Speaker unverified: disagreement

Transcript context

…Yes. But you did say something interesting. So yeah, maybe a distinction from is that and he thinks of LLMs as being a kind of interpretive collection of skilled programs. So he thinks programs are the output of an intelligence system, not the intelligence itself. And with, let's say, and we should talk about what that is. I don't think the concept of a program was an explicit output artifact. It was more a definition of an agent which can succeed in an environment. Is that fair? Yeah. I mean, I suppose a lot of this is kind of semantics a little bit. But the IAC model is a general reinforcement learning agent. So it just takes the standard reinforcement learning thing and tries to make it as sort of a what you might call an upper bound or a superintelligence based on that using Solomonoff induction. And Solomonoff induction is you can think of it as a formalization of Occam's razor. It's just if I have 2 explanations, I pick the simpler 1. And so the idea is that IACI achieves this upper bound in intelligence because if you accept that Occam's razor is some sort of optimal heuristic that you can use. And it does this using Kolmogorov Complexity, which is sort of the optimally compressed version of a model. So if I can compress something more, then it's simpler. And so if I just take the most compressible models, then I can get the simplest ones. And this is useful for thinking about what a superintelligence might do. And because it's reinforcement learning agent, we can sort of model it out. We can build approximations of it. I disagree with some of the theoretical foundations, and I you know, a lot of my publications are about, like, what we could do better, but I find the overall idea of IXC very compelling, and it has informed a lot of my work. Yes. Because I guess for you, reading your work, you said that if know, if we wanted to create AGI, it would be something that looked like a scientist. Because you know, if we frame it at the right level, a scientist can generate hypotheses, and you know, they're they're an agent. They can act in the world. You know, they're embedded in in environment. So you're framed at a at a sort of sufficient level of embedding that you can actually capture the dynamics of the system. And and in that respect, I'd say it is an agent. And it has this principle of compression. And actually, maybe you can contrast it to active inference. Because that's quite similar. It's about this agent that balances energy and entropy. So sort of like predictive control and simplicity in some so called natural way. How is that different from ICSI?…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.