Ex-OpenAI Researcher Launches Jev: A System One Model for Structured Decisions, 100x Faster
KhuyenTran16 · x · 2026-10-01
TypeSafe founder and ex-OpenAI researcher Diogo Almeida launched Jev, the first "System One Model": a new class of frontier model for fast, structured decisions, now in early access.
- Unlike PydanticAI's post-hoc schema validation, Jev constrains the answer space before inference (choices, scoring levels, yes/no), outputting typed probabilistic decisions with no free-text generation
- Built on a new architecture, parallel sampler, and a training method called RLCD (Reinforcement Learning for Calibrated Decisions)
- Claims: similar intelligence on System One tasks as existing LLMs, two orders of magnitude faster and more efficient, and incapable of hallucinating due to constrained outputs
- Pitched as a "frontier-intelligence function call": unstructured state in, typed decisions out—aimed at automation, not chat
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a token-efficiency tradeoff — MandeepKaur9407 · 2026-11-16
- sessionwiki turns your past coding-agent sessions into a searchable local wiki for agents — Cold_Past7184 · 2026-11-16
- Developer hits 700+ commits/day with AI, asks how to manage parallel agent work — blixt · 2026-11-16
- Alibaba's G-CAST: governed continual self-training keeps e-commerce agents fresh in production — Yuechun Yu · 2026-11-16
- harness-evals: open-source library to compare agent versions with success-vs-cost plots — slavadubrov · 2026-11-16
- Developers poll real costs of running coding agents on remote VMs for work — radim11 · 2026-11-16