Does an open-weight decision model beat a hosted one? Jev vs. Laya
Jmeg8r
11 points
2 comments
September 22, 2026
Related Discussions
Found 5 related stories in 108.7ms across 9,386 title embeddings via pgvector HNSW
- Jev vs. Kev: open-source Jev alternative tested side by side felix089 · 12 pts · September 25, 2026 · 66% similar
- Decision models like Jev don't beat LLM-as-a-judge or traditional classifiers tomncooper · 24 pts · October 02, 2026 · 64% similar
- Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms firelex · 425 pts · September 28, 2026 · 58% similar
- Show HN: jevals – replacing LLM judges with typed Jev decisions gbayomi · 15 pts · September 20, 2026 · 57% similar
- Show HN: JevBench, a reproducible benchmark for typed decision models florianstandhar · 88 pts · September 22, 2026 · 56% similar
Discussion Highlights (1 comments)
orsorna
For anyone who was piqued by the title but couldn't stomach the unedited LLM blogpost, you can read the similarity AI-genned docs for Laya directly: https://github.com/NandhaKishorM/laya