TypeSafe AI's Jev introduces 'decision models': text in, probabilistic scores out, at $0.042/M tokens
teropa · x · 2026-09-22
- TypeSafe AI unveiled Jev, billed as the first of a new model category it calls "System One models"; Simon Willison prefers Maggie Appleton's name "decision models".
- Jev takes text input but returns floating-point numbers instead of text: confidence scores for yes/no questions (called "Noul", from Bernoulli), choices among options, and ratings.
- It's fast and cheap: only input is billed, output is free, at $0.042 per million input tokens—cheaper than OpenAI's GPT-5 Nano ($0.05/M).
- You send a "state" object (string, string array, or name-value pairs describing an article, customer, or record) along with one or more questions, and get typed probabilistic answers back—useful for batch decisions over text or semi-structured data.
Related event: Ex-OpenAI researcher launches decision model Jev with bold speed claims(36 posts)→
More from Models
- Google's Physical-Engineering's Last Exam: all 14 frontier models score below 50% — dl_weekly · 2026-11-12
- Commit leak reveals unreleased Gemini 4 variants: Argon, Hydrogen and Helix (unconfirmed) — BlackHC · 2026-11-11
- Rewiring just 89 of 442,368 neurons in Qwen3-8B matches full SFT for a persona — maxsloef · 2026-11-11
- Unsloth ships Qwen3.8-27B Dynamic V3.1 GGUFs with 5-10% accuracy gains — danielhanchen · 2026-11-11
- Zvi: being forced back to an older model is the best reminder of AI progress — TheZvi · 2026-11-11
- Screenshots Made a 4B Browser Agent Worse: A Postmortem With Real Numbers — Stunning-Sherbet1853 · 2026-11-11