devwithjev
— reading now— views
Submit a build

Jev Selects From Predefined Answers

GucciChang connected Jev, a TypeSafe AI judgment model, to two real work projects and ran A/B tests. Jev selects from answers prepared in advance and provides a probability rather than generating content.

GucciChang@gucci0915𝕏
全網都在討論的新模型 Jev,是 TypeSafe AI 做的判斷模型:不生成內容,只從事先列好的答案裡挑一個,並附上機率。官方說它比常見大型模型最高快 193.6 倍,成本不到四百分之一。 我把它接進自己兩個真實工作做了 AB 實測。影片裡有它跟 ChatGPT、Claude 這類大型模型怎麼分工、兩組實測的結果,以及用之前先問的四個問題。
Sep 22, 2026X postsView on X
The video discusses how Jev and large models such as ChatGPT and Claude can divide the work. It also presents the results of the two tests and four questions to ask before using Jev.

Also filed under Triage & routing

  • How to Build Things with Jev & OpenJevs

    How to Build Things with Jev & OpenJevs In this video, we build a model router using both the API-based original Jev and also using Semif. ‍ Github: code will be up in ...

  • Jev is HERE. How to use it

    Jev is HERE. How to use it In this episode, I talk with Ryan Vogel about Jev, a new type of AI built for classification. Ryan shows how Jev takes an input plus ...

  • Jev-Shaped Classification Wrapper

    jevper is a Jev-shaped classification wrapper over OpenAI-compatible clients that returns probabilities and confidence.

  • Local Jev Protocol Multi-Upstream Router

    jev-switch is a local multi-upstream router for the Jev protocol with a Rust backend and React interface.