TypeSafe AI 首支系統一級模型「Jev」解析：代理編程中無盡判斷的智慧化解方

Last week, TypeSafe AI released Jev, its first System One model.Founder Diogo Almeida previously worked at OpenAI on the instruction-following research behind ChatGPT.Jev does not chat, write code or summarize.It takes unstructured state and returns typed decisions with calibrated probabilities.

That makes it a natural fit for the thousands of small judgments inside an agent loop: which model to call, whether a command is safe, which passage is relevant, whether the agent is actually done.How Jev Works Every call sends a state (text or JSON) plus a dictionary of typed questions.

TypeSafe’s docs define 3 primitives: Choice picks one option from a list and returns a probability per option plus confidence.Score rates the state on ordered rubric levels and returns probabilities plus confidence.Noul returns the probability (0 to 1) that a statement is true.

All questions are evaluated in parallel against the same state in one request.TypeSafe trains Jev with Reinforcement Learning for Calibrated Decisions (RLCD), so higher confidence should track higher accuracy.Choice supports up to 255 options.The main claims, 193.6x faster and 444.

6x cheaper, come from TypeSafe’s own workflow evals.The launch post says these figures sit on the higher end of real-world gains and use GPT-6 Astra and Fable 5.1 as the reference answer.Interactive Explainer Run both Schematic animation, not to scale.

Published ranges: frontier LLMs 3 to 329 s end-to-end (benchmark cited by TypeSafe) vs Jev 70 to 500 ms.Jev answer values are from TypeSafe's quickstart docs.<!-- PANEL 2 --> Pick an agent decision

Ticket triage (support agent) Tool-call gate (coding agent) Model router (multi-model agent) Injection screen (RAG agent)

Act automatically when value ≥ 0.60 STATE→ TYPED QUESTIONS→ JEV→ PROBS + CONFIDENCE→ YOUR CODE

State Gate result

RUN Evaluate <!-- PANEL 3 --> Decisions per day:

Input tokens per decision:

LLM input price ($/MTok):

LLM output tokens per decision: $0Jev / month

$0LLM / month

0xLLM ÷ Jev Monthly spend (30 days)

Jev LLM Jev list price: $0.042 per million input tokens, output free. LLM output priced at 5x input, following TypeSafe's "~5x" comparison. Model-call cost only; excludes reviews, retries and escalations. Estimate, not a quote. <!-- PANEL 4 --> Tap a use case

Each tile shows which Jev primitive does the work and where your code takes over. Sources: docs.typesafe.ai · typesafe.ai/blog · openrouter.ai Built by © Marktechpost (function(){ function post(){try{parent.postMessage({type:'mtp-jev-h',h:document.getElementById('app').offsetHeight+40},'*')}catch(e){}} win