TypeSafe Launches Jev: A Probability-Judging Model 25x Faster, 600x Cheaper Than Fable-Class Judges
soumitrashukla9 · x · 2026-09-16
TypeSafe, a new lab co-founded by a ChatGPT co-inventor, launched Jev, a frontier model built for decisions, not chat. You ask fuzzy, subjective questions in plain English and it returns probabilities for yes/no or custom categories—like a smart if-then statement for automated workflows.
- Claims 20-200x faster and 40-400x cheaper than peer models (output tokens free)
- Trained with a new method called RLCD, pitched as 'frontier composable intelligence optimized for decisions'
- Every's evals head clocked it judging his writing in 0.7 seconds; as a judge it was 25x faster and 600x cheaper than a Fable-class model
- Fits background automation: support routing, invoice matching, fraud classification, and real-time checking of agent outputs
Related event: TypeSafe exits stealth with decision model Jev and RLCD training method(86 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