Hands-on with Jev: a classifier model to replace LLM-as-a-judge and route agents
doesdatmaksense · x · 2026-09-17
The author got access to the new Jev model, praised as a classifier, and outlines two concrete uses:
- Replacing binary LLM-as-a-judge: give Jev some state plus a batch of questions and get back probabilities you can actually threshold on.
- An agent control plane: handling fuzzy decisions inside agent harnesses — which model/tool to route to, continue vs retry, whether output is good enough, whether human review is needed — letting the LLM handle generation while Jev makes the judgment calls.
Related event: TypeSafe AI Launches Jev, a Decision-Only Model That Outputs No Text(73 posts)→
More from coding & agent
- One stale date silently broke a WhatsApp reply agent: 19 messages unanswered — petrusenko_max · 2026-11-02
- The 10X engineer is now just a SKILLS.md: 6 workflow rules for AI coding agents — mdancho84 · 2026-11-02
- Auditing my MCP credential broker: the worst hole was the config file — Relevant_Mousse_9117 · 2026-11-02
- AWS's open-source Strands Harness claims 45% cheaper than Claude Code, reigniting harness debate — blaizedsouza · 2026-11-02
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02
- Sketchy v0.1.6: AI diagrams use 29% fewer output tokens than plain text — Nkgsporty · 2026-11-02