Jev is so popular, it's flooding X, so next week's "100
Compared Jev to a classic multiclass classifier closer to traditional machine learning than LLMs, and planned a follow-up on real use cases.
The original post, translated
Jev is so popular, it's flooding X, so next week's "100 Questions" has its topic, let the bullets fly for a while, don't just talk big, when the time comes I want to see where it's used, how it's used, and how effective it is, currently from the few posts I've browsed, Jev is a classic multiclass classifier, under the circumstances of handling logic and output constraints, in a way, Jev is closer to a traditional machine learning model rather than a large language model, save
Show the original post in its source language ▾
Jev 这么火，在 x 上刷屏了， 那么下周的《100 个问题》就有选题了， 让子弹飞一会，别口嗨， 到时候我倒要看看用在哪里、怎么用、效果如何， 目前我刷了几个帖子来看， Jev 是一个经典的多元分类器， 处理逻辑和输出约束的情况下， 某种程度上讲，Jev 更接近传统机器学习模型，而非大语言模型， 省
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 @AgiRay1015 · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post