HackerTrans
TopNewTrendsCommentsPastAskShowJobs

half-kh-hacker

no profile record

comments

half-kh-hacker
·4개월 전·discuss
How does post-training via reinforcement learning factor in? Does every evaluated judgement count as 'the training data' ?
half-kh-hacker
·9개월 전·discuss
the paper already says "Butter-Bench evaluates a model's ability to 'pass the butter' (Adult Swim, 2014)" so