XNews

TypeSafe AI Launches Jev: System One Model for Fast, Calibrated Decisions

TypeSafe AI, founded by ChatGPT co-inventor Diogo Almeida, launched Jev, a 'System One' model that outputs type-safe structured decisions with calibrated probabilities, abandoning text generation. It is 20-200x faster and 40-400x cheaper than frontier LLMs for decision tasks. Jev uses RLCD training to avoid RLHF-induced hallucination and is designed for 'smart if statements' in code, with applications in routing, classification, and guardrails.

Source posts