Greg Brockman (Part 2)
Tetragrammaton with Rick Rubin
00:00
Pre-training vs post-training explained
Greg explains next-step-prediction pre-training and post-training alignment via reward models and RLHF.
Play episode from 01:17:40
Transcript
Greg explains next-step-prediction pre-training and post-training alignment via reward models and RLHF.
