Rubric-Based Zero-Shot Classification Benchmark: Jev vs Claude Haiku 4.5 vs Claude Sonnet 5 vs OpenJev on rubric-conditioned classification, chained decision execution, and exam grading -- with ful...
1 comment
yididev7 days ago
Most videos I've seen about jev seen to be hyping it up as an llm that can produce typesafe results. First, that wouldn't be that worthy of too much hype. We've found many ways to do that already. second, its not really where jev shines.
Read the full thread on Hacker News →
Related stories
- Hacker News · 1 points · 9 days ago
- Hacker News · 3 points · 3 days ago
- Hacker News · 1 points · 5 days ago
- Hacker News · 7 points · 11 days ago
- Hacker News · 2 points · 6 days ago
- Hacker News · 2 points · about 23 hours ago