Recently, you've probably been flooded with Jev.
Made a video showing how to wire Jev into WorkBuddy, framing it as a choice/score/yes-no engine rather than a chat replacement.
The original post, translated
Recently, you've probably been flooded with Jev. But how do you use it? One video teaches you how to integrate Jev into WorkBuddy. After integrating it, what should you use it for? It can't chat, can't write code, and can't spit out a single word. It only answers three types of questions: which one to choose, what score to give, or yes or no. Although the answers it gives are most likely correct, that doesn't mean it won't make mistakes. So what it's best suited for is not 'replacing large models'.
Show the original post in its source language ▾
最近应该都被Jev 刷屏了。 但是该怎么玩呢？ 一个视频教你在 WorkBuddy 中接入 Jev。 接入完该拿它来干什么呢？ 它不会聊天、不会写代码、一个字都吐不出来。 只回答三种题：选哪个、打几分、是或否。 虽然大概率给的答案是正确的，但不代表不会出错。 所以最适合它的，不是「替代大模型」。
The post above is a machine translation from zh; the untranslated text is in the fold-out.
Engagement when collected
Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.
Where this case fits
Filed under general Jev builds. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Browse the full case library for the work it sits next to.
Keep browsing: all 1173 Jev cases · more from @aehyok · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post