YouSaid · the spoken record

Shane Legg

lines on the record

54

first

2023-10-26

most recent

2023-10-26

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, new training data in all kinds of different applications that aren't just purely textual anymore. And what are those applications? Well, probably a lot of them we can't even imagine at the moment because there are just so many possibilities once you can start dealing with all sorts of different modalities in a consistent way.”

   2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

2. “I think it's early days. I think there's, you can see promise there, understanding images and things more and more. But I think it's early days in this transition is when you start really digesting a lot of video and other things like that, that the systems all start having a much more grounded understanding of the world and all kinds of other aspects. And then when that works well, that will open up naturally lots and lots of new applications and all sorts of new possibilities because you're not confined to text chat anymore.”

   2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

3. “I think the next landmark that people will think back to and remember is going much more fully multimodal, I think. Because I think that'll open out the sort of understanding that you see in language models into a much larger space of possibilities. And when people think back, they'll think about, oh, those old-fashioned models, they just did like chat. They just did text. It just felt like every narrow thing. Whereas now they understand when you talk to them and they understand images and pictures and video and you can show them things or things like that and they will have much more understanding of what's going on. And it'll feel like the system's kind of opened up into the world in a much more powerful way.”

   2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

4. “I think they're fairly separate, but they can be somewhat related. So you can learn different ways of thinking through problems and actually learn about this rapidly using your episodic memory. So all these different systems and subsystems interact so that they're never completely separate. But I think conceptually you can probably think of them as quite separate things. I think delusions and factuality is another area that's going to be quite important and particularly important in lots of applications. If you want a model that writes creative poetry, then that's fine because you want to be able to be very free to suggest all kinds of possibilities and so on. You're not really constrained by a specific reality. Whereas if you want something that's in a particular application, normally you have to be quite concrete about what's currently going on and what is true and what is not true and so on. And models are a little bit sort of free wheeling.”

   2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

5. “I don't know. I don't want to pick favorites. It's hard picking favorites. I know the people working on all these areas. I think I think things of the sort of system two flavor there's a work we have going on that Jeffrey Irving leads called deliberative dialogue, which kind of has a system to flavor where you have this sort of debate takes place about the actions that an agent could take or what's the correct answer to something or something like this. people then can sort of review these these debates and so on and they they use these sort of these ai algorithms to help them judge the correct outcomes and so on and so this is sort of meant to be a way in which to try to scale the the alignment to sort of increasingly powerful systems so i think things of that kind of flavor i think have quite a lot of promise in my opinion but that's kind of quite a broad category research there are many different topics within that”

   2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

6. “Um, I think what you'll see is the existing model is maturing. They'll be less delusional, much more factual. They'll become multimodal much more than they currently are. And this will just make them much more useful. So I think probably what we'll see more than anything is just loads of great applications for the coming years. I think that'll be there can be some misuse cases as well, I'm sure somebody will come up with something to do with these models that is quite unhelpful. But my expectation for the coming years is mostly a positive one. We'll see all kinds of really impressive, really amazing applications for the coming years. Yeah.”

   2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

7. “I don't know I don't know. At the moment, it looks to me like all the problems are likely solvable with a number of years of research. That's my current sense.”

   2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

8. “So that was my reasoning process. And I think we're now at that first part. I think we can start training models now where the scale of the data is beyond what a human can experience in a lifetime. So I think this is the first unlocking step. And so, yeah, I think there's a 50% chance that 78-2028. Now, it's just a 50% chance. I mean, I'm sure what's going to happen is going to get to 2029 and someone's going to say, oh, Shane, you were wrong. It's like, come on, it's 50 chance. So, yeah, I think it's. It's entirely plausible. Yeah, it's 50% chance it could happen by 2028. But I'm not going to be surprised if it doesn't happen by then. Maybe, you know, you often hit unexpected problems in research and science that sometimes things take longer than you expect.”

   2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

9. “And so I thought it would be very likely that we'll start to discover scalable algorithms to do this. And then there's a positive feedback between all these things, because if your algorithm gets better at harnessing computer data, then the value of the data in the compute goes up because it can be more effectively used. And so that drives more investment into these areas. If you compute performance goes up, then the value of the data goes up because you can utilize more data. So there are positive feedback loops between all these things. So that was the first thing. And then the second thing was just looking at the trends. If the scalable algorithms were to be discovered, then during the 2020s, it should be possible to start training models on significantly more data than a human would experience in a lifetime. And I figured that that would be a time where big things would start to happen and that would eventually unlock AGI.”

   2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

10. “Before Imagenate, that was 2012. Yeah, so, well, I first formed those beliefs in about 2001 after reading Ray Kurtzwall's The Age of Spiritual Machines. And I I came to conclusion points in his book that I came to believe is true. One is that I... Computational power would grow exponentially for at least a few decades, and that the quantity of data in the world would grow exponentially for a few decades. And when you have exponentially increasing quantities of computation and data, then the value of highly scalable algorithms gets higher and higher. So then there's a lot of incentive to make a more scalable algorithm to harness all this computing data.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

11. “And that, I think, affected the dynamics in some ways. But the community is much, much bigger than, say, deep mind. Maybe we've speed things up a bit, but I think a lot of these things would have happened. For too long, anyway. I think often good ideas are kind of in the air. And as a researcher, when sometimes you publish something or you're about to publish something, you see somebody else who's got a very similar idea coming out with some good results. I think often it's the time is right for things. So, you know, I find it very hard to reason about the counterfactuals there.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

12. “Is far more, right, right, right. I think we have accelerated capabilities, but again, the counterfactuals are quite difficult. I mean, we didn't do ImageNet, for example. And ImageNet, I think, was very influential in investment to the field. We did do alpha Go, and that changed some people's minds. The community is a lot bigger than just DeepMind. I mean, we have, well, not so much now, but because there are a number of other players with significant resources. But if you went back more than five years in the future, we were able to do bigger projects with bigger teams and take on more ambitious things than a lot of the smaller academic groups, right? And so the sort of nature of the type of work we could do was a bit different.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

13. “I know a lot of other people in the area, and I've talked to them over many, many years. I've known Darios since 2005 or something or other. You know, we talked on and off about AGI safety and so on. So I don't know. The impact that DeepMind has had. I guess we were the first. Say the first AGI company, and as the first AGI company, we always had an AGI safety group. We've been publishing papers in this for many years. I think that's lent some credibility to the area when people see, oh, here's a AGI. I mean, AGI was a, you know, there was a fringe term not that long ago. And this person's doing AGI safety. They're a deep mind. Oh, okay. I hope that sort of, you know, creates some space for people.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

14. “Interesting I don't know. It's hard to judge, actually. You know, back in the I've been worried about AGI safety for a long time, well before DeepMind. But it was always really hard to hire people, actually, particularly in the early days, to work on AGI safety. Thinking back in 2013 or so, I think we had the first hire and he only agreed to do it part time because he didn't want to drop all the capabilities work because the impact he could have was a career and stuff. And this was someone who had already previously been publishing in AGI safety. Yeah, I don't know. It's hard to know what is the counterfactual if we weren't there doing it. I think we have been a group that's been Talked about this openly. I've talked about this on many occasions, the importance of it. We've been hiring people to work on these topics.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

15. “I think that's a sensible thing to do. It's actually quite hard to do. There are some people thinking about, I know anthropics has put out, some things like that. We're thinking about similar things actually, you know, putting concrete things down is actually quite a hard thing to do.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

16. “This is not so much a Google deep mind perspective on this. This is my take on. How I think we need to do this kind of thing. There are many different views within. And there are different variants on these sorts of ideas as well”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

17. “Reinforcement has some dangerous aspects to it. I think it's actually more robust to do, you know, check the process of reasoning and check its understanding of ethics. So to reassure ourselves that the system has a really good understanding of ethics, it should be grilled for some time to try to really pull apart its understanding and make sure it has a very robust. And then also if it's deployed, we should have people constantly looking for how the decisions it's making and the reasoning process that goes into those decisions. Try to understand that it is correctly reasoning about these types of things.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

18. “Have to check it as it's doing it. We have to assure ourselves that it is consistently following these ethical principles, at least. I mean, I'm not sure there's such thing as optimally, but at least as well as a group of human experts.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

19. “These things. So every time it makes a decision, it does an analysis using a deep understanding of the world and of ethics and very robust and precise reasoning to do an ethical analysis of what it's doing. And of course we'd want lots of other things. We'd want people checking these processes of reasoning. We'd want people verifying that it's behaving itself in terms of how it reaches these conclusions.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

20. “Now, that's not a technical problem. That's a problem for society and ethicists and so on to come up with. Now, you know, I'm not sure there's such a thing as true or correct optimal ethics or something like that, but I'm pretty sure that it's possible to come up with a set of ethics which is much better than the so-called doomers worry about in terms of the behavior of these AGI systems. And then what you do is you engineer the system to actually follow”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

21. “Well, we've got a couple problems. First of all, we need to decide, we should train the system on ethics generally. I mean, there's a lot of lectures and papers and books and all sorts of things so it understands human ethics well, right? And we need to make sure it understands humans' ethics well, right? Because that's important, at least as well as a very good ethicist. And we then need to decide, okay. Of the sort of general understanding of ethics, what do we want the system to actually value and what sort of ethics do we want it to apply?”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

22. “Yeah, that's the challenge. We need to have systems. The way I think about it is this to have a profoundly ethical AI system, it also has to be very, very capable. It needs a really good world model, a really good understanding of ethics, and it needs really good reasoning. Because if you don't have any of those things, how can you possibly be consistently profoundly ethical? You can't. So we actually need better reasoning, better understanding of the world, and better understanding of ethics in our systems.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

23. “Well, it should preserve them because if it's making all its decisions based on a good understanding of ethics and values and it's consistent in doing this, it shouldn't take actions which undermine that. That would be inconsistent.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

24. “It needs not just a good model of the world, but it needs a really good understanding of ethics. And we need to communicate to the system what ethics and values it should be following.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

25. “And then reason about each of these from an ethical perspective. So you need a system which has a deep understanding of the world, has a good world model, it has a good understanding of people, has a good understanding of ethics, and it has robust and very reliable reasoning. And then you set it up in such a way that it applies this reasoning and this understanding of ethics to analyze the different options which are in front of it and then execute on which is the most ethical way forwards.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

26. “What you need to do is you need to have a system too. You need the system to not just sample from the model, you need the system to go, okay, I'm going to reason this through. I'm going to do step-by-step reasoning. What are the options in front of me? I'm going to use my world model now and I'm going to use a good world model to understand what's likely to happen from each of these options.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

27. “That's not good enough. And if we do RLHF or what's it called, I can't remember. Anyway, it's the AI version without the human feedback. R-A-I-F, is that what it is? Oh gosh, I'm confusing myself. Anyway, constitutional AI tries to do that sort of thing. You're trying to fix the underlying system one in a sense, right? And that can shift the distribution and that can be very helpful, but it's a very high dimensional distribution and you're sort of poking it in a whole lot of points. And so it's not likely to be a very robust solution, right? It's like trying to train yourself out of a bad habit. You know, you can sort of do it.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

28. “If I do each of these things, what will happen, right? And then you have to think about, so that requires a model of the world, and then you have to think about ethically, how do I view each of these different actions and the possibilities and what may happen from it, right? What is the right thing to do? And as you think about all the different possibilities and your actions and what can follow from them and how it aligns with your values and your ethics, you can then come to some conclusion of what is really the best choice that you should be making if you want to be really ethical about this. I think AI systems need to essentially do the same thing. So when you sample from a foundational model at the moment, it's like it's blurting out the first thing. It's like system one, if you like, from psychology from Kahneman, right?”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

29. “The first thing that comes to mind, right? Because you know, there could be a lot of emotions involved and other things, right? It's a difficult problem. So what you have to do is you have to calm yourself down. You've got to sit down and you've got to think about it. You've got to think, well, okay, what could I do? I could do this. I could do this. I could do this.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

30. “And if the system is really capable, really intelligent, really powerful, trying to somehow contain it or limit it is probably not a winning strategy because these systems ultimately will be very, very capable. So what you have to do is you have to align it. You have to get it so it's fundamentally a highly ethical value aligned. System from the get go How do you do that? Well, I have a maybe this is slightly naive, but this is my take on it. How do people do it? If you have a really difficult ethical decision in front of you, what do you do, right? Well. Don't”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

31. “Do you want to know about what we're currently doing, or do you want me to have a stab at what I think needs to be done? Needs to be done. To be done, so I mean, in terms of what we're currently doing, we're doing lots of things. We're doing interpretability, we're doing process supervision, we're doing red teaming, we're doing evaluation for dangerous capabilities, we're doing work on institutions and governance and tons of stuff, right? There's lots of different things. Anyway, what do I think needs to be done? So I think I think that powerful machine learning, powerful AI is coming sometimes.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

32. “Can't say much about how we're training. I think it's fair to say we're doing the sorts of scaling and training roughly that you see many people in the field doing. But we have our own take on our own different tricks and techniques.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

33. “Really, do that kind of a thing. They really are mimicking the data. They are mimicking all the human ingenuity and everything which they have seen from all this data that's coming from the internet that's originally derived from humans. If you want a system that can be truly beyond that and not just generalize in novel ways, so it can, you know, these models can blend things. They can do Harry Potter in the style of a Kanye West rap or something, even though it's never happened. They can blend things together. But to do something is truly creative, there's not just a blending of existing things, that requires searching through a space of possibilities and finding these hidden gems that are sort of hidden away in there somewhere. And that requires search. So I don't think we'll see systems that truly step beyond their training data until we have powerful search in the process.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

34. “Yeah, I think that's on the right track. I think there is these foundation models are world models of a kind and to do really creative problem solving, you need to start searching. So if I think about something like AlphaGo in the move 37, the famous move 37, where did that come from? Did that come from all its data that it's seen of human games or something like that? No, it didn't. It came from it identifying a move as being quite unlikely, but possible, and then via a process of search coming to understand that that was actually a very, very good move. So you need to get real creativity, you need to search through spaces of possibilities and find these sort of hidden gems. That's what creativity is. I think current language models, they don't really...”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

35. “Prediction system. And then once you have that, you can build a general agent on top of it by basically adding search and reinforcement signal. That's what you do with AIX. But what that sort of tells you is that if you have a fantastically good sequence predictor, some approximation of solomanoff induction, then going from that to a very powerful, very general AI system is just sort of another step. You've actually solved a lot of the problem already. And I think that's what we're seeing today, actually, that these incredibly powerful foundation models are incredibly good sequence predictors. They're compressing the world based on all this data, and then you will be able to extend these in different ways and build very, very powerful agents out of them.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

36. “Yeah, I mean, in a sense, what's happened is actually very aligned with what I write about my thesis, which are the ideas from Marcus Hutter with AIX, where you take Solomonoff induction, which is this incomputable but theoretically very elegant.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

37. “Things like alpha fold are not really feeding into AGI. We may learn things in the process that may end up being relevant, but I don't see them as being. Likely being on the path to AGI. But yeah, we're a big group. We've got hundreds and hundreds and hundreds of PhDs working on lots of different projects. So when we find, well, we see like opportunities to do something significant like alpha fold, we'll go and do it. It's not like we only do AGI type work. We work on fusion reactors and various things in sustainability, energy. We've got people looking at satellite images of deforestation. We have people looking at weather forecasting. We've got tons of people. We've got lots of things.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

38. “Different processes, but a comprehensive system should be able to do both. And so I think it's conceivable you could build one system does both, but you can see because they're quite different things that it makes sense for them to do different. I think that's why the brain does it separately.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

39. “I think it'll be architectural in nature because the current architecture's. They don't really have what you need to do this. They basically have a context window, which is very, very fluid, of course, and they have the weights, which things get baked into very slowly. So to my mind, that feels like working memory, which is like the activations in your brain, and then the weights, the synapses and so on in your cortex. Now, the brain separates these things out. It has a separate mechanism for rapidly learning specific information because that's a different type of optimization problem compared to slowly learning deep generalities. There's a tension between the two, but you want to be able to do both. You want to be able to, I don't know, hear someone's name and remember the next day. And you also want to be able to integrate information over a lifetime so you start to see deeper patterns in the world. These are quite different optimization targets.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

40. “It was an effort to say okay, can we just even very theoretically come up with a clean definition? I think we can sort of get there. We have this issue of a reference machine, which is unspecified.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

41. “Sort of setting your reference machine to be such that it emphasizes the kinds of environments that we live in as opposed to some abstract mathematical environment or something like that. And so that's how I've kind of gone on this journey of let's try to define a completely universal, clean mathematical notion of intelligence to, well, it's got a free parameter. One way of thinking about it is say, okay, let's think more concretely now about human intelligence. And can we build machines that can match human intelligence? Because we understand what that is and we know that that is a very powerful thing and it has economic philosophical, historical kind of importance. So that's kind of the, and the other aspect, of course, is that, you know, in this pure formulation of common growth complexity, it's actually not computable. And I obviously knew that there was a limitation at the time, but it was a...”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

42. “Let's think about what's meaningful to us in terms of intelligence. I think human intelligence is meaningful to us and the environment that we live in. We know what human intelligence is. We are human. We interact with other people of human intelligence. We know that human intelligence is possible, obviously, because it exists in the world. We know that human intelligence is very, very powerful because it has affected the world profoundly in countless ways. And we know human level intelligence was achieved that would be economically transformative because the types of cognitive charts people do in the economy could be done by machines then. And it would be philosophically important because this is sort of how we often think about intelligence. And I think historically it would be a key point. So I think that human intelligence is actually quite in a human-like environment, is quite a natural sort of reference point. So you could imagine.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

43. “And that's a free parameter. So that means that the intelligence measure has a free parameter in it. And as you change that free parameter, it changes the weighting and the distribution over the space of all the different tasks and environments. So this is sort of an unresolved part of the whole problem. So what reference machine should we ideally use? There isn't really a, there's no universal like one specific reference machine. People will usually put a universal Turing machine in there, but there are many kinds of universal Turing machines. You have to put a universal Turing machine in there, but there are many different ones. So I think given that it's a free parameter, I think the most natural thing to do is say, okay.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

44. “The nature of intelligence has been able to perform well in lots of different domains and different tasks and so on, it's about that sort of capability of performance and the breadth of performance. So I found that was quite helpful and enlightening. There was always the issue of the reference machine because in the framework you have a weighting of things according to their complexity. It's like an Occam's razor type of thing where you wait tasks, environments which are simpler more highly in this sort of because you've got an infinite, it's countable space of different computable environments or semi-computable environments. And that combograph complexity measure has something built into it which is called a reference machine.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

45. “Yeah, it's evolved a bit. When I did my thesis work around universal intelligence and so on, I was trying to come up with a sort of extremely universal general mathematically clean framework for defining and measuring intelligence. And I think there were aspects of that that were successful. I think in my own mind it clarified”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

46. “There is no one thing that would do it because I think that's the nature of it. It's about general intelligence, so I would have to make sure it could do lots and lots of different things and it didn't have a gap. We already have systems that can do very impressive categories of things to human level or even beyond. So I would want a whole suite of tests that I felt was very comprehensive. And then furthermore, when people come and say, okay, so it's passing a big suite of tests. Let's try to find examples. Let's take an adversarial approach to this. Let's deliberately try to find examples where people can clearly typically do this with the machine fails. And when those people cannot succeed, I'll go, okay, we're probably there.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

47. “I don't see there are big blockers here. I don't see big walls in front of us. I just see there's more research and work and these things will improve and probably be adequately solved.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

48. “I don't think it's a fundamental limitation. I think what's happened with large language models is something fundamental has changed. We know how to build models now that have some degree of, I would say understanding of what's going on. And that did not exist in the past. And because we've got a scalable way to do this now that unlocks lots and lots of lots and new things. Now we can then look at things which are missing such as this sort of episodic memory type thing and we can then start to imagine ways to address that. So my feeling is that there are kind of relatively clear paths forwards now to address most of the shortcomings we see in existing models whether it's about delusions, factuality, the type of memory and learning that they have or understanding video or all sorts of things like that.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

49. “So the models can learn things immediately when it's in a context window. And then they have this sort of this longer process of when you actually train the base model and so on. And that's they're learning over trillions of tokens. But they sort of miss something in the middle. That's sort of what I'm getting at here.”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source

50. “It's very much related to sample efficiency. It's one of the things that enables humans to be very sample efficient. Large language models have a certain kind of sample efficiency because when something's in their context window, they can that sort of biases the distribution to behave in a different way. And so that's a very rapid kind of learning. So there are multiple kinds of learning and the existing systems have some of them, but not others. So it's a little bit complicated”

    2023-10-26 · Dwarkesh Podcast · Shane Legg (DeepMind Founder) — 2028 AGI, superhuman alignment, new architectures · IDENTIFIED FROM THE TRANSCRIPT · source