Jev has only been explosively popular for a few days, and

@Yangtze_Seventh 七仔 · Sep 20, 2026 · case #085052 · listed via Jev Hub

Still from the clip posted with this case; watch it in the original post on X.

Compared Jev with open-source rival Laya, noting both output choices, scores, and probabilities for routing and risk tasks rather than long text.

The original post, translated

Jev has only been explosively popular for a few days, and its open-source rival Laya has already appeared. Neither generates long text; instead, they directly output choices, scores, and probabilities, used to complete fast-thinking, fast-decision tasks such as routing, moderation, and risk judgment. The difference is that Jev was developed closed-source for about two years and only provides an API; Laya has about 300–400 million parameters, with all code and weights open, and can be run and fine-tuned locally. On GitHub

Show the original post in its source language ▾

Jev 爆火没几天呢，它的开源对手 Laya 就出现了。两者都不生成长文本，而是直接输出选择、评分和概率，用来完成路由、审核、风险判断等快思考、快决策任务。不同的是，Jev 闭源研发约两年，只提供 API；Laya 约 3～4 亿参数，代码和权重全部开放，可以在本地运行和微调。在 GitHub

The post above is a machine translation from zh; the untranslated text is in the fold-out.

Engagement when collected

Views25K

Likes15

Bookmarks0

Reposts0

Replies0

Quotes0

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 coding & developer tools. 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. Other posts in the same family are on the coding & developer tools page.

🛠️ Coding & developer tools