Tim Scarfe: preference

Transcript context

…So to me, training is kind of the opposite of what you described. I view there's 2 2 types of knowledge. There's knowledge that is memorized like the capital of New York or the Spanish language, and then there's knowledge that is deduced. So that's, physics, special relativity, general relativity. Right? From axioms, you can deduce these things, and it's a causal tree. And then there's a another type of knowledge, what is the capital of North Dakota. That is a knowledge network. It's not deductive. It's not a tree. And I think pretraining treats all knowledge as a knowledge web. It's embeddings that are connected, but there's no there's no guarantee that you have the correct causal relationship between things, and this is where the memorization comes in. And I think this is actually where compression fits into intelligence. So my view is actually intelligence is compression in that you should be able to deduce you should be able to build a knowledge tree based on almost you can build a knowledge tree based on almost nothing. Right? You can deduce so much of math. You can deduce special relativity from the very, you know, the the very roots of physics. And Einstein was extremely intelligent because the hints that he needed to come up with special relativity are 0. Right? He could start from almost nothing and build up this deductive tree. And I think it's almost like reinforcement learning and reasoning is the process of pruning our knowledge network and replacing it with this tree. And and until we have weights that represent the actual deductive nature of knowledge, we won't actually get generalization. I don't know if this this fits in, but this is kind of how I think about reinforcement learning, which is replacing knowledge web with an with a knowledge tree. Yes. Yes. This is this is brilliant. We're getting to the center of the bull's eye here. Absolutely. And I I remember I read in in the first version of your blog post that you were talking about, we need to do this kind of deduction where we synthesize hypotheses, and then we we test them, and we do this kind of generate test loop. And and that is what creativity is. It's what reasoning is. Because, you know, when I first read Charle's paper, you know, years ago, I was kind of like, I didn't understand whether he was talking about acquisition or synthesis. And I now understand he's talking about synthesis. So reasoning is like you just like Lego, you you build you build this kind of tree, this epistemic tree. And actually, this is what we do. So there's a difference between knowing and understanding. So knowing is is kind of like at the high And understanding is is actually like there's this whole, you know, just imagine this big block of this big Lego structure and you're tracing down the structure of all the building blocks of how you got there. And I actually think even when you teach kids at university, what you're really doing, obviously, like, you teach you teach them facts, but then they kind of synthesize their understanding over time. So they're doing this composition and they're kind of getting there the way that they get there. And and we need to build systems to do this. And there's the perennial problem that you were saying that in deep learning, what we do is we kind of start with this big pattern network and we kind of specify it. And I think reasoning should be more about synthesizing from building blocks. And I I think that when you synthesize, you can actually do types of reasoning which are not in the training data. Right? You can build things that simply are not there. You can just think about things and and and figure things out. So do you think of that as a gap? Yes. I think that's exactly right. And then the question is, can you build the system with language models or not?…

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