I'm really curious why the answers are so verbose. Probably because the training... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		nottorp on May 9, 2023 \| parent \| context \| favorite \| on: LLMs are not greater than the sum of their parts: ... I'm really curious why the answers are so verbose. Probably because the training was done on a lot of blog spam?

revelio on May 9, 2023 [–]

Raters prefer verbose outputs, probably because they want to see the reasoning to help them judge if the answer is getting it right for the right reasons.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact