TypeSafe launches Jev, a "System One" model that answers typed judgments in ~100ms
aronchick · x · 2026-09-18
TypeSafe AI, a San Francisco lab that emerged from stealth on Sep 15, 2026 with $40M in seed funding, released Jev, its first public model — a "System One" model built for fast decisions inside software, not for chat.
Jev isn't a chatbot or coding model: you send data plus a list of typed questions, and it returns one answer per question — a yes/no probability, a pick from a defined option list, or a position on a defined scale — each with probabilities. Most calls complete in 100ms; input tokens cost $0.042/million and output is free.
Flavio Copes' deep dive frames Jev as "a smart if statement": ordinary code branches only on computable values, while Jev handles judgment-based branching ("is this email about billing?", "which button continues checkout?") as a small component inside ordinary applications, with JavaScript examples, practical patterns, and failure modes documented. Commentator aronchick praised the direction: down-scoping very large models into constrained, deterministic components as the next generation of models.
More from coding & agent
- Junior backend dev asks: is learning RAG, vector DBs and agents worth it yet? — Effective_Emphasis21 · 2026-09-18
- WebMCP draws developer buzz as a way to bring MCP into the browser — nickbaumann_ · 2026-09-18
- Demo: Claude with built-in Cowork and Artifacts builds a multiplayer game from one prompt — felixrieseberg · 2026-09-18
- Six Coding Agents Share the Same Plan Mode Shape but Split on Context After Approval — RunAI_Coder · 2026-09-18
- EvoSkill-GUI: training-free skill evolution lifts GUI agents by up to 16.2% — Bofan Chen · 2026-09-18
- Testing Non-Deterministic LLM Agent Pipelines with Property-Based Assertions — Repulsive_Sugar_5252 · 2026-09-18