Hacker News new | past | comments | ask | show | jobs | submit | prrathi's submissions login

1. Why does DeepSeek v3 route to 8 experts per token? (praneet.sh) 2 points by prrathi 15 days ago | past | 1 comment

Consider applying for YC's Spring batch! Applications are open till Feb 11. Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: