TypeSafe launches Jev: a structured-probability model that judges agent outputs in 0.7 seconds
hardimanjames · x · 2026-09-16
- New AI lab TypeSafe launched Jev, a model that skips free-form text and turns fuzzy natural-language questions into structured probabilities your code can use directly.
- Ask 'Does this customer sound angry?' and it returns 0.9, or classify into custom categories like annoyed/irritated/furious.
- Every's head of evals Mike Taylor tested it: judgments land in 0.7 seconds at low cost, making it suitable for real-time QA inside agent workflows — a smart, programmable if-then layer.
Related event: TypeSafe exits stealth with decision model Jev and RLCD training method(18 posts)→
More from coding & agent
- skillmem: open-source procedural memory for MCP agents, with hard-won recursion lessons — mrPetrukovich · 2026-09-16
- Running More Than 2 Sub-Agents in Parallel Burns Tokens for Zero Quality Gain — pvncher · 2026-09-16
- Devin Gets a Cloud Mac: Build and Ship iOS/macOS Apps From a Prompt — Rasmic · 2026-09-16
- Self-evolving agent framework Épi hits 120 research records, tightens Klarner's constant — my_cat_can_code · 2026-09-16
- MCP deferred tools explained: progressive disclosure, like a CLI, model calls first to fetch params — eherrerosj · 2026-09-16
- Muse Code Raises Contributor Tier Limits, Resets All Subscription Usage — armand_ruiz · 2026-09-16