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 Launches Decision Model Jev with New RLCD Training Method(7 posts)→
More from coding & agent
- Harness Engineering: making production AI agent improvement an engineering discipline — MaryamMiradi · 2026-09-16
- PowerShell Idea Lab: an overnight AI loop that finds ideas, codes, runs and publishes — dfinke · 2026-09-16
- Harness Engineering: making production AI agent improvement an engineering discipline — MaryamMiradi · 2026-09-16
- Celesto AI open-sources SmolVM for disposable macOS sandboxes on Apple Silicon — aniketmaurya · 2026-09-16
- Dev launches free MCP server aggregating thousands of lightweight utility tools — apyhubnico · 2026-09-16
- Codex for OSS doubles grants to 10,000, adds $100 Pro plans and $760k in sponsorships — charliermarsh · 2026-09-16