Sholto Douglas: belief

Transcript context

…Yeah, that's what I'm saying. That's good. If you look back at AI discourse going back a decade, there's a sense that there's dumb AI, then there's AGI, then there's ASI, that intelligence is the scalar value. The way you've been talking about these models has a sense of jaggedness. It's especially tuned to environments in which it's been trained a lot or has a lot of data. Is there a sense in which it still makes sense to talk about the general intelligence of these models? Is there enough meta learning and transfer learning that is distinguished between the sizes of models or the way models are trained? Or are we moving into a regime where it's not about intelligence, it's more so about domain? One intuition pump is that this conversation was had a lot when models were GPT-2 sized and fine-tuned for various things. People would find that the models were dramatically better at things that they were fine-tuned for. But by the time you get to GPT-4, when it's trained on a wide enough variety of things with the total compute, it generalized very well across all of the individual sub-tasks. And it actually generalized better than smaller fine-tuned models in a way that was extremely useful. I think right now what we're seeing with RL is pretty much the same story playing out. There's this jaggedness of things that they're particularly trained at. But as we expand the total amount of compute that we do RL with, you'll start to see the same transition from GPT-2 fine-tunes to GPT-3, GPT-4, unsupervised meta learning and generalization across things. I think we're already seeing early evidence of this in its ability to generalize reasoning to things. But I think this will be extremely obvious soon. One nice example of this is just the ability or notion to backtrack. You go down one solution path, "Oh, wait, let me try another one." And this is something that you start to see emerge in the models through RL training on harder tasks. I think right now, it's not generalizing incredibly well.…

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