That's yet to be determined. I think a lot of open-weight models are benchmaxxed... | Hacker News

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

LUmBULtERA 64 days ago | parent | context | favorite | on: Claude Sonnet 5

That's yet to be determined. I think a lot of open-weight models are benchmaxxed and their usefulness for many tasks are not represented by those.

enraged_camel 64 days ago [–]

Yes, this has been my experience. They all struggle with long-horizon tasks and eventually start going in circles.

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