VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO
by from Hacker News on (#76G4B)
External Content
| Source | RSS or Atom Feed |
| Feed Location | http://news.ycombinator.com/rss |
| Feed Title | Hacker News |
| Feed Link | https://news.ycombinator.com/ |
| Reply | 0 comments |