Jev swaps text generation for instant calibrated decisions, plays Doom at 7 req/s

JeremyCMorgan · x · 2026-09-23

A breakdown of TypeSafe's Jev model: instead of generating text token by token, it takes a state (text/JSON) plus named questions and instantly returns calibrated numerical answers. Three question types: choice (pick from a list, returns probabilities + confidence), score (position on an ordered rubric), and noul (probability 0–1 that a claim is true). The pitch is speed and reliable calibration — traditional LLMs are orders of magnitude slower and their self-reported confidence rarely matches reality. In the demo, Jev predicts button presses in real time at 7 requests/second to navigate and clear Doom, something text-generation LLMs can't do. Includes a horse-race handicapping API example.

Related event: Ex-OpenAI researcher launches decision model Jev, claiming 200x speed at fraction of cost(36 posts)→

Original post →

More from coding & agent

coding & agent channel →