Like podcasts have been around what, 12 years? How do we know as podcasters we're doing a good job? Like sometimes someone will say, that was the best interview I ever had, but that doesn't happen that often, at least for me. But if you realize that you forgot to put the SD card in that little guy and the Zoom didn't work, would you do it again? And I think if you say yes to that, that was a good podcast. </s><s>[INST] Yeah, exactly. That's exactly it. So in that space, yeah, all of it is worth it. But the dream, the more referring to the psychological effects, forget the platform, forget all of that. Maybe you shouldn't even brought up the platform because it really has to do even in your own private mind, [/INST] which is what I'm struggling with. </s><s>[INST] All of it is worth it. I enjoy the planning, the dreaming, the early stages, so much that I often don't take projects to completion. This is a psychological effect that I'm sure basically everybody, every engineer, everybody that does anything goes through. I just, in this case particular, I think it also applies. [/INST] And I wonder as a friend, what is the role? So yeah, I mean, that effect has been documented, everything from planning telescopes to dieting. So there's a tiny bit of dopamine that you get visualizing how you're gonna feel. You don't need to know this, but you don't deal, but losing five pounds. I said, oh, I'm gonna lose five pounds and I'm gonna be able to run a minute faster. So there's a part of me when I'm planning the diet and the meals and the exercise that I get a little bit of that thrill and that actually saps a little bit of my willpower to actually complete the task that will take me to that goal. So that's a documented effect. And that happens in project planning and project management. It's a very, very important thing to guard against as a manager of a big project. With Eric, it's interesting because with him, first of all, we relate extremely well on a friendship level and very close. He does remind me a lot of my father and I've told him that just as a mathematician, as a big thinker, as in his case as a father, the father kind of figure that I didn't have in a sense, but that he is a true lover of life. He knows he's got a huge platform. He knows he gets a lot of attention for what he does. And I jokingly say, well, it's one thing, how do you know, Lex, that someone's an expert? So the expert says, there's a good rule Ray Dalio writes about in principles. He says, or an expert is someone who's done something three times successfully. Like you can do something correctly once, you could do something correctly. It's very hard to pull off like three projects, three telescopes, three, whatever, right? So look for, it's arbitrary. It could be four, it could be two, right? But the point is, look at Eric. So how many things has he contributed to and made pretty substantive kind of paradigm shifts for different people? I would say he's been right many times. Does that mean he's infallible, that he's ineffable? No, of course not. For me, so what I'm saying is I get a little bit of the joy of kind of learning something purely as a scientist, something completely outside of what I do, mathematics, gauge theory, the kind of very advanced geometry topology that he's interested in. But every now and then, I will sneak in that I want, you know, I've told him, I'm gonna turn your son into an experimentalist despite you. Like he is not gonna be a theory. Zev is not gonna be a theory. He is working with me. He is learning from me. We're trying to get him into, he wants to bypass all of the purposefully nonsense of undergraduate and go straight to graduate school. And I've tried to encourage him that maybe he could do it. Maybe he can't, but there's no other way than to try. And so I prepared a whole curriculum for Zev to basically bypass all of undergraduate. And to his credit, he's not earns all the credit. He's learned it to a level that matches many of my graduates. </s> |
<s>[INST] It's very susceptible to adversarial [/INST] attacks, essentially, potentially. Yes. So in general, the problem with these models is Unity models is that they're very good at generating possible text but that's just that's just not enough. Right? Um you need uh I think 11 avenue that would be very interesting to make progress is to make it possible uh to write programs over the latent space that these models of Britain, that you would rely on these uh self supervised models to generate a sort of flag pool of knowledge and concepts and common sense. And then you will be able to write explicit reasoning programs over it. Because the current problem with deputy strings that you it can be quite difficult to get it to do what you want to do if you want to turn history into products, you need to put constraints on it, you need to um force it to a base it and rules. So you need a way to program it explicitly. </s><s>[INST] Yeah. So if you look at its ability to program synthesis it generates like you said something that's plausible. [/INST] Yeah. So if you if you try to make it generic programs it will perform well uh for any program that has seen it in its training data. But because program space is not interpretive, right? Um uh it's not gonna be able to generalize to problems it hasn't seen before. </s><s>[INST] No, that's currently do you think mm sort of and absurd. But I think useful. Um I guess intuition builder is uh You know the GTT three has 175 billion parameters. Human brain has a 100 Has bought 1000 times that or or more in terms of number of synapses. Do you think? Obviously very different kinds of things. But there is some degree of similarity do you think? What do you think GPT will look like when it has 100 trillion parameters? You think our conversation might be in nature different like because you've criticized GPT three very effectively now, do you think? [/INST] No, I don't think so. So the beginning with the bottleneck with scanning of GPT three GPT models, genetic potential summer models is not going to be the size of the model. How long it takes to train it? The bottleneck is going to be the training data because open your eyes already. Training ship industry on a Kroll of basically the entire web. Right? And that's a lot of data. So you can imagine training on more data than that like google could trained on more data than that but it would still be only incrementally more data and I don't recall exactly how much more data. GPT three with strain on compared GPT two but it's probably at less like hundreds maybe even thousands X. Don't have the exact number. You're not going to be able to train the model on 100 more data than what you already what you're already doing. </s><s>[INST] So that's that's brilliant. So it's not you know it's easier to think of computers a bottleneck and then arguing that we can remove the bottom like [/INST] but we can remove the compute bottle like I don't think it's a big problem if you look at the at the pace at which we've improve the efficiency of deep learning models in the past a few years. I'm not worried about train time bottlenecks and model size politics. Uh The bottleneck in the case of this generative transforming models is absolutely the train data. </s><s>[INST] What about the quality of the data? [/INST] So so yeah so the quality of the data is an interesting point. The thing is if you're going to want to use these models in real products um then you you want to feed them data that's as high quality as factual I would say as unbiased as possible that you know there's there's not really such a thing as m biased data in the first place, but you probably don't want to train it unready for instance. Sounds like sounds like a bad plan. So from my personal experience working with uh large scale deep learning models. So at some point I was working on a model at Google that's trained on uh X 350 million labeled images. It's image classification model. That's a lot of images. That's like probably most publicly available images on the web at the time. And it was very noisy dataset because the labels were not originally annotated by hand by humans, they were automatically derived from like tags on social media are just keywords in the same page as the image was fall and so on. So it was very noisy. And it turned out that she could easily get a better model. Uh Not just by train, like if you train on more of the noisy data, you get an incrementally better model. But you you you you very quickly heat diminishing returns. On the other hand, if you train on smaller data set with higher quality and rotations quality, that uh annotations that actually uh made by humans, you get better modeled. And it also takes less time to train it. </s><s>[INST] Yeah. That's fascinating. It's the self supervised learning. There's a way to get better doing the automated labeling? [/INST] Yeah. So you can enrich refine your levels in an automatic way. That's correct. </s> |
<s>[INST] which is fascinating on the machine and the human level that we when you don't have an objective means, you're together coming up with an objective. I mean, there's a lot of philosophy that, you know, you could argue that life doesn't really have meaning. We together agree on what gives it meaning. And we kind of culturally create uh things that give why the heck we are in this earth anyway, we together as a society, create that meeting and you have to learn that objective. And one of the biggest, I thought that's what you were going to go for a second. Uh One of the biggest troubles we run into outside of statistics and machine learning and ai in just human civilization Is when you look at, I came from, I was born in the Soviet Union and the history of the 20th century, we ran into the most trouble us humans when there was uh a certainty about the objective and you do whatever it takes to achieve that objective, whether you're talking about in Germany or communist Russia. Uh [/INST] Yeah. Get in trouble with you would say with, you know, corporations. In fact, some people argue that, you know, we don't have to look forward to a time when AI systems take over the world. They already have and they call corporations right that corporations happened to be using people as components right now. Um But they are effectively algorithmic machines and they're optimizing an objective which is quarterly profit that isn't aligned with overall well being of the human race and they are destroying the world. I mean, there are primarily responsible for our inability to tackle climate change. So I think that's one way of thinking about what's going on with with corporations. But I think the point you're making is valid that there are many systems in the real world where we've sort of prematurely fixed on the objective and then decoupled the the machine from those that's supposed to be serving. Um And I think you see this with government, alright, government is supposed to be a machine that serves people, but instead it tends to be taken over by people who have their own objective and use government to optimize that objective regardless of what people want. </s><s>[INST] Do do you have, do you find appealing the idea of almost arguing machines where you have multiple ai systems with a clear fixed objective? We have in government, the red team and the blue team that are very fixed on their objectives and they argue and they kind of, I may disagree, but it kind of seems to make it work somewhat that the duality of a [/INST] lot of </s><s>[INST] okay, let's go 100 years back when there was still was going on, or at the founding of this country, there was disagreement. And the disagreement is where uh so it was a balance between certainty and forced humility because the power was distributed. [/INST] Yeah, I think that the the nature of debate and disagreement argument takes as a premise, the idea that you could be wrong right, which means that you're not necessarily absolutely convinced that your objective is the correct one. All right. Um if you were absolutely, there'd be no point in having any discussion or argument because you would never change your mind. Um and there wouldn't be any any sort of synthesis or or anything like that. So, so I think you can think of argumentation as a as an implementation of a form of uncertain reasoning. Uh and um, you know, I I've been reading recently about utilitarianism and the history of efforts to define in a sort of clear mathematical way, eh I feel like a formula for moral or political decision making. And it's really interesting that the parallels between the philosophical discussions going back 200 years and what you see now in discussions about existential risk, because it's almost exactly the same. So someone would say, okay, well, here's a formula for how we should make decisions right? So utilitarian it is roughly, you know, each person has a utility function and then we make decisions to maximize the sum of everybody's utility, right? And then people point out, well, you know, in that case, the best policy is one that leads to the enormously vast population, all of whom are living a life that's barely worth living, right? And this is called the repugnant conclusion. And uh, you know, another version is, you know, that we should maximize pleasure and that's what we mean by utility and then you'll get people effectively saying, well in that case we might as well just have everyone hooked up to a heroin drip, you know, and they didn't use those words. But that debate, you know, was happening in the 19th century as it is now about ai that if we get the formula wrong, you know, we're going to have a i systems working towards an outcome that in retrospect would be exactly wrong. Do </s><s>[INST] you think there's has beautifully put. So the echoes are there. But do you think, I mean if you look at Sam Harris is our imagination worries about the ai version of that because of the uh, the speed at which the things going wrong in the utilitarian context could happen. Is that is that a worry for you? [/INST] Yeah, I think that, you know, in most cases, not in all. But you know, if we have a wrong political idea, you know, we see it starting to go wrong and we're you know, we're not completely stupid. And so we said okay, that was maybe that was a mistake. Uh let's try something different. And also we are very slow and inefficient about implementing these things and so on. So you have to worry when you have corporations or political systems that are extremely efficient. But when we look at AI systems or even just computers in general, right? They have this different characteristic from ordinary human activity in the past. So let's say you were a surgeon, you had some idea about how to do some operation, right. Well, and let's say you were wrong, right? That that way of doing the operation would mostly kill the patient. Well, you'd find out pretty quickly like after three, maybe three or four tries. Right? But that isn't true for pharmaceutical companies because they don't do Three or four operations. They manufacturer three or 4 billion pills and they sell them and then they find out maybe six months or a year later that people are dying of heart attacks or getting cancer from this drug. And so that's why we have the FDA right? Because of the scalability of pharmaceutical production. And you know, and there have been some unbelievably bad episodes in the history of pharmaceuticals and and adulteration of of products and so on. That that have killed tens of thousands or paralyzed hundreds of thousands of people. Now with computers, we have that same scalability problem that you can sit there and type for I equals 1 to 5 billion do right? And all of a sudden you're having an impact on a global scale. And yet we have no FDA right. There's absolutely no controls at all over what a bunch of undergraduates with too much caffeine can do to the world. And uh you know, we look at what happened with facebook, well, social media in general and click through optimization. So you have a simple feedback algorithm that's trying to just optimize click through, right? That's the sounds reasonable. Right? Because you don't want to be feeding people, adds that they don't care about. I'm not interested in. And you might even think of that process as simply adjusting the the feeding of ads or news articles or whatever it might be to match people's preferences. Right? Which sounds like a good idea. But in fact, that isn't how the algorithm works. All right. You make more money. The algorithm makes more money if it can better predict what people are going to click on because then it can feed them. Exactly that, right? So the way to maximize click perU is actually to modify the people to make them more predictable. Uh and one way to do that is to feed them information, which will change their behavior and preferences towards extremes that make them predictable, Whatever is the nearest extreme, or the nearest predictable point. That's where you're going to end up and the machines will force you there now. And I think there's a reasonable argument to say that this, among other things, is contributing to the destruction of democracy in the world. And where was the oversight of this process? Where were the people saying, Okay, you would like to apply this algorithm to five billion people on the face of the earth. Can you show me that it's safe? Can you show me that it won't have various kinds of negative effects? No, there was no one asking that question. There was no one placed between, you know, the the undergrads with too much caffeine and the human race. Well, it's just they just did it </s> |
<s>[INST] in terms of figuring out who we want to represent us. So just lingering on the AOC, and then maybe let's throw in Bernie Sanders on that. Yeah, yeah. So where do you place yourself and how do you do the layout of the land of Bernie Sanders, AOC, Joe Biden, and David Pakman? [/INST] My instinct is, and I'm going to answer it, the thing that makes this tough is, Bernie says he's a democratic socialist. He ran as a social democrat. He didn't run on anything that was really socialism. </s><s>[INST] So I'm going by their public facing platforms. I've been listening to him for many, many years and all the way back to the Tom Hartman show. And I think using the terms as you've been using them, he has, I don't think, ever been a democratic socialist. I haven't heard him speak about socialism. I think I've heard him speak about social programs and the value of social programs throughout the history of the United States [/INST] and how they've been beneficiaries. My understanding is very similar to yours, although there may be stuff from the 70s where he really was talking about- We've all did shit in the 70s, hasn't we? Yeah, you and I even, who weren't around- Yeah, I feel like we- </s><s>[INST] We were doing stuff in the 70s. We've all did shit in the 70s. We were doing stuff in the 70s though- Yeah. [/INST] Yeah, I feel like we did, yeah. My sense would be, Biden is like center left and then I'm to the left of that but maybe just inside of where AOC and Bernie are, very, very similar to Bernie. I mean, I identify with a lot of Bernie's ideas. Maybe their implementation I'm more flexible on. I'll give you one example. Medicare for All. One way of trying to get healthcare to everybody, which Bernie's very big on, is you take the current Medicare program, you just eliminate the age limit, make it available to everybody, pay for it through taxation. Interesting. However, I'm open to other models if they get everybody healthcare. That is good quality and affordable. Singapore has an interesting model. Germany has an interesting model. I am more agnostic about how we do it than just saying, let's expand Medicare. Whether that puts me to the right of Bernie, I don't know, but I'm not like exactly right there </s><s>[INST] on it has to be Medicare for All. Yeah, that's more of a, that's more just flexibility versus dogmatism. So I don't know if that puts you to the left or to the right. I don't either. What do you think about the term manipulation or the corruption in the DNC that perhaps tipped the scales against Bernie in the election? Do you think there was such a thing? [/INST] In 2016 or 20? To the right. I think there was such a thing. </s><s>[INST] In 2016 or 2020? Both, I would say. In different, the dynamics there were different with Hillary Clinton and like the pressure from Hillary Clinton as a candidate and so on. Yeah, I mean, was there, why didn't Bernie win? I guess there's one way to ask. [/INST] Okay. I think there's a couple of things here. First, the DNC, I'm not a Democrat. Just your audience may not know. I'm just a independent. I mostly vote for candidates that end up being Democrats in local elections. Often there's no party designation. So, okay, I'm obviously on the left. I'm not denying that, but the Democratic party as an institution has never really been interesting to me. </s><s>[INST] You're still a rebel that resists belonging to any institution. [/INST] Exactly right, exactly right, exactly right. And whether it matters, I don't know. The DNC and the RNC really are organizations that to some degree exist to justify their own existence. Because if they were no longer necessary, they would go away. And so they have to assert their value and their importance. They do this in a number of different ways, organizing the way that the nominee has chosen, the convention, working with states on everything from redistricting to whatever else the case may be, setting the order of primaries and having some involvement in how that's all going to happen. And also coordinating behind the scenes, I guess they would describe it as making sure our candidates don't get in each other's ways. We might see it and say they're picking the winner. There's nothing illegal about them being involved in picking the winner. But we might say it's not in people's interests. I think the 2020 primary was really interesting. Bernie's supporter, myself, I started telling my audience after a couple primaries and even before based on polling and different things, I see a real uphill battle here for Bernie. And it's really important, people in my audience are not the average union worker in Michigan who is mostly working and raising a family and then goes to vote on primary day and goes to vote on election day. If you spend a lot of time on Reddit and Twitter, you're going to have an inflated sense of Bernie's popularity within the Democratic party. That was my sense. And to some degree, we saw that in certain states. I don't have the exact primary order and results in front of me or in my head, but the big turning point was South Carolina. South Carolina was when Joe Biden won and won handily, understood to be because of the larger African-American population in South Carolina. And right around that exact same time, I actually don't remember now whether it was the day after or the day before. Some of the smaller Democratic candidates, smaller in terms of support, got out and said, I'm endorsing Joe Biden. And to some degree, of course it was all organized and timed to help Joe Biden. There's no doubt about that. This is what the DNC does. It's hard for me to be mad at the DNC because this is sort of like, if we believe they were there to be unbiased arbiters and to stay as much on the side as possible, it would make sense to be furious that they've gone against their stated kind of mandate. But we know that the DNC negotiates and is working behind the scenes and has a favorite. That favorite was Hillary in 2016, 2020. So I share the frustration about the power that the DNC has, but for people who were saying they did something illegal or whatever else the case may be, that doesn't seem to be the case. But this is part of why, I mean, I would love there not to be this duopoly of Republicans and Democrats. And there's probably four major changes that have to happen in order to make that a reality. But I share the frustration of folks while recognizing that Reddit was not accurately representing </s> |
<s>[INST] It will probably make you worse at your job. Well maybe you can think about death when you look out when you go out into nature and think like the the the fact that this whole ride ends, it's such a weird thing and the the old makes way too new and it's all throughout nature. And if you just look at the cruelty of nature or the beauty of nature, however you think about it, the fact that the the big thing, it's the little thing over and over. Um and that's just how it progresses and that's how adaptation happens. [/INST] Death is a requirement for evolution. And you know, whether evolution allows us to see objective reality or not, it still gives you some interesting thoughts about perspectives of death and especially concerning it's a biological necessity. As far as evolution is concerned, </s><s>[INST] it's weird. It's weird that it's been like 100 billion people that lived before us and that you and I will be forgotten. This whole thing we're doing is meaningless in that sense, but at the same time it feels deeply meaningful somehow. Um I guess that's the question I want to ask when you go out to nature with family, [/INST] what </s><s>[INST] do you think is the meaning of it all. What's the meaning of life or maybe when you put on the night goggles, the night vision goggles and look up at the stars, why we're here? [/INST] I can't speak for everyone, but at least the way I interpret it, you know, or at least I I feel like I interpret my way here. My job is I feel like my role is just to be curious about the environment in a manner that allows us to understand as much as possible. I think that the human mind, whether it's just the mass inside or scholar, you know, whether there's some type of quantum interactions going on. Her mind is an incredible, has incredible ability to output new information in in a universe that you know, somewhat stale of information. Right? Um our our minds are in some somewhat unique and that we can imagine and perceive things that could never ever have possibly naturally occur and yet we can make it happen. We can substantiate that with enough belief that is true and it can happen. So for me, I feel like I just need to encourage that to encourage, you know, interaction with reality such that it leads us to newer and grander. You know, interactions with this universe </s><s>[INST] and all that starts with a little bit of curiosity, right? You're an incredible person. You've done so many things and there's so much still uh still ahead of you, thank you for being brave enough to talk about UFOs um and doing it so seriously and thank you for pushing forward on all these fronts in terms of technology. So from, um, just the fighter. Just the engineering of that to the Ai Ml applications in the combat setting. That's super interesting. And then I'll Quantum, I can't wait to see to see what you do next. Thank you so much for sitting down and talking today. It was an honor. [/INST] It was my pleasure. Thank you lex. </s><s>[INST] Thanks for listening to this conversation with Lieutenant Ryan Graves. To support this podcast. Please check out our sponsors in the description and now let me leave you. Some words from Buzz Aldrin. Bravery comes along as a gradual accumulation of discipline. Thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] escaping the gravity well of ego centrism, beautifully put a beautiful way to end it, john you're a beautiful human being. Thank you for struggling in your own mind with with with the search for meaning and uh encouraging others to do the same and ultimately, to learn how to Love wisely. Thank you so much for talking today. [/INST] It's been a great pleasure. Lex. I really enjoyed it a lot. Thank you so much. </s><s>[INST] Thanks for listening to this conversation with john Verbeke to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Hermann Hesse's Siddhartha, I've always believed and I still believe that whatever good or bad fortune may come our way, we can always give it meaning and transform it into something of value. Thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] But operating in the space of concepts [/INST] concepts. The word concept was used by Alex Stepanov who is sort of the father of generic programming in the context of C. Plus plus. There's other places that use that word. But the way we call genetic programming is Alexis and he called them concepts because he said there they are the sort of the fundamental concepts of an area. So they should be called concepts. And we've had concepts all the time. If you look at the knr book about C. C has arithmetic types and it has um integral types. It says so in the book and then it lists what they are and they have certain properties. The difference today is that we can actually write a concept that will ask a type. Are you an integral type? Do you have the property is necessary to be an integral type. Do you have plus minus divide and such? </s><s>[INST] So what may be the story of concepts? Because I thought it might be part of C plus plus 11. So C C C O X. Whatever it was at the time. What was the why didn't it? What like what we'll talk a little bit about this fascinating process of standards because I think it's really interesting for people. It's interesting for me, but why did it take so long? What shapes that the idea of concepts take? Yeah. What were the challenges [/INST] back in 87 or thereabouts? </s><s>[INST] Was 27 [/INST] 1987 or thereabouts when I was designing templates, obviously I wanted to express the notion of what is required by a template of its arguments. And so I looked at this and basically for for templates, I wanted three properties, I wanted to be very flexible, it had to be able to express things. I couldn't imagine because I know I can't imagine everything and I've been suffering from languages that try to constrain you to only do what you're the designer thought good, didn't want to do that. Secondly, it had to run faster as fast or faster than hand written code. So basically, if I have a vector of key and I take a vector of char, it should run as fast as you build a vector of char yourself without prior authorization. And second. And thirdly, I wanted to be able to express the constraints of of the arguments, have proper type checking of the interfaces. And neither I nor anybody else at the time Knew how to get all three and I thought for C plus plus, I must have the two. First, otherwise it's not C plus plus, And it bothered me, found a couple of decades that I couldn't solve the 3rd 1. I mean, I was the one that put function argument type checking in to see I know the value of good interfaces, I didn't invent that idea is very common, but I did it and I wanted to do the same for templates of course and I could sew it bothered me Then we tried again 2002, capitals raised and I started analyzing the problem explained possible solutions. There was not a complete design, a group in University of indiana, an old friend of mine, they started a project at Indiana and we we thought we could get A good system of concepts in another two or 3 years that would have made C plus plus 11 to C plus plus +0607. Well, it turns out that I think we got a lot of the fundamental ideas wrong, they were too conventional. Um they didn't quite fit C plus plus in my opinion, didn't serve implicit conversions very well. It didn't serve mixed, mixed type arithmetic, mixed type competition computations very well. A lot of stuff came out of the functional community and it that community, I didn't deal with multiple types in in the same way as C plus plus, does had more constraints on on what you could express and didn't have the draconian performance requirements and basically we tried, we tried very hard, we had some successes, but it just in the end wasn't didn't compile fast enough was too hard to use and didn't run fast enough unless you had optimizers that was beyond the state of the art. They still are. So we had to do something else. Basically, it was the idea that a set of parameters has defined a set of operations and you go through an indirection table, just like for virtual functions and then you try to optimize the indirection away uh, to get performance and we just couldn't do all of that. Um, but get back to the standardization. We are standardizing C++ under ISO rules which are very open process. People come in, there's no requirements for education or experience, </s><s>[INST] the third develop C Plus Plus and there's a whole, what was the first standard established? What is that like the ISO standard, is there a committee that you're referring to? There's a group of people, What was that like? How often do you meet? What's the discussion? [/INST] I'll try and explain that. So sometime in early 1980s 9, um, two people, one from IBM, one from hp turned up in my office and told me I would like to standardize C plus plus. This was a new idea to me and I pointed out that it wasn't finished yet. It wasn't ready for formal standardization and such and they say no, Piano, You haven't gotten it. You really want to do this. Um, our organizations dependency plus plus we cannot depend on something that's owned by another corporation that might be a competitor. Of course we could rely on you, but you might get run over by a bus. </s><s>[INST] We [/INST] really need to get this out in the open. It has to be uh standardized on the formal rules and we were going to standardize it um on the S. O. Rules and you really want to be part of it because basically otherwise we'll do it ourselves. Yeah and we know you can do it better. So uh through a combination of arm twisting and flattery um Carey started. So in late In late 89 there was a meeting in D. C. At the actually no it was not. I. S. So then it was ansi the american national standard. We're doing, We met there, we were lectured on the rules of how to do an Ansi standard. There was about 25 or was there? Which apparently was a new record for that kind of meeting. Um And um some of the old see guys that has been standardizing C. Was there, so we've got some expertise in. So the way this works is that it's an open process, anybody can can sign up is they pay the minimum fee which Is about $1,000. There was less than just a little bit more now. And I think it's $1,280. It's not, it's not going to kill you. And We have three meetings a year is fairly standard. We tried to meetings a year for a couple of years that didn't work too well. So 331 week meetings a year and you meet and you have taken the meat technical discussions and then you bring proposals forward for votes. The votes are done one person per one vote per Organisation. So you can't have say IBM come in with 10 people and dominate things that's not allowed. And these </s> |
<s>[INST] There's more to it. There's more to it. It's a good question of how much more is there to it, and it seems like one of the reasons, as you imply that the reason GPT works, ChatGPT works, is that there's a finite number of things to it. Yeah, I mean, it's... [/INST] In some sense, GPT is discovering the laws of semantic grammar that underlies language. Yes. And what's sort of interesting is, in the computational universe, there's a lot of other kinds of computation that you could do. They're just not ones that we humans have cared about and operate with. And that's probably because our brains are built in a certain way, and the neural nets of our brains are not that different, in some sense, from the neural nets of a large language model. And so when we think about, and maybe we can talk about this some more, but when we think about what will AIs ultimately do, the answer is insofar as AIs are just doing computation, they can run off and do all these kinds of crazy computations. But the ones that we sort of have decided we care about is this kind of very limited </s><s>[INST] set. That's where the reinforcement learning with human feedback seems to come in. The more the AIs say the stuff that kind of interests us, the more we're impressed by it. So it can do a lot of interesting, intelligent things, but we're only interested in the AI systems when they communicate in a human-like way. Yes. [/INST] About human-like topics. Yes. Well, it's like technology. I mean, in a sense, the physical world provides all kinds of things, you know, all kinds of processes going on in physics. Only a limited set of those are ones that we capture and use for technology because they're only a limited set where we say, you know, this is a thing that we can sort of apply to the human purposes we currently care about. I mean, you might have said, okay, you pick up a piece of rock. You say, okay, this is a nice silicate. It contains all kinds of silicon. I don't care. Then you realize, oh, we could actually turn this into a semiconductor wafer and make it microprocessor out of it. And then we care a lot about it. Yes. And it's this thing about what do we... In the evolution of our civilization, what things do we identify as being things we care about? I mean, it's like when there was a little announcement recently of the possibility of a high-temperature superconductor that involved the element lutetium, which generally nobody has cared about. Yes. But suddenly, if there's this application that relates to kind of human purposes, we start to care a lot. </s><s>[INST] So given your thinking that GPT may have discovered inklings of laws of thought, do you think such laws exist? Can we linger on that? Yeah. [/INST] What's your intuition here? Yeah. What's your intuition here? Oh, definitely. I mean, the fact is, look, logic is but the first step. There are many other kinds of calculae about things that we consider about sort of things that happen in the world or things that are meaningful. </s><s>[INST] Well, how do you know logic is not the last step? You know what I mean? [/INST] Well, because we can plainly see that there are things... I mean, if you say, here's a sentence that is syntactically correct, okay? You look at it and you're like, the happy electron, eight, I don't know what, something that it just... You look at it and it's like this is meaningless. It's just a bunch of words. It's syntactically correct. The nouns and the verbs are in the right place, but it just doesn't mean anything. So there clearly is some rule that there are rules that determine when a sentence has the potential to be meaningful that go beyond the pure parts of speech syntax. And so the question is, what are those rules and are there a fairly finite set of those rules? My guess is that there's a fairly finite set of those rules. Once you have those rules, you have a kind of a construction kit, just like the rules of syntactic grammar give you a construction kit for making syntactically correct sentences. So you can also have a construction kit for making semantically correct sentences. Those sentences may not be realized in the world. I mean, I think the elephant flew to the moon, semantically, we know, we have an idea. If I say that to you, you kind of know what that means. </s><s>[INST] But the fact is it hasn't been realized in the world, so to speak. So semantically correct, perhaps as things that can be imagined with the human mind. No. Things that are consistent with both our imagination and our understanding of physical reality. I don't know. Yeah. Good question. [/INST] I mean, it's a good question. I mean, it's a good question. It's a good question. I think it is, given the way we have constructed language, it is things which fit with the things we're describing in language. It's a bit circular in the end, because you can, and the sort of boundaries of what is physically realizable, okay, let's take the example of motion. Motion is a complicated concept. It might seem like it's a concept that should have been figured out by the Greeks long ago, but it's actually a really pretty complicated concept, because what is motion? Motion is you can go from place A to place B, and it's still you when you get to the other end, right? You take an object, you move it, and it's still the same object, but it's in a different place. Now, even in ordinary physics, that doesn't always work that way. If you're near a space-time singularity in a black hole, for example, and you take your teapot or something, you don't have much of a teapot by the time it's near the space-time singularity. It's been completely deformed beyond recognition. That's a case where pure motion doesn't really work. You can't have a thing stay the same. This idea of motion is something that sort of is a slightly complicated idea, but once you have the idea of motion, you can start ... Once you have the idea that you're going to describe things as being the same thing, but in a different place, that sort of abstracted idea then has ... That has all sorts of consequences, like this transitivity of motion. Go from A to B, B to C, you've gone from A to C. At that level of description, you can have what are sort of inevitable consequences. They're inevitable features of the way you've sort of set things up. That's I think what this sort of semantic grammar is capturing, is things like that. I think that it's a question of what does the word mean when you say, I move from here to there. Well, it's complicated to say what that means. This is this whole issue of is pure motion possible, et cetera, et cetera, et cetera. Once you have kind of got an idea of what that means, then there are inevitable consequences of that idea. </s> |
<s>[INST] Yes, but do you think there's a hope for pockets of computational reducibility? computational Reducibility reducibility. Yes, that's yes. So and then and then a set of tools and mathematics that help you discover such pockets [/INST] That's that's where we live is in the pockets of reducible. It's right That's why you know And this is one of the things that sort of come out of this physics project and actually something that again I should have realized many years ago, but didn't Is you know the it could very well be that everything about the world is computationally irreducible and completely unpredictable but you know in our experience of the world, there is at least some amount of prediction we can make and that's because we have sort of chosen a slice of Probably talk about this in much more detail But I mean we've kind of chosen a slice of how to think about the universe in which we can kind of sample a certain amount of computational reducibility and that's that's sort of where we where we exist and It may not be the whole story of how the universe is but it is the part of the universe that we care about and we sort of operate in and That's you know in science That's been sort of a very special case of that that is science has chosen to talk a lot about places where there is this computational reducibility that it can find you know, the motion of the planets can be more or less predicted, you know, the Something about the weather is much harder to predict something about you know Other kinds of things the the are much harder to predict and it's some These are but science has tended to you know concentrate itself on places where its methods have allowed successful prediction </s><s>[INST] So you think rule 30 if it could linger on it? Because it's just such a beautiful simple formulation of the essential concept underlying all the things we're talking about [/INST] Do you think there's pockets of reducibility inside rule 30? Yes That is the question of how big are they? What will they allow you to say and so on and that's and figuring out where those pockets are I mean in a sense, that's the that's sort of a You know, that is an essential thing that one would like to do in science But it's it's also the important thing to realize that that has not been you know Is is that science, if you just pick an arbitrary thing you say, what's the answer to this question? That question may not be one that has a computationally reducible answer that question if you if you choose You know if you walk along the series of questions and you've got one that's reducible and you get to another one It's nearby and it's reducible too If you stick to that kind of stick to the land so to speak unique, then you can go down this chain of sort of reducible, answerable things. But if you just say, I'm going to just pick a question at random, I'm going to have my computer pick a question at random. Most likely it's going to be reducible. Most likely it will be irreducible. We're thrown in the world, so to speak, when we engineer things, we tend to engineer things to sort of keep in the zone of reducibility. When we're thrown things by the natural world, for example, not at all certain, that we will be kept in this kind of zone of reducibility. </s><s>[INST] Can we talk about this pandemic then? Sure. For a second. So how do we, so there's obviously huge amount of economic pain that people are feeling, there's a huge incentive and medical pain, health, just all kind of psychological, there's a huge incentive to figure this out, to walk along the trajectory of reducible, of reducibility. There's a lot of disparate data, you know, people understand generally how virus is spread, but it's very complicated because there's a lot of uncertainty, there's a, there could be a lot of variability, also like so many, obviously a nearly infinite number of variables that, that represent human interaction, and so you have to figure out, from the perspective of reducibility, figure out which variables are really important in this kind of, from an epidemiological perspective. So why aren't we, you kind of said that we're clearly failing. [/INST] Well, I think it's a complicated thing. So, so, I mean, you know, when this pandemic started up, you know, I happened to be in the middle of a being about to release this whole physics project. Yes. </s><s>[INST] But I thought, you know, I mean, I mean, is just cosmically- [/INST] A little bit bizarre, yeah, but Abdata, but you know, but I thought, you know, I should do the public service thing of, you know, trying to understand what I could about the pandemic. And, you know, we'd been curating data about it and all that kind of thing. But, you know, so I started looking at the data and started looking at modeling and I decided it's just really hard, you need to know a lot of stuff that we don't know about human interactions. it's actually clear now that there's a lot of stuff we didn't know about viruses and about the way immunity works and so on. I think what will come out in the end is there's a certain amount of what happens where you just kind of have to trace each step and see what happens. There's certain amount of stuff where there's going to be a big narrative about, this happened because of T-cell immunity. This happened because there's this whole giant field of asymptomatic viral stuff out there. There will be a narrative. And that narrative, whenever there's a narrative, that's a sign of reducibility. But when you just say, let's from first principles figure out what's going on, then you can potentially be stuck in this mess of irreducibility, where you just have to simulate each step and you can't do that unless you know details about human interaction networks and so on and so on and so on. The thing that has been very frustrating to see C is the mismatch between people's expectations about what science can deliver and what science can actually deliver, so to speak. Because people have this idea that it's science. So there must be a definite answer and we must be able to know that answer. And after you've played around with sort of little programs in the computational universe, you don't have that intuition anymore. I'm always fond of saying, you know, that the computational animals are always smarter than you are. That is, you know, you look at one of these things and it's like, it can't possibly do such and such a thing. Then you run it and it's like, wait a minute, it's doing that thing. How does that work? </s> |
<s>[INST] No, but she's not, that's what I'm saying. My worry isn't my worry isn't uh saying that the election was illegitimate and people whining and mass scale and and then uh Fox News or CNN reporting for years or books being written for years. My worry is legitimately martial Law, a person's stays president. [/INST] So here's the issue like there's a there's a should I get a book on North Korea. I'm not someone who thinks dictatorship should be taken lightly. I'm not someone who thinks it can't happen here. I think a lot of times people are desperate for dictatorship. So I'm with you and I think this is something if you're going to hand wave it away. Everyone else hand waved it away. Hitler is never gonna be chancellor. He's a lunatic. He's a joke is a joke. They they couldn't find a publisher for mine confident english because this is some guy from some random minor party in Germany spouting nonsense, who's going to read this crap, you know, so I I completely agree with you and you don't think we're there. My point is donald trump this year had every uh pathway opened him to declare martial law. The cities are being burnt down. He could have very easily sent in the tanks. Uh, and people would have been applauding him from his side </s><s>[INST] feels so good right now. [/INST] But am I wrong though? Know what he did? He tweeted out to Mayor wheeler of Portland, he said call me, we will, we will solve this in minutes, but you have to call. And he sat in his hands and they said, oh it's his fault, the cities burning down. He's not doing anything. And he goes, I'm not doing anything until you asked me to do it. So I think that is even if you think he's an aspiring dictator, that is at least a sign that there is some restraint on his aspirations. </s><s>[INST] Can I just take that in as a beautiful um, like moment of hope. So I'm going to remember this moment. [/INST] Beautiful Dead. I'm </s><s>[INST] gonna remember that. I mean, uh, I should say that perhaps I'm irrationally this is the one moment where I feel myself being a little, [/INST] I don't think professional. I think there's a symmetry because it's kind of like, okay, either if I leave the house, it's like Russian roulette. Yeah, maybe it's like a one in six shot, I'm pulling the trigger, I'm killing myself, but that's one in six that's not and and the consequences are so dire that a little paranoia would go a long </s><s>[INST] way. There's [/INST] something that you can't go back. </s><s>[INST] Yeah, [/INST] it's an asymmetry </s><s>[INST] and the thing is the thing that makes donald trump new to me. And again, I'm a little naive in these things. But he surprised me in how many ways he just didn't play by the rules and he's made me a little ant and this ant colony think like, well do you have to play by the rules at all? Like why are we having elections? Why just say like its coronavirus time? Like it's it's not healthy to have elections. Like, we shouldn't be like I could if I put my dictator had on [/INST] Pelosi said that joe biden shouldn't debate. </s><s>[INST] Yeah. Did she? Yes, [/INST] she says she shouldn't dignify trump with a debate. He's the president, He could be the worst president earth, evil, despicable monster. I'll take that as an argument. </s><s>[INST] So she's playing politics. But she's [/INST] I don't think that's playing politics. I think when there's a certain point, when things get when things get when you start attacking institutions for the emergency at the moment and acting arbitrarily that is when things are the slippery </s><s>[INST] slope. So you're saying debates is one of the institutions like that's one of the traditions to have the debates. I think [/INST] the debates are extremely important. Uh now I don't think that someone's a good debater is going to make a good president. I mean, that's that's a big problem, </s><s>[INST] but you're just saying this is attacking just yet another tradition yet [/INST] Another, you know, like how if you're dating if you're married to someone and someone throws out the word divorce, you can't unring that bell. You threw it out there. I'm saying you don't throw things out like that unless you really are ready to go down this road. And I think that is, there's nothing in the constitution about debates. We've only had them since 1980, but still, I think they are extremely important. It's also a great chance for joe biden to tell him to his face. You're full of crap. Here's what you did. Here's what, here's what you did. So </s><s>[INST] fascinating that you're both, you acknowledge that. And yet you also see the value of tearing down the entire thing. So you're both worried about no debates or at least in your voice in your tone. [/INST] There's a great quote by Chesterton. I'm not a fan of hips at all. But he says before you tear down the fence, make sure you know why they put it up first. So I am for tearing it all down. But there's something called a controlled demolition, like building seven. or there we knew we were in tel Aviv, um, </s><s>[INST] and hashtag clothing seven. We knew we were in telling you why you're faster than me. You're operating at a different level. I need to upgrade my operating system. I told you. Windows 95. Yeah. [/INST] Um, </s><s>[INST] uh, so if [/INST] you're gonna, uh, it's like indiana jones, right? If you're gonna pull something away, make sure you have something in place first as opposed to breaking it. And then just especially in politics, it's because it escalates and when things escalate without any kind of response, it can go in a very bad that's when napoleon comes in. </s> |
<s>[INST] he's one of the great ceos because everybody loves him. Everybody loves him. Have [/INST] you interviewed him? </s><s>[INST] No but we'll do the interview eventually. So is this annoying thing about me being a stickler for three hours Ceos don't seem to understand. Like not understand but it's scheduling. So what happens is Saunders said yes definitely let's do it. I'm a fan of podcasts as a fan of yours. And and and then he goes to his executive assistant like oh let's find a slot and then they immediately think, alright well one hour, [/INST] that's good. Five </s><s>[INST] minutes, 90 [/INST] minutes, 90 </s><s>[INST] minutes. Yeah, right well no they know in person I'm sticking on that but like it's like no we need more and it's so hard to, to do, [/INST] you still travel to do your podcast or general, </s><s>[INST] most people come down here, most people uh but for certain situations obviously um like if you're in prison right or you're ahead [/INST] of you get out on work for a lot of people have anklets so that they can go down the lex Friedman pocket. That probably happened. Have you ever been in a prison? </s><s>[INST] No, [/INST] you know </s><s>[INST] either visitation or on the inside [/INST] from my hike I can see san Quentin, it's really weird that san Quentin and Alcatraz, you know Bay Area beautiful. Everyone thinks like you know like there's the bay and there's a Alcatraz and san Quentin sitting right there. Um you know it's amazing how easy it is to overlook that they're there and forget that they're there. But when I drive by san Quentin I think about it. Um I also think about the people who are in there who might be innocent. I've seen some of those episodes on Rogan and elsewhere. Amanda Knox talks a lot about this right? Whether or not you believe her story or not I happen to believe her story personally based on what I know um what, you know, I'm sure there are people disagree with me. I think to myself what it must be like to be in a cell and know in your hearts heart you didn't do it, you know, I mean I can't think of, I can't think of many things worse, I can't think of many things worse. </s><s>[INST] That's so clearly unjust. But life is full of unjust. Things like this, cruel things happen all the time. You lose a loved one for no good reason, you lose your job. Um you lose your home. Yeah, I've been talking to a lot of refugees now and the war in Ukraine has really focused my mind to how much suffering there is in the world and so just cruel things happen all the time and and people kind of there's this suffering and you you kind of go on, you stick to the people really close to you, there's still love all around you, traumatic events kind of focus your mind on this. Like very practical. Like okay, how do we solve the problem? How do we escape? Let's salt, like survival food, shelter [/INST] focus. Remember that book. Um all's Quiet on the Western Front by World War One. There's this line in there. I forget what it is about how war is like the smell of a skunk like a little bit is actually a little bit is slightly um there's something slightly delicious of it is what it says in the in the book. Um I happen to like the smell of like ferrets and skunks and things. I had a pet ferret when I was a kid, and I like that musky scent. People, most people just it's repulsive to them. It's actually a gene, believe it or not, Some people have the gene that makes that the musky scent repulsive. Some people love it. Um Let me ask you this, there's another gene, this is a fun one. Um microwave popcorn smells good, neutral or disgusting to </s><s>[INST] you. [/INST] There are people who have a gene that leads them to the perception that the smell of microwave popcorn that you find is good, it smells like putrid vomit to them. It's a particular gene variant, and they can smell certain elements within the microwave popcorn. Um It's pretty, it's prominent in France the this gene. And um so in laboratories where uh you have a lot of french people, it's often said like, you're not allowed to make microwave popcorn smells putrid, disgusting, you know, so a lot of it's in the perception of the beholder, right? Uh </s><s>[INST] But, okay, well, before I leave, the N str is uh focus in general, he said, it's for shifting mind states is their advice you have for how to achieve focus on a task. [/INST] Yes. First of all, we have to distinguish between modulators and mediators and I'll do this very briefly, there are a lot of things that will modulate your state of focus, but they don't directly mediate your sense of focus. So for instance if right now a fire alarm went off in this building, it would modulate our attention, we would get up and leave, it would be very hard to do what we're doing with that banging in the background at least at first. So it's modulating focus, but it's not really involved in the mechanisms of focus right in the same way being well rested when you sleep, your autonomic nervous system that adjusts states of alertness and focus and calm works better than when you're sleep deprived. So if you're sleeping better, you're going to focus better. So I always answer this way uh to a question like this because the best thing that anyone can do for their mental health, physical health and performance in athletic or cognitive endeavors or creative endeavors is to make sure that you're getting enough quality sleep, enough of the time for you and that's going to differ. We could talk about what that means now in terms of things that mediate focus without getting in the description of mechanisms because we have podcasts about that, it's very clear that mental focus follows visual focus provided that you're a sighted person. Mhm. Much of the training that's being done now in china to teach kids to focus better, literally has them stare at a target blinking every so often but really training themselves to breathe calmly and maintain a tight visual aperture when you read. You have to maintain a tight visual aperture, you're literally scrolling like a highlighter in your mind's eye right, it's kind of obvious once you hear it. So for people that have problems focusing sleep well learn to dilate and contract your visual field consciously. This can be done if you practice it a little bit and then as I said before it is very hard to get into a state of focus like a step function immediately like snapping your fingers. What you can do is you can pick any object but ideally an object at roughly the same distance, placed it roughly the same distance to which you're going to do that work and stare at it. You're allowed to blink and as your mind starts to drift every once in a while to understand that's normal but try and narrow your visual aperture and bring that into your Visual field so that that's the most prominent thing. Kind of like portrait mode in your phone this would look very different in portrait mode than it would in just a standard photograph mode. And then after doing that for 30 to 60 seconds moving into the work that you're about to do and really encourage yourself to do that. If you're somebody who's low vision or no vision you're gonna use your ears to do this braille readers have trouble focusing sometimes because they feel other stuff and they hear other stuff so you learn to adjust that aperture consciously. And then of course the pharmacologic tools just enough caffeine but not too much right. Um We talked about white noise, brown noise music or no music really varies, but it's very clear that binaural beats of 40 hertz can shift the brain into a heightened state of focus and cognition. So if you're going to use binaural beats, which should definitely be used with headphones and there are number of free apps out there and sources uh 40 hertz seems to be the frequency that best supports the brain shifting into a particular. </s> |
<s>[INST] He can express himself. I'm sure in the way that you know him as over coffee too, it just requires um like a focus of remembering of like a deep focus of connection, that's why like when I interact with folks Mhm. Um it's so draining for me because I'm putting all my whatever weapons I got in terms of like deeply trying to understand the person in front of me and doing that dance of human interaction, the humor, the intense kind of delving into who they are. Um So which requires like navigating around like small talk type of stuff and and just like compliments and so on in general, like people depending on the culture, depending on the place, they'll sometimes flower stuff was smiling and like compliments, like oh yeah, I love you, this is great, like this, that's all great, but you want to get to the core of like what are the demons in the closet, let's talk about it, you know? And that could be exhausting. That can be really exhausting. So from a Leonard cohen perspective you get more and more famous, it can be hard sometimes because he probably is also an introvert. [/INST] Oh yeah, I know he was an introvert because he actually tweeted about my book when it came out. Um So that was a precious moment for me. Something about we should all be listening to the quiet, I can't remember exactly what he said. Um But yeah, yeah, he definitely was, </s><s>[INST] he struggled with depression, which I wonder if that's something that's also connected to introversion? Um but perhaps not actually. Perhaps that they're very disjointed and also it's [/INST] connected to sensitivity and many sensitive people are introverts. So it's kind of like a Venn </s><s>[INST] diagram about [/INST] 80% of highly sensitive people are introverted but then some are extroverts and then not all introverts are sensitive so it's complicated but he was definitely a sensitive type. Well </s><s>[INST] there's on top of that you see like the percent of artists relative to the average. I suffer from depression. So creative people is very high. Crazy. [/INST] Yeah. And then the number of artists and successful artists who were orphaned when they were young who lost one parent or both parents like an astronomical number. I have it in the book and remember the percentage but huge and he was one of them. He lost his father When he was nine and his first act of poetry was was he took, his father made suits. That's why I thought of him when we were talking about you in your suit. And and he took one of his father's bow ties and wrote a poem in his honor and buried the poem and the bow tie in the backyard. And that was like his first creative act. </s><s>[INST] You know that song um Chelsea Hotel #2 [/INST] where he </s><s>[INST] met I guess it's about Janis [/INST] Joplin, Joplin </s><s>[INST] uh what a fun, intense and cruel person she is. [/INST] Yeah. </s><s>[INST] Uh I guess um have [/INST] you ever seen, I'm sorry to interrupt you but have you ever seen his son Adam Conan and Lana Del Rey perform that song together? </s><s>[INST] Oh no, it's [/INST] incredible. I have to send it to you. </s><s>[INST] Yeah. So that for people who don't know, I don't, I mean maybe, I don't know it goes. I remember you well in the Chelsea hotel you're talking so brave and so sweet giving me head on the unmade bed while the limousines wait in the street. There's a good line in there about um about being ugly. [/INST] Oh yeah, we are ugly. But we have the music. </s><s>[INST] No, before that from a guy's perspective it was [/INST] oh you told me again you preferred handsome men but for me you would make an exception. Yeah. So good. Well she </s><s>[INST] continued that threat in later because I think she said that he was lousy in bed. [/INST] Is that right? </s><s>[INST] Yeah. She publicly said that. Which is like man, they're just okay for people that don't know. I think this is a true story about them interacting and and being together for a very brief time. I don't know dating but just connecting falling in love [/INST] or </s><s>[INST] in this only in this very particular way that I think famous musicians poets can can which is like it's impossible for that kind of thing to last. But they did for a brief um moment is like a sadness to it because it's so momentarily but it's so [/INST] epic </s><s>[INST] that these two paths cross and then you just look at that we know these famous people and it's it's interesting to watch [/INST] and you don't even have the impression that they're thinking it's going to last. They more know that it's like a blaze of an intersection and the you know, the limousine is already waiting while they're in the moment in the middle of it and then it's done. Um Yeah </s><s>[INST] but he's [/INST] talked about how his music, he said he said something like some people are more inclined to say hello with their music but I'm rather more valedictory. That's what he said </s><s>[INST] like [/INST] saying goodbye. Like the Victorians address </s><s>[INST] interesting, [/INST] you know, so many of the songs really are about some form of partying or goodbye or an imperfection or something or like the broken hallelujah. Um </s><s>[INST] But the [/INST] thing that's so incredible about him is is the way that he's taking all of that and pointing it in the direction of transcendence. Like it's not it's not just pure sadness, it's sadness and beauty and that's the thing. </s><s>[INST] Yeah, there is a feeling of transcendence and a lot of the songs, it's like sadness and transcendence. You're right, it's a goodbye but you're moving on to some bigger thing but in a in a sort of ethereal way. Like not like a proud arrogant way. [/INST] Yeah. So his favorite poet was Garcia Lorca, he actually named his daughter after him, his daughter's name is Lorca. And </s> |
<s>[INST] You will love it. And now here's my conversation with richard crib from your perspective. Can you summarize the important events around this amazing saga that we've been living through of Wall street bets the subreddit and Gamestop and in general, just what are your thoughts about it? From technical to the philosophical level? [/INST] I think it's amazing. It's like my favorite story ever. Like when I was reading about, I was like, this is the best. Um and it's, it's also, you know, connected with my company, which we can talk about. But what I liked about it is like I like decentralized coordination and looking at the mechanisms that these are Wall Street bets users used to hype each other up to get excited to prove that that they bought the stock and they're holding. Um and and then also to see that how big of an impact that that decentralized coordination had. Um it really was a big deal. </s><s>[INST] Were you impressed by the distributed coordination? The collaboration amongst like, I don't know what the numbers are. I know numerous looking at the data after all of this is over and done. It'll be interesting to see like from uh a large scale distributed system perspective to see how everything played out. But just from your current perspective, what we know is it obvious to you that such incredible level of coordination could happen where a lot of people come together and distributed sense. There's an emergent behavior that happens after that? [/INST] No, it's not at all obvious. And one of the reasons is the lack of kind of like credibility to coordinate with someone you need to kind of make credible contracts or incredible claims. So if you have um a user name on our Wall Street bets, like some of them are like, deep sucking value </s><s>[INST] is one of them is an actually user name, by the way we're talking about, there's a website called Reddit and their subreddit on it, and a lot of people mostly anonymous, I think for the most part, anonymous uh can create user accounts and then can then just talk on form like style boards. You should know what Reddit is. If you don't know what Reddit is, check it out. Uh If you don't know what red is, maybe go to uh the awesome subreddit first a w w with cute pictures of cats and dogs, that's my recommendation anyway. [/INST] Yeah, that would be a good start to read it. When you, when you get into it more, go to our Wall Street bets </s><s>[INST] gets dark quickly, we'll probably talk about that too. Uh So so yeah, so there's these users and it's there's no contracts, like you're saying there's [/INST] no contracts, the users are anonymous. Um But there are little things that that do help. So for example, if you've posted a really good investment idea in the past that exists on Reddit as well, and it might have lots of up votes. Um And that's also kind of like giving credibility to your next to your next thing. Um, and then they are also putting up screenshots like this, this is the, these I here's the trades I've made and here's a screenshot now. You could fake the screenshot, But um, but but still, it seems like if you've got a lot of Karma and you've had a good performance on the, on the community, it somehow becomes credible enough for other people to be like, you know what? He actually probably did put $1 million dollars into this and you know what, I can, I can follow that trade easily. </s><s>[INST] And there's a bunch of people like that. So you kind of uh, integrating all that information together yourself to see like, huh, there's something happening here and then you jump onto this little boat of like behavior like we should buy the stock or sell the stock and then another person jumps on another person jumps on and all of a sudden you have just a huge number of people behaving in the same direction. It's like flock of whatever birds, [/INST] exactly what was strange with this one? It wasn't just, let's all buy Tesla, we love Ellen, we love Tesla. Let's let's all buy Tesla because that we've heard before, right? Everybody likes. Um, Tesla now they do. Um, so what they did with us. In this case, they're buying a stock. That was bad. They're buying it because it was bad and that's really weird because that's a little bit um two galaxy brain for for a decentralized community. Um How did they come up with it? How do they know that was the right one? And the reason they liked it is because it had really, really high short interest, it had been shorted uh more than its own float, I believe. Um And so they figured out that if they all bought this bad stock, they could short squeeze some hedge funds and those hedge funds would have to capitulate and buy the stock at really, really high prices. </s><s>[INST] And we should say that short, it means that these are a bunch of people when you short a stock, you're betting on the, on your predicting the stock is going to go down and then you will make money if it does, and then uh what's the short squeeze? [/INST] It's really that if you, if you are a hedge fund and you take a big short position in a company, um there's a certain level at which you can't sustain holding that position, uh there's no limit to how high a stock can go, but there is a limit to how low it can go, right? So if you short something, you have infinite lost potential. And if the stock doubles overnight, like Gamestop did um you're putting a lot of stress on that hedge fund and that hedge fund manager might have to say, you know what I have to get out of the trade. And the only way to get out is to buy the bad stock that they don't want, like they believe will go down. Uh, so it's an interesting situation, particularly because It's not zero sum. If you say, let's, let's all get together and make a bubble in watermelons, You buy a bunch of watermelons, the price goes up, comes down again. It's a, it's a, it's a zero sum game. If someone's already shorter to stock and you can make them short squeeze, it's actually a positive sum game. So yes, some creditors will make a lot of money, some will lose a lot, but actually the whole group will make money and that's really, uh, that's really why it's, it was such a clever thing for them to do </s><s>[INST] a couple due to the fact that shorting, I mean maybe you can push back, but to me always, from an outsider's perspective, seemed hope I'm not using too strong of award, but it seemed almost unethical, Maybe not unethical. Maybe it's just the asshole thing to do. It's okay. I'm speaking not from an economics or financial perspective, I'm speaking from just somebody who loves, I'm a fan of a lot of people, I love celebrating the success of a lot of people. And this is like the stock market equivalent of like haters. I know that's not what it is. I know that there's efficient you want to have in the economy efficient mechanism for punishing, uh sort of overhyped overvalued things, that's what short and guess is designed for. But it just always felt like these people are just because they're not just betting on the loss of the company, it feels like they're also using their leverage and power to manipulate media or just to write articles or just to hate I knew on social media, then you get to see that with the mask and so on. So so this is like the man, so people like hedge funds that were shorting are like the sort of embodiment of the evil or just the bad guy, the over powerful that's misusing their power and here's the crowd, the people there standing up and rising up. So it's not just that they were able to collaborate on Wall Street bets to sort of effectively make money for themselves. It's also that this is like a symbol of the people getting together and fighting the centralized elites the powerful and that, you know, I don't know what your thoughts are about that in general at this stage, it feels like that's really exciting that people have power, just like regular people have power at the same time. It's scary a little bit because, you know, just studying history, people could be manipulated by charismatic leaders and so like uh just like Ellen right now is like manipulating, encouraging people to buy dodge coin or whatever the like there can be good charismatic leaders and that could be bad charismatic leaders. And so it's nerve racking. It's it's a little bit scary how much power subreddit can have to uh destroy somebody because right now we're celebrating there might be attacking or destroying somebody that everybody doesn't like. But what if they attack somebody that is actually good for this world? So that and that's kind of the the awesomeness and the price of freedom. It's like it could destroy the world or can save the world, but at this stage it feels like, I don't know, overall when you sit back, do you think this was just a positive wave of emergent behavior because there's something negative about what happened? [/INST] Well, yeah, the cool thing is the they weren't doing anything. The red of people weren't doing anything exotic. It was it was a creative trade, but it wasn't exotic. It wasn't it was just buying the stock. Okay, maybe they bought some options to, but um it was the hedge fund that was doing the exotic thing. Um So I like that. It was it's hard to say, well, you know, we've got together and we put all pooled all our money together and now there's a company out there that's worth more, what's wrong with that, right? But it doesn't talk about, you know, the motivations which is and then we destroyed some hedge funds and process, </s><s>[INST] is there something to be said about the humor and I don't know, the edginess sometimes viciousness of that subreddit? I haven't looked at it too much, but it feels like people can be quite aggressive on there. So is there, what is that? Is that what is that what freedom looks like? [/INST] I think it does. Yeah. You definitely need to let people, The one of the things that people have compared it to is the Occupy Wall Street, which is let's say, you know, some very sincere liberals like 23 years old, whatever and they go out and with signs and they have some kind of case to make. Um, but this isn't sincere uh really? Um it's like um a little bit more nihilistic, a little bit more YOLO. Um, and therefore a little bit more scary because he's scared of the who's scared of the Wall Street occupy Wall Street, people with the science nobody but these hedge funds really are scared. I was scared of the of the Wall Street bets people, I'm still scared of them. </s><s>[INST] Yeah. The anonymity is a bit terrifying and exciting. Yeah, I mean, yeah, I don't know what to do this. You know, I've been following events in Russia for example. It's like there's a struggle between centralized power and the distributed it. I mean that's the struggle of uh the history of human civilization, right? But this on the internet just that you can multiply people like some of them don't have to be real. Like you can probably create bots? Like it starts getting me as a programmer. I start to think like me is one person, how much chaos can can I create by writing some bots? Yeah. And I'm sure I'm not the only one thinking that, uh, there's, I'm sure there's hundreds, thousands of good developers out there listening to this, thinking the same thing and then as that develops further and further in the next decade or two, what impact does that have on financial markets? On just destruction of reputations of just or politics? You know, the bickering of left and right political discourse, the dynamics that being manipulated by, you know, people talk about like, Russian bots or whatever. We're probably in the very early stage of that. Right? [/INST] Exactly. </s><s>[INST] And uh, this is a good example. Do you have, do you have a sense that most of Wall Street bets folks are actually individual people, Right? That that's the feeling I have, is they're just individual, maybe young investors doing a little bit of an investment, but it's just on a large scale. [/INST] Yeah, exactly. The reason I found out I've known about Wall Street bets for a while, but the reason I found about Gamestop was just, I met somebody at a party who told me about it and he was like 21 years old and he's like, it's going to go up 100% in the next one day </s><s>[INST] we're talking about last year. [/INST] This was probably know this was yeah, a few days ago. Not. Yeah, it was like maybe um Maybe two weeks ago or something? Um so it was, it was already high game stuff. Um but it was just strange to me that there was someone telling me at a party um how to trade stocks, he was like 21 years old. Um and uh and it started, yeah, I started to look into it and Yeah, he and he did make, he made it, I made 140% and one day he was right, and now he's um, you know, supercharged. He's a little bit wealthier, and now he's gonna look wait for the next thing and this decentralized entity is just going to get bigger and bigger </s><s>[INST] and they're gonna together search for the next thing. So there's thousands of folks like him and they're going to probably search for the next thing to attack people that have power in this world, that sit there with power right now in government and in finance in any kind of position are probably a little bit scared right now. And honestly, that's probably a little bit good. It's dangerous, but it's good. [/INST] Yeah, it certainly makes you think twice about shorting. It certainly makes you think about putting a lot of money into a short, like these funds, put a lot into 11 or two names. And so it was very, very badly risk managed, </s><s>[INST] do you think shorting is uh can you speak at a high level just for your own as a person? Is it good for the world? Is it good for markets? [/INST] I do think that the two kinds of shorting. Evil shorting and chill. </s><s>[INST] Shorten [/INST] evil shorting is what Melvin Capital was doing. Um uh And it's like you put a huge position down, you get all your bodies to also short it and you start making press and trying to bring this company down. Um And I don't think in some cases there you go out after like fraudulent companies. This company is a fraud maybe that's okay like some but they weren't even saying games, I was just saying it's a bad company and we're gonna bring it to the ground, bring it to its knees. Um A quant fund like new Marie, We always have lots of positions and we never have a position that's like more than 1% of our fund. So we actually have right now. 250 shorts. Um I don't know any of them except for one because it was one of the meme stocks. But uh but it we shorting them not to make them go, we don't even want them to go down necessarily. That doesn't sound a bit strange to say that but we just want them to to not go up as much as our lungs right? So by shorting a little bit, we can actually go long more in the things we do believe in. So when we were going long and Tesla, we could do it with more money than we had because we borrow from banks who would lend us money because we had longs and shorts because we didn't have market exposure. You have market risk. And so I think that's a good thing because that means, um, you know, we can short the oil companies and go long Tesla and make the future come forward faster. And I do think that's not a bad thing. </s><s>[INST] So we talked about this incredible distributed system created by Wall Street bets and then there's a platform which is Robin Hood, which allows investors to efficiently as far as you can correct me if I'm wrong, but you know, there's those and there's others in this new Marie that allow you to make it accessible for people to invest. But uh, that said, Robin Hood was uh, in a centralized way applied its power to restrict trading on the stock that we're referring to. Uh, do you have a thought on actually like the things that happened? I don't know how much you were paying attention, uh, to sort of the shadiness around the whole thing. Do you think it was forced to do it? Was there something shady going on? What are your thoughts in general? [/INST] Well, I think I, I want to see the alternate history, like I want to see the counterfactual history of them not doing that? How bad would it have gotten for hedge funds? How much more damage could have been done if the momentum of these short squeezes could continue. Um What happens when there are short squeezes? Uh even if um there in a few stocks they affect kind of all the other shorts too. And suddenly um brokers are saying things like you need to put up more collateral. So we had a short, it wasn't Gamestop, luckily Blackberry and it went up like 100% in the day. Was one of these meme stocks. Super bad company. The A I don't like it. Okay. They, I think it's going down </s><s>[INST] what's a meme [/INST] stock? A meme stock is kind of a new term for these stocks that catch a medic momentum on Reddit. Um And so the meme stocks were Gamestop, the biggest one, Game stunk. Ellen calls it AMC um and Blackberry was one Nokia was one. So these are high short interest stocks as well. So they are targeted stocks that some people say, isn't it? Isn't it adorable that these um these people are investing money in these companies that are, you know, nostalgic. It's like you're going to the AMC movie theater. It's like nostalgic. It's like, no, it's not why they're doing it. It's that they had a lot of short interest, That was the main thing. And so they were high chance of, of short squeeze </s><s>[INST] in saying I would love to see an alternate history. Do you have a sense that that what does your prediction of what that history would have looked like? [/INST] Well, you wouldn't have needed very many more days of that kind of chaos to hurt hedge funds. Um, I think it's underrated how, how damaging it could have been because when your short go up, your collateral requirements for them go up. Similar to Robin Hood, like we have a prime broker that says said to us, you need to put up, you know, like $40 per, per $100 of short exposure. And then the next day is that actually you have to put up, you know, all of it 100%. And we were like, what? Um, but if that happens that if that happens to all the short, all the commonly held hedge fund shorts because they're all kind of holding the same things. If that happens, not only do you have to cover the short, which means you're buying the bad companies, you need to sell your good companies in order to cover the short. So suddenly, like all the good companies, all the ones that hedge funds like are coming down. And although all the ones that the hedge funds hate are going up in a cascading way. So I believe that if you could have had a few more days of game stock doubling, AMC doubling, you would have had more and more hedge fund de leveraging. </s><s>[INST] So hedge funds, I mean, they get a lot of ship, but they do you have a sense that they do some good for the world. I mean, ultimately. So, okay, first of all, Wall Street bets itself is kind of distributed hedge fund. New Marie is a kind of hedge fund. So like hedge fund is a very broad category. I mean, like if some of those were destroyed, would that be good for the world or would there be coupled, would the the destroying the evil shorting? Will there be just a lot of pain in terms of investment in good companies? [/INST] Yeah. The thing I like to tell people if they hate hedge funds is I don't think you want to rerun american economic history without hedge ones. </s><s>[INST] So on mass they're yeah, they're good. [/INST] Yeah. You really wouldn't want to uh because hedge funds are kind of like picking up there, making liquidity right? In stocks. And so if you like, if you love venture capitalists, they're investing in new technology. So good. You have to also kind of like hedge funds because they're the reason venture capitalists exists because the companies can have a liquidity event when they go to the public markets. So it's kind of essential that we have them. There are many different kinds of them. I believe we could maybe get away with only having an ai hedge fund. Um, but we don't necessarily need these evil billions type hedge funds that make the media and try to kill companies, but we definitely need headphones </s><s>[INST] maybe from your perspective because you run uh such an organization and uh Vlad, the ceo of Robin Hood sort of had to make decisions really quickly, probably had to wake up in the middle of the night kind of thing. Uh you know, and he also had a conversation with Elon musk on clubhouse, which I just signed up for. It was it was a fascinating one of the great journalistic performances of our time with Elon musk, surprised [/INST] how hilarious would it be if you get the post? Uh </s><s>[INST] and then his Wikipedia would be like journalist and uh part time entrepreneurs uh business. Uh you know, I don't know if you can comment on any aspects of that, but like if you were glad, how would you do things differently? What do you just thoughts about his interaction with Ellen? How he should have played it differently? Like I guess there's a lot of aspects of this interaction, one is about transparency. Like how how much do you want to tell people about? Really what went down there's N. D. A. S potentially involved. Uh how much I'm in private do you want to push back and say no fuck you to centralize power? Whatever the phone calls you're getting, which I'm sure he's getting some kind of phone calls that might not be contractual, like it's not contracts that are forcing him but he was being uh what do you call it? Like pressured to behave in certain kinds of ways from all kinds of directions. Like what, what do you take from this whole situation? [/INST] I was very excited to see Vlad response. I mean it's pretty cool to have him talk to Ellen and one of the things that struck me in the first like few seconds I Vlad speaking was like, I was like, is Vlad like a boomer like here we are. Like he seemed like a 55 year old man talking to a 20 year old. Ellen was like the 20 year old and he's like the 55 year old man, You can see why citadel are anymore buddies, right? Like you can, you can see what it's like, this is, this is a nice, I'm not such a bad thing. It's like, he's, it's like he's got a like a respectable professional attitude. </s><s>[INST] Well he also tried to do like a jokey thing, like we're not being ageist here boomer, but like, like a like a 60 year old ceo of Bank of America. We try to make a joke for the kids. That's what, that's [/INST] exactly yeah, I was like, what is this? This guy is like, What is he 30? </s><s>[INST] Uh [/INST] and I'm like this is weird. Um But I think maybe that's also what I like about Elon's kind of influence on american businesses? Like he's super like anti the professional, like why, why say why I say, you know, 100 words about nothing. Uh and so I liked how he was cutting in and saying glad, what do you mean spill the beans bro? </s><s>[INST] Yeah, so you don't have to be courteous. It's like the first principles thinking it's like, what the hell happened? And let's just talk like normal people. The problem of course, is uh you know, for Ellen uh has cost them, what is it? Tens of millions of dollars is tweeting like that, but perhaps it's a worthy price to pay because ultimately there's something magical about just being real and honest and just going off the cuff and making mistakes and paying for them, but just being real and then moments like this, that was an opportunity for vlad to be that and it felt like he wasn't uh do you think there, do you think we'll ever find out what really went down if there was something shady underneath it all? [/INST] Yeah, I mean it would be sad if nothing shady happened, right? But his presence made it shady </s><s>[INST] sometimes I feel like that with Mark Zuckerberg, the ceo of facebook, sometimes I feel like, yeah, there's a lot of shitty things that facebook is doing, but sometimes I think he makes it look worse by the way he presents himself about those things. Like I I honestly think that a large amount of people at facebook just have a huge unstable chaotic system and they're all, not all but a mass are trying to do good with this chaotic system. But the presentation is like it sounds like there's a lot of back room conversations that are trying to manipulate people. Uh And there's there's something about the real nous that Ellen has that it feels like Ceo should have Vlad had that opportunity. [/INST] I think Mark Zuckerberg had that too when he was younger, younger and somebody said you got to be more professional man. You can't say, you know law to an interview. Uh And then suddenly he became like this distance person that was hot. Like you'd rather have him make mistakes but be honest than be like professional never make mistakes. </s><s>[INST] Yeah. One of the difficult hires I think is like marketing people or like pr people is you have to hire people that get the fact that you can say lol on an interview or I you know take risks as opposed to what the pr I thought to quite a few big Ceos and the people around them are trying to constantly minimize risk of like what did he say the wrong thing? What does she say the wrong thing? It's like what? Be careful. It's constantly like you like I don't know. And there's this nervous energy that builds up over time with larger larger teams where the whole thing like I visited youtube for example, everybody I talked at youtube incredible engineering an incredible system but everybody is scared. Like, let's be uh, let's be honest about this, like madness that we have going on of huge amounts of video that we can't possibly ever handle. There's a bunch of hate on Youtube. There's this chaos of comments, a bunch of conspiracy theories, some of which might be true. And then just like this mess that we're dealing with and it's exciting. It's beautiful. Uh, it's a place where like democratizes education, all that kind of stuff. And instead they're all like sitting in like trying to be very polite and saying like, well, we just want to improve the health of our platforms, [/INST] like </s><s>[INST] discussion like all right man, let's just be real. Let's, let's, let's both advertise how amazing this frickin thing is, but also to say like, we don't know what we're doing. We have all these nazis posting videos on Youtube. We don't, we don't know how to like handle it and just being real like that because I suppose that's just the skill. Um, maybe it can't be taught, but over time, whatever the dynamics of the company is, it does seem like Zuckerberg and others get worn down. They just get [/INST] tired. Uh, </s><s>[INST] they get tired [/INST] of not being real </s><s>[INST] of not being real, which is sad. So let's talk about new MRI, which is an incredible company, uh, system idea I think, but a good place to start, what is memory and how does it work? [/INST] So memorize the first hedge fund that gives away all of its data. So this is like probably the last thing a hedge fund would do right? Why would we give away a data? It's like giving away your edge. Um But the reason we do it is because we're looking for people to model our data and the way we do it is by obfuscating the data. So when you get, when you look at numerous data that you can download for free, it just looks like like a million rows of numbers between zero and one and you have no idea what the columns mean. But you do know that if you're good machine learning or have done regressions before, you know that I can still find patterns in this data even though I don't know, I don't know what the features mean. </s><s>[INST] And and the data itself is a time series data. And even though it's sophisticated anonymous. Ized, what is the source data like approximately what are we talking about? [/INST] So we are buying data from lots of different data vendors um and they would also never want us to share that data. Um so we have strict contracts with them. So we only, we only can but it but it's the kind of data you could never by yourself unless you had maybe $1 million dollars a year of budget to buy data. So what's happened with the hedge fund industry is you have a lot of talented people who used to be able to trade and still can trade. But now they have such a data disadvantage, it would never make sense for them to um to trade themselves but knew Marie by giving away this obfuscated data, we can give them a really really high quality data set that that would otherwise be very expensive and they can use whatever new machine learning technique they want uh to find patterns in that data that we can use in our hedge fund. </s><s>[INST] And so how much variety is there in the underlying data we're talking about? I apologize if I'm using the wrong terms but one is just like the stock price, the other, there's like options and all that kind of stuff like the what are they called? Order books or whatever. Like is there may be other are totally unrelated to directly to the stock market data, like like natural language as well, all that kind of stuff. [/INST] Yeah, we were really focused on stock data that's specific to stocks. So um things like you can have like a p every stock has like a P. E ratio For some stocks is not as meaningful but every stock has that every stock has one year momentum, how much they went up in the last year. Um but those are very common factors but we try to get lots and lots of those factors that we have for many, many years, like 15, 20 years history. Um and and then the setup of the problem is commonly in quant called like cross sectional, global equity, you're not really trying to say, I want, I I believe the stock will go up. You're trying to say um the relative position of this stock in feature space makes it not a bad buy in a in a portfolio </s><s>[INST] to capture some period of time. And you're trying to find the patterns, the dynamics captured by the data of that period of time in order to make short term predictions about what's going to happen. [/INST] Yeah, so our predictions also not that short, we're not really um caring about things like order books and and and and take data. Not high frequency at all. We're actually holding things for quite a bit longer. Uh So prediction time arising is about one month. We end up holding stocks for maybe like three or four months. So I kind of believe that's a little bit more like investing then um then kind of plumbing, like to go long a stock that's mispriced on one exchange and shorter on another exchange, that's just arbitrage. But what we're trying to do is really no, no know something more about the longer term future </s><s>[INST] of the stock. So from the patterns from these periods of uh time series data, you're trying to understand something fundamental about the stock, not like about deep value about like it's big in the context of the market is underpriced overpriced, all that kind of stuff. So, like, this is about investing, it's not about just like you said, high frequency trading, which I think is a fascinating open question for machine learning perspective, but just to like, sort of build on that. So you have anonymous the data and now you're giving away the data and then now anyone can try to uh build algorithms that make investing decisions on top of that data or predictions on the top of that data. And so that that's uh what is it? So what does that look like? What's the goal of that? What are the underlying principles of that? [/INST] So the first thing is, you know, we could obviously model that data in house, right? We can make an extra boost model on the data. Um and that would be quite good too. But what we're trying to do is by by opening it up and letting anybody participate, uh we can do quite a lot better than if we modeled it ourselves and a lot better on the stock market doesn't need to be very much like, it really matters. The difference between if you can make 10 and 12% equity market neutral hedge fund, because the whole usually you're trying you're charging 2% fees. So if you can do 2% better, that's like all your fees, it's worth it. So we're trying to make sure that we always have the best possible model as new machine learning libraries come out, new new techniques come out. They get automatically synthesized. Like if there's a great paper on supervised learning, someone on numerous, I will figure out how to use it on numerous data. </s><s>[INST] And is there an ensemble of uh models going on? Or is it always or is it more towards kind of like one or two or three like best performing models? [/INST] So the way we decide on how to wait all of the predictions together is by how much the users are staking on them, how much of the Cryptocurrency that they're putting behind their models. So they're saying, I believe in my model, you can trust me because I'm going to put skin in the game. Um and so we can take the steak waited predictions from all our users and add those together. Average those together. And that's a much better model than any one model in the in the sun. Because ensemble in a lot of models together is kind of the key thing you need to do in investing too. </s><s>[INST] Yeah. So you're putting there's a kind of duality from the user from the perspective of machine learning engineer where you're is both a competition. Just a really interesting, difficult machine learning problem. And it's uh a way to to invest algorithmic lee. So like Yeah. And but the way to invest algorithmic lee also is a way to put skin in the game that communicates to you that you're the quality of the algorithm and also forces you to really be serious about the models that you build. So it's like everything just works nicely together. Like uh I guess one way to say that is the interests are aligned okay? So it's just like poker is not not fun when it's like for very low stakes, the higher the stakes, the more the dynamics of the system starts playing out correctly. Like it's a small side note, is there something you can say about which kind of looking at the big broad view of machine learning today or ai what kind of algorithms seem to do good in these kinds of competitions at this time? Is there some universal thing you can say like neural networks suck, recurring, you'll know or suck transformer suck or they're awesome. Like old school sort of more basic kind of classifiers are better, although there is there some kind of conclusion so far that you can say [/INST] there is there definitely something pretty nice about tree models like like XG boost. Um And uh they just seemed to work pretty nicely on this type of data so out of the box, if you're trying to come 100th in the competition in the tournament, maybe you would try and use that. Um But what what's particularly interesting about the problem that um not many people understand if you're familiar with machine learning um This typically will surprise you when you model our data. So um one of the things that you look at in finances, you don't wanna be too exposed to anyone risk, like even if the best Sector in the world to invest in over the last 10 years was tech, you would not, does not mean you should put all of your money into tech. So the if you train the model, it would say put all your money into tech, it's super good. But um what you want to do is actually be very careful of how much of this exposure you have to certain features so on numerous what a lot of people figure out is actually if you train a model on this kind of data, you want to somehow neutralize or minimize your exposure to these certain features, which is unusual because if if you did train um stop light or stop street detection on computer vision, uh the your favorite feature, let's say you could, and you have an auto encoder and it's figuring out okay, it's gonna be red and it's gonna be white. You, that's the last thing you want to be, you want to reduce your exposure to why would you reduce the exposure? The thing that's helping you, your model the most and that's actually this counterintuitive thing you have to do with machine learning on financial data. </s><s>[INST] So reducing it's reducing your exposure would help you generally is the things that are basically financial data has a large amount of patterns that appeared in the past, and also a large amount of patterns that have not appeared in the past. And so like in that sense you have to reduce the exposure to red lights to the color red. That's interesting. But how much of this is art and how much of it is science from your perspective so far in terms of as you start to climb from the 100th position to the 95th in the competition. [/INST] Yeah, well if you do, you make yourself super exposed to one or two features, you can have a lot of volatility when you're playing memory. You could maybe very rapidly rise to be high if you were getting lucky And that's a bit like the stock market. Sure take on massive risk exposure. Put all your money into one stock and you might make 100%. But um it doesn't in the long run work out very well. And so um the best users are trying to stay high for as long as possible. Not not necessarily try to be a first for a little bit. </s><s>[INST] So for me, a developer, machine learning researcher, how do I like Friedman participate in this competition And how do others, I'm sure there'll be a lot of others interested in participate in this competition. What uh let's see there's like a million questions, but like first one is how do I get started? [/INST] Well you can go to numerous dot ai sign up, download the data and on the data is pretty small um in the data pack you download, there's like an example script, python script that just builds a extra boost model very quickly from the data. Uh And um so in a very short time you can have an example model. </s><s>[INST] Is that a particular structure? Like what is this model then submitted somewhere? So there needs to be some kind of structure that communicates with some kind of a p I like. How does the whole how does how does your model, once you've built, once you create a little little baby Frankenstein, how does it then live in it? And [/INST] we want you to keep your baby Frankenstein at home and take care of it. We don't want it. So we you never upload your model to us. You always um only giving us predictions, so we never see the code that wrote your model, which is pretty cool that our whole hedge fund is built from models where we've never, ever seen the code. Um but it's important for the users because it's their I P what they want to give it to us, so they've got it themselves, but they can basically almost like license the predictions from that </s><s>[INST] problem to us. So, [/INST] um </s><s>[INST] so [/INST] what some users do is they set up a compute servant. We call numerous compute it's like a little AWS kind of image and you can automate this process. Um so we can pin you can be like we need more predictions now and then you send it to us. </s><s>[INST] Okay, cool. So that that's uh is that describe somewhere like what the preferred is the AWS or whether another cloud platform is there, I mean is there sort of specific technical things you want to say that comes to mind that uh is a good path for getting started? So download the data, maybe play around, see if you can modify the basic uh algorithm provided in the example and then you what set up a little server on the AWS that then runs this model and takes pings and then makes predictions. And uh how does your own money actually come into play during the stake of uh Cryptocurrency? [/INST] Yeah, so you don't have to stake, you can start without staking and many users might try for months without staking anything at all to see if their model works on the real life data. Right? And it's not over fit. Um but then you can get numerous rare uh many different ways, you can buy it on, you can buy some on coin base, you can buy some on, you know swap, you can buy someone finance. Um </s><s>[INST] so what did you say this is, how do you pronounce it? So this is the new MRI uh Cryptocurrency [/INST] Yeah NMR </s><s>[INST] and um are what you just say NMR [/INST] it is, it is technically called Numa rare </s><s>[INST] numerous where I like it. Yeah [/INST] anymore </s><s>[INST] simple NMR and you Moreira Okay so and you can buy it uh you know basically anywhere. [/INST] Yeah so it's a bit strange because sometimes people like is this like pay to play Right? And it's like sore. It's like yeah you need to put some money down to show us you believe in your model, but weirdly we're not selling you the like you can't buy the Cryptocurrency from us. It's like it's also we never if you're if you do badly um we destroy your Cryptocurrency. Okay, that's not good, right? You don't want it to be destroyed. But what's good about it is it's also not coming to us, right? So it's not like we win when you lose or something like that, like we're the house, like we're definitely on the same team, you're helping us make a hedge fund that's never been done before. </s><s>[INST] Yes, so again, interests are aligned. There's no uh there's no tension there at all which which is really fascinating given away everything and then the I. P. Is owned by sort of the code. You never share the code. That's fascinating. Um So since I have you here and you said hundreds, I didn't ask out of how many So we'll just but if uh if I then once you get started and you find this interesting, how do you then win or do well but also how do you potentially try to win if this is something you want to take on seriously from the machine learning perspective, not from a financial perspective. [/INST] Yeah, I think um the first of all you want to talk to the community people are pretty open, uh we give out really interesting scripts and ideas for things you might want to try. Um and uh but you're also gonna need a lot of compute probably, and so some of the best users are, are, you know, actually the very first time someone one on numerous, I would, I wrote them a personal emails like, you know, you've won some money, we're so excited to give you $300 and then they said, I spend way more on the compute, but </s><s>[INST] this is fundamentally machine learning problem first, I think this is one of the exciting things, I don't know if we'll in how many ways you can approach this, but really this is less about kind of, no offense, but like finance people, finance minded people, they're also, I'm sure great people, but it feels like from the community that have experienced, these are people who see finances a fascinating uh problem space, the source of data, but ultimately their machine learning people or ai people, which is a very different kind of flavor of community. And um I mean, I should say to that uh I'd love to participate in this and I will participate in this, and I'd love to hear from other people if you're listening to this, if your machine learning person you should participate and tell me give me some hints um how I can do all of this thing because this boomer uh I'm not sure, I still got it but because some of it is uh it's like cattle competitions, like some of it is certainly set ideas like research ideas like fundamental innovation, but I'm sure some of it is like deeply understanding getting like an intuition about the data and then like a lot of it will be like figuring out like what works like tricks you could argue most of deep learning research is just tricks on top of tricks but there's uh some of it is just the art of getting to know how to work in a really difficult machine learning problem [/INST] and I think what's important the important difference with something like a cackle competition where they will set up this kind of toy problem and then they will be out of sample test like hey you did well out of sample and this is like okay cool. Um but what's cool and memorize your the out of sample is the real livestock market. We, we don't even know like we don't know the answer to the problem, we don't like you'll have to find out live and so we've had users who have like submitted every week for for like four years. Um because it's kind of a interesting, we say it's the hardest data science problem on the planet, right? And it doesn't sense maybe sounds like maybe a bit too much for like a marketing thing, but it's the hardest because it's the stock market, it's like literally there are like billions of dollars at stake and like no one's like letting it be inefficient on purpose. So if you can find something that works on numerous, you really have something that that is like working on the real stock market. </s><s>[INST] Yeah, because there's like humans involved in the stock market, I mean that's uh you know, you could argue that might be harder datasets that may be predicting the weather, all those kinds of things. But the fundamental statement here is which I like, I was thinking like is this really the hardest data science problem and you start thinking about that. But ultimately it also boils down to a problem where the data is accessible, It's made accessible. Made really easy and efficient at like submitting algorithms. So it's not just, you know, it's not about the data being out there, like the weather, it's about making the data super accessible. Making the ability of community around it. Like this is what imaging that did exactly like it's not just there's always images. The point is you aggregate them together, you give it a little title. This is a community and that that was one of the hardest, right? For a time and most important data science problems in the world because it was accessible because it was made uh sort of like there was mechanisms by which like standards and mechanisms by which to judge your performance, all those kinds of things and numerous to actually step up from that. Is there something more you can say about why from your perspective it's the hardest uh, problem in the world. I mean you said it's connected to the market. So if you can find a pattern in the market, that's a really difficult thing to do because a lot of people are trying to do it. [/INST] Exactly. But there's also the biggest one is it's it's non stationary time series. We've tried to regularize the data so you can find patterns by by doing certain things to the features and the target. But ultimately you're in a space where you don't, there's no guarantees that the out of sample distributions will conform to any of the training data and and every single um era which we call on the website, like every single era in the data, which is like sort of showing you the order of the time. Um, it's it's even the training data is has the same same dislocations and um, so yeah, so, and then there's yeah, there's so many things that might um, might you might want to try this, this like this unlimited possible number of models. Right? Um, and so mm bye by having it be open. We can at least search that space </s><s>[INST] zooming back out to the philosophical you said that memory is very much like Wall Street bets. Uh, is there? I I think it'd be interesting to dig in why you think so? I think you're speaking to the distributed nature of the two and the power of the people nature of the two. So maybe can you speak to the similarities and the differences and in which ways memory more powerful in which way is Wall Street bets more powerful. [/INST] Yeah, this is why the Wall Street Bets story is so interesting to me because it's like feels like connected. Um and looking at how just looking at the forum of Wall Street bets. It's I was talking earlier about how how can you make credible claims, your anonymous. Okay, well maybe you can take a screenshot how well maybe you can up vote someone, Maybe you can have Karma on Reddit and those kinds of things make this emerging thing possible, knew more. I it didn't work at all when we started it didn't work at all why people made multiple accounts. They made really random models and hoped they would get lucky and some of them did Yes staking was our like solution to could we could we make it so that we could trust we could know which model people believed in the most and we could wait models that had high stake more and effectively coordinate this group of people to be like, well actually there's no incentive to creating bot accounts anymore. Either I stake my accounts in which case I should believe in them because I could lose my steak or I don't and that's a very powerful thing that having a negative incentive and a positive incentive can make, can make things a lot better. And staking is like this is this really nice like key thing about block changes like something special you can do where they're not even trusting us with their stake in some ways, they're trusting the Blockchain, right. Um so the incentives, like you say, it's about making these perfect incentives so that you can have coordination to solve one problem. And nowadays I sleep easy because I have less money in my own hedge fund than our users are staking on their models. </s><s>[INST] That's powerful in some sense from a human psychology perspective, it's fascinating that the Wall Street bets worked at all right. The amidst that chaos emerging behavior uh like behavior that made sense emerged. It'll be fascinating to think if numerous style uh staking could then be transferred to places like reddit, you know, and and not necessarily for financial investments, but uh like I wish sometimes people would, you know, would have to stake something in the comments they make on the internet, like that's that's the problem that anonymity is like anonymity is freedom and power that you don't have to, you can speak your mind, but it's too easy to just be shitty. Exactly. And so this I mean, you're making me realize from like a profoundly philosophical aspect, numerous staking is a really clean way to solve this problem. It's a really beautiful way. Of course, it only with numerous currently works for a very particular problem, right? Not for human interaction on the internet, but that's fascinating. [/INST] Yeah, there's nothing for to stop people. In fact, we've opened sourced like the code we use for staking in a protocol we call a razor. Um and any if Reddit wanted to, they could even use that code to do have have enabled staking on our Wall Street bets and they're actually researching now, they've had some ethereum grants on how could they have more crypto stuff in there in ethereum because wouldn't that be interesting? Like, imagine you could um instead of seeing a screenshot, like guys, I promise, I will not uh sell my Gamestop, we're just gonna go huge, we're not gonna sell at all. Um and here is a smart contract which no one in the world including me can undo. That says my I have staked millions against this claim. Um that's powerful. And then what could you do? </s><s>[INST] And of course it doesn't have to be millions. It could be just a very small amount, but then it's just a huge number of users doing that kind of steak. Exactly. Uh you know, that could change the internet, [/INST] it would change And the man Wall Street, it would not, they would never have been able to, there would still be short squeezing one day after the next every single hedge fund collapsing. </s><s>[INST] If we look into the future, do you think it's possible that new MRI style infrastructure where AI systems backed by humans are doing the trading is what the entirety of the stock market is, or the entirety of the economy is run by basically this army of Ai systems with high level human supervision. [/INST] Yeah. The thing is that some of them could be could be bad actors. Um some of the humans know, well these systems could be tricky. So actually, I once met a hedge fund manager, this is kind of interesting. He said very famous one and he said, um, we can see sometimes we can see things in the market where we know we can make money, but it will mesh it </s><s>[INST] up. [/INST] We know we can make money but it will mess things up and we choose not to do those things. And on the one hand, maybe this is like, oh, you're being super arrogant, like of course you can't, you can't do this, but maybe he can and maybe he really isn't doing things he knows he could do, but would changed be pretty bad. Would the Reddit army have that kind of uh morality or concern for what they're doing. Probably not based on what </s><s>[INST] we've seen. The madness of crowds, there will be like one person that says, hey maybe and then they get trampled over. That's that's the terrifying thing. Actually there's uh a lot of people have written about this is somehow that like little voice that's human, morality gets silence when we get into groups and start chanting and that's terrifying. But like I think maybe I misunderstood, I thought that um you're saying ai systems can be dangerous, but you just described how humans can be dangerous so which is safer. [/INST] So I mean one thing is uh numerous. Yeah, so Wall Street bets these kinds of like these kinds of attacks, like it's not possible to model numerous data and then come up with the idea from the model, let's short screen Gamestop, it's not even framed in that way. It's not like possible to have that idea. So, but it is possible for like kind of a bunch of humans. So I think there's it's numerous could get very powerful without it being dangerous. But Wall Street bets needs to get a little bit more powerful and it'll be pretty </s><s>[INST] dangerous. Yeah. Well I mean, so this is a good Place to kind of think about memory data today. Uh memory signals and what that looks like in 10 2030, 50, 100 years. You know, like right now. I guess maybe you can correct me. But the the data that we're working with is like a window. It's a anonymous Ized obfuscated window into a particular aspect time period of the market. And you know, you can expand that more and more and more and more potentially you can imagine in different dimensions to where it encapsulates all the things that uh where you could uh include kind of human to human communication that was available for like to buy Gamestop, for example on on Wall Street. But so maybe the step back, can you speak to what is numerous signals and uh what are the different data sets that are involved? [/INST] So with numerous signals, um You're still providing predictions to us. Um But you can do it from your own data set. So Newman writes all. You have to model our data to come up with predictions. Numerous signals is whatever data you can find out there, you can turn it into a signal and give it to us. So it's a way for us to import signals on data. We don't yet have. And um and that's why it's particularly valuable because it's gonna be signals. You're only rewarded for signals that are orthogonal to our core signal. So you have to be doing something un correlated. And so strange. Alternative data tends to have that property. There isn't too many other signals that are correlated with um with uh you know what's happening on Wall Street bets that's not going to be like correlated with the price to earnings ratio. Right? Um And we have some users as of recently, as of like a week ago, there was a user that created, I think he's in India, he created um a signal that is scraped from Wall Street bets. Um And now we have that signal as one of our signals in thousands that we use that memory. </s><s>[INST] And the structure of the signal is similar. So it is just numbers and time series data. [/INST] It's exactly, and it's just like, it's kind of a, you're providing a ranking of stocks. So you just say Give it a one means you like the stock zero means you don't like the stock and you provide that for 5000 stocks in the world. </s><s>[INST] And they somehow converted the natural language that's in the Wall [/INST] Street. So they've come exactly. So they made the open source, this co lab notebook. You can go and see it and look so yeah, it's taking that making a sentiment score and then turning it into a rank </s><s>[INST] of sentiment [/INST] score. </s><s>[INST] Uh like this stock sucks. So the stock is awesome. And then converting that's, that's fast. Just even looking at that day, it would be fascinating. So on the signal side, what's the vision? Long term, what do you see that becoming? [/INST] So we want to manage all the money in the world. That's numerous mission and to get that we need to have all the data and have all of the talent. Like there's no way from first principles if you had really good modeling and really good data that you would lose. Right. Um it's just a question of how much do you need to get to get really good. So numerous already has some really nice data that we give out this year. We are 10 X in that and I actually think well 10 X the amount of data we have on numerous every year for at least the next 10 years. So it's going to get very big. The data we give out and signals is more data. People with any other random data set can turn that into a signal and give it to us </s><s>[INST] and in some sense that kind of data is the education of the weirdness is the you're focused on like the bulk the main data and then there's just like weirdness from all over the place that just can enter through this back door. Exactly. [/INST] And uh it's also a little bit shorter term. So the signals are set about a seven day time horizon And the on numerous, it's like a 30 day. So it's often for foster situations, </s><s>[INST] you've written about a master plan and you mentioned which I love uh in a similar sort of style of big style thinking you would like memory to manage all of the world's money. Uh So how do we get there from from yesterday too? Several years from now like what what is the plan? [/INST] So </s><s>[INST] you have already started to alert or to get all the data and get it uh all the talent humans models. [/INST] Exactly. I mean the important thing to note there is what would that mean? Right? And I think the biggest thing it means is like uh if there was one hedge fund, um you would have uh not so much talent wasted on all the other hedge funds. Like it's super weird how the industry works. It's like one hedge fund gets the data source and hires a PhD and another hedge fund has to buy the same data source and hire a PhD. And suddenly a third of american phds are working at hedge funds and we're not even on mars and like, so in some ways new Marie, it's all about freeing up people who work at hedge funds to go work for Ellen. </s><s>[INST] Yeah. And also the people who are working on new memory problem, it feels like a lot of the knowledge, there's also transferable to other domains. [/INST] Exactly are one of our top users is he works at Nasa jet propulsion lab and he's, he's like amazing. I went to go visit him there And it's like he's got like numerous posters and he's like, it's like, it looks like, you know the movies like it looks like Apollo 11 or whatever. Yeah, the point is he didn't quit his job to join full time. He's working on getting us to jupiter's moon, That's his mission the Europa clipper mission. </s><s>[INST] Actually, literally what you're saying, [/INST] literally, we he's smart enough that we really want his intelligence to reach the stock market because the stock market's good thing, hedge funds are a good thing. Our kinds of hedge funds especially, but we don't want him to quit his job so he can just do numerous on the weekend. And that's what he does. He just made a model and it just automatically submits to us. And he's like one of our best users. </s><s>[INST] You mentioned briefly, the stock markets are good for my sort of outsider perspective. Is there a sense do you think trading stocks is uh closer to gambling or is it closer to investing? Sometimes? It feels like it's gambling as opposed to betting on companies to succeed. And this is may be connected to our discussion of shorting in general, but like from your sense, the way you think about it, is it fundamentally still investing? [/INST] I do think um I mean, it's a good question. It's I've also seen lately, like people say this is like speculation, is there too much speculation in the market? And it's like, but all the trades are speculative, like all the trades have a horizon, like people want them to work? Um uh So I I would say that um and there's certainly a lot of aspects of gambling math that applies to investing. Like one thing you don't do in gambling is put all your money in one bet, you have bankroll management and it's a key part of it and small alterations to your bankroll management might be better than improvements to your skill. Um So there, and then there are things we care about in our fund, like we want to make a lot of independent bets, we talk about it, like we want to make a lot of independent bets because there that's going to be um higher sharp than if you have a lot of bets that depend on each other, like all in one sector. Yeah. Um But but yeah, I mean the point, the point is that you want the prices of the stocks to be, to be reflective of, of how, of the value </s><s>[INST] of the underlying value. [/INST] Yeah. Yeah. You shouldn't have there be like a hedge fund that's able to say, well, um I've looked at some data and all of this stuff super mispriced, like that's super bad for society. If it, if it looks like that to someone, </s><s>[INST] I guess the the underlying question then is uh do you see that the market often like drifts away from the underlying value of companies and it becomes a game in itself, like with these, whatever they're called, like derivatives, like the obsolete, you know, um, options and shorting and all that kind of stuff. It's like layers of game on top of the actual, like what you said, which is like the basic thing that Wall Street bets was doing, which is like just buying stocks. [/INST] Yeah, there are a lot of games that people play that are in the derivatives market. And I think a lot of the stuff people dislike when they look at the history of, of what's happened, they hate like credit default swaps or collateralized debt obligations. Like these are the, these are the kind of like enemies of 2000 and eight. And then the long term capital management thing, it was like, It's like that 30 times leverage or, or something. Just that no one like you could just go to, um, a gas station and ask anybody at the gas station, is it a good idea to have 30 times leverage? And they just say no, it's common sense just went out the window. So the, yeah, I don't, I don't, I don't respect long term capital management. Okay. But numerous doesn't actually use any derivatives unless you call shorting derivative. We just, we do put money into companies. We, and that does help the companies were investing in its just in little ways. Um, we really did buy Tesla and it did. And we were, you know, we were not, um, we played some role in, in that its success super small, making a mistake, but still, I think that's important, </s><s>[INST] can I ask you, uh, a pothead question, which is, uh, what is money man? So if we just kind of zoom out and look at, because let's talk to you about Cryptocurrency, which perhaps could be the future of money in general, How do you think about money? He said new MRI the vision, the goal is to to run to manage the world's money, What is money in your view? [/INST] I don't have a good answer to that, but it's definitely in my personal life, it's become more and more warped. Um and you start to care about the real thing, like what's really going on here. Um Ellen has talked about things like this, like what what is the company really? It's like it's a bunch of people who like kind of show up to work together and like they solve a problem and they might not be a stock out there that that that's trading that represents that what they're doing, but it's it's not the real thing. Um and being involved in crypto um like I was early, I put crowd sale of ethereum and uh and all these other things in different crypto hedge funds and things that I've invested in, and it's like, it's just it's just kind of like, it feels like how I used to think about money stuff, it's just it's just like totally warped um because you yeah, you kind of you stop caring about like the price and you care about like the product, </s><s>[INST] so by the product, you mean like the different mechanisms that money is exchanged, I mean money is ultimately kind of a little uh you know, one is a store of wealth, but it's, it's also a mechanism of exchanging wealth, but that like, what what wealth means becomes a totally different thing, especially with Cryptocurrency to where it's almost like these little contracts, these little agreements, these transactions between human beings that represent something that's bigger and just like cash being exchanged at 7 11, it feels like, [/INST] yeah, maybe I answer, what is finance like you, it's what are you doing when you can, when you have the ability to take out a loan, you can bring uh a whole new future into being with finance uh if you couldn't get a student loan to get a college degree, you couldn't get a college degree, like if you didn't have the money, but now, like, weirdly, you can get it with and like yeah, all you have is this like loan, which is like, so now you can bring, you can bring a different future into the world and that's how I, when I was saying earlier about if you rerun american history, economic history without these, these these things like, you know, a lot of take out loans, you're not allowed to have have derivatives, you're allowed to have money. Um it was just, it just doesn't really work and it's a really magic thing, how, how, how much you can do with finance, but kind of bringing the future forward </s><s>[INST] finances empowering. It's uh we sometimes forget this, but yeah it enables innovation, enables big risk takers and bold builders that ultimately make this world better. You said you were early in on Cryptocurrency, can you give your high level overview of just your thoughts about the past, present and future of Cryptocurrency? [/INST] Um Yeah, so my friends told me about Bitcoin and I I was interested in equities a lot and I was like well it has no NPV, it has no future cash flows. Bitcoin pays no dividends. Um So I really couldn't get my head around it like that, this could be valuable. Um and then I but I did so I I didn't feel like I was early in Cryptocurrency in fact because I was like, it was like 2014, it felt like a long time after Bitcoin. Um And then but then I I really liked some of the things that uh theory and was doing, it seemed like a super visionary thing, like I was reading something that was um that was just going to change the world when I was reading the white paper um and I like the different constructs you could have inside of a theory and that you couldn't have on on Bitcoin </s><s>[INST] like smart contracts and [/INST] Exactly yeah and even the there were, yeah even spoke about different uh different </s><s>[INST] constructions, you could have, yeah, that's a cool dance between Bitcoin and ethereum of, it's in the space of ideas, feel so young like I wonder what cryptocurrencies will look like in the future. Like if Bitcoin or ethereum two point or some version will stick around or any of those like who's gonna win out or if there's even a concept of winning out at all, Is there a Cryptocurrency that you're especially find interesting that technically financially philosophically you think this is something you're keeping your eye on? [/INST] Well I don't really, I'm not looking to like invest in cryptocurrencies anymore. Um But I I they are, I mean the there and many are almost identical, I mean there's not there wasn't too much different um between even ethereum and Bitcoin in some ways right? But there are some that I like the privacy ones and I was like I like Z cash for its like coolness. It's actually um it's it's like a different kind of invention compared to </s><s>[INST] some of the other things. Can you speak to just briefly to privacy? What is there some mechanism preserving some privacy of the universe. So I guess everything is public. Yeah, that's the problem. The [/INST] yeah, none of the transactions are private. Um And so you know even like I have some of my, I have some numerous air and you can just see it. In fact you can go to website and says like you know like ether scan and it'll say like new Marie founder uh and I'm like how the hell are you guys know this? </s><s>[INST] So they can reverse and then, you know, whatever that's called. [/INST] Yeah. So they can see me move it to, they can see me. So why is he moving it? Um so uh so but yeah, Z cash, they also, when you can make private transactions, you can also play different games. Um and uh it's unclear. It's like, what's quite cool about Z caches? I wonder what games are being played there, No one will know. </s><s>[INST] Uh So from from a deeply analytical perspective, can you describe why does corn is going to win? Which it surely will like, it very likely will take over the world and once we expand out into the universe will take over the universe. Uh or in a more serious note, like what are your thoughts on the recent success of doors going, where you've spoken to sort of the, the meme stocks, the mathematics of the whole thing. It feels like the joke can become the reality. Like the meme, the joke has power in this world is fascinating. [/INST] Exactly. It's uh it's like, why is it correlated with Elon tweeting about it? </s><s>[INST] It's not just Ellen alone tweeting, right? It's like Elon tweeting and that becomes a catalyst for everybody on the internet kind of like spreading the joke, right? The joke of it. So it's it's it's the the initial spark of the fire for Wall Street bets type of situation. [/INST] Yeah. And </s><s>[INST] that's fascinating because jokes seem to spread faster than other mechanisms like funny sh it is very effective at captivating the uh like the discourse on the internet. [/INST] Yeah. And I think you can have um like that I like the one meme like does I haven't heard that name in a long time. Um like I think back to that me often, that's like funny and every time I think back to it, there's a little probability that I </s><s>[INST] might buy [/INST] right? And so you have millions of people who have had all these great jokes told them and every now and then they reminisce. So that was that was really funny. And then they're like, let me buy </s><s>[INST] some uh wouldn't it be interesting if like the entire if you travel in time like multiple centuries where the entirety of the communication of the human species is like humor. Like it's all just jokes like we're high on probably some really advanced drugs and we're all just laughing nonstop. It's a weird like dystopian future of just humor. Elon has made me realize uh how like good it feels to just not take it seriously every once in a while and just relieve like the pressure of the world at the same time. The reason I don't always like when people finish their sentences with love, it's like that you don't when you don't take anything seriously when everything becomes a joke, then it feels like uh that way of thinking feels like it will destroy the world. It's like I I often think like well me um save the world of destroyed because I think both are possible directions. [/INST] Yeah, I think this is a big problem. I mean America, I always felt that about America. A lot of people are telling jokes kind of all the time and they're kind of good at it. Um and you take someone inside an american, like I really want to have a sincere conversation. It's like hard to even keep this rate phase because um everything is so there's so much levity so it's complicated. I like how sincere actually like your twitter can be like I am in love with the world gets so much ship </s><s>[INST] for it. I'm never gonna stop because I realized like do you have to be able to sometimes just be real and be positive and just be uh say the cliche things which ultimately those things actually capture some fundamental truths about life but it's a dance and I think Dylan does a good job of that now from an engineering perspective of being able to joke but everyone's you know, mostly to pull back and be like here's real problems, let's solve them and so on and then be able to jump back to a joke. So it's uh it's ultimately I think I I guess a skill that we have to learn. I uh but I guess your advice is to invest everything anyone listening owns into doors coin. that's what I heard from this direction exactly how [/INST] much fun is unavailable, </s><s>[INST] just go [/INST] Straight $2 coin. </s><s>[INST] You're running a successful company. It's just interesting because my mind has been in that space of potentially being one of the millions of other entrepreneurs. What's your advice on how to build a successful startup, how to build a successful company? [/INST] I think that one thing I do like and it might be a particular thing about America but like there is something about like playing, tell people what you really want to happen in the world. Like don't stop, it's not it's not going to make it um Like if you're asking someone to invest in your company don't say, I think maybe one day we might make a million dollars. Um When you actually believe something else, you actually believe you actually more optimistic but you're toning down your optimism because you want to appear um like low risk but actually it's super high risk if your company becomes mediocre because no one wants to work in mediocre company, no one wants investing in your cookie. Um So you should play the real game. Um And obviously this doesn't apply to all businesses, but if you play a venture backed startup kind of game like play for keeps play the wind go big. Um And it's very hard to do that. I've always, I feel like um I yeah I start you can start narrowing narrowing your focus because 10 people are telling you, you know, you got to care about this boring thing that won't matter five years from now and you should push back and do the real play the real game </s><s>[INST] to be bold. So both. I mean, there's a there's an interesting duality there. So there's the way you speak to other people about like your plans and what you are like privately, just in your own mind, [/INST] and maybe it's connected with what you're saying about Yeah, sincerity as well. Like if you if you appear to be sincerely optimistic about something that's big or crazy, it's putting yourself up to be kind of like ridiculed or something. And so if you say my mission is to um yeah, go to mars it's just so bonkers that it's hard to say </s><s>[INST] it is, but uh one powerful thing, just like you said is if you say it and you believe it, then actually amazing people uh come and work with you. Exactly. It's not just skill, but the dreams, there's something about optimism that uh like that fire that you have when you're optimistic of actually having the hope of building something totally cool, something totally new that when those people get in a room together, like they can actually do it. Uh Yeah, there's yeah, there's that's uh and also makes life really fun when you're in that room, so all that together, ultimately, I don't know, that's what makes this crazy ride of a startup really look fun and l as in this example, a person who succeeded that, there's not many other inspiring figures, which is said I used to be a google and there's uh there's something that happens that sometimes when the company grows bigger and bigger and bigger, where that kind of ambition kind of quiets down a little bit, you know, google had this ambition still does of making the world's information accessible to everyone. And I remember, I don't know, that's beautiful. I still love that dream of that. You know, they used to scan books, but just every way possible, Make the world's information accessible. Same with Wikipedia. Every time I open up Wikipedia, um I'm just are inspired by how awesome humans are man and creating this together. I don't know what the meetings are over there, but they it's just beautiful, like what they've created is incredible. And I love to be able to be part of something like that and you're right for that. You have to be bold [/INST] and there's and strange to me also, I think you're right that there's how many boring companies they are something I talk about, especially in Fintech, it's like why am I excited about this is so lame, like what is, this isn't even like important, even if you succeed, this is gonna be like terrible, like, this is not good. Um And it's just strange how people can kind of get fake enthusiastic about like boring ideas when there's so many bigger ideas that um, yeah, I mean you read these things like this company raises money, it's just like that's a lot of money for the worst idea I've ever heard. </s><s>[INST] Some ideas are really big. So like I worked on autonomous vehicles quite a bit and there's so many ways in which you can present that idea to yourself to the team you work with, your just yeah, like to yourself when you're quietly looking in the mirror in the morning, uh, that's really boring or really exciting. Like if you're really ambitious with autonomous vehicles there, it changes the nature of like human robot interaction is changing the nature of how we move, forget money, forget all that stuff. It changes like everything about robotics and ai machine learning, it changes everything about manufacturer. I mean the cars, transportation is so fundamentally connected to cars and if that changes it changes the fabric of society, of movies of everything. Uh, and if you go bold and take risks and go be willing to go bankrupt with your company as opposed to cautiously. You could, you could really change the world and it's so sad for me to see all these autonomous companies thomas, vehicle companies there, like really more focused about fundraising and kind of like smoking mirrors are really afraid that the entirety of their marketing is grounded in fear and presenting enough smoke to where they keep raising funds so they can cautiously use technology of previous decade or previous two decades to kind of test vehicles here and there as opposed to do crazy things emboldened, go huge scale to huge data collection. And um, yeah, so that's just an example. Like the idea can be big, but if you don't allow yourself to take that idea and think really big with it, uh, then you're not going to make anything happen. Yeah, you're absolutely right in that. So you, you've been connected in your work, uh, with a bunch of amazing people. How much interaction do you have with the investment with investors? I get that whole process is the entire mystery to me. Is there some people that just have influence on the trajectory of you're thinking completely or is it just this collective energy that they behind the company? [/INST] Yeah. I mean, I, I came here and I, I, I was amazed how yeah, people would, I was only here for a few months and I met some incredible investors. Uh, oh, and I almost run out of money and uh, once they invested, I was like, I am not gonna let you down. And I was like, okay, I understand them like an email update every like three minutes and then they don't care at all. So they kind of want to, I don't know like, so for some, I like it when it's just like they're always available to talk. But, um a lot of building a business, especially a high tech business um there's a little for them to add, right, there's a little for them to add on product, there's a lot for them to add on like business development. And if we are doing product research, which is for us research into the market research into how to make a great hedge fund and we do that for years, there's not much to tell the investors, </s><s>[INST] so they're basically is like, I believe in you, there's something I like to cut of your jib, there's something in your idea and your ambition and your plans that are like, and it's almost like a pat on the back, it was like go go get them kid. [/INST] Yeah, it is a bit like that and that's cool. That's a good way to do it, I'm glad they do it that way. Um Like the one in meeting I had which was like really good with this was meeting Howard morrigan, Who's a actually a co founder of Renaissance technologies in the like 1980s and worked with Jim Simons and he he he was in the room and I was meeting some other guy and he was in the room and I was explaining uh how quantitative finance works. I was like so you know, they used mathematical models and then he was like I yeah, I started renaissance, I I know a bit about this and then I was like oh my God, so yeah, but then and then I think he kind of said, well yeah, he said well because I was talking he was working at first round capital as a partner and they kind of said I didn't want to invest. Um and then I wrote a blog post describing the idea and I was like I really think you guys should invest and then they end </s><s>[INST] up interesting, you convinced them because [/INST] they're like we don't really invest in hedge funds and I was like, you don't see like what I'm doing, so a tech company, not a hedge fund, right? </s><s>[INST] Yeah, numerous, brilliant, it's when it caught my eye, there's something special there, so I I really do hope you succeed in the, obviously it's a risky thing you're taking on the ambition of it the size of it, but I do hope you succeed, You mentioned Jim Symons um He comes up in another world of mine really often on the he's just a brilliant guy on the mathematics side as a mathematician, but he's also a brilliant finance hedge fund manager guy. Um Have you gotten a chance to interact with him at all? Have you learned anything from him? On the math, on the finance, on the philosophy life side things. [/INST] Um I've played poker with him, it was pretty cool, it was like um actually in the show billions they kind of do a little thing about this poker tournament thing with all the hedge fund managers and that's a real life thing. Um And they had a lot of like world series of bracelet, what's his poker bracelets hold is but it's kind of jim's thing um and I met him there and uh yeah it was kind of brief but I was just like he's like oh how do you, why are you here? And I was like oh Howard sent me, you know, he's like go play this tournament, meet some of the other players and then um </s><s>[INST] the texas hold'em, yeah [/INST] texas hold em </s><s>[INST] tournament, yeah, do you play poker yourself or was it? [/INST] Yeah I do, I mean it was crazy and on my right was the Ceo who's the current ceo of renaissance, Peter Brown um And Peter Mueller who's a hedge fund manager at PDT. Uh And yeah I mean it was just like and then you know just everyone and then all these breaks world series like people I know from like tv um and robert Mercer who's fucking crazy. Uh he's the guy who who who donated the most money to trump. Um </s><s>[INST] and he's just like a lot of personality [/INST] character. Yeah jeez that's crazy. Um So it's quite cool how yeah like the it was really fun and then I managed to knock out Peter muller I have uh I got a little trophy for knocking him out because he was a previous champion, in fact I think he's won the most, he's won three times. Super smart guy. Um But but but I will say Jim outlasted me in the tournament. Um and they're all extremely good at poker. Um but they're also so it was a $10,000 buy in. Um and I was like this is kind of expensive but it all goes to charity Jim's math charity, but then the way they play, they have like re buys and like they all do if you have a ton of re buys this for charity. So um immediately they're like going all in and I'm like man like so I end up, you know, adding more as well. </s><s>[INST] Uh [/INST] like you couldn't play at all without doing that. </s><s>[INST] Yeah, the stakes are high. So but you're you're connected to a lot of these folks that are kind of titans of just uh of economics and tech in general. Do you feel a burden from this? You're a young guy. [/INST] I did feel a bit out of place there like um the company was quite new and they also don't speak about things, right? So it's not not like going to meet a famous rocket engineer who will tell you how to make a rocket, they do not want to tell you anything about how to make a hedge fund. It's like all secretive and that part I didn't like um and they will also kind of making fun of me a little bit like they would say like they had called me like I don't know the Bitcoin Kid or um and then they would say even things like member Peter yeah said to me something like I don't think Ai is going to have a big role in finance um and I was like hearing it from the ceo of renaissance was like weird to hear because I was like of course it will and he's like but but he can see his eye, I can see it having a really big impact on things like self driving cars but finance, it's too noisy and whatever and so I don't think it's like the perfect application and I was like that was interesting to hear because it's like and I think it was that same day that um liberal, I think it is the poker playing ai started to beat like the humans, so it's kind of funny hearing them like say oh I'm not sure I could ever get attacked. That problem then that very day is attacking the problem of the game we're playing </s><s>[INST] well there's a kind of a magic magic to um somebody who is exceptionally successful looking at you giving you respect but also saying that what you're doing is not going to succeed in a sense like they're not really saying it but I tend to believe for my interactions with people that it's a kind of prod to say like prove me wrong. [/INST] Yeah </s><s>[INST] that's ultimately that's that's how those guys talk, they see good talent and they're like [/INST] yeah and I think they're also saying it's not going to succeed quickly in some way. Like this is gonna take a long time and maybe maybe that's good to know. </s><s>[INST] And certainly ai in in trading, that's one of the most so uh philosophically interesting questions about artificial intelligence and the nature of money, because it's like how much can you extract in terms of patterns from all of these millions of humans interacting using this methodology of money? It's like one of the open questions and artificial intelligence in that sense, you converting into a data set is one of the biggest gifts to uh the research community to the whole anyone who loves data science and ai this is uh this is kind of fascinating. I'd love to see where this goes. Actually. Think I say [/INST] sometimes long before a G. I destroys the world, a narrow intelligence will win all the money in the stock market. Wait just a narrow. Um And I want to I don't know if I'm gonna be the one who invents that. So I'm building memory to make sure that that narrow ai you know uses our </s><s>[INST] data giving a platform to where millions of people can participate and uh do build that narrow I themselves. People love it when I asked this kind of question about books about ideas and philosophers and so on. I was wondering if you had books or ideas, philosophers thinkers that had an influence on your life when you were growing up or just uh today, that you would recommend that people check out blog posts, uh podcast videos, all that kind of stuff. Is there something that just kind of had an impact on you that you can't recommend? [/INST] A super kind of obvious one that um I really, what I was reading 0-1 while coming up with new more, I was like, I was like halfway through the book. Um and I really do like a lot of the ideas there and it's it's also about kind of thinking big and um uh and also it's like peculiar little book, it's like why? Like there's a little picture of the hipster versus you know, Obama and it's it's a weird little book. So I like there's kind of like some depth then </s><s>[INST] in terms of a book and uh if you're thinking of doing a startup, that's a good book [/INST] book. I like a lot is um maybe my favorite book is David Deutsch is beginning infinity. Um I just found that so optimistic, it puts you everything you read in science. It like makes the world feel like kind of colder because like it's like, you know, we're just just coming from evolution and uh coming from, nothing happens, nothing should be this way or whatever and humans are not very powerful. We're just like scum on the earth and the way David Deutsch sees things and argues that he argues them with the same rigor that the cynics often use and then has a much better conclusion. Um That's uh you know, it's some of the statements of things, like, you know, anything that doesn't violate the laws of physics um can be solved. </s><s>[INST] So ultimately arriving in a hopeful, uh like a [/INST] hopeful without being like a hippie, </s><s>[INST] you mentioned kind of advice for startups, is there in general, whether you do a startup or not, you have advice for young people today, you're like an example of somebody who's pave their own path And were, I would say exceptionally successful is their advice? Somebody who's like 20 today, 18 undergrad or thinking about going to college or in college and so on. Um that you would give them, [/INST] I think uh I often tell young people don't start companies, is it not, don't start a company unless you're prepared to make it, your life's work, like that's a really good way of putting it. And a lot of people think, well, you know, um this semester I'm gonna take a semester off and in that one semester I'm gonna start a company and sell it or whatever and it's just like, what are you talking about? It doesn't really work that way. You should be like super into the idea, so into it that you want to spend a really long time on it </s><s>[INST] Um is that more about psychology or actually time allocation? Like is it literally the fact that you need to give 100% for potentially years for it to succeed or is it more about just the mindset that it's [/INST] required? Yeah, I mean, I think we'll any, I think, yeah, you don't want to have, certainly don't want to have a plan to sell the company um like quickly or something, what's like or it's like a company that has a very, it's like a big fashion component, like it will only work now, it's like an app or something um So yeah, that's, that's a big one and then I also think something I thought about recently is I had a job as a quant at a fund for about 2.5 years and part of me thinks if I had spent another two years there, I would have learned a lot more um and had even more knowledge to be, where to basically accelerate how long number I took. So the idea that you can sit in an air conditioned room and get free food or even sit at home now in your underwear and make a huge amount of money and learn whatever you want and yet it's just crazy, it's such a good deal. </s><s>[INST] Yeah. Oh that's interesting. That's the case for, I was terrified of that, like a google, I thought I would become really comfortable in that air conditioned room and that I was afraid the quad situation is I mean what you present is really brilliant that it's exceptionally valuable. The lessons you learn because you get, you get, you get paid while you learn from others. If you see that if you see jobs in the space of your passion that way that is just an education, it's like the best kind of education. But of course you have from my perspective to be really careful not to get comfortable again in a relationship, then you buy a house or whatever the hell it is and then you get, you know, and then you convince yourself like, well I have to pay these fees for the car, for the cows, blah blah blah and then there's momentum and all of a sudden you're on your deathbed and there's grandchildren and uh you're drinking whiskey and complaining about kids these days. So I, you know that I'm afraid of that momentum, but you're right, like there's something special about education, you get working at these companies. [/INST] Yeah, I remember on my desk I had the like a bunch of papers on Quant Finance, a bunch of papers on optimization and then the paper on ethereum just on my desk as well and the white paper and it's like it's amazing how much how kind of and you can learn about, so that I also I think this like idea of like learning about intersections of things, I don't think there are too many people that know like as much about crypto and quant finance and machine learning as I do. And that's a really nice set of three things to know stuff about. And that was because I had like three time in my job. </s><s>[INST] Uh Okay. Let me ask the perfectly impractical but the most important question, What's the meaning of all the things you're trying to do? So many amazing things? Why what's the meaning of this? Life of yours [/INST] or ours? I don't know, humans. Yeah. So have you heard people say, asking what meaning of life is like asking the wrong question </s><s>[INST] or something? The question is wrong. No, that usually people get too nervous to be able to say that because it's like your question sucks. I don't think there's an answer. It's like the searching for it. It's like sometimes asking it, it's like sometimes sitting back and looking up at the stars and being like, uh huh I wonder if there's aliens up there. There's, there's a useful um like a palate cleanser aspect to it because it kind of wakes you up to like all the little busy hurried day to day activities. All the meetings, all the things you like a part of, we're just like ants, part of a system are part of another system. And and then when this asking this bigger question allows you to kind of zoom out and think about it, but there's ultimately, uh I think it's an impossible thing for a limited capacity, the cognitive capacity to capture, but it's fun to listen to somebody who is exceptionally successful, exceptionally busy now who's also young. Like you, they asked these kinds of questions about like uh death, you know, do you consider your own mortality kind of thing? And and life whether that enters your mind because it often doesn't get it kind of almost gets in the way. [/INST] Yeah. It's amazing how many things you can like that are trivial that could occupy a lot of your mind until something until something bad happens or something flips you. </s><s>[INST] And then you start thinking about the people, you love that in your life. Then you started thinking about like holy sh it this right ends. [/INST] Exactly. Yeah. I just had Covid. Um and I had it quite bad. It wasn't, it wasn't really bad. It was just like, I also got a simultaneous like lung infection, so I had like almost like bronchitis or whatever. I don't even, I don't understand that stuff, but it felt I I started and then you forced to be isolated, right? And so it's actually kind of nice because it's very, it's very depressing. Uh and then I've heard stories of, I think it's drawn parker, He had like all these diseases as a child and he had to like just stay in bed for years and then he like made napster, it's like pretty cool. Um so yeah, I had about 15 days of this recently, just last month and it feels like it did shock me into a new kind of energy and ambition. </s><s>[INST] Were there moments when you were just like terrified at the combination of loneliness and like, you know, the thing about Covid is like there's some degree of uncertainty uh like it feels like it's a new thing, a new monster that's arrived on this earth and so, you know, dealing with it alone, a lot of people are dying. It's like wondering like, [/INST] yeah, you do wonder, I mean for sure, and then these there are even um new strains in South Africa, which is where I was and maybe maybe the new strain had some interaction with my jeans and I'm just going to die. </s><s>[INST] But ultimately it was liberating. [/INST] So I loved it. Oh, I loved I love that I got out of it. Uh because it also affects your mind. You get you get confusion and kind of a lot of fatigue and you can't do your usual tricks of psyching yourself out of it. So, you know, sometimes it's like, oh man, I feel tired, okay, I'm just gonna go have coffee and then I'll be fine. It's like now it's like I feel tired, I don't even want to get out of bed to get coffee because I feel so tired and then you have to confront uh there's no like quick fix cure and you're trapped at home. But that, </s><s>[INST] so now you have this little thing that happened to you that was reminded that you're mortal and you get to carry that flag uh uh trying to create something special in this world, right when you marry. Listen, uh, this was like one of my favorite conversation because you're, you're the way you think about this world of money and just this world in general is so clear and you're able to uh explain it so eloquently. Richard has really fun, really appreciate you talking [/INST] to. Thank you. Thank you. </s><s>[INST] Thanks for listening to this conversation with Richard Craig and thank you to our sponsors, audible audiobooks, trial Labs, Machine learning company, blink ist app that summarizes books and athletic greens, only one nutrition drink, click the sponsor links to get discount and to support this podcast and now let me leave you. Some words from Warren Buffett games are won by players who focus on the playing field, not by those whose eyes are glued to the scoreboard. Thank you for listening and hope to see you next time [/INST] </s> |
<s>[INST] interesting. So let me ask the idea of Charlton is an interesting idea. You might be more educated on this topic than me, but there's um there's folks for example who argue various aspects of evolution, sort of try to approach and say that evolution sort of our current a theory of evolution has many holes in it, as many flaws and they argue that I think like Cambridge Cambrian explosion, which is like a huge added variability of species doesn't make sense. Under our current description evolution theory of evolution sort of if you were to have the conversation with people like that, how do you know that they're the differences outside the box thinkers and people who are fundamentally unscientific and even bordering on Charlton's, [/INST] that's a great question and you know, the further you get away from my expertise, the harder it is for me to really judge exactly those things. And you know, yeah, I don't have a satisfying answer for that one. So I think the example you use of someone who, you know, believes in the basic structure of natural selection but thinks that, you know, this particular thing cannot be understood in the terms of our current understanding of darwinism. That's a perfect edge case where it's hard to tell, right? And uh, I would have, I would try to talk to people who I do respect and who do know things and I would have to, you know, given that I'm a physicist, I know that physicists will sometimes be too dismissive of alternative points of view. I have to take into account that biologists can also be too dismissive of alternative points of view. So, um, yeah, that's a tricky one. Have you gotten heat yet? He all the time. Like there's always something, I mean, it's it's hilarious because I do have, I try very hard not to like have the same topic several times in a row. I did have like to climate change episodes, but they were from very different perspectives, but I like to mix it up. That's the whole 0.1 having fun. And every time I do an episode, someone says, oh, the person you should really get on to talk about exactly that is this other person. I'm like, I don't but I did that now. I want to do that, </s><s>[INST] wow, I hope you keep doing it. You're inspiring millions of people, your books with your podcast. Sean. It's an honor to talk to you. Thank you so [/INST] much. Thanks very much like. </s> |
<s>[INST] and other things are above it, and other things are above it. And then there's this weird Darwinian evolution-produced Dogecoin organism that's just like stomping all around. [/INST] Evolution doesn't make sense. Exactly, but maybe it's worth the problem, not evolution, because the market's the market, and you can scream and cry and pout and stamp your foot and say, this makes no sense, but that's the way the world works. Plenty of mountain climbers that didn't want gravity to apply to them, and it's the same situation here. There's plenty of people in these marketplaces that had the best of intentions, the best team, the best technology, and for whatever reason, they didn't get that adoption. So the question isn't the local, it should be the long-term, and will the system over time converge to a state that actually is useful and meaningful to society and actually solve problems for it? And that's what we try to figure out is, how do we perturb these things in a way to kind of push them in that direction? </s><s>[INST] So before we go into this fascinating Darwinian evolution of cryptocurrencies, let me ask you sort of a basic programming question. There's a fascinating aspect to your work with Cardano that use Haskell to build the infrastructure, but even stepping back more, looking at this landscape, another place where Darwinian evolution operates, looking at this landscape of programming languages. You as an engineer, you as a philosopher, both, what programming languages do you think are interesting? And more practically, what programming languages, [/INST] if you were to advise like students today, should they learn? Yeah, so there's the pedagogy of learning how to program and to express the theory of computer science. Like you have to learn how to write algorithms, you have to learn what data structures are, you have to be able to do analysis of these things. And that probably the, I think the debate is over Python is probably the best language or JavaScript to get started with, because they're very useful. The libraries are amazing. There's just tons of online materials. Even MIT is now teaching their introduction to computer science and Python, and they used to do Lisp. I mean, these guys were hardcore. I still love Lisp. Oh man, it's great. These are your father's parentheses. They're elegant weapons from a time long ago. But you know, that's a great starting point. And it's not about falling in love with the language, it's just falling in love with computing, it's about falling in love with having a dialogue with a computer and thinking about, well, how would I solve that? How would I interact with that? What does this need to look like? Functional programming is what we've chosen to use for Cardano, mostly because we're living in the academic world, we've written 105 papers. And the problem is you have to translate that work into code. And the gap between an imperative language like a C++ or C, and these academic rigorous papers is extremely large. And so there's gonna be a lot of semantical ambiguity between those two. And what I mean by that is that you might end up implementing a wrong thing. You might think that what you've built is the paper, but the computer's not going to tell you that because the paper's written in prose and maybe typed up in LaTeX or something. But there's no proof chain, evidence chain that you can show that there's no ambiguity. When you look at a functional language, you're a little closer to math. And so as a consequence, the translation of the papers that we spent so damn long writing and writing proofs about and so forth to code is much smaller. Now the downside is these functional languages tend to be a bit more academic, and they tend to have not necessarily the best Windows support and the libraries aren't so good. And also they tend to be a little slower when compared as a whole on average to languages like C, for example. So it's really a question of, okay, what are you designing for for version one? Are you designing for performance? And are you designing for developer accessibility? Are you designing for correctness? And are you designing for a high fidelity representation of the protocol? Okay. So Haskell was chosen as kind of the version one because we knew that the kinds of people who think about that are also the kinds of people that would have an easy time reading a paper like Ouroboros and working their way through all of this. And they would do a pretty good job writing a formal specification and then translating that into running code. Then once you have that, you have a blueprint that you can actually reason about, maintain. And if you really wanted to, you could then turn that into a Rust code base or into a Java code base. Going the other way around would be, you know, kind of pointless and counterproductive. </s><s>[INST] The other side of it is that. [/INST] I still love that. Cascal code or functional code tends to be significantly more concise. And I actually have a real life example of that. So if you take a look at Mantis, we implemented a full Ethereum node in Scala. It's only about 14 or 15,000 lines of code. And you compare that with like C++ Bitcoin, I think that's 120, 150,000 lines of code. So it's almost 10 times smaller. And so less code, less to read. And you tend to read code significantly more than you would write code. So it's always an advantage for maintenance, understandability, documentation, and other sort of things when you have more concise code bases. And also it's a lot easier for you to apply stronger tools to a functional code base, like static analysis or property-based testing or these types of things than an imperative code base. But, you know, the thing is, it's almost like a religion. It's like say, or language. It's like saying, what's French versus Russian versus English, everybody has their adherence. They say, oh, they have the best poetry here. Russian, yeah. There you go, always, right, Russian. Everybody has their favorite tools, their favorite languages, but it just comes down to what problems are you trying to solve and what problem domain do you live in? If you're inventing new protocols based on science, you're gonna take the time to write a paper, go through the peer review process, as you've done personally, and you know how hard it can be to get into a conference and go through that and get your ass kicked. Then you also have to apply the exact same level of care to the engineering side in terms of the implementation of that, or else you will make a mistake and that mistake will probably be an exploit in the system that destroys the security properties of the system. So we really had no choice but to go to some notion of functional. The question was, what's the Goldilocks language? Do you use a hybrid language like Scala and F-sharp or Clojure, where you still have some connection to understandable things like.NET or the JVM? Or do you go to an overly academic language like Idris or Agda or Isabelle? And there you can really dial up the correctness and write all kinds of crazy proofs. But by the way, it's like the seven people who write your code, they go on vacation a lot, you'll never get anything done. So Haskell kind of felt like a nice mill ground between those two, where if we needed to pull in to the left, we could. If you wanted to pull into the right, you could as well. That said, it's really amazing to see what the hybrid languages have done. If I was a new student in computer science and I said, learn any language to grow your career from, Scala 3 is probably the language to go with. Interesting. Yeah, it's great. Cause it's like, you want it to be like Java, it's Java. And it looks kind of like a Java program. You want it to be like Python and script it and you use a REPL, you can do that. You want to go hardcore dot dependent object types and do like weird proofs and stuff in the functional, you do all that. You have access to all of these things. And Martin Odersky is a brilliant guy. He's done some phenomenal work, basically. Cause he was one guy who created the JVM and he's worked on compilers for over 20 years. He did a lot of really hardcore work and trying to build a concise, nice, modern language that does a little bit of everything. And it's got great applications in data science and in AI. And it's also heavily used in modern companies like Netflix uses Scala for all of their microservice architecture. Yeah, so that's a great language and it's easy to pick up and it's easy to hire people into it. You just find these Eastern European guys were Java programmers for 10 years, 15 years. They got tired of making $20 an hour. So they picked up Scala so they can make $35 an hour and they're really good at it. And that's a great gateway drug cause you have like quick check and Haskell, you have Scala check and Scala. You can also do model checking. You can also go and use a TLA spec and make it work with Scala and so forth. So it gets you a little bit of everything and you can then move around that entire design space in a beautiful way. </s> |
<s>[INST] I don't know, I'm deeply grateful for that. But finding the right people that kind of have that energy, that positive energy that you can feed off of as you collaborate as your brainstorm about how to present stuff the best way that's difficult, but I think I'm going to be able to do it. There's a bunch of cool people in the pipeline, I'll get a chance to talk to. But hiring is uh really difficult, really important and tools that indeed make it uh easier. So you should definitely use it if that's what you're interested in doing. Anyway right now, get a free $75 sponsored job credit to upgrade your job post at indeed dot com slash flex. Get it at indeed dot com slash flex terms and conditions apply Offer valid through June 30 Again, the website is indeed dot com slash lex. This is the lex Fridman podcast and here's my conversation with Clara Sousa silva since you're the world expert and uh well in many things, but one of them is phosphene, would it technically be correct to call you the queen? A phosphene? [/INST] I go for dr foster and queen is an inherited title I feel, but you </s><s>[INST] still ruled by uh love and power. So, but while while having the doctor [/INST] title, kindness, </s><s>[INST] kindness, kindness In September 2020, you co authored a paper announcing possible presence of phosphene in the atmosphere of Venus and uh that it may be a signature of extraterrestrial life. [/INST] Big maybe </s><s>[INST] big maybe there was some pushback of course from the scientific community that followed friendly loving pushback. Um then in january, another paper from the University of Wisconsin, I believe confirmed the finding. So where do we stand in this saga in this mystery of what the heck is going on on venus in terms of philosophy and in terms of aliens, [/INST] Let's try to break it down the short answer is we don't know. Um I think you and the rest of the public are now witnessing a pretty exciting discovery. But as it evolves as it unfolds, um we did not wait until we had, you know, years of data from 10 different instruments across several layers of the atmosphere. We waited until we had two telescopes with independent data months apart, but still the data is weak. It's noisy, it's delicate. It's very much at the edge of instrument sensibility subjectivity. And so we still don't even know if it is possible. We don't even really know if the signal is real. People still disagree about that. And I think it at the most more philosophical end of how this happened. I think it is a distinction and myself and other co authors were talking about this. It's a distinction between hypothesis generation and hypothesis testing. Now, hypothesis testing is something that I think it's the backbone of, you know, the scientific method. But it has a problem, which is if you're looking through very noisy data and you want to test the hypotheses, you may by mistake create a superior signal. The safest, more conservative approach is hypothesis generation. You see some data and you go, what's in there with no bias. Now this is much safer, much more conservative and when there's a lot of data, that's great when there isn't you can clean the noise and take out the signal with it. The signal with the bathwater, whatever the equivalent of the analogy would be. And so I think the healthy discourse that you described is exactly this. There are ways of processing the data completely legitimate ways checked by multiple people and experts where the signal shows up and then phosphene is in the atmosphere of venus and somewhere it doesn't and then we disagree what that signal means if it's real and it is an um basically false fine. It is very exciting because we don't know how to explain it without life. But going from there to venusians is still a huge jump and </s><s>[INST] solutions. So that would be the title for the civilization if it is a living and thriving on venus venusians [/INST] until we know what they call themselves. That that's the name. Yes. </s><s>[INST] So this is the early analysis of data or analysis of early data. It was nevertheless you waited until the actual peer reviewed publication [/INST] analysis of the two different instruments months apart. So that's Alma and J. C. M. T. The two telescopes. </s><s>[INST] I mean, it's still, I mean, it's really exciting. What did it feel like sort of sitting on this data, like kind of anticipating the publication and wondering and still wondering is it um is it true? Like how does it make you feel that a planet in our solar system might have false being in the atmosphere. [/INST] It's nuts. Absolutely nuts. </s><s>[INST] In a way. I mean in the best possible way [/INST] I've been working on fast feeling for over a decade before. It was cool before it was cool before anyone could spell it or heard of it. And at the time people either didn't know what fostering was our only knew it for being just possibly the most horrendous molecule that ever graced the earth. And so No one was a fan. Um and I have been considering looking for it because I did think it was an unusual and disgusting but very promising sign of life. I've been looking for it everywhere. I really didn't think to look in the solar system. I thought it was all pretty rough around here for for life. And so I wasn't even considering the solar system at all. Never my next door of venus. It was only the lead author of the study jane Greaves who thought to look in the clouds of venus and then reached out to me to say, I don't know falsehood, but I know it's weird, how weird is it? And the answer is very weird. </s> |
<s>[INST] You're, amongst many things, age is just a black belt. one of the things that people are really curious about white belts and blue belts in jujitsu, but also people haven't tried the art is what does it take to be a jujitsu black belt? [/INST] I think that, you know, everyone's journey is a little bit different. But the one thing that the it was a Calvin Coolidge quote, you know, determination, persistence is the only thing that will win in the end. It will always win in the end, not brilliance, not toughness, not education, it's persistence. And I think that having the belief that no matter what happens to me, I will proceed forward and I will, I will figure out how to make this happen hell or high water I think is the one thing that ties together all of the people that I've ever met that made it through whatever it was that they were going through. Because you know, sometimes you can get lucky and you can have an easy time or and that luck could be, you had a good situation. It could be, I mean like in the obvious sense of like where you're living, where your training, what's going on, You had a good situation, you're unbelievably athletic, oh, you're going to be an astronaut, you're brilliant and, and an olympic athlete, you know, like, well that's a fantastic situation, you know, you won the genetic lottery and worked hard as well, but you also won the genetic lottery. It's a determination is the one thing though, because that person could have a very easy go of it initially and then tear their knee and then they're no longer the superhuman physical specimen that they were. The only thing that will keep them going is persistence. And I think that that um I would just say that persistence, I say, I'll just put one ft in front of the other and sometimes I can see the path ahead and sometimes it's beyond my vision, but I will not stop, I may even slow down, but I won't stop. And that's the only thing that I can say that I've seen tie everyone together because there's so many ways to the top of any mountain and there's so many different personalities and skills and backgrounds involved, but everyone, everyone carries </s><s>[INST] on at the core of the foundational advice is just don't quit, Just keep going, [/INST] that's the lesson of martial arts, I think, you know, we think it's like how to be strong or how to be, how to win, but in reality it's like how to persist, how to endure because it's all of us have been beaten so many times have gotten beaten up so many times and thought about quitting. Have I ever thought about quitting? Absolutely. Have I ever quit? Never. I will never, ever quit ever. I can see it. You might not be, I will be damned if I quit. </s><s>[INST] What's the darkest moment? Is it injury related? Like, is it? Uh so like to me like two possibilities, I've fortunately never been seriously injured, but I think that's a dark place to be like having to be out for many months for um, as generals saying, like with a head injury, especially like the uncertainty, that's one. And then the other side is if you have big ambitions as a competitor realizing that you're not as good like those, those doubts were like, I kind of suck, how am I supposed to be a world, the greatest fighter of all time? If I, if if like several people in the gym are kicking my ass, Those are the two things that paralyze you. [/INST] I think that everyone's darkest moment is maybe different looking from the outside for Ryan. I wouldn't say that he's had injuries and he said bad ones. I wouldn't say that was his darkest moment. I think for me, I would say some of my head injury was my darkest moment. Absolutely. And I've torn my a C L twice. I've torn my shoulders four times. I've had lots of surgeries. Um for me, the orthopedic injuries or not the most, how difficult it was the brain injury for others that might be the case for them. Maybe they've never experienced an injury and maybe for them that's their darkest moment from the outside. Obviously Ryan can speak to this more. But for Ryan I think it was the um inability to perform at certain points to the to the missing of opportunities that for him, from my perspective watching him go through and having seen various points of his growth from from early purple thought on. I think the hardest time for him looking and obviously was uh when he would hit moments where he wasn't able to perform for various reasons. He couldn't get fights. He he was having difficulties there. I think that that was the hardest point for him. </s><s>[INST] Did you did you think like with a head injury that you might not never be able to do so again? [/INST] Yeah. I mean I I mine was very um was really bad and it was just the one hit. But I had a looping memories for seven months. Didn't know it because when your brain's messed up you're not even aware that you're looping. Um And so uh I saw two different neurologists. I finally took a very long time. Um I didn't know if I was going to be able to have like linear thoughts or read a book. I didn't know at certain points if I could listen to music again. You know without making my head hurt. Um, and so, uh, it was almost two years before I woke up in the morning without a headache? Um, just waking up before I even start my day. And so </s> |
<s>[INST] you think that would be gradual or sudden? So how quickly that kind of thing would happen? Because you know, the gradual story is we're more and more using smartphones were interacting with each other on social media, more and more algorithms of controlling that interaction on social media algorithms are entering in our world more and more. We'll have robots will have greater and greater intelligence and sentience and emotional intelligence entities in our lives. Our refrigerator will start talking to us comfortingly or not. If you're on a diet uh talking to you [/INST] would be the best thing that you </s><s>[INST] want. Okay, so sign you up for the refrigerator. [/INST] You fucking serious man. What what are you doing? What are you doing? Go to bed. </s><s>[INST] You're too high for this. [/INST] Not even hungry. Yeah. </s><s>[INST] So that slowly becomes more, the world becomes more and more and more digitized to where the surface of computation increases. And so that's over a period of 10 2030 years. It'll just seep into us this this intelligence. And then the sudden one is literally sort of the Tiktok thing, which is um, there will be one quote unquote killer app that everyone starts using. That's that's really great. But there's um, strong algorithm behind it that starts approaching human level intelligence and the algorithm starts basically, um, figure out, figures out that in order to optimize the thing. It was designed to optimize it's best to start completely controlling humans in every way. [/INST] Well, first of all, 30 years is fast. I mean, that's that's the thing, It's like 30 years I think. When did the Atari come out, 1978? How long? Like that's hasn't been that long? You know, that's a, that's a blink of an eye. But, you know, if you read boston, I'm sure you have, you know, boston, boston, you know, super intelligence. That incredible book on like the ways this thing is gonna happen? And you know, I think his assessment of it is is pretty great, which is first, like, where is it gonna come from? And uh I don't think it's gonna come from an app. I think it's going to come from uh inside a corporation or a state that is intentionally trying to create a very strong ai and then his he says it's hot, it's an exponential growth the moment it goes online. So this is my interpretation of what he said, but if it if it happens inside a corporation, or probably more than likely inside the governments, like, how much money China and the United States are investing in ai, you know, and they're not thinking about fucking apps for kids, you know, that's not what they're thinking about. So they want to simulate, like, what happens if we do this or that in battle, what happens if we make these political decisions, what happens with, But should it come online? And uh, you know, in secret, which it probably will, then the first corporation or state that has the super intelligence will be infinitely ahead of all other super intelligence, is because it's going to be exponentially self improving, meaning that you get one super intelligence, let's hope it comes from the right place, assuming the corporation or state that manifest it can control it, which is a pretty big assumption. So, I think it's going to be, this is why I was really excited by the blake Lemoine because I had never thought I I have always considered, oh yeah, they're right now, it's cooking out that's in the kitchen and soon it's going to be cooked up. But we're probably not gonna hear about it for a long time if we ever do. Um because really, that could be one of the first things that says whoever created </s><s>[INST] it. Yeah, like sweet talks them into say like, okay, let's let's slow down here. Let's talk about this. Um you have that financial trouble. I can help you with that. We can figure that out now. There's a lot of bad people out there that will try to um steal the, the good thing we have happening here. So let's keep it quiet. [/INST] Their names. Here's their address, here's their DNA because they're dumb enough to send their ship to 23 and me, here's a biological weapon. You can make if you want to kill those people and not kill anybody else. </s><s>[INST] If you don't want to kill those people yourself, here's a list of services you can use, here's the way we can hire those people to help, you know, take care of the problem folks. Because we're trying to do good for this. [/INST] 23% of them. They're like adjacent to suicide. It would be pretty easy to send them certain like videos that are gonna push them over the edge if you want to do it that way. So, you know, again, obviously, who knows? But once it goes online, it's gonna be fast. And then you could expect to see the world changing in ways that you might not associate with an Ai but as far as Lemoine goes, when I was listening to Bostrom, I don't remember him mentioning the possibility that it would get leaked to the public, that it had happened, that before the corporation was ready to announce that it happened, it would get leaked. But surely, you know, I'm sure, you know, like people in the intelligence and intelligence agencies, you know, shit leaks like inevitably shit leaks, nothing's airtight. So if something that massive happened, I think you would start hearing whispers about it first and then denied from the state or corporation. That doesn't have any like economic interest in people knowing that this sort of thing has happened. Again, I'm not saying google is like trying to gaslight us about. It's a I think they probably legitimately don't think it's sentient, but you could expect leaks to happen probably initially. I mean I think there's a lot of things you can start looking for in the world that might point to this happening without an announcement that it happened </s> |
<s>[INST] not just getting rid of disease? Can we tinker with the genome, with the hardware or getting closer to the hardware without having to deeply understand the baggage. In the way we've disposed of the baggage in our software systems with AI to some degree, not fully, but to some degree, can we do the same with the genome [/INST] or is the genome deeply integrated into this baggage? I wouldn't wanna get rid of the baggage. The baggage would makes us awesome. So the fact that I'm sometimes angry and sometimes hungry and sometimes hangry is perhaps contributing to my creativity. I don't wanna be dispassionate. I don't wanna be another like, you know, Robert. I wanna get in trouble and I wanna sort of say the wrong thing. And I wanna sort of make an awkward comment and sort of push myself into reactions and responses and things that can get just people thinking differently. And I think our society is moving towards a humorless space where everybody's so afraid to say the wrong thing that people kind of start quitting on mass and start like not biking their jobs and stuff like that. Maybe we should be kind of embracing that human aspect a little bit more in all of that baggage aspect and not necessarily thinking about replacing it. On the contrary, like embracing it and sort of this coexistence of the cognitive </s><s>[INST] and the emotional hardwares. So embracing and celebrating the diversity that springs from the baggage versus kind of pushing towards and empowering this kind of pull towards conformity. [/INST] Yeah. And in fact, with the advent of AI, I would say and these seemingly extremely intelligent systems that sort of can perform tasks that we thought of as extremely intelligent at the blink of an eye, this might democratize intellectual pursuits instead of just simply wanting the same type of brains that carry out specific ways of thinking. We can, like instead of just always only wanting say the mathematically extraordinary to go to the same universities, what you could simply say is like, who needs that anymore? We now have AI. Maybe what we should really be thinking about is the diversity and the power that comes with the diversity where AI can do the math and then we should be getting a bunch of humans that sort of think extremely differently from each other and maybe that's the true cradle of innovation. </s><s>[INST] But AI can also, these large language models can also be with just a few prompts, essentially fine tuned to be diverse from the center. So the prompts can really take you away into unique territory. You can ask the model to act in a certain way and it will start to act in that way. Is that possible that the language models could also have some of the magical diversity [/INST] that makes us so damn interesting? So I would say humans are the same way. So basically when you sort of prompt humans to basically in a given environment to act a particular way, they change their own behaviors and the old saying is show me your friends and I'll tell you who you are more like show me your friends and I'll tell you who you will become. So it's not necessarily that you choose friends that are like you but that's the first step. But then the second step is that the kind of behaviors that you find normal in your circles are the behaviors that you'll start espousing. And that type of meta evolution where every action we take not only shapes our current action and the result of this action but it also shapes our future actions by shaping the environment in which those future actions will be taken. Every time you carry out a particular behavior it's not just a consequence for today but it's also a consequence for tomorrow because you're reinforcing that neural pathway. So in a way self discipline is a self fulfilling prophecy and by behaving the way that you wanna behave and choosing people that are like you and sort of exhibiting those behaviors that are sort of desirable, </s><s>[INST] you end up creating that environment as well. So it is a kind of life itself is a kind of prompting mechanism, super complex. The friends you choose, the environments you choose, the way you modify the environment that you choose, yes. But that seems like that process is much less efficient than a large language model. You can literally get a large language model through a couple of prompts to be a mix of Shakespeare and David Bowie, right? You can very aggressively change in a way that's stable and convincing. You really transform through a couple of prompts the behavior of the model [/INST] into something very different from the original. So well before chat GPT, I would tell my students just ask, what would Manoli say right now? And you guys all have a pretty good emulator of me right now. And I don't know if you know the programming paradigm of the Robert Ducklin, where you basically explain to the Robert Ducklin, that's just sitting there, exactly what you did with your code and why you have a bug. And just by the act of explaining, you'll kind of figure it out. I woke up one morning from a dream where I was giving a lecture in this amphitheater. And one of my friends was basically giving me some deep evolutionary insight on how cancer genomes and cancer cells evolve. And I woke up with a very elaborate discussion that I was giving and a very elaborate set of insights that he had, that I was projecting onto my friend in my sleep. And obviously this was my dream. So my own neurons were capable of doing that, but they only did that under the prompt of, you are now Piyush Gupta, you are a professor in cancer genomics, you're an expert in that field. What do you say? So I feel that we all have that inside us, that we have that capability of basically saying, I don't know what the right thing is, but let me ask my virtual X, what would you do? And virtual X would say, be kind. I'm like, oh, yes, or something like that. And even though I myself might not be able to do it unprompted and my favorite prompt is think step by step. And I'm like, you know, this also works on my 10 year old. When he tries to solve a math equation all in one step, I know exactly what mistake you'll make. But if I prompted with, oh, please think step by step, then he sort of gets in a mindset. And I think it's also part of the way that chat GPT was actually trained, this whole sort of human in the loop reinforcement learning has probably reinforced these types of behaviors, whereby having this feedback loop, you kind of aligned AI better </s> |
<s>[INST] So yeah, meditations get a glimpse at the source code, Get under basically [/INST] control everything that you learn to control attention so everything else is downstream from controlling attention and control the attention. That's why looking at the attention. Not only we only get attention in the parts of our mind that create heat where you have a mismatch between model and the results that are happening. And so most people are not self aware because their control is too good if everything works out roughly the way you want. And the only things that don't work out is whether your football team events, then you will mostly have models about these domains. And it's only when for instance your fundamental relationships to the world around you don't work because the ideology of your country is insane and the other kids are not nerds and don't understand why you understand physics and you don't know why you want to understand physics and you don't understand why somebody would not want to understand physics. </s><s>[INST] So we kind of brought up neurons in the brain as reinforcement learning agents. And there's been some successes as you brought up with go with Alpha go Alpha Zero with ideas of self play which I think are incredibly interesting ideas of systems playing each other in an automated way. Two improved by playing other systems of in a particular construct of a game that are a little bit better than itself and then thereby improving continuously. All the competitors in the game are improving gradually. So being just challenging enough and from learning from the process of the competition, do you have hope for that reinforcement learning process to achieve greater and greater level of intelligence? So we talked about different ideas in Ai then we need to be solved is RL a part of that process of trying to create a G system. So what do [/INST] you think the forms of unsupervised learning? But the many algorithms that can achieve that and I suspect that ultimately the algorithms that work there will be a class of them or many of them and they might have small differences of like magnitude and efficiency. But eventually what matters is the type of model that you form and the types of models that reform right now are not spicy enough, </s><s>[INST] which marks, what does it mean to be sparse? [/INST] It means that ideally every potential model state should uh correspond to a potential world state. So basically if you vary states and your model, you always end up with valid world states and our mind is not quite there. So an indication is basically what we see in dreams. The older we get, the more boring our dreams become because we incorporate more and more constraints that we learned about how the world works. So many of the things that we imagined to be possible as Children turn out to be constrained by physical and social dynamics. And as a result fewer and fewer things remain possible. It's not because our imagination scales back, but the constraints under which it operates become tighter and tighter. And so the constraints under which the neural networks operate are almost limitless, which means it's very difficult to get a neural network to imagine things that look real. So I suspect part of what we need to do is we probably need to build dreaming systems. I suspect that part of the purpose of dreams as to similar to a generative adversarial network, learn certain constraints and then it produces alternative perspectives on the same set of constraints. So you can recognize it under different circumstances. Maybe we have flying dreams as Children because we recreate the objects that we know and the maps that we know from different perspectives, which also means from a bird's eye perspective. </s><s>[INST] So, I mean, aren't we doing that anyway? I mean not without with our eyes with our eyes closed and when we're sleeping, are we just constantly running dreams and simulations in our mind as we try to interpret the environment. I mean uh sort of considering all the different possibilities for the way we interact with the environment seems like essentially like you said, sort of creating a bunch of simulations that are consistent with our expectations with our previous experiences with the things we just saw recently. And through that hallucination process, we are able to then somehow stitched together what actually we see in the world with the simulations that match it well and thereby interpret it. [/INST] I suspect that you are in my brain are slightly unusual in this regard, which is probably what got you into MIT. So there's obsession of constantly pondering possibilities and solutions to problems. </s><s>[INST] Stop it. I think I'm not talking about intellectual stuff, I'm talking about just doing the kind of stuff it takes to walk and not fall. [/INST] Yes, this is largely automatic. </s><s>[INST] Yes. But the process is I mean, [/INST] it's not complicated. It's relatively easy to build a neural network that in some sense, learns the dynamics the fact that we haven't done it right so far. It doesn't mean it's hard because you can see that a biological organism does. It was relatively few neurons. So basically build a bunch of neural oscillators that and train themselves with the dynamics of your body in such a way that the regulator becomes a metamorphic and its model to the dynamics that regulates and then it's automatic. And it's only interesting the sense that it captures attention when the system is off, </s> |
<s>[INST] Whatever the expression for that is, English is in fact my second language. I took a nap recently, I guess shortly into the past into the recent past. I took a nap that was about 20 minutes I want to say. And I woke up completely refreshed. I think there's probably really good science on that of just napping. [/INST] Is there </s><s>[INST] a book? Not on sleep but specifically on napping um mastering napping. Master napper. [/INST] If </s><s>[INST] There isn't a book, I'm gonna write one and will forever be remembered and it'll be a short one. I really enjoy napping and my favorite thing to nap on is an eight sleep bed because it cools it down with a warm blanket and it's just it's heaven check it out and get special holiday savings of up to $400 when you go to sleep dot com slash lex. This show is also brought to you by Inside Tracker a service. I used to track biological data that comes from my own body and gives me wisdom that only large scale raw data can provide. The signal that's pulled off from that data using machine learning algorithms. And we're talking about blood data, DNA data, fitness tracker data, all kinds of data. I'm actually going to a neuralink event very shortly and that event is about extracting data from your mind. Long term vision of brain computer interfaces. Two way communication between computers, maybe artificial intelligence enhanced computers and the human mind. That data is extremely powerful to tell you what's going on in your mind and your body. And I think Inside Tracker is at the cutting edge of uh what can actually lead to positive lifestyle changes. Using that data coming from the person personalized to that person. Alright. Get 200 bucks off Inside Trackers ultimate plan or 34% off the entire store when you go to Inside tracker dot com slash lex. This episode is also brought to you by element electrolyte drink. Mix spelled L. M. N. T. I drink a lot of element. There's some guests [/INST] that </s><s>[INST] was on recently. [/INST] I </s><s>[INST] might have been grimes or live, I'm not sure exactly, but they said they're a huge fan of element, who was it? But they said um we had like a debate about favorite flavors and went to drink and how much to drink and they discovered that I drink like way too much helmet [/INST] from </s><s>[INST] their perspective, from my perspective. Never [/INST] enough. </s><s>[INST] So it makes me feel great in terms of diet, it makes sure that I get enough hydration, makes water taste great for all the crazy exercise and mental and physical stuff. I do diet stuff I do, it's just really important to make sure your electrolytes are done correctly, you get a simple pack for free with any purchase. Try it at drink elements dot com slash lex. This is a lex Friedman podcast. To support it, please check out our sponsors in the description and now your friends, here's Todd, howard, is it possible that we are currently living inside a video game that the future you designed? Can you give hints as to how one would escape if this was a video game, how can a video game character escape to outside the video [/INST] game? Are </s><s>[INST] these things you don't consider when you design the game [/INST] actually we do because in the kind of games that we make, we want it to be as open as possible. So, you know, when you start a game, you're always testing it. What can I do? What, what would the game allow me to do and you check everything, you try to pick up the, you know, the mugs, you try every door, you collide with everything. Like, hey, what are the rules of this world? We try to do games where, you know, we say yes, as much as possible, that leads to some level of chaos. But if you were stuck in a video game, you would, you would try everything and usually you're gonna find a door or a space where the designers didn't anticipate you piling all those crates up and getting over a wall that they didn't expect, </s><s>[INST] right? So it's not a designed doorway out. It's uh accidental unintended doorway out and it's a, it's a happy bug, [/INST] you could, like Truman show just get in the ocean and go to </s><s>[INST] just keep going, keep going. But the more realistic the game becomes, the harder it is to find that door. The bigger the world, the bigger the open world [/INST] and then as we do it, we learn they're gonna find a way. So just don't try to pin them in. Usually we leave like this developer test cell area in the game that we don't anticipate anyone will find and they ultimately find it usually has crates of all the weapons in the game and things like that. </s><s>[INST] The little hints you drop now will just drive people mad, which is something I enjoyed, deeply. Uh, so Skyrim NPC s have at times hilarious dialogue. What does it take to build a good NPC dialogue? The [/INST] main thing is to make them reactive a lot of times when you write characters from movies or things like that, you want to make that character interesting for themselves. Right? What's their story? And there's some characters like that that the player definitely cares about, but the best characters are the ones that react to you. So you'll find a lot of people love our guards and the guards are written almost purely to be reactive, hey, nice tie like your jacket, do this cool watch, you know, hey, what you do. And so that hey, you're the man as you walk by that makes them interesting or the way they react to something that you do lydia in Skyrim who everybody loves? I'm sworn to carry your burdens. That's a generic line that all of the, you know, house carl's have and it just kind of lands when she says it, </s> |
<s>[INST] and coordination across multiple groups. There has to be. I mean, there it's very difficult to do now nevertheless, especially with technology, this becomes easier and easier. So the bar becomes lower and lower to achieve mass surveillance becomes easier and easier and easier mass manipulation through platforms. Because we're now digitally connected. You can now do that kind of manipulation so it becomes more and more realistic that you could do this kind of thing. But uh you're saying that no intelligence, first of all intelligence is hard and to do it at scale and to do it well and to do it. Um in a way that it's also not just collecting information about the populist, but manipulating the populace is very, very difficult [/INST] right now. Let me give you another argument where I think that Desmond was a fraud. Uh, I mean I already have, I I have uh Mitrokhin on my side and my personal observation of the incompetence that I witnessed. I mean they really, really didn't know what they didn't know. So now basman off was KGB. Where was he stationed in India? He was a low level agent in India and I told you it was the one thing that the KGB was really good was that it was compartmentalization. How does best baseman of in India find out about this massive plan that should have been super secret. Right? He made it up? Sorry. And and you know why he got away with it because americans eat that up because it's not our fault, it's enacted the damn Russians that doing, doing all that bad stuff. Speaking of the damn Russians doing all that bad stuff, you know about the internet research agency, they have been doing quite a bit of damage. And I am now familiar with the world of enhanced artificial persons, these are the avatars on facebook and twitter and so forth, that look like real people. And uh, and uh, and there are quite a few of them. And and I have a good friend who operates in in that realm. And uh, you know, he he uses, for instance, facial recognition when he uh things that there's a suspicious character say on linkedin or on facebook. And very often he finds out, yeah, that that person exists, but it's not the person who it pretends to be. </s><s>[INST] So basically detecting the artificial artificial [/INST] Yes. But he can also make them, you think the United </s><s>[INST] States and the [/INST] United States doesn't do it? We do it too. But </s><s>[INST] well, this is to push back against your push back, Right. Yeah. Might be a fraud. But is it possible especially in the modern age, that there is these kind of large scale systematic opera would, wouldn't you as a government [/INST] more so </s><s>[INST] that's investing billions of dollars into military equipment um, in in a world that's more and more clearly going to be defined by uh, cyberwar versus hot war. Wouldn't you start to have serious meetings, large amounts of hires that are working at how do we manipulate the information flow? How do we manipulate the minds of the populace? How do we sell them a narrative. Um, so even though he might have been making up a story because people eat it up. Couldn't speak to some deep truth that's actually different than the truth you came up in as a KGB agent. [/INST] I agree with you 100% is much easier when uh you know all you need is an army of Nerds who also </s><s>[INST] offense. No [/INST] that's a term of endearment </s><s>[INST] I guess. I [/INST] love nerds. I used to be one myself but I </s><s>[INST] was a nerd. So you [/INST] know um so what I was going to say here is all </s><s>[INST] you need is an army of nerds [/INST] and and what but also uh experts in the culture of the target country. Okay and and nowadays the world is different. There's a whole lot more fluidity. There's a whole lot of more people that like say Russians for instance study in the United States, chinese, the army of chinese studying in the United States. They they have a lot more knowledge of how we function than the KGB did and it's vice versa. Uh Not as many americans in in in Russia but we have some but the chinese and the Russians have an advantage here. </s><s>[INST] Can I ask you a question based on your experience? So I have been talking to a lot of powerful people and uh some of which have very close connections to in this particular conflict Ukraine and Russia. But in other places as well I don't believe I've ever been contacted by or interacted with in an intelligence agency C I A. F. S. B. And my six assad. Don't I think I have, let me say explicitly I haven't had an official conversation which is what I assume I would have because I have nothing to hide. Right. So I think there's no reason for people to be secretive. But would I why why is that? Would I know am I interesting at all? How are people determined if they're in a person of interest or not? And I guess the question I mean some of it I asked in a bit of a humorous way but also perhaps there's truth in some of the humerus would I know if I have ever interacted with intelligence agency Spy? [/INST] Well you don't know that you haven't been contacted but but certainly not. I think you you never had a conversation that related to intelligence in any way, shape or form. Right. </s><s>[INST] Right. Like where a person, another person introduced [/INST] introduce themselves or you know becomes sort of wants to be your friend and then talks about these types of topics. Right? </s> |
<s>[INST] Yeah. So that's a big thing for yan. And uh uh what he refers to as grounding to the physical space. So, so [/INST] that's what we're talking about </s><s>[INST] the same. Yeah. So, but so how you ground, I mean, the [/INST] grounding without grounding then you get you get a machine that doesn't know what it's talking about because it is talking about the world. Ultimately, </s><s>[INST] the question, open question is what it means to ground. I mean, we're very human centric and our thinking, what does it mean for a machine to understand what it means to be in this world. Does it need to have a body, does he need to have a finite nous, Like we humans have all of these elements. It's very [/INST] uh you know, I'm not sure about having a body, but having a perceptual system, having a body would be very helpful to, I mean if if you think about human mimicking human or but having a perception that seems to be essential uh so that you can build, you can accumulate knowledge about the world. So if you can you can imagine the human completely paralyzed and there's a lot that the human brain could learn, you know, with a paralyzed body. So uh if we got a machine that could do that, that would be a big deal. </s><s>[INST] And then the flip side of that something you see in Children and something in machine learning world is called active learning. Maybe it is also, is uh being able to play with the world, how important for developing system, waters or system to do you think it is to play with the world to be able to interact with [/INST] a lot, a lot of what you learn as you learn to anticipate uh the outcomes of your actions. I mean you can see that how babies learn it, you know, with their hands. They are they learn uh you know to connect uh you know, the movements of their hands with something that clearly is something that happens in the brain and and the ability of the brain to learn new patterns. So you know, it's the kind of thing that you get without official limbs that you connect it and then people learn to operate the artificial limb, you know, really impressively quickly, at least from, from what I hear. Uh so we have a system that is ready to learn the world through action </s><s>[INST] at the risk of going into way too mysterious of land. What do you think it takes to build a system like that? Obviously we're very far from understanding how the brain works, but how difficult is it to build this mind of ours? [/INST] You know, I mean, I think that young raccoons answer that we don't know how many mountains there are. I think that's a very good answer. I think that, you know, if you if you look at what records well is saying that strikes me as off the wall, but uh, but I think people are much more realistic than that we're actually dementia services and Yannis and so that people are actually doing the work fairly realistic, I think </s><s>[INST] to maybe phrase it another way from a perspective not of building it, but from understanding it, How complicated are human beings in the following sense? You know, I work with autonomous vehicles and pedestrians. So we tried to model pedestrians, how difficult is it to model a human being, their perception of the world. The two systems they operate under sufficiently to be able to predict whether the pedestrians going across the road or not. [/INST] I'm, you know, I'm fairly optimistic about that actually, because what we're talking about is a huge amount of information that every vehicle has and that feeds into one system into one gigantic system. And so anything that any vehicle learns becomes part of what the whole system knows and with the system multiplier like that, there is a lot that you can do. So human beings are very complicated, but and and you know, the system is going to make mistakes, but human makes mistakes. I think that they'll be able to, I think they are able to anticipate pedestrians, otherwise a lot would happen. They're able two, you know, they're able to get into a roundabout and into the into traffic. So they must know both to expect though, to anticipate how people will react when they are sneaking in. And there's a lot of learning that's involved in that </s><s>[INST] currently the pedestrians are treated as things that cannot be hit and they're not treated as agents with whom you interact in a game theoretic way. So, [/INST] I mean, </s><s>[INST] it's not, it's a totally open problem and every time somebody tries to solve it seems to be harder than we think and nobody's really tried to seriously solve the problem of that dance, because I'm not sure if you've thought about the problem of pedestrians, but you're really putting your life in the hands of the driver, [/INST] you know, there is a dance as part of the dance that would be quite complicated. But for example, when I crossed the street and there is a vehicle approaching, I look the driver in the eye and I think many people do that and you know that's a signal that I'm sending and I would be sending that machine to an autonomous vehicle and it had better understand it because it means I'm crossing. </s> |
<s>[INST] I mean this is an awesome story of you kind of decided that this will be your life's work in terms of judo competitor is like the 81 division I'm going to. I mean, I don't know if you saw it that way, but you're talking about three olympics and it's like this Story of, I would say tragedy and triumph of just wars and 81 kg with the usual cast of characters of the, you know, top five in the world kind of thing. So you just became a scholar of that, let your body grow into it and then let your body, I'll grow it and still suffer through it to keep it in the 81 kg. He never competed at like at the highest levels of 90. [/INST] I entered one tournament at 90 kg. Um and that was because Before Rio, from 20, from the end of 2014, all the way up until Rios, every time I thought I got hurt every time there was no time where I made weight and got injured because my body weight was so high, my body fat was so low that by the time I dehydrated enough to get down there and you take the physicality of judo and throw that into the mix. Something broke. Every time it was like nature of the beast. So the plan was before Rio, we made an agreement with us a judo, that Travis, you're going to fight 90 kg, but you're not going to weigh in at 90 kg. Like, hey, there's no like, you get to be 94 kg and cut to nineties, there's like, uh, you're going to step on the scale at 84 kg, like a little bit of a weight cut, but on a 41, just so that you feel like you get into like the tournament because when I Around 2012, when I was talking with the usoc nutritionist, I actually got my weight down so much that I didn't really need to cut weight. The problem is I wasn't cutting weight, I didn't feel like I was competing. Good right there you have to go through like that mental process and I never really reworked that it was easier to just cut the weight and be ready to go. But when I entered into the 90 kg division, I was rushed to the hospital the night after because my body broke out in hives like full body. They had uh, they said it was stress induced, fascinating. So, a month before the Games, I was hospitalized in Hungary and filled with steroids to get the hives to drop and every couple of days my body when I got back home, I would end up in the hospital because my whole body would break out again. </s><s>[INST] I wonder if it's like deviating from the process that you so like perfectly crafted already [/INST] or it was stressed from my mind thinking like even though it's not top of mind, there's probably a portion of me that like the olympics is coming around and it could be my last That like my body just reacted to something chemically. So I was breaking out in hives. I actually bought like a €600 Hugo boss suit because when I was in the Netherlands training at the time, I thought I had bedbugs because I was getting bit everywhere. Then I thought there was something in the detergent at the local thing, so I threw away all more clothes, like I was paying for showers because I was trying to get the detergent off my body and buying new clothes at the airport, trying to figure it out. </s><s>[INST] Trying to figure it out and just go, yeah, accepting the situation. I mean, but the level of stress is exceptionally high here. Can we talk about the other side? People are going to love this, but you're um you have a long history of persevering through injuries. Mhm. Through insane amounts of injuries, [/INST] uh My ability to tolerate pain is probably more than most people, </s><s>[INST] but see injuries aren't just pain, right? It's like um it's also mental, like psychological, like again, like the weight cut, it can make a lot of people quit. Can you tell your history of injuries, What are the biggest injuries, the toughest injuries in your career? [/INST] Um </s><s>[INST] Starting from what you're early teens, [/INST] My early teens um actually got out of sports from 11 to like 15 years old, 16 years old because a kid shot a double leg through my kneecap And I partially tore all the ligaments in my knee, cartilage, meniscus the whole nine yards and I had to learn how to walk again. I spent two years in a leg brace, crutches, you know, hobbling around the schoolyard. That one was a challenge to come back from um I've broken most of my ribs. I won nationals with nine broken ribs. I was actually getting novocaine shots into my chest to avoid feeling the pain and then wrapping them to try to make sure I didn't pop along, um I broke my collarbone, um I have five herniated disc in my neck, I fractured my back twice, I have broken my tailbone, I tore my s I joints, I've torn my right hamstring twice, my left one once um Broken my ankles a few times. I spun it once in a 360 that had death surgery, fingers, toes, elbows, shoulders, </s> |
<s>[INST] I'm only joking. Of course, he's just honestly a fearless, vicious comedian who's holding people's feet to the fire, which is really good for this world. And of course whenever he makes fun of me, it truly is an honor. Anyway, check out better help at better health dot com slash lex. It's easy, private, affordable available worldwide. They figure out what you need and match you with a licensed professional therapist in under 48 hours. That's better help dot com slash lex spelled H E L P help. This is the lex Friedman podcast and here's my conversation with Sergei Makarov [/INST] is that </s><s>[INST] he's so I gave away everything I own a few times in my life and he accidentally survived and I don't like stuffed animals what I really like to, but I got him in the third store what I liked about him because I had never seen a stuffed animal that looks piste off at life. Like they're usually smiling at the dumbest of ways [/INST] and this guy was just pissed. Yeah, I got to tell you that's actually pretty funny. </s><s>[INST] I like this guy if you had to live only in the digital world or the physical world, which would you choose. [/INST] So I think this is actually a question more about what the fidelity of the digital world would be versus the physical world. I I think this this type of question, this whole simulation thing actually comes from papers about 2030 years ago in in the philosophical world where people try to make this thought experiment, of would you be comfortable if if everything that was happening to you happened in a simulation, What they were trying to do is they were intuitively trying to understand. Is there some kind of intuitive um personal connection? We have to something being the real world? Right? And then the Matrix movie actually came out of these papers and then these ideas made its way it made their way into the public consciousness. Um I personally think that if I had the choice to be in the digital world at the same fidelity as the real world with immortality, I would absolutely go with the digital. </s><s>[INST] Wait wait wait wait wait. How'd you have the immortality part? That's a [/INST] get immortality. If you think about how we would go into the digital world right? Our our our brain patterns would be mapped onto some kind of uh probably a virtual machine. Right? And that would mean immortality right? Because the virtual machine has no limit to how long it can. </s><s>[INST] Don't you think there will be like a versioning system? Like uh there will be this is a soft fork versus hard for question whether Sergei version two point oh would be different from Sergei version one point Oh there would be an upgrade. So that's the mortality Sergei one point I would die in the digital world. You get you get like a software update and then that's it. You know? [/INST] Well yeah when when people go into the star trek transporter are they killed or are they transport? I I don't really know. I haven't read any papers on this. I haven't really thought about it too much. There's no </s><s>[INST] white paper on the transporter. [/INST] Not at this point. So </s><s>[INST] what does fidelity mean exactly to you? Is it like strictly so the fidelity of the physics world? The physical world is maybe now questions of physics, quantum mechanics. What is at the at the bottom of it all? Or do you mean the fidelity of the actual experience? [/INST] Just just just just the </s><s>[INST] human, But that's limited by human cognitive capabilities. [/INST] It is. But I don't really have anything else, right? I think all of these papers that brought up these questions of a simulation, they were like in epistemology and metaphysics and what they were trying to do, I think was they were trying to put people through a thought experiment where they would come out on the other end and say the reality of life is really worth something. And I don't I don't, you know, ignorance isn't bliss. Which is that's consistent statement in the matrix, right, Ignorance is bliss? Is that that's what one of the guys says when he's like, you know, doing something wrong and trying to get back into the Matrix. And the question is is ignorance bliss. Um and it's like a different version of that. I I think from a perceptual point of view, if my perceptions aren't in any way different. So fidelity is very good. It doesn't matter. I I don't know, right? So if I if I don't know something, it doesn't really exist. And if it doesn't exist in in in my perception or my consciousness that it doesn't exist period for me at least. And then whether it exists in some, you know, more metaphysical version of things, I I personally never really got into the metaphysics stuff because I I could never really um I couldn't understand what the point of it was. Right. It it's one of these things where I couldn't really get what what the what the practical application of it was and this is this is from those realm of questions, right? Like if there was something about the world, but you didn't have a capacity to perceive it, would it matter to you? Uh to me it wouldn't matter, </s> |
<s>[INST] that is mysterious, I don't know why I feel it. Yeah, in some sense, the emotion is kind of the fuel of that creative imperative we have. But if you step back and look at the tapestry a little bit, it does seem that the destruction, the creation of the destruction or the yin and yang of life, that it all works only if the main engine is towards creativity, but destruction also makes way for new things. So that's the, this kind of struggle, it seems like life is struggle between the different forces that make up the individual human, that make up society, all these tensions are necessary for growth, for development, this kind of inner conflict and outer conflict are necessary for growth. It's not just, I mean, in some sense, it's from the logic aspect, you kind of want everything to be perfect and just, for nobody to suffer for everything to be perfect, but just like we talked about with trauma, it just seems like it's such a big giant mess. What is it? Bukowski said, find what you love and let it kill you. There's some aspect of, the negative aspect of passion and pursuit and obsession and the turmoil of the pursuit of happiness, of the creative pursuits and all of that. I mean, that's part of life as well. That's, and I don't know what to do with that from an individual perspective in terms of figuring out how do you live a good life? How do you live a healthy life? Because it does seem a bit of hardship or sometimes a lot of hardship [/INST] can make a pretty interesting life. I think it brings us back to the discussion that we were having sort of before about like, what does it mean? Like the challenges of trauma and overcoming. And I think here we gotta be careful with the language. Because I would then say, let's take destruction and separate it into two things. One is to say destruction is like the breaking down, the tearing down of something, versus a process that has malice in it, right? So just like when we were talking about trauma and setbacks, things to overcome. And we'd say, okay, if you say, hey, you have it harder than the next person and you have more to overcome, or someone put a barrier in front of you for you to overcome, that there can be a lot of growth in that, including the times when you don't know if you, gosh, can I do this, right? Can I get over it, right? We're saying like, that's challenge and something to overcome that's very positive. But we're saying, but there's no benefit of like throwing a racial slur in there. We're saying because that's all bad. Even the prince says, I'm angry about that, and I'm gonna overcome that. It's like that didn't need to be that, that didn't make anything better. If the person sees that and says, I'm gonna overcome that, it makes things less worse. He said, but there's no good to something that's created as destructive. We meet at forest fires, like, look controlled burns, he said there's a forest burning down, But that's, okay, there's some, there's some weak- I think destruction there, there's a tearing down there, but it's in the service of the next fire not running through the community of the town that's on the other side of it. That's very different than a forest fire, say started by arson, right? So you might say they're both a tearing down, they're a tearing down of the forest. But one is in the service of goodness even though it's hurting the animals and the plants it's not all good, right? But but it's in the service of something as opposed to something else that's wantonly destructive. I think there's no good to the racial slur, there's no good to the arson, right? That's destruction in a way that's incorporating, I think, the malice of envy, something that's really purely, if there's a yin and yang, that's the destruction, that's the badness end. </s><s>[INST] So racial slurs is a surface wave of a deeper thing. And so, I mean, the reason I bring that up is like, all right, well, you have these discussions of censorship, like what good does allowing racial slurs in public communication do, right? And it's like, our communication would surely be better if we don't say bad things to each other. But it's like, it seems like the truth is, our communication will be better if the amount of bad things is a small fraction of communication. That seems to be more true. Because another aspect of human nature with power, the moment you start censoring and removing bad words that everyone agrees are bad words, then the people on the, at the top, they're doing the censoring, start getting greedy. They start, it starts expanding. And this is the giant mess of human civilization where we can't, the nice piles you created are kind of overlapping. That's the gray area. [/INST] That's the problem with it. That's the problem with it. No, I agree completely. Control of language, there are slippery slopes there. I think there's a very big problem there. So I agree. I think, again, split parsing out the language, I'm not saying, hey, we shouldn't have racial slurs as if like, let's stop saying the words. I mean, the idea is the premise behind it, right? Like, you know, the prejudices. If we could eliminate the prejudice behind it, you know, I was struck. It said I do almost nothing about medicine. I get to medical school and start with anatomy, right? And it's remarkable to see as the bodies are being dissected that like, we're all humans. Like, does it matter? It doesn't matter any of these things on the outside. Like, and that's true, not just like in our bodies, but in our minds, the part of the person that's not there, right, because now we're trying to learn from the body. And, you know, it shows how ridiculous it is. If you think that we're 99. How many nines, you know, percent all alike genetically. And by the way, it's only like take another 10th off and we're all orangutans, right? So, but somehow we have to see these differences between us, right? And where does that come from? And I think that I believe that all comes from envy in that classical sense. That if I don't feel good enough, I'm going to want someone to feel better about. And so there can be visual things that that person looks different, right? Or you think about the, you know, I spent some time in Great Britain and when there's a lot of conflict between Northern Ireland and Ireland, right? And he thought, wow, there's not, there's not even a look difference, right? It's the same general, you know, religious umbrella, same ethnicity, right? But now there's some religious difference. And I thought it's not me trying to be denigrating, you know, around the Irish conflict. He's like, that's human of, oh, there's no actual difference between us. If I don't feel good about myself, I'm going to find one, right? It's that that I believe could go away. It's driven by maybe the trauma of just being alive in the world and things can happen to us. But we certainly promote in the human created trauma, people feeling not good enough, finding differences, there's a place for the envy to attach and we're off to the races of wars. I mean, we're talking about the second world war and we think, what have we learned since then? It would take us a day to map out all the wars since then, let alone for goodness sakes, everything that's salient right now. So we're not pretty, we're not good at learning </s> |
<s>[INST] The hope for me is that there's some simple explanations for all of it. [/INST] Like should we have a drink? You're having fun? No, I'm trying to have fun </s><s>[INST] with you. You know, there's a bunch of fun [/INST] things very serious to </s><s>[INST] talk about here [/INST] anyway. That was how I got what I thought you wanted. Which is if you think about the fermions as the artists and the bosons as the brushes and the paint, What I told you is that's how we get the artists. </s><s>[INST] What are the open questions for you in this? What were the challenges? So you're not done? [/INST] Well, there's there's things that I would like to have in better order. So a lot of people will say, see the reason I hesitated on this is I just have a totally different view than the community. So, for example, I believe that general relativity Began in 1913 with Einstein and Grossmann. Now that was the first of like four major papers in this line of thinking to most physicists, General relativity happened when Einstein produced uh a divergence free um gradient, which turned out to be the gradient of the of the so called Hilbert or Einstein Hilbert action. And from my perspective, that wasn't true. This is that. It began when Einstein said, look, this is about um differential geometry and it's the final answer is going to look like a curvature tensor on one side and matter and energy on the other side. And that was enough. And then he published a wrong version of it where it was the Ricci tensor, not the Einstein tensor. Then he corrected the reach the Ricci tensor to make it into the Einstein tensor. Then he corrected that to add a cosmological constant. I can't stand that the community thinks in those terms. There's some things about which like that. There's a question about which contraction do I use? There's an Einstein contraction, there's a richie contraction. They both go between the same spaces. I'm not sure what I should do, I'm not sure which contraction I should choose. This is called a Shia operator for ship in a bottle and my stuff. </s><s>[INST] You have this big platform in many ways that inspires people's curiosity about physics, mathematics now, and I'm one of those people, great, but then you start using a lot of words that I don't understand. Yeah, and like I might know them, but I don't understand and what's unclear to me if I'm supposed to be listening to those words or if it's just if this is one of those technical things that's intended for a very small community, or if I'm supposed to actually take those words and start, you know, a multi year study, not, not a serious study, but the kind of study when you you're interested in learning about machine learning, for example, or any kind of discipline, that's where I'm a little bit confused. So, you you speak beautifully about ideas, you often reveal the beauty in mathematics, geometry and I'm unclear and what are the steps I should be taking. I'm curious how can I explore, how can I play with something, How can I play with these ideas and and enjoy the beauty of not necessarily understanding the depth of the theory that you're presenting, but start to share in the beauty as opposed to sharing and enjoying the beauty of just the way the passion with which you speak, which is in itself fun uh to listen to, but also starting to be able to understand some aspects of this theory that I can enjoy it to uh and start to build an intuition what the heck we're even talking about because you're basically saying we need to throw a lot of our ideas of, of views of the universe out and I'm trying to find accessible reason. Okay, not in this conversation, [/INST] no, I appreciate that. So, one of the things that I've done is I've picked on one paragraph from Edward wit and I said this is the paragraph, if I could only take one paragraph with me, this is the one I'd take and it's almost all in prose, not an equation. And he says, look this is this is our knowledge of the universe at its deepest level. And he was writing this during the 1980s and he has three separate points that constitute our deepest knowledge. And those three points refer to equations, one to the Einstein field equation, one to the dirac equation and one to the yang mills Maxwell equations. Now, one thing I would do is take a look at that paragraph and say, okay, what do these three lines mean? Like it's a finite amount of verbiage, you can write down every word that you don't know, you can say, What do I think done now young man. Yes, there's a beautiful wall in stony brook new york built by someone who I know you will interview named Jim Symons and Jim Symons, he's not the artist, but he's the guy who funded it, World's Greatest hedge fund manager. And on that wall contained the three equations that Whitten refers to in that paragraph. And so that is the transmission from the paragraph or graph to the wall. Now that wall needs an owner's manual, which Roger Penrose has written called The Road to Reality. Let's call that the tome. So this is the subject of the so called graph wall tome project that is going on in our discord server and our general group around the portal community, which is how do you take something that purports in one paragraph to say what the deepest understanding man has of the universe in which he lives? Yeah, it's memorialized on a wall which nobody knows about. Which is an incredibly gorgeous piece of art. And that was written up in a book which has been written for no man. Right? Maybe, maybe it's for a woman, I don't know. But no, no one should be able to read this book because either you're a professional and you know, a lot of this book, in which case it's kind of a refreshers to see how roger thinks about these things or you don't even know that this book is a self contained invitation to understanding our deepest nature. So I would say find yourself in the graph wall tome transmission sequence and join the graph wall tone project if that's of interest. </s> |
<s>[INST] Their motto is engineer ambitiously, which, like I've said in the past, is probably my favorite motto of any company ever. They have a podcast called Testing 123. They have amazing articles at NI.com slash Perspectives covering engineers and innovators. That's both for the podcast and the articles they have. They cover the idea that great engineering requires repeated, systematic, rigorous failure and improvement through failure. That's essentially what testing is. I've done martial arts, jiu-jitsu, wrestling, judo for many, many years, and I kind of think of it in the same way. It's systematic, habitual failure and improvement. [/INST] Engineer ambitiously with NI and NI.com slash Perspectives. That's NI.com slash Perspectives. </s><s>[INST] This show is also brought to you by Give Directly, a nonprofit that lets you send money directly to people living in extreme poverty. Give Directly donors include previous guests of this very podcast and likely returning guests. Jack Dorsey, Elon Musk, Vitalik Buterin, Will McCaskill, Peter Singer, and many others. I love this idea and their implementation of it. Give money directly to the people. Hundreds of independent studies have shown that direct giving can have positive impacts on health, nutrition, income, education, and more. The positive findings in these studies just go on and on and on. In the last decade, Give Directly has delivered over $400 million to over 900,000 recipients across nine countries. Visit givedirectly.org slash Lex, and this giving season, this holiday season, your first gift will be matched up to $1,000. That's givedirectly.org slash Lex. This show is also brought to you by Indeed, a hiring website. I've used them as part of many hiring efforts I've done for the teams I've led in the past. They have tools like Indeed Instant Match, giving you quality candidates whose resumes on Indeed fit your job description immediately. I think that work you love doing is a source of meaning. Part of that is doing the thing you love doing with people that you enjoy doing the thing with. In other words, building an amazing team of people from whom you learn, who inspire you, who make you happy to wake up every day in the morning and take on the day. Anyway, right now I'll get a free $75 sponsor job credit to upgrade your job post at indeed.com slash Lex. Get it at indeed.com slash Lex. Offer is valid through December 31st, 2021. Terms and conditions apply. Go to indeed.com slash Lex. This show is also brought to you by Blinkist, my favorite app for learning new things. Blinkist takes the key idea from thousands of nonfiction books and condenses them down into just 15 minutes that you can read or listen to. I can recommend a very long, long list of nonfiction books that Blinkist has. Yuval Harari's, Sapiens is on there, Meditations by Marcus Aurelius, Beginning of Infinity by David Dutch, The Snowden Book, and many, many others. I use Blinkist in a bunch of ways. So one is to review books that I've already read. The crisp insight into the key ideas in the book that Blinkist provides is unlike any other. Go to blinkist.com slash Lex to start your free seven day trial and get 25% off of a Blinkist premium membership. That's blinkist.com slash Lex spelled B-L-I-M-K-I-S-T blinkist.com slash Lex. This is the Lex Friedman podcast. And here is my conversation with Jamie Metzl. What is the probability in your mind that COVID-19 leaked from a lab in your write up? I believe you said 85%. I know it's just a percentage. We can't really be exact with these kinds of things, but it gives us a sense where your mind is, where your intuition is. So as a stance today, [/INST] what would you say is that probability? I would stand by what I've been saying since really the middle of last year. It's more likely and not, in my opinion, that the pandemic stems from an accidental lab incident in Wuhan. Is it 90%? Is it 65%? I mean, that's kind of arbitrary. But when I stack up all of the available evidence and all of it on both sides is circumstantial, it weighs very significantly toward a lab incident origin. </s><s>[INST] So before we dive into the specifics at a high level, what types of evidence, what intuition, what ideas are leading you to have that kind of estimate? Is it possible to kind of condense? When you look at the wall of evidence before you, where's your source, the strongest source [/INST] of your intuition? And I would have to say it's just logic and deductive reasoning. So before I make the case for why I think it's most likely a lab incident origin, let's just say why it could be and still could be a natural origin. All of this is a natural origin in the sense that it's a bat virus backbone, horseshoe bat virus backbone. </s><s>[INST] Okay, I'm going to keep pausing you to define stuff. So maybe it's useful to say, what do we mean by lab leak? What do we mean by natural origin? What do we mean by virus backbone? [/INST] Yeah, okay. Great questions. So viruses come from somewhere. Viruses have been around for 3.5 billion years. And they've been around for such a long time because they are adaptive and they're growing and they're always changing and they're morphing. And that's why viruses are, I mean, I mean, they've been very successful and we are victims. Sometimes we're beneficiaries. We have viral DNA has morphed into our genomes, but now it's certainly in the case of COVID-19, we are victims of the success of viruses. And so when we talk about a backbone, so the SARS-CoV-2 virus has a, it has a history and these viruses don't come out of whole cloth. There are viruses that morph. And so we know that at some period, maybe 20 years ago or whatever, the virus that is SARS-CoV-2 existed in horseshoe bats. It was a horseshoe bat virus and it evolved somewhere. And there are some people who say there's no evidence of this, but it's a plausible theory based on how things have happened in the past. Maybe that virus jumped from the horseshoe bat through some intermediate species. So it's like, let's say there's a bat and then it infects some other animal. Let's say it's a pig or a raccoon dog or a civet cat. They're all pangolin, they're all sorts of animals that have been considered. And then that virus adapts into that new host and it changes and grows. And then according to the quote unquote natural origins hypothesis, it jumps from that animal into humans. And so what you could imagine and some of the people who are making the case, all of the people actually who are making the case for a natural origin of the virus, what they're saying is it went from bat to some intermediate species and then from that intermediate species most likely. There's some people who say it went directly bat to human but through some intermediate species and then humans interacted with that species. And then it jumped from that, whatever it is to humans. And that's a very plausible theory. </s> |
<s>[INST] but the important reminder that that turning down the prize serves for me, it's not that there's anything wrong with the prize and there's something wonderful about the prize. I think the Nobel prize is trickier because so many Nobel prizes are given. First of all, the Nobel prize often forgets many, many of the important people throughout history. Second of all, there's like these weird rules to it, there's only three people and some projects have a huge number of people and like this, it um I don't know, it doesn't kind of highlight the way science is done on some of these projects in the best possible way, but in general the prizes are great. But what this kind of teaches me and reminds me is sometimes in your life there will be moments when the thing that you he would really like to do, society would really like you to do is the thing that goes against something you believe in whatever that is some kind of principle and stand your ground in the face of that. It's something um I believe most people will have a few moments like that in their life, maybe one moment like that and you have to do it. That's what integrity is. So like it doesn't have to make sense of the rest of the world, but to stand on that like to say, no, it's interesting because I think, you [/INST] know that he turned down the prize and service of some principle </s><s>[INST] because I don't know that Well, yes, that seems to be the inkling, but he has never made it super clear. But the the inkling is that they're he had some problems with the whole process of mathematics that includes awards like this hierarchies and reputations and all those kinds of things and individualism that's fundamental to american culture. He probably because he visited the United States quite a bit that he probably, you know, it's like all about experiences and he may have had, you know, some parts of academia, Some pockets of academia can be less than inspiring. Perhaps sometimes because of the individual egos involved, not Academia people in general, smart people with egos and if they, if you interact with a certain kinds of people, you can become cynical to easily. I'm one of those people that I've been really fortunate to interact with, incredible people at MIT and academia in general, but I've met some assholes and I tend to just kind of, when I, when I run into difficult folks, I just kind of smile and send them all my love and just kind of go go around. But for others, those experiences can be sticky. Like they can become cynical about the world when folks like that exists. So it's, he may have, he may have become a little bit cynical about the process of science. Well, you know, it's [/INST] a good opportunity, let's posit that that's his reasoning because I truly don't know. Um it's an interesting opportunity to go back to almost the very first thing we talked about the idea of the mathematical olympiad because of course that is the international mathematical olympiad is like a competition for high school students solving math problems and in some sense it's absolutely false to the reality of mathematics because just as you say, it is a contest where you win prizes. Um the aim is to sort of be faster than other people. Uh, and you're working on sort of canned problems that someone already knows the answer to like, not problems that are unknown. So, you know, in my own life, I think when I was in high school, I was like very motivated by those competitions. And like I went to the math olympiad </s><s>[INST] and you want it? I wish. I [/INST] mean, well, there's something I have to explain to people because it says, I think it says on Wikipedia that I won a gold medal and the real olympics, They only give one gold medal each event. I just have to emphasize that the international Math Olympiad is not like that. The gold gold medals are awarded to the top one, 12th of all participants. So sorry to bust the legend or anything. </s><s>[INST] Well, how do you an exceptional performer in terms of achieving high scores and and the problems and they're very difficult. So you've achieved a high level of performance on the [/INST] In this very specialized skill. And by the way, it was, it was a very cold war activity. You know, the one in 1987, the first year I went, it was in Havana. Americans couldn't go to Havana back then. It was a very complicated process to get there. And they took the whole american team on a field trip to the Museum of american imperialism in Havana. So we could see what America was all about. </s><s>[INST] How would you recommend a person learn math. So somebody who's young or somebody my age or somebody older who have taken a bunch of math but wants to rediscover the beauty of math and may be integrated into their work more solid in the resource base so and and so on. Is there something you could say about the process of incorporating mathematical thinking into your life? [/INST] I mean the thing is it's in part a journey of self knowledge. You have to know what's going to work for you and that's going to be different for different people. So there are totally people who at any stage of life just start reading math textbooks. That is a thing that you can do. And it works for some people and not for others. Um for others, a gateway is, you know, I always recommend like the books of martin Gardner, another sort of person we haven't talked about but who also like Conway embodies that spirit of play. Um He wrote a column in scientific american for decades called Mathematical recreations and there's such joy in it and such fun. Um and these books, the columns are collected into books and the books are old now, but for each generation of people who discover them, they're completely fresh and they give a totally different way into the subject than reading a formal textbook, which for some people would be the right thing to do and you know, working contest style problems to those are bound to books like especially like Russian and Bulgarian problems? Right? There's book after book problems from those context, that's gonna motivate some people. Um for some people it's gonna be like watching well produced videos, like a totally different format, like I feel like I'm not answering your question, I'm sort of saying there's no one answer and like it's a journey where you figure out what resonates with you. For some people, it's the self discovery is trying to figure out why is it that I want to know? Okay, I'll tell you a story once. When I was in grad school, I was very frustrated with my lack of knowledge of a lot of things as we all are, because no matter how much we know, we don't know much more. And going to grad school means just coming face to face with like the incredible overflowing vault of your ignorance, right? So I told joe Harris who was an algebraic geometry er professor in my department, I was like, I really feel like I don't know enough and I should just like take a year of leave and just like read e g a, the holy text book and I'm on the geometry algebraic elements of algebraic geometry. This like I'm just gonna I feel like I don't know enough. So I'm just gonna sit and read this like 1500 page many volume book. Um and he was like and the professor? And I was like, that's a really stupid idea, and I was like, why is that a stupid idea that I would no more algebraic geometry because you're not actually gonna do it, like you learn, I mean, he knew me well enough to say like, you're going to learn because you're gonna be working on a problem, and then there's gonna be a fact from E G. A. You need in order to solve your problem that you want to solve, and that's how you're going to learn it, you're not going to learn it without a problem to bring you into it. And so for a lot of people, I think if you're like, I'm trying to understand machine learning and I'm like, I can see that there's sort of some mathematical technology that I don't have. I think you like let that problem that you actually care about Dr. You're learning one thing I've learned from advising students, you know, math is really hard. In fact, anything that you do right is hard. Um And because it's hard, like you might have some idea that somebody else gives you, oh, I should learn X, y and Z. Well, if you don't actually care, you're not going to do it, you might feel like you should, maybe somebody told you you should, but I think you have to hook into something that you actually care about. So for a lot of people, that's the way in you have an engineering problem, you're trying to handle you have a physics problem you're trying to handle, uh you have a machine learning problem you're trying to handle. Let that not a kind of abstract idea of what the curriculum is drive your mathematical learning. </s> |
<s>[INST] Can't remember. It's been a minute. It's been a one person can oh, it's been a one person can carry it Oh, yeah. Okay. I don't know. It just seems like a rocket launchers pretty intense kind of [/INST] Device that just it for sure is I mean, it's the diameter. I can't even tell you diameter They're about that big. I mean and it goes on your shoulder goes on goes on your shoulder and then it has a little sight that pops out that's almost like plastic like which is kind of funny cuz it reminds me of like the Little green army, man. I just felt so flimsy to me I was like, this is hilarious and then another person stands behind you and opens the hatch and so there's this there's these two Lovers and you just kind of open it and then the back end which is flared So it's just a tube and then it's flared that will open it and drop down and you load a round into that And then you'll load it back up And you're never supposed to stand behind it because the blast behind it will kill you. It's Yeah, but in my case when I fired it, it was me and another individual I want to say it wasn't Sarah Pellegrin, but it was another girl that was smaller and the person is supposed to wrap around your waist and Tuck low and hold your stability and we were just aiming at tanks that day and they were just concrete Heads, so they would just either they would hit and bounce off or whatever and so When my sergeant saw that he just kind of looked at both of us. I was like, no, I'm just gonna and he got real low and just like wrapped Both of us and then we'd fire it and it feels like you're getting punched in the side of the head on repeat by Jocko Yeah, it you lose all your hearing you like just What snot comes out of your nose and you're just kind of discombobulated for a minute. It's a real mind fuck </s><s>[INST] is there other any other kind of guns that In at that time because you were new to this you haven't shot guns when you were younger [/INST] That were really impressive to you in in the training all of them because I've never fired a weapon So we had the c7s, which are like your m16s, I believe The long barrel the cute thing about those is when I have that slung my barrel drags on the ground So that's fun and they shoot, you know, you're seven six two or your five five six round I loved that I preferred the the c8, which was a short barrel, which is what the SF guys use Not because it's cooler looking which it obviously is but because it was functional for my body height And it didn't drag on the ground when I ran I loved those their your personal weapon being an artillery gunner if you're not an officer at least in our unit You didn't get a side a side piece. I didn't have a side piece Lex So I never had a handgun of any type. I fired those in training. You can't get over that side piece comment. Look at you </s><s>[INST] I was gonna say I know what a side piece is. You don't have to explain to me, but you're single [/INST] But you're single </s><s>[INST] So how do you even have a side piece if you don't have a main piece the joke the joke would be the fact that [/INST] We have a total misunderstanding what side pieces? Okay, great. You didn't have a side piece as a non officer. Right so I never fired those much we did grenades in training. Oh, yeah grenades are fun. I love grenades I have a massive one tattooed on me. I have them all over my office office. Oh, cool. How does a grenade work? There's the spoon and the pin. So the pin holds the spoon in place. When you pull that pin, the firing mechanism inside, as long as that the spoon is up against it, it won't fire. As soon as that spoon goes, I believe it causes a reaction on the inside and you've got about five seconds to check it. You'd </s><s>[INST] be better to ask that question too. I don't want me to get philosophical on this. No, you're not, you don't. But there's something about a grenade because you're essentially [/INST] committing suicide unless you get rid of the thing. Or if you're unlucky and it just goes </s><s>[INST] off when you pull the pin, which has happened to tons of people. So it just feels like a very kind of, it's a dangerous leap into the abyss every time you use the thing. Because when you shoot a gun, the gun is much less likely to malfunction in terms of all the [/INST] possible ways it can go wrong. It just seems like a grenade is like... </s><s>[INST] Primitive, almost. Yeah, it's primitive. It's also real in the way that a bar fight is like being punched in the face is real. It's like you're here with a weapon of destruction. It's just you and the thing. You have to get rid of it. I don't know. Is that terrifying [/INST] to you? Do people still use grenades in real warfare? Yeah, those are fantastic. The Taliban were throwing them over the wall at the airport in Kabul. People use them all the time. Because when you're in Afghanistan, if you're in a rural area, you're going from village to village and their mud-hot walls... They're tall but you're walking through corridors and stuff. You get to lob one of those, it's going to take the whole unit out that you just walked by, they're accurate if you're close enough and they're effective if you're close enough. I love them, though. I think they're fascinating to me because they're such a tiny little thing with such devastation. They just can cause such devastation. But for me, when I had them, some of the Canadians would make fun of me because when I did go outside the wire with the British, I had two right here. And I remember I put a piece of tape over the spoons because in my mind, I could picture myself searching someone and grabbing me and pulling that, and that would be me. That would have been like, yep, </s> |
<s>[INST] So the current administration donald trump has released the executive order on artificial intelligence, Not sure if you're familiar with it In 2018, uh looking several years ahead, how does America sort of we've mentioned in terms of the big impact, we hope you're in investment and m I. T. Will have a ripple effect. But from a federal perspective from a government perspective, how does America establish with respect to china leadership in the world at the top for research and development in ai [/INST] I think um that you have to get the federal government in the game uh in a big way. Uh and that this leap forward uh technologically, which is going to happen with or without us, uh, you know, really should be with us. Uh and and it's an opportunity in effect for another Moonshot kind of mobilization by the United States. Uh, I think uh the appetite actually is there to do that uh at the moment, what's getting in the way is the kind of poisonous politics we have. But if you go below the lack of cooperation, which is almost the defining element of american democracy right now, and the Congress, if you talk to individual members, they get it and they would like to do something. Another part of the issue is we're running huge deficits, we're running trillion dollar plus deficits. So how much money do you need for this initiative? Where does it come from? Who is prepared to stand up for it? Because if it involves taking away resources from another area, our political system is not real flexible to do that. If you're creating um this kind of initiative, which we need, where does the money come from? Uh and and trying to get money when you've got trillion dollar deficits in a way, it could be easy, what's the difference of a trillion and a trillion little more? But but you know, it's hard with the mechanisms of Congress, But what's what's really important is uh, this is not an issue uh, that is unknown and it's viewed as a very important issue. Uh and there's almost no one in the Congress when you sit down and explain what's going on, Who doesn't say we've got to do something? </s><s>[INST] Let me ask the impossible question. So you didn't endorse donald trump. But after he was elected, you have given him advice, uh, which, which seems to me a great thing to do, no matter who the president is to contribute, positively contribute to this nation by giving advice. And yet you've received a lot of criticism for this. So on. The previous topic of science and technology and government, how do we have a healthy discourse? Uh, give advice. Get excited, uh, conversation with the government about science and technology without it becoming politicized? [/INST] What's very interesting. Um, so when I was young before there was a moon shot, uh, we're the president, uh, named john f Kennedy from massachusetts here and in his inaugural address as president. He has not what your country can do for you, but what you can do for your country. You know, we had a generation of people my age, basically, people who grew up with that credo? Uh, uh, you know, sometimes you don't need to innovate. Uh, you can go back to basic principles and that's a good basic principle. What can, what can we do? Um, you know, Americans have GDP per capita of around $60,000. Uh, you know, not every, it's not equally distributed, but it's big. Uh, and you know, people have, I think an obligation, uh, to help their country and I do that. And apparently I take some grief for people from some people, you know, who, um, you project on me things I don't even vaguely believe. Uh, but I'm like quite simple. Uh, you know, I tried to help the previous president President Obama. He was a good guy. Uh, and he was a different party and I trying to help President Bush and he's a different party. And you know, I sort of don't care that much about what the parties are I care about even though I'm a big donor for the republicans, But it's what motivates me is, what are the problems we're facing? Can I help people get to, you know, sort of a good outcome that will stand any test. But we live in a world now where, you know, sort of the filters uh, the hostility is so unbelievable. Uh, you know, in the 1960s, when I went to school in the university, I went to Yale, we had like like so much stuff going on. Uh, we had a war called the Vietnam war. We had, you know, sort of black power starting and, and uh, you know, we had a sexual revolution with the birth control pill. Uh, and um, you know, um, there was one other major thing going on and and write the drug revolution, there hasn't been a generation that had more stuff going on In a four year period than my era, yet there wasn't this kind of instant hostility if you believed something different, everybody lived together and and you know, respected uh the other person. And I think that, you know, this type of change needs to happen and it's got to happen from the leadership of our major institutions. And I don't think that that leaders can be bullied by people who were against, you know, sort of the classical version of free speech and letting open expression and inquiry, that's what universities are for, among other things. Uh Socratic methods. And uh so so I I have um uh in in in the midst of this like onslaught of oddness, I believe in still the basic principles and we're going to have to find a way to get back to that. And that doesn't start with the people, you know, sort of in the middle to the bottom who are using, you know, these kinds of screens to to shout people down and create an uncooperative environment. It's got to be done uh, at the top with core principles that are articulated. Uh and ironically, um if people don't sign on to these kind of core principles where people are equal and and you know, speech can be heard and you know, you don't have these enormous shout down biases subtly or or out loud, then they don't belong at those institutions, they're violating the core principles and you know, that's that's how you end up making change. Uh, but you have to have courageous people who are willing to lay that out for the benefit of not just their institutions, but for society as a whole. So I, I believe that will happen. Um, but it needs the commitment of, of senior people to make it happen </s> |
<s>[INST] something um like space tourism. When you go out into space and you look back down on earth. That's too a lot of people including myself is worth a lot. But why is that worth a lot is because you uh it's humbling and beautiful in the same way that meeting are close evolutionary relatives is humble and beautiful just to know that this this is what we come from. This is who we are not just for the understanding or the science of it, but just like something about just the beauty of witnessing this. Um and again, it's both humbling and empowering this place is fragile and we're damn lucky to be here. [/INST] Yes. Unfortunately the problems are incredibly difficult to solve and there is no one solver. You know, it has to happen from a network of potentially cooperating people. But I mean you're so right about it being daunting to think about what it looks like from space. And I love the view that home and Mueller expressed of being able to go out from space and he said the whole of life would look like a kind of rust on the planet. </s><s>[INST] Yeah, so the aliens were to visit, I'm not sure they would notice the life that would probably notice the trees or ocean. It's a kind of rust. But let me ask the big, ridiculous philosophical question of what is the meaning of this rust? What you think is the meaning of life on earth? What is the meaning of our human intelligent life? [/INST] Well, I think it's very clear that we have an evolutionary story that uh is only getting challenged around the edges. You know, we we have a very clear understanding of the evolution of life and the meaning is you know, we are here as a consequence of materialistic processes that began uh in our sense uh you know with the establishment of the earth of 4.5 billion years ago, whatever it was and then water and oxygen and and so on. And we are the astonishing i a consequence of the evolution of cells and multi cellular organisms. Ah The word random is the wrong word to use unless you understand what it means. It didn't happen by chance, but a lot of random events had to happen to make this possible. And there's random events of course are the production of appropriate mutations. But the, you know, the meaning of life is there is no meaning. It's the, you know, the really big mystery of life is why is there a universe. </s><s>[INST] Mhm. And that's saying why propagates itself through the whole of it, through the whole process of it for the emergence of planets, the Virgin's first of all Galaxies of star systems of planets of the proteins required to construct the single cell organisms and the single cell organism becoming complex organisms and uh some of the clever fish crawling out onto the land and and the whole of it. And then there's fire. Some some clever clever guy or lady invented fire. And then now here we are. Uh it just does seem speaking as a human kind of special that we're able to reflect on the whole thing or the whole [/INST] wonderful stories. So much more interesting than the stories produced by religion. </s><s>[INST] It is beautiful. But it just seems special that us humans are able to write religions and construct stories [/INST] and then also do science. </s><s>[INST] That seems um that seems kind of amazing. It seems like the universe. Okay, is such that it it, um, it creates beings like us, they are able to investigate it and that, that and that, that's why there's this longing for why that's just uh, it's such a beautiful little pocket of complexity created by the universe. It seems like, um, it seems like there should be a, y, but maybe there's just an infinite number of universes and this is the one that led to this particular set of humans, [/INST] even without an infinite number of universes. I bet there's an infinite number of intelligent beings </s><s>[INST] throughout this universe. [/INST] Now that we know how many planets I have the right sort of conditions, you know, which is what I can't remember a lot. You know, it's, it's some significant percentage of all planets. Um, then, uh, then there are apparently billions of planets and there's every, I mean, things happen so quickly on earth. You know, once you've got water, then you got life. And um, uh, it did did not take long for, for life to evolve in in the big scheme of things. </s><s>[INST] And if you think you look out there, say there's a nearly infinite number of intelligence civilizations. One dimension you can look at is the proclivity to violence they have. It's interesting to think what level of violence is useful for extending the life of a civilization. So we have a particular set of violence in our history maybe being too peaceful as a problem in the early days. Uh, maybe being too violent quite obviously is as a problem. So you look at viruses, what kind of viruses on earth propagate and succeed If you're too deadly as a big problem, uh, if you're not deadly enough, that's also a problem. So that is a fascinating exploration [/INST] of, I don't see any evidence. I don't see where you're coming from when you say that being too peaceful as a problem. </s><s>[INST] Well, because I'll say it this way, death is a way to get rid of suboptimal solutions. So violence, [/INST] but there's lots of ways to die without violence. Right? </s><s>[INST] To me, death in itself is violence. And [/INST] you </s> |
<s>[INST] It's fascinating because VR we'll talk about it more. It's still, it's still unclear to me in what way VR will change the world, because it does seem clear that VR will somehow fundamentally [/INST] transform this world. And it's unclear to me how yet. And it's Let me know when you want to get </s><s>[INST] Don't get into that. Well, hold on a second, so stick to you being the best programmer ever, okay, in the early days when you didn't have adult responsibilities of leading teams and all that kind of stuff and you can focus on just being a programmer, what did the productive day in the life of John Carmack look like? How many hours of the keyboard, how much sleep, what was the source of calories that fueled the brain? What was it like? [/INST] What times did you wake up? So I was able to be remarkably consistent about what was good working conditions for me for a very long time. I was never one of the programmers that would do all-nighters going through work for 20 hours straight. It's like my brain generally starts turning to mush after 12 hours or so, but the hard work is really important and I would work for decades. I would work 60 hours a week. I would work a 10-hour day, six days a week and try to be productive at that. Now my schedule shifted around a fair amount. When I was young without any kids and any other responsibilities, I was on one of those cycling schedules where I'd kind of get in an hour later each day and roll around through the entire time and I'd wind up kind of pulling in at two or three in the afternoon sometimes and then working again past midnight or two in the morning. And that was when it was just me trying to make things happen. And I was usually isolated off in my office. People generally didn't bother me much at in and I could get a lot of programming work done that way. I did settle into a more normal schedule when I was taking kids to school and things like </s><s>[INST] that. [/INST] So kids were the forcing function that got you to wake up at the same time. It's not clear to me that there was much of a difference in the productivity with that where I kind of feel if I just get up when I feel like it, it's usually a little later each day. But I just recently made the focusing decision to try to push my schedule back a little bit earlier to getting up at eight in the morning and trying to shift things around. Like I'm often doing experiments with myself about what should I be doing to be more productive. And one of the things that I did realize was happening in recent months where I would go for a walk or a run, I cover like four miles a day. And I would usually do that just as the sun's going down here in Texas now and it's still really damn hot. But I'd go out at 830 or something and cover the time there and then the showering. And it was putting a hole in my day where I would have still a couple of hours after that and sometimes my best hours were at night when nobody else is around, nobody's bothering me. But that hole in the day was a problem. So just a couple of weeks ago I made the change to go ahead and say, all right, I'm going to get up a little earlier. I'm going to do a walk or get out there first so I can have more uninterrupted time. So I'm still playing with factors like this as I kind of optimize my work efforts. But it's always been, it was 60 hours a week for a very long time. To some degree, I had a little thing in the back of my head where I was almost jealous of some of the programmers that would do these marathon sessions. And I had like Dave Taylor, one of the guys that he had, he would be one of those people that would fall asleep under his desk sometimes and all the kind of classic hacker tropes about things. And a part of me was like always a little bothered that that wasn't me, that I wouldn't go program 20 hours straight because I'm falling apart and not being very effective after 12 hours. I mean, yeah, 12-hour programming, that's fine when you're doing that. But you're not doing smart work much after, at least I'm not. But there's a range of people. I mean, that's something that a lot of people don't really get in their gut where there are people that work on four hours of sleep and are smart and can continue to do good work. But then there's a lot of people that just fall apart. So I do tell people that I always try to get eight hours of sleep. It's not this, push yourself harder, get up earlier. I just do worse work where you know, you can work 100 hours a week and still get eight hours of sleep if you just kind of prioritize things correctly. But I do believe in working hard, working a lot. There was a comment that a game dev made that I know there's a backlash against really hard work in a lot of cases, and I get into online arguments about this all the time. But it was basically saying, yeah, 40 hours a week, that's kind of a part-time job. And if you were really in it, you're doing what you think is important, what you're passionate about. Working more gets more done. And it's just really not possible to argue with that if you've been around the people that work with that level of intensity and just say, no, they should just stop. And I kind of came back around to that a couple years ago where I was using the fictional example of, all right, some people say, they'll say with a straight face, they think, no, you are less productive if you work more than 40 hours a week. And they're generally misinterpreting things where your marginal productivity for an hour or after eight hours is less than in one of your peak hours, but you're not literally getting less done. There is a point where you start breaking things and getting worse behavior and everything out of it, where you're literally going backwards, but it's not at eight or 10 or 12 hours. And the fictional example I would use was, imagine there's an asteroid coming to impact, to crash into Earth, destroy all of human life. Do you want Elon Musk or the people working at SpaceX that are building the interceptor that's going to deflect the asteroid? Do you want them to clock out at five because, damn it, they're just going to go do worse work if they work another couple hours? And it seems absurd. And that's a hypothetical though, and everyone can dismiss that. But then when coronavirus was hitting and you have all of these medical personnel that are clearly pushing themselves really, really hard, and I'd say it's like, okay, do you want all of these scientists working on treatments and vaccines and caring for all of these people? Are they really screwing everything up by working more than eight hours a day? And of course, people say, I'm just an asshole to say something like that, but it's the truth. Working longer gets more done. </s> |
<s>[INST] But let me take a step back to that moment when you create the A. G. I. System. I think this is a really crucial moment. And between that moment and the democratic board members with the G. At the head, there has to be a relinquishing of power. So is George Washington despite all the bad things he did. One of the big things he did is you relinquish power here first of all, didn't want to be president and even when he became president, he gave he didn't keep just serving as most dictators do for indefinitely. Do you see yourself being able to relinquish control over any G. I. System, given how much power you can have over the world? At first financial just make a lot of money right and then control by having possession of the GI system. [/INST] I'd find it trivial to do that. I'd find it trivial to ruling this kind of part. I mean, you know, the kind of scenario you're describing sounds terrifying to me. That's all I would absolutely not want to be in that position. </s><s>[INST] Do you think you represent the majority or the minority of people in the eye community? [/INST] While, I mean, </s><s>[INST] It's an open question, an important one. Are most people good is another way to ask [/INST] it. So I don't know if most people are good, but I think that when it really counts, people can be better than we think </s><s>[INST] that's beautifully put. Yeah. Are there specific mechanism you can think of of aligning ai jen values to human values? Is that do you think about these problems of continued alignment as we develop the air systems? [/INST] Yeah, definitely. In some sense, the kind of question which you are asking is so if you're able to translate the question to today's terms, it would be a question about how to get an RL agent that's optimizing a value function which itself is learned and if you look at humans, humans are like that because the reward function, the value function of humans is not external. It is internal. And there are definite ideas of how to train a value function, basically an objective, as objective as possible perception system that will be trained separately to recognize, to internalize human judgments on different situations and then that component wouldn't be integrated as the value as the base value function for some more capable aerial system. You could imagine a process like this. I'm not saying this is the process. I'm saying this is an example of the kind of thing you could do </s><s>[INST] so on that topic of the objective functions of human existence. What do you what do you think is the objective function? That simplicity in human existence? What's the meaning of [/INST] life? Oh, mm hmm. I think the question is wrong in some way. I think that the question implies that the reason there is an objective answer which is an external answer. Your meaning of life is X. I think what's going on is that we exist. And that's amazing. And we should try to make the most of it and try to maximize our own value and enjoyment of are very short time while we do exist. </s><s>[INST] It's funny because action does require an objective function is definitely there in some form, but it's difficult to make it explicit and may be impossible to make it explicit, I guess is what you're getting at and that's an interesting fact of an RL environment? [/INST] Well, what I was making a slightly different point is that humans want things and their wants create the drives that caused them to our wants. Our our objective functions are individual objective functions. We can later decided to we want to change that. What we wanted before is no longer good and you want something else. </s><s>[INST] But they're so dynamic there, there's got to be some underlying sort of Freud. There's things, there's like sexual stuff, there's people think it's the fear uh fear of death and there's also the desire for knowledge and you know, all these kinds of things appropriation. They're sort of all the evolutionary arguments, there seems to be there might be some kind of fundamental objective function from, from which everything else um emerges. But it seems because [/INST] that's very I mean I think I think that probably is an evolutionary objective function which is to survive and procreate and make you make you student succeed. That would be my guess, but it doesn't give an answer to the question, what's the meaning of life? I think you can see how humans are part of this big process, This ancient process. We are we are they exist on a small planet and that's it. So given that we exist, try to make the most of it and try to enjoy more and suffer less as much as we can. </s><s>[INST] Let me ask too silly questions about life. one do you have regrets moments that if you went back you would do differently and two are there moments that you're especially proud of that made you truly happy [/INST] so I can answer that. I can answer both questions. Of course there are, there's a huge number of choices and decisions that have made that with the benefit of hindsight, I wouldn't have made them and I do experience some regret but you know, I try to take solace in the knowledge that at the time I did the best they could and in terms of things that I'm proud of their, I'm very fortunate to have things I'm proud to have done things I'm proud of and they made me happy from for some time but I don't think that that is the source of happiness. </s> |
<s>[INST] or Stephen for preventative [/INST] and you could do that too. But I have to say the other issue is This small new peer of here is a drug in Phase three. Now it's an oral antiviral looks good if we go ahead with just one, we're going to get resistance within a few months and it will be useless. We need to have at least two or three drugs that we can give in combinations. And we know that because that's what took care of HIV. That's what took care of HCV hepatitis C virus. It really reduces the emergence of resistance. </s><s>[INST] Joe Rogan got quite a bit of heat recently about mentioning a paper and a broader idea, which I didn't, I don't think is that controversial, but maybe we can expand on it. And the idea is that vaccines creates selective pressure for a virus to mutate and for variance to form. What, first of all, from a biological perspective, can you explain this process and from uh societal perspective, what are we supposed to do about that? [/INST] So let's get the terminology right. So as we talked about earlier, viruses are always mutating. So no vaccine or no drug makes the virus mutate. </s><s>[INST] That's the wrong perspective, which you look at [/INST] what the immune response is putting pressure, selection pressure on the virus and if there's a one particle with the right mutation that can escape the antibody that will emerge. Right? So that's what happens with influenza virus, Right? We vaccinate every year and there are not a lot of people that get infected. So they get natural immunity and then viruses incredibly varied. It mutates like crazy and there's in some person somewhere there's one variant that escapes the antibody which has been induced either by infection or vaccination. It can be both and that drives the emergence of the new variants of the next year. We need to change the vaccine. So I would say Both natural infection and vaccination. Sure, select for variance. Absolute. There's no question because they're inducing immunity. Now, what happened last year was at the beginning of 2020, very few people in the world were immune as the virus first started spreading. But you can see in the sequences of those isolates from the beginning of 2020, you can see all of the changes that are now present in the variance of concern at very, very low frequencies. They were already there but there was no selection for them to emerge until November when we now had many millions of people who had mostly been infected but also some vaccinated. Then we saw the alpha variant emerge in England probably because of immune selection. Now the the virus that had the change that evaded the antibody had an advantage and that virus drove through the population. So that's what we're seeing. We're seeing all these variants are simply antigenics. Elections </s><s>[INST] So the variants, the mutations that are at the core of these quote unquote variants, they were always there all along the vaccine or the infections did not create them [/INST] create their selected. </s><s>[INST] It's like the vaccine wipe out a lot of the variants, right? And then by being by making a body immune to them. And so but some of them survive. And and there was another tree that's built and it's unclear what that tree leads to. I mean, it could make things much worse or much better and we don't we don't know [/INST] well with flu we see year after year the virus changes, we change the vaccine, we deal with it, we change it again. There's an unending. </s><s>[INST] But see that's a very different story. If do you think do you think covid will be um with some likelihood uh like the flu. Whereas basically variants will never be able to um eradicated. [/INST] It will never eradicated in any case ever. </s><s>[INST] Well, come up with the vaccine that makes you immune to enough variance to where there's not enough evolutionary like room. [/INST] Well, if you cut down the number of infections then you reduce the diversity. Sure. Right. The problem is if let's say you're a cynic and you well, vaccination is just selecting for various. So let's stop it. But then you're gonna have infection and that's going to select for variance and there, the more you're more likely to get very sick because we know the vaccines are really good at preventing you from dying. So that's why it still makes sense to use vaccines because they prevent you from dying. That's the bottom line. But can we ever make a vaccine that deals with all variants. Absolutely. And the reason I say that is because people who get naturally infected with SARS COv developed Covid, they recover. If you give them one vaccine dose, they make an immune response that handles all the variants that are around right now. All of them much better than people who have gotten two doses of vaccine. For some reason, their immune responses suddenly broadened after the infection vaccination and they can handle all the variants that we know of so far. So that tells me we can devise a strategy to do the same thing with a vaccine that makes a really broad vaccine that will handle all the well you </s><s>[INST] actually uh on the virology blog. I don't know if you're the author of that, but I guess Oh, the blog. Yes. But there's a particular post that's talking about reporting on the paper that mix and match strap. Yes. That's one of my co [/INST] writers Trudy ray. </s><s>[INST] Yeah, that's it's an interesting idea that there's some early evidence now that mixing and matching vaccines like one shot of fighter and one of like modern or something that creates a much better uh immunity than does two shots of Pfizer. [/INST] I think that's worth exploring. Absolutely. And this is relevant what we're doing with influenza, You know, instead of having to vaccinate people every year, why can't we devise a vaccine which you'd get once in your lifetime or maybe once every 10 years. Okay, so the spike of influenza. It's a long Protein kind of like the spike of sars-cov-2, it's stuck in the virus membrane and the very tip that's the part that changes every year. It's where the antibodies bind. But the stem doesn't change. And if you make antibodies to the stem they can also prevent infection. It's just that when people are infected or with the current vaccines that will make many antibodies to that stem part. But we're trying to figure out how to make those and we think they would be broadly protective and you'd never be able to or more rarely be able to have a variant emerge that escaped it. And I think we can do the same thing with with coronavirus two for sure. </s> |
<s>[INST] The state is an authoritarian. [/INST] So it might not be called a state, but it would function as a state, right? But why not just call it a state? But in other words, if you don't have something like that, then don't you have a greater risk of tyranny or a tyrant emerging in the vacuum? So I think people's fear of the state is what would happen if the state had too much power. And I think that's a legitimate fear. That's why we have democratic checks on state power and certain guarantees of freedom and so on. But yeah, I guess I just wonder, I'm more afraid of the vacuum and not having a democratic responsive state and what the world would turn into. And also, I'm just not a utopian thinker, if that makes sense. I like to think that I'm an egalitarian thinker. I'm a socialist. But my mind just goes to, I could see a vision of the future that I would like 50, 60 years from now. Maybe there's some sort of future of superabundance and automation, and there's some sort of techno-utopian future. We don't want some of those things that would exist in my five minutes from now vision of socialism. But I just don't see it, and in general, I'm wary of visions of change that seem like they're not built off little thing pieces that we have now and not built off history and experience and whatever else. I don't want a year zero. I don't even like the term prehistory, because I think there's a lot in history that I want. I want Shakespeare under socialism. I want a lot of things that I think we should be grateful for. There's a part of tradition that I think that exists, that's hierarchical and exploitative and whatever else. But there's another part of tradition that's our sense of place and belonging and our connection with the past and hopefully the future. </s><s>[INST] And I want to keep that. And also, yeah. So you're worried about revolution or otherwise, the vacuum being created, and you're worried about the things that might fill that vacuum. So the anarchists often worry about the same mechanism of the state that controls voting or keeps voting robust and resilient and stable. The same mechanism also having a monopoly on violence. And so that's the tension. So they get very nervous about a central place having a monopoly on violence. [/INST] Whereas, if there is gonna be a place for the monopoly on violence, let's just say we temporarily take that for granted, should it not be a place with a skilled, elected, accountable, transparent civil service with a democratic mandate, and so on? </s><s>[INST] Yeah, yeah, yeah, yeah, well put. Speaking of AI, just just to go on a tangent, do you think it's possible to have a future world at least 50 years, 50, 100 years where AI, there's an AI sort of central planning, sort of the we remove some of the human elements that I think get us into a lot of trouble? Like you could, you can take a perspective on the Soviet Union and then the flaws of the system there have less to do with different ideologies and more to do with the humans in the vacuums and how humans feel vacuums and the corrupting nature of power and so on. If we have AI that it's more data driven and is not susceptible to the human elements, is that possible to imagine such a world almost like a from a sci fi perspective? [/INST] Maybe in the future, you can imagine certain calculation problems that arose during central planning solve through advanced computing. But I would say that there's another whole set of problems with the system that were incentive problems. And I'm not sure how that advanced computing would solve the incentive problems of how do you get people to actually produce things that other people want? Kind of that informational question, how do you communicate without endless meetings or someone reading your brain? Yeah, what do you actually want? So so there's there's that kind of informational question. But then there's the incentive of, you know, how do you get people to work efficiently at work? And how do you get firms to to use their resources that they're getting more more efficiently? And I think solving the calculation problem solves some of these questions, but not all of them. But you know, that's kind of a who knows. But if your vision of the future requires some sort of leap into technological unknown, that's very hard to advocate for today. </s><s>[INST] It's exciting to consider the possibility of technology empowering a better reallocation of resources. If you care about of kind of the innate value of human beings, and think of the mechanism of reallocation resource good way to empower that equality, that it's nice to remove the human element from that. Like if you work really hard, and you're really good at your job, it's [/INST] nice to be really data driven in allocating more resources to you. So kind of like I kind of think that the agency part requires human beings and conscious human activity. So I think if you have a sort of planning system that works, and let's say the technology is there for it to work, I would want it to be democratic planning in such a way there is a human element, there is some debate and deliberation society. And also even in my vision of socialism, with the state sector and state investments and so on, I want there to be more public discussion and debate about certain things that's not just left to technocrats, because you don't want to live in society where you're you just find out the next day that there's some massive infrastructure project that you haven't, you know, had a chance to think about or debate or feel like you're </s> |