Back to News

TypeSafe AI's Jev 'System One' model gains traction as agent evaluator

52 points · 20 comments#jev#typesafe-ai#system-one-models#llm-evaluation

TypeSafe AI unveiled Jev, a 'System One' model that outputs typed probabilistic decisions instead of text, and it has quickly gained traction in AI developer communities. LangChain published a Jev-as-a-Judge experiment on September 20 testing it as an agent evaluator, and related posts have drawn 37 million views. Jev supports three judgment types—Noul, Choice, and Score—and is priced at $0.042 per million input tokens with free output.

Coverage timeline

  1. 机器之心机器之心

    最近,AI 圈又冒出了一个新名字:Jev。 https://typesafe.ai/blog/introducing-system-one-models-and-jev 过去几天里,Jev 在 X、GitHub 和 Agent 开发者社区迅速刷屏。有人拿它在 40 秒内分析 724 条实时广告,有人把它接进 Claude Code 清理上下文,有人用它给 AI Agent 做任务验收,还有开发者把 Jev 接入浏览器 Agent,用它决定下一步该点哪个按钮、进入哪个页面。 LangChain 也很快跟进,在 9 月 20 日发布了一项 Jev-as-a-Judge 实验,测试它作为 Agent 评估器的表现。 连 OpenAI「重置之神」Tibo 也为 Jev 宣传。 Jev 到底是什么? 简单来说,它是一种专门处理「判断题」的 AI。 9 月 15 日,TypeSafe AI 正式发布 Jev,并将这类模型称为「System One Models」。按照 TypeSafe 的定义,这类模型接收一段程序状态或文本信息,然后快速返回结构化判断结果以及对应概率。 Jev 刚发布时, 我们就报道过它 。几天过去,它的热度又上了一个台阶,相关推文已有 3700 万人围观。 举个例子,假设一个客服系统收到一封邮件,开发者可以让 Jev 同时判断:「这是销售线索吗?」「用户情绪是否激烈?」「是否需要人工介入?」「属于账单、技术还是销售问题?」 Jev 返回的可能是一组概率:销售线索:0.91;需要人工介入:0.12;技术问题:0.83。应用程序可以立刻根据这些数字进入下一步流程。 Wasp 联合创始人兼 CEO Matija Sosic 也在 X 上发布了一段 45 秒的 Jev 解读视频。 目前 Jev 提供三类核心判断形式:Noul、Choice 和 Score。Noul 负责 Yes/No 类型判断,Choice 从给定选项中选择答案,Score 根据预设标准进行评分。每个结果都会附带概率或置信度,多道问题还可以围绕同一份输入同时进行判断。 这套设计让 Jev 很快找到了一个爆发式增长的应用场景:给 Agent 当「裁判」。 今天的 AI Agent 经常需要连续完成几十甚至几百个步骤。写代码、调用工具、搜索网页、修改文件之后,系统还需要判断任务是否已经完成。这类问题恰好

  2. Simon Willison

    Last week TypeSafe AI unveiled Jev , their first example of a new category of model that they are calling "System One models" (I'm with Maggie Appleton, I think "decision models" is a better name for these). Jev is an interesting variant on the usual LLM format: it still accepts text inputs, but instead of text output it returns floating point numbers corresponding to categories, yes/no questions, ratings, and associated confidence scores. TypeSafe describe Jev like this: Think of Jev as a frontier-intelligence function call: unstructured state in, typed probabilistic decisions out. It's also very fast, and really cheap . Regular LLMs are priced in terms of input and output tokens, with output generally charged at significantly higher rates. Jev charges only for input - output is free - and the input price of their first model is $0.042 per million tokens - cheaper even than OpenAI's GPT-5 Nano ($0.05/million). Jev lets you ask questions about text or semi-structured data. You compose

Related stories

  • TypeSafe AI Raises ~$870M at $7.5B Valuation Led by a16z

    TypeSafe AI, the startup behind the viral Jev model, has raised approximately $870 million in a funding round led by Andreessen Horowitz (a16z), with participation from Sequoia and others. The round values the company at $7.5 billion, just weeks after Jev's launch.

    1 reports · 1 sources
  • TypeSafe AI's Jev model draws attention; NeurIPS 2025 ConfTuner explored similar probability calibration

    TypeSafe AI's Jev model, which outputs decisions plus probabilities from input states, has gained attention for its focus on probability calibration. Coverage highlights its conceptual alignment with the NeurIPS 2025 paper ConfTuner, whose Tokenized Brier Score method trains the probability distribution over candidate confidence tokens to better reflect true accuracy. Jev is not open-sourced, and its architecture and training details remain undisclosed.

    1 reports · 1 sources
  • Prime Intellect launches Prime Inference serving platform for open models

    Prime Intellect announced the launch of Prime Inference, a serving platform for frontier open-source models offering resilient serverless and reserved serving across multiple datacenters. The platform's production architecture includes prefill/decode optimization, NVFP4 KV compression, and NIXL transfer, as demonstrated in its GLM-5.3 deployment on GB200 NVL72.

    2 reports · 1 sources
  • Cloudflare releases open-weight multimodal decision models Clef and Clef-flash

    Cloudflare has introduced Clef and Clef-flash, open-weight multimodal decision models based on Qwen3.8-27B and Qwen3.5-9B respectively. The company claims these models outperform Jev in both intelligence and speed, and they are available on Hugging Face for local deployment.

    1 reports · 1 sources

News updates every hour. Subscribe in your RSS reader to get new stories automatically.

Subscribe