
Episode 27: Noam Brown, FAIR, on achieving human-level performance in poker and Diplomacy, and the power of spending compute at inference time
Generally Intelligent
What Are Your Instincts on How to Make It More General?
We didn't try many other options. We threw around like a few different options for how to approach this. One of the things we consider for example is just doing RL in language. But I'm pretty happy with what we arrived at, I think it's a good proof of concept that this works well. What are your instincts on how to make it more general? That's going to be the focus for a lot of my work going forward. It would be nice to look beyond just diplomacy.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.