Speaker unverified: belief

Transcript context

…Yeah. I mean, I I think we mostly agree. I I think I mean, you know, let's look at alpha 0 or mu 0 or something like that. They did this training loop where they were actually updating the, you know, like, the the value network and the policy network. And then it was frozen, and they did some kind of, you know, Monte Carlo tree search. So they were achieving adaptivity through exhaustive search during the actual games. And in an ideal world, we would have this adaptivity that's actually updating the weights. Now I believe the only reason we can't do that at the moment is just computational tractability. Right? We have these huge models. We couldn't possibly have a a dynamically updating model for every single person that's using ChatGPT. It it would it would just be ridiculously slow. But I think you and I agree that if that were possible, that would be an entirely different kind of form of intelligence. I don't think that's so intractable, actually. I think, my guess is and, you know, NVIDIA just put in a $100,000,000,000 into OpenAI. Open Sam Altman's plan is to produce a gigawatt of, what, of of compute, a week, something like that, I actually don't think with, you know, ever efficient, algorithms that that is, like, crazy far off. I mean, right now, you could buy a GPU, You could have it running in your house, it could be running OSS 1 20 b. Right? And fine tuning is relatively trivial compared to, you know, the entire process for pretraining. I actually think that is a that is totally within the realm of possibilities in the next 10 years. And I think that that actually is is potentially where this goes. Yeah. I mean, you know far more about this than I do, but I think the reason why fine tuning is so expensive is, you know, we have this continual learning problem. And when you fine tune a model on OpenAI, they're not just fine tuning it on the data you give them. They you know, just to stop this catastrophic forgetting problem, they presumably have to sample in a bunch of the original training data and maintain the distribution and so on. And and if if they did this for everyone, it would be insane. But I am excited about it just like you are because I I interviewed the architects and I I think they got first place on the on the private version last year. And they were doing this transductive active fine tuning. Right? So they and they actually said, by the way, that this is a a curious oddity with transformers that if you start with a, you know, almost like a virgin 8,000,000,000 transformer, it almost doesn't matter what it knew about before. You could just pretty much start training it from scratch on the ARC challenges. So they did a whole bunch of augmentation and active fine tuning, and they built an intelligent artifact. I mean, intelligence is domain specific as per Cholet, and they actually built the system which was per task adapting and solving the tasks, and they were updating the weights, and it was beautiful. So that was an existence proof of nothing else that this thing could work.…

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