Ex-OpenAI RLHF co-inventor launches Jev: 100x faster, hallucination-free structured-output model
AxSaucedo · x · 2026-09-25
TypeSafe AI, founded by ex-OpenAI RLHF co-inventor Diogo Almeida, emerges from two years of stealth with its first System One Model, Jev (early access).
- Positioning: not a chat model but a "frontier-intelligence function call" — unstructured state in, typed probabilistic decisions out, ready for software to consume directly.
- Stack: a new model architecture, a parallel sampler, and a training method called RLCD (Reinforcement Learning for Calibrated Decisions).
- Claims: matches existing LLMs on System One tasks while being two orders of magnitude faster; gives up string generation, so it is optimized for structured outputs and cannot hallucinate.
Related event: Ex-OpenAI researcher launches Jev, a non-text "System One" decision model(12 posts)→
More from Models
- Gemini 4 Carbon matches predecessor's score but explores less, gets distracted — patience_cave · 2026-11-11
- Fable 5.2 takes MazeBench frontier, matches GPT-6 Astra puzzle-solving — patience_cave · 2026-11-11
- MazeBench: Fable 5.2 scores 15%, near-frontier at half price; Gemini 4 Carbon 11% — patience_cave · 2026-11-11
- Indie dev flips from $20 Pro back to $200 Gemini Ultra after two days of deep use — yihui_indie · 2026-11-11
- OpenAI retiring ChatGPT's Standard Voice with 9 original voices on Dec 11, petition launched — ChaosGremlinOG · 2026-11-11
- Leak: Google's upcoming model lineup includes Hydrogen, Krypton, Helix and a video model — koltregaskes · 2026-11-11