logoalt Hacker News

half-kh-hackertoday at 6:29 AM2 repliesview on HN

How does post-training via reinforcement learning factor in? Does every evaluated judgement count as 'the training data' ?


Replies

abcde666777today at 7:08 AM

I guess I'd place both within a broader umbrella: human generated input. So it still holds that they're regurgitating the decisions made by humans.

internet_pointstoday at 8:50 AM

yes