Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Constitutional AI: RLHF on Steroids. Parent comment
A better ref is https://openai.com/research/scaling-laws-for-reward-model-ov...
There are no comments on this comment yet.
A better ref is https://openai.com/research/scaling-laws-for-reward-model-ov...