YouSaid · the spoken record

Oriol Vinyals

lines on the record

127

first

2022-07-26

most recent

2022-07-26

sittings or episodes

1

sources

podcast

Every line below is reproduced as it was said and linked to the record it came from. Nothing here is summarised or generated. Directory · Search · Corrections

1. “Yeah, I think it certainly feels like action is a necessary condition to be more alive, but probably not sufficient either.”

   2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

2. “The fact Yes, so when we call it, I mean, it's a good question, right? When do we call a model? I mean, everything is a model, but what is an agent, in my view, is indeed the capacity to take actions in an environment that you then send to it and then the environment might return with a new observation, and then you generate the next action and so on.”

   2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

3. “More than a language model because even though you can chat with Gato, like you can chat with Chinchilla or Flamingo, it also is an agent, right? So that's why we call it Gato, like the word, the letter A. And also it's general. It's not an agent that's been trained to be good at only StarGraph or only Atari or only Go. It's been trained on a vast variety of data sets”

   2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

4. “And then write it down if you're chatting with the system and so on. So Gato basically can be thought as inputs, images, text, video, actions. It also actually inputs some sort of proprioception sensors from robotics because robotics is one of the tasks that it's been trained to do. And then at the output, similarly it outputs words, actions. It does not output images that's just by design we decided not to go that way for now. That's also in part why it's the beginning because there's more to do clearly. But that's kind of what Gaeto is, is this brain that essentially you give it any sequence of these observations and modalities and it outputs the next step. And then you fit the next step into and predict the next one and so on. Now, it is.”

   2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

5. “Modalities, observations that could be words, could be vision, or could be actions, and then its own objective that you train it to do when you train it is to predict what the next anything is and anything means, what's the next action. If this sequence that I'm showing you to train is a sequence of actions and observations, then you're predicting what's the next action and the next observation, right? So you think of this really as a sequence of bytes, right? So take any sequence of words, a sequence of interleaf words and images, a sequence of maybe observations that are images and moves in a tarried up, down, left, right. And these you just think of them as bytes and you're modeling what's the next byte going to be like. And you might interpret that as an action as an action and then play it in a game or you could interpret it as a word.”

   2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

6. “Yeah, so maybe the basics of Gatto are not that dissimilar from many, many work that come. So here is where the sort of the recipe hasn't changed too much. There is a transformer model that's the kind of recurrent neural network that essentially takes a sequence of.”

   2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

7. “Are very powerful. So Gatto was named after, I believe, I can only from memory, right, these things always happen with an amazing team of researchers behind. So before the release, we had a discussion about which animal would we pick. And I think because of the word general agent, right? And this is a property quite unique to Gato. We kind of were playing with the GA words and then Gato. Yes. And Gato is obviously a Spanish version of Kat. I had nothing to do with it, although I'm from Spain.”

   2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

8. “The meow. No, no. Definitely it is the beginning. I mean, I probably was just explaining a bit. The field is going, but let me tell you about Gato. So first, the name Gato comes from maybe a sequence of releases that named animal names to name some of their models that are based on this idea of large sequence models. Initially, their only language, but we expanding to other modalities. So we had these were language only. And then more recently, we released flamingo, which adds vision to the equation. And then Gato, which adds vision and then also actions in the mix, right? As we discussed actually, actions, especially discrete actions like up, down, left, right? I just told you the actions, but they're words. So you can kind of see how actions naturally map to sequence modeling of words, which this model...”

   2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

9. “Based task or a classification, a vision style task. But it still feels like more breakthroughs should be had, but it's a great beginning, right? We have a good baseline. We have an idea that this maybe is the way we want to benchmark progress towards AGI. And I think in my view, that's critical to always have a way to benchmark the community sort of converging to this overall, which is good to see. This is actually what excites me in terms of also next steps for deep learning is how to make these models more powerful, how do you train them, how to grow them if they must grow, should they change their weights as you teach it task or not. There's some interesting questions, many to be answered.”

   2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

10. “Learn from one another, I tell you hey, you should do this new task. I'll tell you a bit more. Maybe you ask me some questions. And now you know the task, right? You didn't need to retrain it from scratch. And we've seen these magical moments almost in this way to do few shot prompting through language on language only domain. And then in the last two years, we've seen this expanded to beyond language, adding vision, adding actions and games, lots of progress to be had. But this is maybe, if you ask me about how are we going to crack this problem. This is perhaps one way in which you have a single model. The problem of this model is it's hard to grow in weights or capacity, but the model is certainly so powerful that you can teach it some tasks, right? In this way that I teach you, I could teach you a new task now if we were, or let's text.”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

11. “You generally throw away, which feels very sad. Although maybe in the last, especially in the last two, three years and when we last spoke, I mentioned this area of meta-learning, which is the idea of learning to learn. That idea, and some progress has been had starting, I would say mostly from GPT-3 on the language domain only, in which you could conceive a model that is trained once. And then this model is not narrow in that it only knows how to translate a pair of languages or only knows how to assign sentiment to a sentence. These actually, you could teach it by a prompting it's called. And this prompting is essentially just showing it a few more examples, almost like you do show examples, input output examples, algorithmically speaking to the process of creating this model. But now you're doing it through language, which is a very natural way for us to.”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

12. “You need some specificity to the actual problem you're solving. Protein folding being such an important problem has some basic recipe that is learned from before, right? Like transformer models, graph neural networks, ideas coming from NLP, something called BERT that is a kind of loss that you can place to help the model knowledge distillation is another technique, right? So this is the formula. We still had to find some particular things that were specific to alpha fold, right? That's very important because protein folding is such a high value problem that as humans, we should solve it no matter if we need to be a bit specific. And it's possible that some of these learnings will apply then to the next iteration of this recipe that deep learners are about. But it is true that so far the recipe is what's common, but the weights”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

13. “Recipe, right, that you can use. And this recipe with very little change. And I think that's the core of deep learning research, right? That what is the recipe that is universal, that for any new given task, I'll be able to use without thinking, without having to work very hard on the problem at stake. We have not found this recipe, but I think the field is excited to find less tweaks or tricks that people find when they work on important problems specific to those and more of a general algorithm, right? So at an algorithmic level, I would say we have something general already, which is this formula of training a very powerful model, a neural network on a lot of data.”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

14. “Maybe stepping back. If we look at the field of machine learning, but especially deep learning at the core of deep learning, there's this beautiful idea that is a single algorithm can solve any task. So it's been proven over and over with more increasing set of benchmarks and things that were thought impossible that are being cracked by this basic principle that is you take a neural network of uninitialized ways, so like a blank computational brain, then you give it in the case of supervised learning a lot, ideally of examples of, hey, here is what the input looks like and the desired output should look like this. I mean, image classification is very clear example images to maybe one of a thousand categories. That's what ImageNet is like. But many, many, if not all problems can be mapped this way. And then there's a generic”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

15. “Mentally, we might find it, but it's not very clear how it will look. There's many ideas and it's super exciting as well.”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

16. “Inspiration from how we got here, how the universe evolved us, and we keep evolving. It feels that it's a missing piece, that we should not be training models from scratch every few months, that there should be some sort of way in which we can grow models much like as a species and many other elements in the universe is building from the previous sort of iterations. And that from a just purely neural network perspective, even though we would like to make it work, it's proven very hard to not throw away the previous weights, this landscape we learn from the data and refresh it with a brand new set of weights given maybe a recent snapshot of this data set we train on, et cetera, or even a new game we're learning. So that's that feels like something is missing from the”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

17. “This experience is lacking. And in fact, as I said, we don't even train them when we're talking to them other than their working memory, of course, is affected. So that's the dynamic part, but they don't learn in the same way that you and I have learned, right? basically when we're born and probably before so lots of fascinating interesting questions you ask there i think um The one I mentioned is this idea of memory and experience versus just kind of observe the world and learn its knowledge, which I think for that I would argue lots of recent advancements that make me very excited about the field. And then the second maybe issue that I see is all these models, we train them from scratch. That's something I would have complained three years ago or six years ago or 10 years ago. And it feels if we take...”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

18. “You say, Oh, what's your name? It could remember that, but then it might forget beyond 2000 words, which is not that long of context if we think even of this podcast books are much longer. Technically speaking, there's a limitation there. Super exciting from people that work on deep learning to be working on, but I would say we lack maybe benchmarks and the technology to have this lifetime like experience of memory that keeps building up. However, the way it learns offline is clearly very powerful, right? So you asked me three years ago, I would say, oh, we're very far. I think we've seen the power of this imitation again at the internet scale that has enabled this to feel like at least the knowledge, the basic knowledge about the world now is incorporated into the weights.”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

19. “Interconnect and how we learn over our lifetime. But it's true that the context of the conversation that takes place with when you talk to these systems, it's held in their working memory, right? It's almost like you start a computer, it has a hard drive that has a lot of information, you have access to the internet, which has probably all the information. But there's also a working memory where these agents, as we call them, or start calling them build upon. Now, this memory is very limited, right now we're talking to be concrete about 2,000 words that we hold. And then beyond that, we start forgetting what we've seen. So you can see that there's some short-term coherence already, right? When you said, I mean, it's a very interesting topic, having sort of a mapping an agent to have consistency, then if.”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

20. “Don't then experience themselves. They just are observers, right? They're passive observers of the data. And then we're putting them to then generate data when we interact with them. But that's very limiting. The experience they actually experience when they could maybe be optimizing or further optimizing the weights. We're not even doing that. So to be clear, and again, mapping to alpha go, alpha star, we train the model. And when we deploy it to play against humans or in this case, interact with humans like language models, they don't even keep training, right? They're not learning in the sense of the ways that you've learned from the data. They don't keep changing. Now, there's something a bit more feels magical, but it's understandable if you're into neural net, which is, well, they might not learn in the strict sense of the words the way it's changing. Maybe that's mapping to how neuron.”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

21. “Just learn a function that will be happy, that maximizes the likelihood of seeing all this through a neural network. Now, I think there's a few places where the way currently we train these models would clearly like to be able to develop the kinds of capabilities you save. I'll tell you maybe a couple. One is the lifetime of an agent or a model. So you learn from this data offline, right? So you're just passively observing and maximizing this, you know, it's almost like a mountain, like a landscape of mountains. And then everywhere there's data that humans interacted in this way. You're trying to make that higher and then lower where there's no data.”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

22. “What's happening today is you take all these human interactions. It's a large vast variety of human interactions online. And then you're distilling these sequences going back to my passion, like sequences of words, letters, images, sound. There's more modalities here to be at play. And then you're trying to.”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

23. “Yes, I actually recall I was just listening to our first podcast where we discussed Turing test. So I would say from a neural network, AI builder perspective, usually you try to map many of these interesting topics you discuss to benchmarks and then also to actual architectures on how these systems are currently built, how they learn, what data they learn from, what are they learning, right? We're talking about ways of a mathematical function and then looking at the current state of the game, maybe what do we need leaps forward to get to the ultimate stage of all these experiences, lifetime experience, fears, like words that currently barely we're seeing progress just because”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

24. “Trying to evaluate this from excerpts from the internet, right, that has lots of information. And then if you can learn a function automated ideally, so you can also optimize it more easily, then you could actually have conversations that optimize for non-obvious things such as excitement. So yeah, that's quite possible. And then I would say in that case, it would definitely be a fun exercise and quite unique to have at least one site that is fully driven by an excitement reward function. But obviously, there would be still quite a lot of humanity in the system, both from who is building the system, of course, and also ultimately if we think of labeling for excitement, those labels must come from us because it's just hard to have a computational measure of excitement as far as I understand. No such thing”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

25. “Yeah, that makes sense. I think maybe looping back a bit to games and the game industry, when you design algorithms, you're thinking about winning as the objective, right, or the reward function. But in fact, when we discussed this with Blizzard, the creators of StarCraft in this case, I think what's exciting, fun, if you could measure that and optimize for that, that's probably why we play video games or why we interact or listen or look at cat videos or whatever on the internet. So it's true that modeling rewards beyond the obvious reward functions we've used to in reinforcement learning is definitely very exciting. And again, there is some progress actually into a particular aspect of AI which is quite critical, which is, for instance, is a conversation or is the information truthful, right? So you could start”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

26. “With your creativity, you might actually find very interesting questions that you can filter. We call these cherry-picking sometimes in the field of language. And likewise, if I had now the tools on my side, I could say, look, you're asking this interesting question. From this answer, I like the words chosen by this particular system that created a few words. Completely replacing it feels not exactly exciting to me, although in my lifetime, I think given the trajectory, I think it's possible that perhaps there could be interesting maybe self-play interviews, as you're suggesting, that would look or sound quite interesting and probably would educate or you could learn a topic through listening to one of these interviews at a basic level at least.”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source

27. “Good question. I think partly I would say do we want that? I really like when we start now with very powerful models interacting with them and thinking of them more closer to us. The question is if you remove the human side of the conversation, is that an interesting artifact? And I would say probably not. I've seen for instance last time we spoke, like we were talking about StarCraft and creating agents that play games involves self-play. But ultimately what people care about was how does this agent behave when the opposite side is a human? So without a doubt, we will probably be more empowered by AI. Maybe you can source some questions from an AI system. I mean, that even today I would say it's quite plausible.”

    2022-07-26 · Lex Fridman Podcast · #306 – Oriol Vinyals: Deep Learning and Artificial General Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source