--:-- Host: Any LLM that was trained on pre-1915 physics would never have come up with a theory of relativity. Einstein had to sort of reject the Newtonian physics and come up with this space-time continuum. He completely rewrote the rules. AGI will be when we are able to create new science, new results, new math. When an AGI comes up with a theory of relativity, it has to go beyond what it has been trained on to come up with new paradigms, new science. And that's by definition of ATA.
--:-- Host: On this episode of the A16Z podcast, I talk with Vishal and A16Z's Martin Fasato about how that moment led to retrieval augmentation generation and how Vishal's formal models explain what large language models can and can't do. We discuss why LLMs might be hitting their limits, what real reasoning looks like, and what it would take to go beyond them. Let's get into it. Martin, I knew you wanted to have Vishal on. What do you find so remarkable about him and his contributions that inspired this?
--:-- Martin Fasato: Vishal and I actually have very similar backgrounds. We both come from networking. He's a much more accomplished networking guy than I am. That's a high bar given to you. And so we actually view the world in an information theoretic way. It is actually part of networking. And with all this AI stuff, there's so much work trying to create models that can help us understand how these LLMs work. And in my experience over the last three years, the ones that have most impacted my understanding, and I think have been the most predictive, are the ones that Vishal has come up with.
--:-- Martin Fasato: He did a previous one that we're going to talk about called Matrix, is it? Beyond the black box, but yeah. Beyond the black box. Actually, we should put this in the notes for this, but the single best talk I've ever seen on trying to understand how LLMs work is one that Vishal did at MIT, which Hari Bala Krishnan pointed me to, and I watched that.
--:-- Martin Fasato: So he did that work, And then he's doing more recent work that's actually trying to scope out not only how LLMs reason, but like it has some reflections on humans reason too. And so I just think he's doing some of the more profound work and trying to understand and come up with models, formal models for how LLMs reason.
--:-- Host: On that note, you said his most recent work helped you change how humans think. Why don't you flesh that out a little bit? How did it sort of...?
--:-- Martin Fasato: Well, okay, so can I just try to take a rough sketch at it and then you just tell me how wrong I am? Right ahead. You're trying to describe how LLMs work, and one thing that you found is that they reduce a very, very complex multidimensional space into basically a geometric manifold that's a reduced state space. So it's reduced degrees of freedom, but you can actually predict where in the manifold the reasoning can move to, roughly.
--:-- Martin Fasato: So you've reduced the dimensionality of the problem to a geometric manifold, and then you can actually formally specify kind of how far you can reason within that manifold. And the articulation is that we, or one of the intuitions is that we as humans do the same thing, is we take this very complex, heavy-tailed, stochastic universe, and we reduce it to kind of this geometric manifold. And then when we reason, we just move along that manifold.
--:-- Martin Fasato: Yeah, I think you captured it accurately. That's kind of the spirit of the work. Wait, can I just hear it in your words? Because I'm a VC, so.
--:-- Martin Fasato: You're a VC with an H index of what, 60? True. Yeah, so ultimately what all these LLMs are doing, whether the early LLMs or the LLMs that we have today with all sorts of post-training, RLHF, whatever you do, at the end of the day, what they do is they create a distribution for the next token. So given a prompt, these LLMs create a distribution for the next token or the next word, and then they pick something from that distribution using some kind of algorithm to predict the next token, pick it, and then keep going.
--:-- Martin Fasato: Now, what happens because of the way we train these LLMs, the architecture of the transformers, and the loss function, the way you put it is, right, it sort of reduces the world into these Bayesian manifolds. Yeah. And as long as the LLM is going in, sort of traversing through these manifolds, it is confident. And it can produce something which makes sense. The moment it sort of wears away from the manifold, then it starts hallucinating and starts spotting nonsense. Confident nonsense, but nonsense.
--:-- Martin Fasato: So it creates these manifolds. And the trick is the distribution that is produced. You can measure the entropy of the distribution. Entropy the way Shannon just says it. Shannon entropy. Shannon entropy, not thermodynamic entropy.
--:-- Martin Fasato: Suppose you have a vocabulary of, let's say, 50,000 different tokens. And you have a distribution, next token distribution, over these 50,000 tokens. So let's say the cat sat on the, right? If that is a prompt, then the distribution will have a high probability for mat or hat or table and a very low probability of, let's say, ship or whale or something like that, right? So because of the way it's trained, it has these distributions.
--:-- Martin Fasato: Now, the distributions can be low entropy or high entropy. A high entropy distribution means that there are many different ways that the LLM can go. with a high enough probability for all those paths. Low entropy means that there are only a small set of choices for the next token. And the prompts also you can categorize into two kinds of prompts. One prompt is, as you can say, high information entropy. And one prompt is low information entropy.
--:-- Martin Fasato: So the way these manifolds work, the LLMs start paying attention to prompts that have high information entropy and low prediction entropy. So what do I mean by that? So when I say I'm going out for dinner, so when I say I'm going out for dinner, that phrase, the LLMs have been trained, they've seen it a lot, and there are many different directions I can go with it. I can say I'm going for dinner, Tonight I'm going to dinner to McDonald's or I'm going to dinner, blah, blah, blah.
--:-- Martin Fasato: There are many different. But when I say I'm going to dinner with Martin Cassado, you know, the LLM, now this is information rich. This is sort of a rare phrase. And now the sort of realm of possibilities reduces because Martin is only going to take me to Michelin star restaurants. I'm not going to go to a McDonald's. You get what I'm saying.
--:-- Martin Fasato: The moment you add more context, you make the prompt information rich, the prediction entropy reduces. Yep, yep, yep, yep. And another example that I often cite is...
--:-- Martin Fasato: But just quickly, but what is your takeaway? What is your implication on that? Which is, of course, as you're... So, yeah, so you're... Sorry, I forgot how you described it, but so the more precise you are, the more tokens you are, I presume, the less options you have for the next token. Is that correct or not correct?
--:-- Martin Fasato: Yeah, yeah, essentially. So you're reducing it to a very specific state space when it comes to confidence in an answer. And this is kind of a manifold that you can go on. And then, I mean, do you have kind of a conclusion of what that means for systems or what that means for reasoning? or is it just a nice way to articulate the bounds of LLMs?
--:-- Martin Fasato: No, there is something, I don't know if I should say profound, but there is something about it which tells what these LLMs can or cannot do. So one of the examples that I often tell is, suppose I ask you what is 769 times 1025. You have no idea. You can have some vague idea, given the two numbers, right? And so in your mind, the next token distribution of the answer is going to be diffuse, right? You don't know. You have maybe a vague guess.
--:-- Martin Fasato: If you are mathematically very good, maybe your guess is more precise, but it is still going to be diffuse. And it's not going to be the correct answer. But if you say, can I write it down and do it the way we have learned multiplication tables? Now you know exactly what to do next step. You write 769 and then 1025 and then you know exactly.
--:-- Martin Fasato: So at each stage of that process, your prediction entropy is very low. You know exactly what to do because you have been taught this algorithm. And by invoking this algorithm saying, okay, I'm not going to just guess the answer, but I'm going to do it step by step. Then your prediction and entropy reduces. And you can arrive at an answer which you're confident of and which is correct.
--:-- Martin Fasato: And the LLMs are pretty much the same way. That's why chain of thought works. What happens with chain of thought is you ask the LLM to do something chain of thought. It starts breaking the problem into small steps. These steps it has seen in the past. It has been trained on. Maybe with some different numbers, but the concept it has been trained on. And once it breaks it down, then it's confident. Okay, now I need to do A, B, C, D, and then I arrive at this answer, whatever it is.
--:-- Host: I want to get into LLMs, but first, Vishal, maybe you can give more context on your background and how that informs your work here.
--:-- Vishal Misra: Okay. So yeah, as Martin said, my background is very similar to his. We come from doing networking. So my PhD thesis, my sort of early work at Columbia has all been in networking. But there's another side of me, another hat that I wear, which is both an entrepreneur and a cricket fan.
--:-- Vishal Misra: I was going to say, don't you own a cricket team or something? I'm a minority owner for your local cricket team, the San Francisco Unicorns. That's right. I'm very proud to have you. Yeah. So, but, so say, in the 90s, I was one of the people who started this portal called Crickinfo. And Crickinfo, at one point, it was the most popular website in the world. It had more hits than Yahoo. That was before India came on.
--:-- Vishal Misra: That's remarkable. And so, you know, we built, cricket is a very start with sport. You'll think baseball multiplied by 1,000. And we had built this free searchable stats database on Cricket called Stats Guru. And this has been available on Cricket 4 since 2000. But because you can search for anything, everything was made available on Stats Guru.
--:-- Vishal Misra: And you know, you can't expect people to write SQL queries to query everything. So how did we do it? Well, it was a web form. where you could formulate your query using that form, and in the back end, that was translated into SQL query, got the results, and got it back. But as a result, because you could do everything, everything was made available.
--:-- Vishal Misra: The web form had 25 different checkboxes, 15 text fields, 18 different dropdowns. The interface was a mess. It was very daunting. So, and ESPN acquired CrickInfo in the mid-2006, I think, but they still kept the same interface. And that has always sort of nagged me.
--:-- Vishal Misra: And so I still know the people who are on ESPN. Wait, wait, what nagged you? Is that CrickInfo did not have informal language that had a web form for doing queries? That web form was terrible Because of that only the real nudges you Of all the things in the world that bother you the fact that an old website was a web form I appreciate your commitment to aesthetic.
--:-- Vishal Misra: So I'm still friendly with the people who run ASVN Cricket. The editor-in-chief, whenever he comes to New York, we meet up, we go out for a drink. And so he was here in 2000. So now the story shifts to how LLM and me sort of met.
--:-- Vishal Misra: So January 2000, right before the pandemic, he was here. And I again said, why did you do something about Stats Guru? And he looks at me and says, why did you do something about Stats Guru? He was kind of joking, but he thought maybe, you know, I had some ways to fix the interface.
--:-- Vishal Misra: So anyway, then the pandemic hit, the world stopped. But in July of 2020, the first version of GPT-3 was released. And I saw someone use GPT-3 to write a SQL query for their own database using natural language. And I thought, can I use this to fix StatsGuru?
--:-- Vishal Misra: So I got early access to GPT-3, you know, getting access those days was difficult, but somehow I got it. But soon I realized that, you know, no, I cannot really do it. Because stats guru, the backend databases were so complex. And if you remember, GPT-3 had only a 2048 token context window. There was no way in hell I could fix the complexities of that database in that context window.
--:-- Vishal Misra: And GPT-3 also did not do instruction following at that time. but then in trying to solve this problem I accidentally invented what's now called RAC where based on the natural language query I created a database of natural language queries and the structured queries I created a DSL which then translated into a REST call to StatsGuru so based on the new query I would look through my set of natural language queries.
--:-- Vishal Misra: I had about 1,500 examples, and I would pick the six or seven most relevant ones. And then that and the structured query I would send as a prefix and the new query, and GPD3 magically completed it, and the accuracy was very high. So that had been running in production since September 2021.
--:-- Vishal Misra: You know, about 15 months before chat GPD came, and, you know, the whole revolution in some sense started and Rack became very popular. I didn't call it Rack, but this is something sort of I accidentally did in trying to solve that problem for QuickInfo.
--:-- Vishal Misra: Now, once I built it, I was thrilled that this worked, but I had no idea why it worked. I stared at that transformer architecture diagram. I read those papers, but I couldn't understand how or why it worked. So then I started in this journey of developing a mathematical model, trying to understand how it worked.
--:-- Vishal Misra: So that's been sort of my journey through this world of AI and LLMs because I was trying to solve this cricket problem. Yeah, amazing. And so maybe reflecting back since the release of GPT-3, what has most surprised you about how LLMs have developed?
--:-- Vishal Misra: So what has most surprised me the pace of development so gpd3 was you know it was a nice pilot trick and you had to jump through hoops to get it to do something useful but starting with the you know chat gpd was an advance over gpd3 and then you had all these things like chain of thought instruction following gpd4 really made it polished and you know the pace of development has really surprised me.
--:-- Vishal Misra: Now, you know, when I started working with GPT-3, I could sort of see what its limitations were, what I could make it do, what I couldn't make it do. But I never thought of it as, you know, what these LLMs have become for me now and what have become for millions of people around the world. We treat these models as our co-workers, almost like an intern that, you know, you're constantly chatting with them, brainstorming, making them do all sorts of work, which we couldn't imagine, you know.
--:-- Vishal Misra: Just when ChatGPT was released, it was nice, it could write poems, it could write limericks, it could answer some hallucinogenic questions. But the capabilities that have emerged now, that pace has been very sort of surprising to me. Do you see progress plateauing? Or how do you, either now or in the near future, or how do you see it going?
--:-- Martin Fasato: Yes, in some sense, progress is plateauing. It's like the iPhone. When the iPhone came out, wow, what is this thing? And the early iterations, constantly we were amazed by new capabilities. But the last seven, eight, nine years, it's maybe the camera got a little bit better or one thing changed here or memory is more. but there has been no fundamental advance in what it's capable of.
--:-- Martin Fasato: You can sort of see a similar thing happening with these LLMs. And this is not true for just one company and one model. You look at what OpenAI is coming up with or what Anthropic, Google, or all these open source Chinese model or Mistral, the capabilities of LLMs has not fundamentally changed. They've become better, right? They've improved, but they have not crossed into a different realm.
--:-- Martin Fasato: So this is something that I really appreciate about your work. And so the thing that really struck me is as soon as these things showed up, you actually got busy trying to have a formal model of what they're capable of, which was in stark contrast to what everybody else was doing. Everybody else was like, AGI, these things are going to, you know, recursively self-improve. Or they'll say, oh, these are just stochastic parents, which doesn't mean anything.
--:-- Martin Fasato: So everybody had rhetoric. And sometimes this rhetoric was fanciful. And sometimes this rhetoric was almost reductionist. Like, oh, it's just a database, which is clearly not true. And the thing that really struck me about your work is you're like, no, let's figure out exactly what's going on. Let's come up with a formal model. And once we have a formal model, we can reason about what that means.
--:-- Martin Fasato: And then, you know, in my reading of your work, I kind of break it up in two pieces. There's the first one where you basically, you came up with this, you know, matrix abstraction. I think it's worth you talking through. And then you took in-context learning as an example and you mapped it to Bayesian reasoning, which to me was incredibly powerful because at the time, nobody knew why in-context learning worked.
--:-- Martin Fasato: So I think it would be great for you to discuss that because, again, And I think it was the first real kind of formal effect on like how are these things working. And then the more recent work that you're working on now is a kind of more generalized version of what is the state space that these models output when it comes to confidence, which is the manifold that we were talking about before.
--:-- Martin Fasato: So I think it would be great if you just described your matrix model and then how you use that to provide some bounds, what in-context learning is doing, what's happening. Okay, so let's start with that matrix abstraction. So the idea behind the matrix is you have this gigantic matrix where every row corresponds to a prompt. and then the number of columns of this matrix is the vocabulary of the LLM, the number of tokens it has that it can emit.
--:-- Martin Fasato: So for every prompt, this matrix contains the distribution over this vocabulary. So when you say the cat sat on the, you know, the column that corresponds to mat will have a high probability. Most of them will be zero. But, you know, reasonable continuations will have a non-zero probability. And so you can imagine that there's this gigantic matrix.
--:-- Martin Fasato: Now, the size of this matrix is, you know, if we just take just the old first-generation GPT-3 model, which had a context window of 2,000 tokens and a vocabulary of 50,000 NEXT tokens or 50,000 tokens, then the size of it, the number of rows in this matrix, is more than the number of atoms across all galaxies that we know of. So clearly, we cannot represent it exactly.
--:-- Martin Fasato: Now, fortunately, a lot of these rows do not appear in real life. An arbitrary collection of tokens, you are not going to use that as a prompt. similarly you saw a lot of these rows are absent and a lot of the column values are also zero right when you say the cat sat on the it's unlikely to be followed by the token corresponding to let's say numbers or you know an arbitrary collection of tokens there will be only a very small subset of tokens that can follow a particular prompt so this matrix is very very sparse but even after that sparsity and even after removing the sort of gibberish prompts the size of this matrix is too much for these models to represent even with the trail in parameters
--:-- Martin Fasato: So what in an abstract sense what is happening is the models get trained on certain data from the training set and certain a small subset of these rows, you have reasonable values for the next token distribution. Whenever you give the prompt something new, then it'll try to interpolate with what it has learned and what's there in the new prompt and come up with a new distribution.
--:-- Martin Fasato: But it's basically, so it's more than a stochastic parrot. It is sort of based on this subset of the matrix that it has been trained on. So when I say, you know, I'm going out for dinner with Martin tonight. Now, I'm reasonably sure that it has never encountered that phrase in its training data. But it has encountered variants of this phrase. and given that I'm going out with Martin, it can produce a Bayesian posterior. It uses that evidence that Martin is the one that I'm going for dinner with and it'll produce a next token distribution that will focus on the likely places that we are going.
--:-- Martin Fasato: So this matrix, because it's represented in a compressed way, yet the models respond to everything, every prompt. How do they do it? Well, they go back to what they've been trained on, interpolate there, and use the prompt as sort of some evidence to compute a new distribution. Right, so the context of the prompt impacts the posterior distribution. Exactly, yeah. Right.
--:-- Martin Fasato: New evidence, exactly. To learn from. So I'll give you, so for instance, the Cricut example that I spoke about earlier. Yeah. So I created my own DSL. Yep. Which you know mapped a natural language query in Cricut to this DSL which then I can translate into a SQL query or a REST API or whatever But getting the DSL is important Now these LLMs have never seen that DSL I designed it. But yet, after showing a few examples, it learned it. How did it learn it? And this is in the prompt. You didn't know training, no post-training. 100% in the prompt, right? So like it's the way to understand it. Yeah, this was happening in October 2020. I had no access to internals of OpenAI. I could just access the API. OpenAI had no access to internal structure of Stats Guru or the DSL that I cooked up in my head. Yet, after showing it only a few examples, it learned it right away.
--:-- Martin Fasato: So that's an example where it has seen DSLs or structures in the past. and now using this evidence that I show, okay, this is what my DSL looks like, now a new natural language query, it is able to create the right posterior distribution for the tokens that map to the example that I've seen. Now, the other beautiful thing about this is, this is an example of few-shot learning or in-context learning, right? But when I give that prompt, along with these examples to this LLM, I'm not saying to the LLM, okay, this is an example of few-shot learning, so learn from these examples. You just pass this to the LLM as a prompt and it processes it exactly the way it would process any other prompt, which is not an example of in-context learning.
--:-- Martin Fasato: So that really means that the underlying mechanism is the same. whether you give a set of examples and then ask it to complete a task like an in-context learning or just give it some prompt for continuation that I'm out for dinner with Martin tonight there's no in-context learning there but the process with which it's generating or doing this inferencing is exactly the same and that's what I have been trying to model and come up with a formal model of what I've found very impressive is you've used this basic model to show a number of things, right? To describe context learning and to map the Bayesian learning.
--:-- Martin Fasato: But you did it for another one where you kind of, you've sketched out this almost glib argument on Twitter, on X, where you made this, you made a rough argument for why recursive self-improvement can't happen without additional information. And so maybe just walk through very quickly how like the same model, you can just very quickly show that a model can never recursively self-improve.
--:-- Martin Fasato: So, you know, another phrase that we've been using recently is, you know, the output of the LLM is the inductive closure of what it has been trained on. Yeah. So when you say that it can recursively self-improve, it could mean one of two things. So let's get back to the... Well, actually, you know what's kind of interesting is like often most people agree that if you have one LLM and you just feed the output and the input, like it's not going to do anything. But then often people will say, well, what if you have two LLMs? You have no external information, but you have two LLMs talking to each other. Maybe they can improve each other and then you can have like, you know, a takeoff scenario.
--:-- Martin Fasato: But again, you even address this, even in the case of like n number of LLMs using kind of the matrix model to show that you just aren't gaining any information. Yeah. Yeah, so you can represent the sort of information contained in these models. And let's go back to that matrix analogy that I have, the matrix abstraction. So like I said, you know, these models represent a subset of the rows, right? Yeah.
--:-- Martin Fasato: So a subset of the rows are represented, but some of these rows are able to help fill out some of the missing rows. For instance, you know, if the model knows how to do multiplication doing the step-by-step, then every row that is corresponding to, let's say 769 times 125 or whatever, all those multiplications, it can fill out the answer. Because it has those algorithms sort of embedded in them. you just need to unroll them.
--:-- Martin Fasato: So it can sort of self-improve up to a point. But beyond a point, these models can only sort of generate what they have been trained on. So let me give you, I'll give you three examples. Yeah. So any model, any LLM that was trained on pre-1915 physics would never have come up with a theory of relativity. Einstein had to sort of reject the Newtonian physics and come up with a space-time continuum. He completely rewrote the rules, right? So that is an example of, you know, AGI, where you are generating or generating new knowledge.
--:-- Martin Fasato: It's not simply unrolling what's already... It's not computing something. It's actually discovering something fundamental about the universe. And for that, you have to go outside your training set. Similarly, you know, any LLM that was trained or didn't would not have come up with quantum mechanics. Right? That's where particle duality or this whole probabilistic notion or that, you know, energy is not continuous, but it is quantized. You had to reject Newtonian physics.
--:-- Martin Fasato: Yeah. Or Gettel's incompleteness theorem. Yeah. He had to go outside the axioms to say that, okay, it is incomplete. So those are examples where you're creating new science or fundamentally new results. That kind of self-improvement is not possible with these architectures. They can refine these, they can fill out these rows where the answer already exists.
--:-- Martin Fasato: Another example, you know, which has received a lot of press these days is these IMO results, International Mathalipiad. You know, whether it's a human solving it or the LLM solving it, they are not inventing new kinds of math. They are able to connect known results in a sequence of steps to come up with the answer. So even the LLMs, what they are doing is they are exploring all sorts of solutions. In some of these solutions, they start going on this path where their next token entropy is low. So that's where I say they are in that Bayesian manifold where you have this entropy collapse.
--:-- Martin Fasato: And by doing those steps, you arrive at the answer. But you're not inventing new math. You're not inventing new axioms or new branches of mathematics. You're sort of using what you've been trained on to arrive at that answer. So those things LLMs can do, you know, they'll get better at it, of connecting the known dots. Yeah. But creating new dots, I think we need an architectural advance. Yeah.
--:-- Martin Fasato: So Martin was talking earlier about how the discourse was either stochastic parrots or AGI recursive solving room. How do you conceive of the AGI discourse or even the concept? What does it mean to the extent that it's useful? How do you think about that?
--:-- Martin Fasato: It's sort of a number. The way I think about it, the way we've tried to formulate it in our papers, it's beyond a stochastic parrot, but it's not AGI. It's doing Bayesian reasoning over what it has been trained on. So it's a lot more sophisticated than just a stochastic parrot. How do you define AGI?
--:-- Martin Fasato: Okay, so AGI. So how do I define AGI? So the way I would say that LLMs currently navigate through this known Bayesian manifold, AGI will create new manifolds. So right now, these models navigate. They do not create. AGI will be when we are able to create new science, new results, new math. When an AGI comes up with a theory of relativity, I mean, it's an extremely high bar, but you get what I'm saying.
--:-- Martin Fasato: It has to go beyond what it has been trained on to come up with new paradigms, new science. That's my definition of AGI. Vishal, do you think that based on the work you've done, can you bound the amount of data, computer, or data or compute that would be needed in order for it to evolve? So what are the problems, if you just take LLMs as they exist there is so much data used to create them to create a new manifold will need a lot more data just because of the basic mechanisms otherwise it will just get consumed into the existing set of data have you found any bounds of what would be needed to actually evolve the manifold in a useful way or do you think we just need a new architecture
--:-- Vishal Misra: I personally think that we need a new architecture the more data that we have the more compute we have we'll get maybe smoother manifolds so it's like a map there's this view that people have they're like well Vishal this is all good and well but I could just take an LLM and I can give it eyes and I can give it ears and I can put it in the world and it'll gain information and based on that interface it'll improve itself and therefore it can learn new things.
--:-- Vishal Misra: But the counterpoint that I've always just intuitively thought to that is the amount of data used to train these things is so large. How much can you actually evolve that manifold given an incremental, I mean, almost none at all, right? There has to be some other way to generate new manifolds that aren't evolving the existing one.
--:-- Vishal Misra: I completely agree. There has to be a new sort of architectural leap that is needed. to go from the current, you know, just throwing more data and more compute, you know, it's going to plateau. It's, you know, the iPhone 15, 16, 17. And are there any research directions that are promising in your mind that might help us, you know, go beyond LLM limitations?
--:-- Vishal Misra: So, I mean, again, I love LLMs. They are fantastic. They are going to increase productivity like nobody's business. But I don't think they are the answer. So, you know, Yad Likhan famously says that LLMs are a distraction on the road to AGI. They're a dead end. They're a dead end to AGI. I don't think, I'm not quite in that camp, but I think we need a new architecture to sit on top of LLMs to reach AGI.
--:-- Vishal Misra: You know, a very basic thing, you know what Martin just said, you give them eyes and you give them ears, you make them multimodal, of course they'll become more powerful. But you need a little bit more than that. You know, the way human brains learn with very few examples, that's not the way transformers learn. And, you know, I'm not saying that we need to create an Einstein or a Gator, but there has to be an architectural leap that is able to create these manifolds.
--:-- Vishal Misra: And just throwing new data will not do it. It'll just smoothen out the already existing manifolds. Is that something, so is your goal to actually help think through new architectures or are you primarily focused on putting formal bounds on existing architectures?
--:-- Vishal Misra: A bit of both. I mean, the former goal is the more ambitious one that everybody is chasing. And yeah, I think about that constantly. Are there any new even like sort of hints that a new architect, or like have we started to make any progress on new architectures? Or is it? Uh You know Yarn has been pushing at this JPEG architecture energy architectures They seem promising.
--:-- Vishal Misra: The way I have been sort of thinking about it is, you know, there's this set of benchmarks or the ARC prize. Yeah. that Mike Canoop and Francois Chalet have. And if you understand why the LLMs are failing on this test, maybe you can sort of reverse engineer a new architecture that'll help you succeed in that, right?
--:-- Vishal Misra: And I agree with a lot of what several people say that, you know, language is great, but language is not the answer. You know, when I'm looking at catching a ball that is coming to me, I'm mentally doing that simulation in my head. I'm not translating it to language to figure out where it'll land. I do that simulation in my head. So, you know, one of the new architectures, architectural things is how do we do, how do we get these models to do approximate simulations? To test out that idea and whether to proceed or not.
--:-- Vishal Misra: So, yeah, you know, another thing that I've always wondered about is, did we develop as humans, did we develop language because we were intelligent? Or because we developed language, we accelerated our intelligence? So, I don't know which side of the camp you follow on that question. I mean, what's interesting is like you have these anecdotal examples of humans developing languages de novo that have been recorded, right? Like it's either the Guatemalan or Nicaraguan sign language, right?
--:-- Vishal Misra: Where there is these students that develop their own language without being taught. And so that would suggest that language just follows intelligence. The problem is, is they're all anecdotal, right? Like who knows if somebody didn't teach them sign language? Like nobody really knows. There is no controls. So this is all these observational studies, and there's so few of them, you have to wonder if it's just kind of sloppy observation.
--:-- Vishal Misra: And so I think that the question is still outstanding. Yeah. So, I mean, language definitely accelerated our intelligence. There's no
