Ex-OpenAI RLHF builder launches Jev: a chatless decision model with 150ms responses and $42/B input tokens

SucceededMind · x · 2026-09-16

Diogo Almeida, who helped build RLHF at OpenAI, has launched TypeSafeAI and its first model, Jev. The thesis: generating prose is a major bottleneck for agentic workflows, so structured decisions shouldn't require words.

Jev is a pure API "System One" model — ask a question, get back typed answers with exact confidence scores, no generative text at all. That yields:

The author frames it as a complement to chat models: route logic and structured decisions to Jev so your if-statements get a decision they can actually trust, while chat models handle the parts that genuinely need generated text.

Related event: ChatGPT Co-inventor's Lab TypeSafe Launches Decision Model Jev with RLCD(10 posts)→

Original post →

More from coding & agent

coding & agent channel →