Raza Habib: belief

Transcript context

…still important. I feel like when I saw chainlethbot for the first time, I went from a world in which I was like, okay, models are not good at reasoning to models can do some reasoning. It was a sort of step change in my beliefs about the capabilities of these models. And I still think that the LLM Cascades paper hasn't had the impact that it should have. Can you summarize that? So this was a paper from Google and it's just sort of getting you to view LLMs as a way of doing inference in a probabilistic programming framework. So that's a lot of words. So let me, try and sort of you have a PhD in this. But, but, you know, before, before AI was all LLMs. There was, and there still is, like a huge branch of research around probabilistic programs. So this is just ways of like writing code where probability and random variables are first class citizen. So you can have like random variables, and then there's lots of different operations you can do to condition and make predictions about them and do inferences around them. And this language modeling cascades paper basically said, Hey, actually, like large language models are a really powerful inference engine that could be used as a composable piece inside something that looks like a probabilistic programming language. And we were chatting earlier today. About the framework that will emerge for, for large language models. And I know you're working on small and you've given this a lot of thought. And you know, LangChain and LlamaIndex and all these different groups, AutoGPT, are trying to circle around, like, what's the right set of abstractions? How might we be able to compose LLMs in ways to write more complex programs? And I think that LLM Cascades paper was one of the first attempts to think about that in first principles. And say, okay, what are the primitives you might want? And I think I'm surprised it hasn't been built on more. The very, very first AI grant from Nat Friedman mentioned that they were looking for a UI for Cascades.…

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