
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
Is There Anything You've Been Excited About?
The promise from all the games research is that it would one day be applicable to the real world. And I felt like MuZero was a really nice step in that direction because you no longer need to know the specific rules of the game. It learns that transition function from experience. There's still a question of how you extend that to imperfect information games like poker and real, so that's another direction that I think is worth pursuing.
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.