Keith Duggar: belief

Transcript context

…, they're not going to be brilliant and have these amazing insights. And so I think there's really big implications here in terms of both efficiency, creativity, generalization and continual learning. Because what I said about if you want to keep learning, it depends on how you represent the world, how efficient that's going to be. So like, don't think we can just say, grokking might fix it and like everything's going to be fine. Let me just jump in on 2 points. So 1 is and I I want to know if you think this analogy is fair. This this issue of the problem with fractured representations, I kind of think of it as, you know, if you set out to build a nice UI for an application or something and instead of starting with a stencil that has triangles and squares and ellipses and whatever, start with a jigsaw puzzle, you know, it's gonna be a lot harder, Right? To try and build a nice u out UI out of fractured weirdly shaped, you know, components. Like that's a fair analogy. Right? Yeah. Okay. And and I guess I wanted to ask you like, I I really see, you know, connections between this kind of path dependence that you talk about like, it matters a lot how you got to your state of knowledge, how you got to your representations. I think there's a a direct or deep connection with, you know, poet like the work, you know, your earlier paper, right, on this kind of increasingly complex curriculum and environment where you start off training in simple cases and make them more and more complex. I mean, there is a connection there. Right? And maybe that's a simple tool that can be utilized. For sure, yeah. I mean that's 1 of the other factors we talked about that might help to mitigate the issue is the kind of open ended search where it sort of naturally guides the process through a set of tasks of increasing complexity but in a way that's divergent. That's like what's happening in pick breeders so we could extrapolate that that's actually partly or maybe largely responsible for what we see in these representations. But it raises questions about are there very different training paradigms from just dumping in all the data in the world in a kind of a batch, are more intentionally focused on the chronology being intuitive or at least aligned in some way with building good representations. I mean, it evokes ideas about curriculum and things like that. But there's also a kind of concept of a natural curriculum where the human being themself by their nature tends to learn things in an order that's actually useful for building good representations. Example, you take little kids learning arithmetic and if you start trying to teach them calculus, they're just going to ignore it. They're not going to start absorbing it. Mean, that's not the same as LLMs. Like they'll take anything you feed them and start to make the connections, which arguably is really unhealthy. Because if you start to learn calculus before you've learned arithmetic, you can actually create some kind of heuristic version of arithmetic. You can't avoid it. At the same time as you're learning arithmetic somewhere else in your brain. And this is what causes this kind of redundancy or fracture. You get like multiple representations of the same thing. Some of them diminished in their capacity.…

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