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

I share the sentiment, as far as I've used it, Sonnet 3.7 is a downgrade and I use Sonnet 3.5 instead. 3.7 tends to overlook critical parts of the query and confidently answers with irrelevant garbage. I'm not sure how QA is done on LLM-s, but I for one definitely feel like the ball was dropped somewhere.


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

Search: