Jev handed our LLM the wrong page a tenth as often as our embeddings
Bocajmai
12 points
3 comments
October 13, 2026
Related Discussions
Found 5 related stories in 115.3ms across 9,386 title embeddings via pgvector HNSW
- Jev vs. LLMs on 770 "Am I the Asshole?" posts dchristopoulos · 16 pts · September 23, 2026 · 59% similar
- Show HN: jevals – replacing LLM judges with typed Jev decisions gbayomi · 15 pts · September 20, 2026 · 58% similar
- Language models for text classification: From bag-of-words to Jev Anon84 · 70 pts · September 29, 2026 · 56% similar
- A single function Jev-like wrapper for LLMs, including vision models allanrbo · 22 pts · September 26, 2026 · 56% similar
- Jev vs. Kev: open-source Jev alternative tested side by side felix089 · 12 pts · September 25, 2026 · 54% similar
Discussion Highlights (2 comments)
branislavkacer
Really interesting. Thanks for the insight!
bigstarat
Alright. But have you tested with a wider data set? It’s interesting but hardly proves Jen has more utility than say a regular LLM or the OpenAI decisions API.