Memory and Continual Learning: Engram's Dan Biderman and Jessy Lin

What about pre-training or even post-training makes it possible for the models to generalize in these magical emergent ways and controlling that process so that a company has a set of private data. How do we make the models learn that just as well as the models know like the capital of France or you know like how to write Python? So I think it's a really fun problem to think about. [Music] Welcome to training data. We are delighted to have Don Beetherman and Jesse Lin co-founders of NGram today. NGram is a Neolab focused on memory and continual learning and two of the hottest topics in all of AI research today and Sean and I are delighted to dig in on those topics with you today. Awesome. I'll be to be here. Great. So maybe to kick off the NGram website says we don't see the world through the lens of pre-training or post-training. Our models are always training. What does that mean? So I think like models today obviously know a lot of things. They're incredibly smart. But we kind of think the bottleneck for making these models more useful these days is not really raw intelligence but understanding like new and evolving context. So whether it's like you know a new task that you're doing or a particular context for you know like a job or something like this. How do you bake that into the model weights? The same way that you know pre-training and post-training bake-sexy into the model weights very deeply. And this is kind of why we think of ourselves as working on these fundamental problems of memory and continual learning which are really two sides of the same coin. How do you make the models learn new things and bake them deeply into the weights of the model? And is your premise then that memory as a separate database or separate you know thing that you've shoved into the context window is not true memory and it's not true continual learning? I think all of these tools will kind of come together. So these days like the way that people are solving these problems is with context engineering. So you take like a huge prompt. Maybe you like keep talking to the model over many many turns and hours and you know reorganize the context to better understand like what you're trying to do. And we think like these kinds of things like tool use context engineering will play a part. But I think an under leveraged full these days is using the same kind of training pipeline or framework or kind of workflow that the frontier labs are using to make these models really good at frontier math or code. But applying that to every kind of domain, every kind of context that you have like let's say in a company. Yeah and to me it's like as an individual taking notes and having sticky notes is a very valuable thing. We should never discard this. But whenever we get back to business the next day, we always have some sort of trace of memory in our brain. Some new intuition about how things should be and where should we look. So these two things should come together. And current solutions are a more kind of externalized memory. And this has two two issues. One is that the amount of tokens we will all collectively individually generate is going to be in the tens of millions of tokens per day soon. So just keeping it and searching through it is going to be rereading it's going to be pretty expensive, but it's going to also be pretty hard, pretty confusing for the models. Unless we have major, major breakthroughs in how we do it. Tens of billions of tokens for Sean. That's good. Depends on the day. Could you maybe tell us a little bit about the Ngram architecture, the Ngram product and how it works? Yeah, I mean at a high level I think what we're trying to do is take any context like there's all these different work spaces let's say. So we're working with partners like notion, Microsoft and Harvey that have these places where people are doing a lot of work over a long period of time. There's all this context. Both in terms of like, you know, documents that you've already written as a team as well as like now people are interacting with these agents more and more in these products. We're having conversations, giving them feedback. And figuring out how to have a model that deeply understands that context. So not just reading the files at test time, but really understanding it the way that an employee that's worked out your company for years has. So you kind of understand at a high level, oh these are the initiatives across the company. This is the way that we do things. You've studied like how to run the hiring pipeline or how to do this kind of thing within the company and can operate just as well as like anybody else can in the company. And so what we're doing is training per team models within these work spaces that deeply understand those contexts and can improve with time on the things that people care about. So the way that we do this at like a technical level maybe is training these into weights. So we do a lot of like adapter fine tuning. So adapters in many types like I think people have looked into this for decades at this point, like whether it's Laura's or prefixes or you know sparse architectures. I think like all of these tools are at our disposal. And then figuring out what the right data is. So how do you turn any kind of raw like document or interaction into useful training signal for the model. So again, we have like a variety of tools now like supervised fine tuning, you know, RL you know on policy distillation like all of these things that you know the field has kind of developed and trying to fit these pieces together into a model that learns continuously on the things that people care about. Yeah. And it's not a bet that tools are not there. Like our model is always work under the assumption that some knowledge is externalized. Some tools are always there. But what you need to do is you need to figure out and that's the hard task is what needs to be internalized and what can be externalized. And for even for stuff that's externalized many individuals and companies have their own bespoke tools and ways of doing things. Not everyone has the same, you know, bash CLI tools that you know the frontier models are training on and how to get them all to better understand your bespoke setup. I think is its own interesting thing. And so is the premise then that my notion agent will be a custom agent that is Laura fine tuned or you know it's some way with an adapter tune so that it's constantly learning on new content that's added into my notion workspace is that the premise. Yeah. And they're working with many models and they're the early users of all the frontier models and they're probably going to keep doing that. Does this approach work on the frontier models or are the closed frontier models? We need white you know we need white box access to the weights right so you know we can partner with companies that have you know closed source weights and do this with them but it's easiest for us to do it with open source models. But any model that's a transformable model we can do our thing to it. And what's the tradeoff then when people are comparing the before and after using you is it that they're no longer sending so much context. And so the tradeoff is like you burn more compute upfront to learn your companies way of doing things into the weights and then you're sending less context to the model on every inference fast is that the rough tradeoff? That's one that's one thing. The fact that you don't have to research things and the fact and we read things and the fact that you don't have to write like monstrous system prompts they're already that can give you you know two orders of magnitude reduction in token inference consumption it's not like you know 50% or it can be 100x fewer tokens because many things especially things that relate to people and teams and organization and priorities these are things that you can't really find in one document unless like you really have it really regimented and document everything. These kinds of things the model can kind of implicitly learn by training on some of the data and answer you know within 100 tokens what what the best frontier models we can see 100,000 tokens? doing so these kinds of examples are interesting and also the quality you know they're tasks that are you know not supernatural for the current generation of the models and we we kind of think there's going to be consistently this gap of like three to six months ahead where there's certain things that are bespoke that people are just exploring the models are not fully great for them the models will at some point be great for them but if you can autonomous the learn in in a very lightweight way it will give value in that time and terms of capabilities. Why train on the workspace level versus the individual level for example? Either is fine for us it's just easier to start with you know it teams of people have you know are more you know disciplined in how they collect context and in the amount of context they have over years and it's easy for us to start there but every person's computer and every person's phone one day is a useful you know target for our technologies and in fact will be very interesting to go there we just think you know the big deposits of information are now in teams of people collaborating in knowledge work. Is it a feature or a bug that there is so much fact memorization basically built into the large language models and there's a school of thoughts that you know the the models just wrote memorizing the fact that the capital of France is Paris is actually a bad thing and what we would prefer for the models to do is you know abstractly learn the concepts of countries and capital cities but not to memorize all these facts in the weights and so I'm curious what you think about disentangling memorization versus learning how it's done in the models today and then how you're thinking of approaching it. Yeah I think it's a really interesting question like to some extent you kind of need to remember stuff in order to like compose them into more complex concepts. I think the thing that's kind of missing is figuring out what's important to remember and I think even now when you think about like learning new knowledge if you look at a lot of these academic benchmarks it's like how can we learn very specific facts like you know the length of a bridge in this like African country and that's not something that you really want the models to devote capacity for and it's not something that we devote capacity to so I think if you look at human memory I mean you can say a lot more about this but like it's lossy because part of the feature of intelligence is compressing what's important and separating that from what's not important. And so I think like you can't really separate fact learning from like non-fact learning or skill learning as some people would like to think. Like if you take a model and like some people have done this with models where you like strip out that you know like all the facts and just have it like the pure core or something like this. It's very unnatural as a model. It doesn't know basic things and you kind of need need that. But I think why do you need that? Like why can't you look up facts and then just have. I think if you look at like how the models think if you need to recall basic facts in order to like take the next step in your thinking you can't get very far. Maybe that's like a high level intuition, but it's part of like the reason why we think training is really important in order to like think more and more complex and deep thoughts about things. You kind of need to internalize something so that you can compose them into more abstract concepts. And there have been efforts before that were hard to scale to try and you know this entangled the two and pre train the models in a way that's you know allows it to retrieve and search for things and not internalize them. It's just the recipe we know to help climb on collectively right now is this you know fact pre training step. And I think that the magic of or the mystery of this approach is that you know traditionally in CS we would have you know databases as its own curriculum and we would have algorithms and the databases is like facts about the world and cabitals of whatever store them query them. And I think the magic of deep learning is that these two things are now mush together and we need all these smart people and for a big interpretability to try and break them apart. And I think a lot of what we're seeing now in the adoption of AI into the economy is that these things are gradually separating again where companies have their own context and they really handle them with care and engineer them with care. And there's a generic model that's completely stranger to these context and the model is operating on them. For us it's clear that there needs to be a certain convergence at least with some cadence where the fact and the stories and the details are getting mixed into the model. It has disadvantages as well because if you have to you know capitals of of countries are you know they can change but it's not very frequent but there's many other facts are changing all the time and just imprinting them into weights is a challenging thing to do. I see so you're saying it's a false dichotomy that's try to separate algorithms from databases here. What really matters is like how the distinguished was important to remember versus what's not important. Yeah and it's an open question. And are you guys taking any inspiration from that in terms of ranking very very loosely I think just the idea that that's kind of a phase that's missing maybe where you take a context and you deeply internalize it right now it's like everything happens at test time you look at the you know context that the user gives you. And you do some like thinking on the fly but again like you can't get very far or you can get so far maybe and like you make mistakes along the way like how do you digest that back to the model so that next time you do it you do it the right way and make even more progress. Yeah and then what are dreams dreams are pretty crazy things to say we want to build an AI that's like our dreams sounds a little bit like a nothing to do. There's not a lot of coherence there but what's interesting there is like what happens in our dreams we we see things we talk to ourselves and we experiment with the affordances of what can we do and can't we do in the world and social situations and and you know any any it's heavily biased towards social stuff right so for us to things we're building is you know. We give the models the time to then go back retreat from the actual interaction and experiment with its affordances what can it do in an environment what can and what doesn't know how fast can it kind of you know handle these kind of tale extreme things that same ones that we dream about at night you guys come from academic backgrounds like what's economical example that motivates this problem or you know like or that's a win so far. Yeah I have one example you just you can give another one hypothetical one for example imagine one of the AI lab say open AI has to win some math Olympiad in a week time from now. Would they construct a catalog of all the math textbooks and really have people annotate which chapters to get in which graphs to to see or will they actually collect this synthesize some training data. Launch a training job see where lands in five six days started evaluating it and stuff like that so it's it's obvious for anyone who's trained models that there's superior way to integrate across ideas and capabilities and involves this kind of magic of training. And we are clear that this has to happen in those high stake domains of math and coding and cyber and stuff we just think much of this magic can actually end up in the hands of many more people and interesting ways like why isn't it. Just to find the foundation model labs that own the end product here you like how do you go between giants yeah so I think like the world view that we have is a bit different from the frontier lab world view where it's like we want one model that's bigger and bigger that's more and more intelligent across a variety of domains. Instead how we see it like we kind of imagine this world where everybody has their own model a lot of the things that people want to learn are either private like things that will never see the light of day in a post training data set or even conflicting like oh the way that I want to do the task is different from how another company or another individual wants to. And I think a lot of these things were already seeing are hard to train into the models with the same tools that we have used for like decades and machine learning which is like you have really clean supervision you have like ground truth reward signals and you like create a nice environment and you like train the model to like use the tools to better accomplish this like coding task and instead a lot of the things that actually happen on in the world are very ambiguous or like. It's hard to say like what makes something good and so I think a lot of these things are very specific to individuals and I think very kind of misaligned or not very lined with how the frontier labs think about the whole training pipeline and what kind of models will exist in the longer term yeah and to add to it I think you know what is the p.0 for frontier labs and some of you here are pretty close with them it's getting to a GI getting this one generic model that's extremely capable. In coding and math and then using it to automate the economy or to solve really hard you know long term problems in cryptography and defense or whatever and it's pretty clear what needs to happen to push this you know more pre training bigger models more data more RL more inference time compute that kind of stuff that's p.0 that's where the majority of expenditure and talent goes and definitely all of them are thinking about memory and all of them are thinking about continue learning it's just more of a product kind of effort right now we think it deserves it deserves its own its own attention and we think breakthroughs need to happen there and and and the sqa event about a month ago said pretty clear that we need new breakthroughs around these topics and obviously they're thinking about them we're just focusing exclusively on this and we think certain things are on incentives of where the data is and who owns the model are pretty interesting. So if you could learn from many humans or organizations at scale without this is certainly sending someone work with them shoulder shoulder that would be a pretty big unlock and maybe another point on that is like I think a lot of things need to look different in the world so one is there needs to be new research breakthroughs to his new infrastructure for training like you know small models for everybody rather than like one big model one big run. And then the third I think is a different way of kind of combining research and product so right now I think like there's like researchers in these frontier labs they kind of train the model they throw it over the fence to the product team who then like prompts or context engineers like new product surfaces on top of the core models. But in this world where the models are always training I think the inputs that users provide are very intricately tied to what the models learn from like what the training signal is and so there needs to be a lot more of a kind of integrated loop between like research and product and so like while we're focused on tackling a lot of the core research challenges and that's our background. I think we're also very focused on like how to deploy this as quickly as possible to like learn from actual feedback in the real world. I think like it's obviously like one of the grand challenges in AI I think everybody's talking about it these days because like the models are so smart what what else is left you know it's I think learning like at the edges like learning the remainders of what makes these models useful. It's not just about raw intelligence anymore it's about like learning new things and I think it also feels very fundamental because it kind of goes back to really understanding what makes the model so good. So right now the models kind of incidentally know a lot of things from pre training and we don't really understand why it's like the internet was just you know this gift granted to us where there's like a diverse set of data that contains like all these different examples of coding and like writing and all these other things and it just happened that way and now to figure out how to crack this problem of continual learning it's about figuring out what about pre training or even post training. So it's possible for the models to generalize in these magical emergent ways and controlling that process so that you know a company has a set of private data how do we make the models learn that just as well as the models knows. like the capital of France or, you know, like how to write Python. And then you came from the neuroscience world, is that right? Yes, yes. So I was initially interested in questions around, you know, consciousness and the human condition and things like that. Are the models not just? Don't have any, any advanced thoughts on this more than you would, you would read that. I don't think so, but it's important that smart people are thinking about it. I would say like I was interested in how humans think, how humans perceive. And as almost versky, the Israeli psychologist used to say like, he's not interested in artificial intelligence. He's interested in natural stupidity. So I would say like I started kind of similarly trying to see how people and animals experienced the world. Gradually, you know, my inclinations took me to the stats and AI domains. And there I figured that so many of the same problems of memory and continual learning are really, really urgent. And the kind of solutions we have in the current systems are pretty far from what we have in biology. And I'm not one of these people would say that the machine should be like, you know, like the animal or the human brain. I don't think so. There's many things computers can do better than us. But human memory has these like very different things in it. It's, you know, if you want to store a whole code base or you, you can use a computer. You don't even need AI on the computer to store everything losslessly and just get it. But the human brain evolved to work in these constraints of, you know, information capacity and to have these fuzzy representations that can then, you know, be abstracted and form connections and inform the next day. Current systems don't really have that beyond the generic pre-training step. And I was really interested in, you know, what are ways to build that in? What are ways to learn from that? This is more of a philosophical question. You know, you mentioned in the brain, I was a bunch of different, real estate, different co-processing units, whatever modern computer architecture. There's CPUs, GPUs, you know, memory. There's different co-processors with like the bitter lesson. Do you think that what's happening is that like LLMs are, you know, converged to say like one co-processor that's just totally dominant. It's like everything all compute is going to happen in, you know, the GPU equivalent of, like, a language model. Or do you think that these models are kind of building a bunch of co-processors, like, you know, emergently inside the model? Like, like, you know, and take with memory, like, do you think that the models themselves will just build, you know, whatever part of the brain equivalent would be that's good at memory? Or do you think there needs to be like another standalone architecture with it? Yeah, like is memory an emergent property? Exactly. And almost everything. Like is everything that we need in intelligence will just be emergent with better training data and more scaled compute? Yeah, I would say just on a more like a superficial perspective on the current deployment of AI, it's way more than than just GPUs and we're seeing all these, you know, of course, sandboxes, exploding and models operating on other computers, trying things. I'm more mean on the model architecture level rather than on the other experiments. Either there have been many previous experiments, different architectures that we contributed to, like the state space family and others to try and handle very, very long context more efficiently. The thing with all these methods, it ends up being a trade off, usually a trade off between memory and accuracy and memory, not in the behavioral cognitive sense, memory and the computer sense, right? Instead of having, you know, the memory footprint of the transformer attention, which is quadratic in the sequence length. These models claiming, you know, they have sub quadratic. Yeah, someone claimed some do have it, right? And some of the best Chinese model have layers that are, you know, inspired by those state space architectures and are, you know, not quadratic and cost thing is, is that in our hands, we find that you always compromise accuracy for this memory. There's no free lunch. And what we're saying is like, look, if you're really bitterless and pilled, what do you want to do is you want to think, how can I burn more compute and how can I burn it on, you know, new context that I have not seen before. So we're as bitterless and pilled as anyone else. And we are not betting that the overall direction of AGI is is going to, you know, end anywhere soon. We just think there's more compute to scale. And if I truly want to understand Sean and Sean's work and Sean's context, just like rereading files is not going to make it, especially for a special person like you. We got a trade off. Just a raw good story. You got to change. 100 trillion for our business. Yep. Cosine, cosine. Yeah. What are you finding that people care most about their models learning? Like is it memorizing facts about the organization? Is it remembering like, ah, no, we do CI this way? Is it like what are people actually hoping to? And then maybe this feeds into how you do the, do the ranking of memory slots and all that. Yeah. Well, I think if you look at what people are spending their time in the app layer doing these days, it's a lot of just trying to make the model work well for your use case. Like, oh, I want the model to like, you know, let's say like design my website with my brand style. Like that's like a, you know, very common example these days. But there's many kinds of different tasks that people do with agents, like learning how to run a workflow. Or, you know, kind of your particular way of like writing, let's say, um, so there's many, many kinds of things. And honestly, like I think when we think about these methods, kind of going back to this distinction between like facts and skills, there really is none. I think the methods are kind of agnostic to that. Yeah. To me, it's like the natural thing, almost all the app layers are basically, you know, a frontier model wrapped in a loop with search tools and stuff. And what they're all interested in doing with us is finding ways to kind of interface with their data in a way that's, you know, faster, more efficient and also has more contextual. So almost all of them, it's like, we want to have our, you know, our firm knowledge, you know, being coded and something that's more efficient that I don't have to research. We want to have the model know in a targeted way, who's the person I should triage a thing to. And we're just showing them that with pretty lightweight training, these things can can be instinctual to the models they don't have to have these very involved long repalue to solve them. So it's in a sense it's like, you know, it's, it's a rag killer kind of kind of thing. Again, we can always do a rag and we can always retrieve, but that's the thing that people are interested in interfacing with very large data planes and automating very repetitive things this way. Yeah. And I want to double click on this rag killer thing and I'm sorry to beat it, that horse. I just don't fully rock it yet. Yeah. Is the premise that there's some trade off between doing rag versus up, updating your model weights is the idea that you should be doing both like what types of things should be done in the weights versus what types of things should be externalized to rag. I think it's a, it's an unsolved problem. I don't think anyone has answer to it. We're all working on it. It's also the fundamental question of like biological memory, what should be internalized versus what not. I do think that things that are like, you know, do you need to internalize the room number and a hotel that you were in like a year ago, probably no, not in your neural tissue. Probably that's good to write down, but do you need to internalize you maybe the password to your home right now probably it's useful for the next few years to have that imprinted somewhere. So yeah, how does this translate into like knowledge, work and products. This is still something we figure out and we try to take the approach that we try to use as few heuristics as possible. It's easier on filters on the data and say like I'm going to keep this this card that train on this train on that. But as humans, you know, we watch TikTok and we get exposed to a lot of garbage and still the brain is able to learn and not completely go off the rails and we think models should be the same as well. Yeah, maybe concretely in the short term, I think a lot of what people are worried about these days is the huge inference costs of running these agents like for days on end. Hi inference costs a good thing. I mean, consuming tokens for what? So in your words of fireworks, really loves. We love inference. Yeah, so I think it's like in the short term, I think that's the immediate pain point like why are you reading the same files over and over again, you know, even in the same query, but like definitely, you know, across people in the same company, they're running the same queries and the same documents over and over again. And that should be something the model just knows like in the same way you ask an employee, they don't, you know, type into the search box like what was I working on yesterday, they just know. But doesn't cash in kind of solve that. I think to some extent, yeah, but I think going back to this like question of what should be internalized versus what's like something you retrieve at test time. I think again, like a lot of it is about building on your knowledge. So if you are always doing raw, you can't make associations like, oh, you know, I see somebody, you know, on the team is doing this kind of research and I kind of. Like recall at an abstract level, oh, there's this like related thing that you might want to know about you didn't even ask about it, right, but I think like these kinds of associations can only happen in weights because they're not really about, you know, you asked me to search for this. I'm going to search for this. And also, I think the main limitation with retrieval systems in general and in AI specifically is like the problem is not so much what to store and where to put it. It's the problem is like how how to address it like how to query the thing. Do you know what to look for even. Yeah, and this is involved some sort of intuition that sometimes the models don't have interestingly enough, they don't know where to look. And especially if you're, you know, limited to the current way of doing things, which is keyword search does just easier to scale in our role and lead. involved in terms of like, info for embeddings and stuff. So yeah, knowing what to search is something that's intuitive and can happen in the way. And also about caching and inference, like much of this company started with us taking it like a deep dive into like KVCache's and caching. And this is a fascinating thing, right? KVCache is a monstrosity of the current way of doing things that, you know, think about it. A KVCache for a single like Wikipedia article for some, you know, Taylor Swift or something like this, it will be like 80 gigabytes of HBM memory on the GPU and an entire Lama, it's for say a 70B Lama model. And the entire weights of the model would be about 100 gigabytes. And you know, with some distortion, they remember the entire internet. And how come this thing is so, one thing is so bit efficient. And we have this proof of existence that gradient descent can pack a lot of information in very few numbers. Whereas this KVCache thing, you take a few tens of kilobytes of article and it becomes those 80 gigabytes of brain state. So you sure you can cache this, you can load this, you'll have issues with disk to HBM. Stuff, people are working on it. It's pretty interesting. But what if we can take those 80 gigabytes, spend some compute offline, maybe also in fireworks, but then compress it and make it really, really small. So that the thing we load in cache is like a thousand X smaller that would have tremendous implications for how we load things, how fast we can do things and what the fidelity of their representation is. Super interesting. Yeah. What are some of the things that could happen in the next year or two that would be like the chat GBT moment of memory? Or do you think that that's not how things will play out? It's a good question. I don't know. I think like the first proof of concept of the thing that people keep talking about with continual learning, which is you have an intern that you can teach things over time and it actually gets better. I think everybody's waiting to see that. And no matter how sophisticated the context engineering approaches are these days, they're not getting there. So I think you need all of these tools that you're disposal to make that happen. But I think it will be something like that where it's like the model's actually getting smarter. Like whoa, it's different from yesterday. Yeah. And it's important to say that the chat GPT model was not anticipated. We just read about all the different products that you, the product directions that certain people had before chat GPT was different. I feel like to me the example is like, look, if you, you know, resigned from your job today and your sole mission was to make a model that's better for you. And you would use OpenAI and FOP pick and all these frontier models and you just 24/7 engineer the context right skills. Your way to move the needle is very limited as an individual. You will just be better off waiting for the next version of the model and you'll take it from there. And we would like to see a future where actually the more time you spend on the thing actually translates to the quality of performance and at least in the things and domains you care about. And this is pretty hard to achieve and the only reason we think it could be achieved is if you start scaling compute and training on these data without destroying them all importantly, which is pretty hard. Just a couple like this is just for fun like rapid-fired questions going off. Just memory. Once last time you reached surprised about something in AI in any area when reading about fundraising. I would say all of us felt you know a little bit of a change around the capabilities of the coding agents. But we've been you know, dabbling with these things and trying to make them work in more effortful ways before so it didn't come as a complete surprise. But yeah, I think to me, the main events were get up copilot that for me was just the main event and chat GPT and then seeing the agentic stuff. We all anticipated I think and different people had different expectations on how far it can go and how long horizon it can go. But I feel yeah, it's we're yet to see something fundamentally different and people are working on completing new ways of doing things now. But yeah, to me it's it's models actually changing in a way that's not harmful and learning new things on the fly that are you know, personally and economically viable. That's interesting. Right now there's this idea of like we're each kind of a token wallet that we're going to bring around to companies or different to different apps, different workspaces. Do you think that we're going to end up with like a memory bank, a memory wallet that we're going to move around to across the digital world as we go? I think it's an interesting question. I don't know if we've fully figured out what the right kind of like product form factor is in the sense. In a way even with like chat GPT memory, let's say, I kind of don't want it to remember across my like personal and work context. Oh yeah, like it's like, oh, you know, you might like these sheets because you trained a model on a GPU last week. It's like, that's totally irrelevant. And to some extent it's like because the memory is flawed, but also I think you do want memory in your I guess tools and the products that you use to be separated to have control over that. So I personally think like there needs to be some separation there, but I guess to be determined what that might look like. Yeah. And like I think a holy grail is like you go to work and you're just burned through all these tokens and you create all this value and somehow, you know, all the IP and stuff stays with the company, but somehow the skills you learned, the things you invented, your ways of doing things, some of them you can take with you as well. To your next job in a way that's, you know, sanitized and not, you know, harmful to any other company's IP. So I do think like carrying a set of skills will be interesting. We do it in our biology right now and we just, you know, sign NDAs and have like ethical rules around it. But I think doing it in a digital world would be pretty interesting and pretty rewarding because it will force each of us to push the frontier and implement AI more deeply in our companies and our individual life and then be rewarded for it. I started a PhD in Satsurman 2007 at Stanford and AI, like AI was boring as hell. At the time, it was all statistical learning and there's basically two areas like computer vision and LLP. So like vision and language were kind of the two areas and I think that's still true. In 2012, Alex and happened like vision was dominating for six years or whatever. Are you guys surprised that language seems to be like the language approach seems to be like dominating over vision in progress? Question two, do you think vision has any chance of coming back? How do you think about this? Yeah, I think it is pretty surprising to me. I mean, some people maybe saw it coming, but I think I've always kind of been interested in language as like, I don't know, I guess like a medium for communication and like so many kind of complex abstract things can be done in language. I do think like, I imagine like in the longer term, language and vision will kind of like combine in this more unified system where we kind of like take inputs from all of these different modalities and like understand them in this abstract way. But yeah. Yeah, to me, like I've never been interested in language. It seemed to me such such an advanced capability that is very, the entire animal kingdom has very different forms of speech and language than what we, you know, how we communicate with ourselves and writing. And I was always as many other leaders in AI had this thought that you know, the natural thing is you have to experience the world, act in it, envision an action that will be the key. But then I've, you know, like anyone else seen the chat GPT moment and went to do some work at mosaic and stuff like that to learn how the sausage is made on the on the NLP side. And the thing that striking is that like the the language should be pretty hard like each word has this one hot embedding vector that's as dissimilar to any other word than it is, you know, to, you know, it's it's a completely high dimensional space. And it's really artificial in a sense and we learn it with models that are order of magnitude bigger than the best vision models. And still, you know, things work pretty well. I do think there's a lot of juice to be squeezed in an image and video. And I think you guys doing good good investments in this space. But it's I think the two would keep being interesting in different ways. I mean, now it's so you might that was my lead up. Now I'm going to tell you the crackpot theory. And this this podcast is not for me to pontificate for you guys. But this is something I've been thinking a lot about. And I just you're the right people to share this with. I was pretty shocked that language kind of surpassed vision. And I underestimated what was happening with LLM's in like 2018, 2019, 2020 because I just had this bias towards vision. And when I look back on it now, like I think what's basically happening is that in biology, like vision has a massive fundamental advantage over language in biology. And maybe I'm wrong. But basically like the bit rate that your brain can process optical data through the eye is in this my I'm not a biologist. This is just kind of my dumb assessment. It seems many or as magnitude greater. And there's a lot of like optical processing that happens like even before you reach, you know, like electrons. And so it's just like the total bit rate that is of training data that's kind of being processed and then making it to your brain. It seems many or some I greater than the audio data where, you know, it's sound waves, where sound waves are fundamentally, much slower bit rate than light. And then there's almost like an upscaling from the acoustics to electronics, which make it into your brain, whereas like a downscaling from photons to electrons with vision, whereas in computers today, everything is electronic. So it's kind of like you nerfed vision and you like promoted language where the it's like all processing is on the same playing field. It's all electronic. And I just, I think this might, this is like my crazy ass dumb non-technical crackpot theory, but I think this might be part of why just like from an information theory perspective that like maybe language and vision are on a similar playing field, by the time you get to like LLMs. And then LLMs are we're just a really, really smart architecture that's better suited for language than for vision. How dumb this is, I'll just show you to you done the neuroscientists. Just also has some background in cognitive computational science, right? So I would say my, my point of year is like look much of what we're doing in knowledge work, we haven't evolved to do, right? We're sitting on this computer, is waiting these things, writing these memo, is whatever. We are not evolved to do this. It's new to us. Our brains are not wired for this. Still nevertheless, it's useful to have LLMs to do this for us. And you know, as humans, we're heavily visioned by us. You know, other rodents are more olfactory bias than I've worked on these things myself before. So what's the real estate in the brain that's allocated to vision and you know, exhibiting alobs versus like language areas, temporal lobe, probably more vision. I'll have to track which track with child GPT, but I think that's the situation. You don't know from memory? No, man, I'm externalizing. I'm a big track believer in my personal lifestyle. But I think in the limit we're all it's all ragged. I internalize just, you know, important things like my emotions to you. I was just kidding. Sorry. Yeah. In vision is dominating. When people are training vision language models, they end up the language ends up dominating the vision content there. But yeah, it's hard to say that because a certain brain is more, you know, biased towards certain modality, doesn't mean necessarily that we're going to more efficiently do it. I do think that efforts on like brain computer interfaces should take this into account. How do you then relay it back to the brain? That's where I think it's way important to think like what real estate do we have there right now? But for knowledge work, it's equally fine if it's text, I think. Last question. If everything is right, what does the world look like in five, 10 years and then what is in grams rolling it? I think I'm imagining like a world where everyone has their own model that is really different from the other person's model and from the frontier model and all of these kind of serve different purposes and to have a model that really, you know, I think people often talk about like knowing, knowing you, but also like kind of like helping you in the ways that makes sense to you personally, whether it's like an individual or a team, I think there's an element of like having different kinds of intelligence everywhere. Yeah. And to me actually, it's a variant of the story where like, you know, in neuroscience, we know that memory and navigation are pretty closely related same circuits in the brain that, you know, present landmarks in space are in charge of some, you know, elements of episodic memory and things like this. And for me, I think the company can be, you know, the actual LLM interface to the data plane for everyone. So sharing some similarities to great companies like, you know, Databricks and Oracle where, you know, we form these memories that happen to be neural memories with models that happen to be personalized and happens to be there's hundreds of millions of them. But they're basically a neural interface to the data plane in a way that's that's very different from what we know. And it's more efficient. It's more associative. It's not representing the file system as it is. It's representing a brain state of that file system. So that's for me a vision. Beautiful vision to end on. Thank you guys so much for coming by the show with your building. Awesome. Love it. Thank you. [Music]