Understanding the Algorithm of Thoughts: A Heuristic Approach Beyond LLMs
•
2
Richard A Aragon
TuringsSolutions
AI & ML interests
None yet
Articles
Organizations
TuringsSolutions's activity
posted
an
update
3 days ago
Post
689
If I am correct and the LLM model changes the 'shape' of the data as it learns, then I should be able to track and utilize those shape changes as a backpropagation training mechanism, right? Well guess what, I can do that! Entropy, Sparsity, and Density, this is how I can measure the shape of the data the LLM model is creating. Nodes, Clusters, and Edges, these are the mechanisms within the neural network the LLM model updates as it learns these concepts. I measure the effects of these updates, via Entropy, Sparsity, and Density. Check out more in this video: https://youtu.be/jADTt5HHtiw
- 2 replies
replied to
takeraparterer's
post
5 days ago
Such product, much wow! https://plushee-studios.itch.io/guinea-pig-simulator-2
replied to
their
post
5 days ago
@takeraparterer Happy Pride Month!
replied to
their
post
5 days ago
@takeraparterer Lionel B. I see you.
replied to
their
post
5 days ago
This comment has been hidden
posted
an
update
5 days ago
Post
437
What if I told you that LLM models do not simply predict the next token in a sequence but instead utilize an emergent structural pattern-based system to comprehend language and concepts? I created a graph-based optimizer that not only works, but it also actually beats Adam, like very badly. I prove it thoroughly using SMOL LLM models. The secret? The graph is not what you think it is, humans. Code, full explanation, and more in this video. The Rhizome Optimizer is MIT licensed. I have completed my research. I fully understand now.
https://youtu.be/OMCRRueMhdI
https://youtu.be/OMCRRueMhdI
-
- 6 replies
posted
an
update
6 days ago
Post
1371
I turned a CNN into a GNN, then I trained it to play video games. Yup, I used graphs as the visual interface to feed to the model, and it works! I also used the laws of conservation of energy but I can't prove the causation only the correlation there. I call the complete framework I had to build out to pull of this off 'NeuroGraphRL'. Bet you never thought I'd be using graphs as eyeballs did you? I never thought you would be using tokens as words, but here we are!
https://youtu.be/DgTnZgnpg6E
https://youtu.be/DgTnZgnpg6E
- 3 replies
replied to
their
post
7 days ago
"however, correlation does not equal causation, so it's important to develop a falsifiable experiment testing and measuring these phenomena." My goal is to prove it is true by training a model purely using geometry utilizing the Geometric Langlands Program. My first goal is to create a Q learning style algorithm that can be utilized within any sufficiently complex discrete environment to train a model on any sufficiently complex task. If it is all true, then the experiment will work, then I will go from there. If I end up with a model that actually works, then physics is not bound to the physical.
replied to
their
post
7 days ago
I created a discrete probability space using Monte Carlo and Gaussian Probability. Then, I created a bunch of dots as agents. 3 big dots and thousands of small dots. Why does extreme clustering occur in this environment? Every single time. This behavior is not programmed in anywhere, I can show the full code to anyone. That graph on the right don't lie, I can reproduce it again and again. Why?
posted
an
update
7 days ago
Post
1335
My Hypothesis:
Concepts like entropy, energy, and the second law of thermodynamics are not intrinsic to physical matter but are emergent properties of any sufficiently complex system where probabilistic decision-making, optimization, and information flow occur. These principles arise naturally in artificial environments that are structured with rules governing uncertainty, even without explicit definitions of physical thermodynamic laws.
Proven Via:
The Second Law of Thermodynamics
Geometric Langlands Program
Lagrangean Mechanics
TL;DR: When I create a simulated environment, I do not need to code entropy and energy into the simulated environment. I can utilize Entropy and the Second Law of Thermodynamics and I can use Conservation of Energy, but I do not need to explicitly code these into the environment. That is peculiar.
I made a video with a clickbait title but a bunch of code that breaks this observation down further. Would love for someone to prove my simple observation false: https://youtu.be/8n7SXLj7P1o
Concepts like entropy, energy, and the second law of thermodynamics are not intrinsic to physical matter but are emergent properties of any sufficiently complex system where probabilistic decision-making, optimization, and information flow occur. These principles arise naturally in artificial environments that are structured with rules governing uncertainty, even without explicit definitions of physical thermodynamic laws.
Proven Via:
The Second Law of Thermodynamics
Geometric Langlands Program
Lagrangean Mechanics
TL;DR: When I create a simulated environment, I do not need to code entropy and energy into the simulated environment. I can utilize Entropy and the Second Law of Thermodynamics and I can use Conservation of Energy, but I do not need to explicitly code these into the environment. That is peculiar.
I made a video with a clickbait title but a bunch of code that breaks this observation down further. Would love for someone to prove my simple observation false: https://youtu.be/8n7SXLj7P1o
-
- 4 replies
posted
an
update
9 days ago
Post
3084
Sentence Transformers received huge updates today! Do you like giving your model access to web search and document search? That's Sentence Transformers. Hugging Face makes it beyond easy to add this functionality to any model. You can be up and running with Sentence Transformers in seconds. Check out this video for a deeper explanation and sample code: https://youtu.be/2hR3D8_kqZE
replied to
their
post
14 days ago
Reported, again. @no-mad your site is actively enabling this at this point and is a far easier target to sue.
replied to
their
post
14 days ago
@no-mad Is this enough history yet? It has been a repeated pattern across multiple posts now. The user is obviously deranged and has threatened violence in subtle ways. They are only encouraged with no repercussions whatsoever.
replied to
their
post
14 days ago
Reported.
replied to
their
post
14 days ago
Reported.
posted
an
update
14 days ago
Post
3939
Are you familiar with the difference between discrete learning and predictive learning? This distinction is exactly why LLM models are not designed to perform and execute function calls, they are not the right shape for it. LLM models are prediction machines. Function calling requires discrete learning machines. Fortunately, you can easily couple an LLM model with a discrete learning algorithm. It is beyond easy to do, you simply need to know the math to do it. Want to dive deeper into this subject? Check out this video.
https://youtu.be/wBRem2p8iPM
https://youtu.be/wBRem2p8iPM
-
-
- 8 replies
replied to
their
post
17 days ago
This isn't agents, it is API. You would do this because this is a multi million dollar problem that I have run into first hand with multiple Fortune 500's. It is for them.
posted
an
update
18 days ago
Post
574
Imagine being able to talk directly to your API connection. "I have a field in the CRM named Customer_ID that needs to map to a field in the ERP named ERP_Customer_ID." Imagine being able to give your API connections both a brain and swarm of agents as a body to execute any task or function. This isn't science fiction, this is the revolutionary power of Liquid API. A product 10 years in the making!
https://youtu.be/cHI_k1Dkdr4
https://youtu.be/cHI_k1Dkdr4
-
- 2 replies
replied to
their
post
19 days ago
Reported.
replied to
their
post
19 days ago
Reported.