News for hackers. Stuff that matters.

A comment on VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO. Parent comment

Re:VibeThinker: 3B param model that beats Opus 4.5 on reason... by uberex on Tuesday June 23, 2026 @07:21AM (#48643308)
Maybe limiting logits to what is syntactically correct? E.g. {"hello" has to be followed by whitespace or colon. Any other logits get dropped.
[ Parent | on HN ]

There are no comments on this comment yet.