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

Olmo author here, but I can help! First release of Qwen 3 left a lot of performance on the table bc they had some challenges balancing thinking and non-thinking modes. VL series has refreshed posttrain, so they are much better!


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

Search: