State of the art for non-generative decisions: 78.9% on the public typed-decisions benchmark, above every frontier model. One forward pass, bounded output, calibrated with no temperature fitted, 16 ms a decision.
0 comments
No comments yet.
Related stories
- Hacker News · 2 points · 4 days ago
- Hacker News · 1 points · 10 days ago
- Hacker News · 3 points · 3 days ago
- Hacker News · 1 points · 6 days ago
- Show HN: A local alternative to Jev – 94% on Banking77gist.github.comHacker News · 2 points · 5 days ago
- Hacker News · 7 points · 11 days ago