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
00:00
Scaling Up Inference
Inference is essentially amortizing the cost of training over all the different situations that you can encounter. In real time, you're now able to come up with a much finer-grained plan for what to do in any given situation. I think there's a big open question about how can you leverage extra computation at inference time to get better.
Transcript
Play full episode
