Speaker unverified: belief

Transcript context

…Yeah. Completely agree. So it it sounds like we have very, very similar intuitions. And and Charlie talks about this as well. Mean, in his measure of intelligence paper, it was actually about the measure of intelligence. He's never really spoken about the machinations of intelligence. He talks about it just casually. He says, you know, we need the spell key priors and we need to so those are like the basis functions and we need to do library learning and library transfer and we do some kind of like, you know, symbolic compositional process, you know, to adapt to novelty. And he's kind of sketched out the the mechanics of it, but he's never actually formally spoken about it. I assume that's what he's building at at at his company. But there was a famous guy called Jerry Fodor in 1988. He had this connectionism critique. He had this beautiful paper. And he was basically saying that symbolic systems have systematicity and productivity. And systematicity is this compositional thing. It's that, you know, it's the ability to generalize between Mary loves John and Mary loves Jane. Right? So you so you have semantics. You have these kind of like, you know, the the symbolic relations. And they have certain computational properties, like you can do a variable binding and and quantification over potentially infinite domains. Like, we intuitively understand that symbolic things have very interesting properties. And then what we're trying to do is, like, we know neural networks are really good, and we want to somehow graft this capability onto neural networks. Yes. Yeah. And I actually think neural networks are in some ways a superset of symbolic systems. I think you can generally you should be able to encapsulate a symbolic system with a neural network in the same way I think that you can do the I think you can do the same thing with the brain as well. I think there's there's nothing fundamentally blocking, but of course, once you have have the symbolic system in the neural network, it might catastrophically forget when you fine tune it. Like, guess that's a that might be where we we disagree a bit. I think everything you're describing is totally possible, but then when you're when you're coming to train it again, there's no guarantee that it keeps the same structure. I think it's possible because a neural network is is not too incomplete. So I I think in principle, can't do many of these things, but you can build a controller. Right? So you you could just build a very simple kind of envelope just as you did with your solution. So you you you had a bunch of code and it was doing this in, you know, this basically compositionality in code on top of the neural network substrate. And that gives you many of those things. You know, for example, we we often talk about library learning and library transfer. And I'm not sure if you've seen Eric Pang's solution. I'm speaking to him in Hong Kong actually in a couple of weeks. But he rather than the DreamCoder approach where they do this explicit library learning, He was doing it in a kind of implicit way using the LLMs. And I think there's a whole spectrum between you know, you don't have to do it explicitly. I think you can kind of use neural networks and you can do some kind of implicit composition and you can get many of these features.…

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