HackerTrans
トップ新着トレンドコメント過去質問紹介求人

growdark

no profile record

コメント

growdark
·9 か月前·議論
I'd love to see a benchmark that tests different LLMs for slop, not necessarily limited to code. That might be even more interesting than ARC-AGI.
growdark
·9 か月前·議論
Does this actually work or would the slop just become more subtle?