Brothers, the hottest model in Silicon Valley these past
Explained that Jev takes predefined options like refund risk low/medium/high and returns a label instead of prose.
The original post, translated
Brothers, the hottest model in Silicon Valley these past two days is actually a "mute." It's called Jev, from TypeSafe AI. It can't chat, can't write code, can't write articles, and can't even say a complete sentence. It only does one thing: make judgments. For example, when a customer service email comes in, you tell it the options in advance: `Refund risk = low / medium / high` It doesn't analyze a bunch with you, it directly returns: `low:
Show the original post in its source language ▾
兄弟们，这两天硅谷最火的模型，居然是个“哑巴”。 它叫 Jev，出自 TypeSafe AI。 不能聊天，不能写代码，不能写文章，甚至连一句完整的话都不会说。 它只干一件事：做判断。 比如一封客服邮件进来，你提前告诉它选项： `退款风险 = low / medium / high` 它不跟你分析一堆，直接返回： `low:
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 @xd1309007813404 · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post