TypeSafe AI 发布 System One 模型 Jev 的 20 个智能体用例
20 Agentic Use Cases of TypeSafe AI’s Jev
TypeSafe AI 上周发布首个 System One 模型 Jev，它不做对话、写代码或摘要，而是接收非结构化状态并返回带校准概率的类型化决策，适合智能体循环中的小判断，例如调用哪个模型、命令是否安全、哪段内容相关、智能体是否已完成。每次调用发送状态加一组类型化问题，所有问题在同一请求中并行评估，Choice 最多支持 255 个选项，并用 RLCD 训练使置信度与准确率挂钩。官方称其比逐 token 的 LLM 快 193.6 倍、便宜 444.6 倍，该数据来自 TypeSafe 自身工作流评测；OpenRouter 的 Banking77 测试中，Jev 准确率比 Claude Opus 5 低 3.3 个百分点，中位速度快 13 倍，成本约为其 1/22。
正文
当前显示原文，中文全文译文尚未就绪。
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.
Every call sends a state (text or JSON) plus a dictionary of typed questions. TypeSafe’s docs define 3 primitives:
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.
Race a token-by-token LLM against Jev’s single pass, move a confidence threshold to see how code gates each decision, estimate monthly cost, and browse all 20 use cases.
Open-model figures are self-reported by each project on its own harness, so treat them as directional. OpenRouter’s Banking77 test is the cleanest head-to-head: Jev was 3.3 points less accurate than Claude Opus 5, 13x faster at the median, and about 1/22 the cost.