A model has appeared that overturns the premise that "AI
A writer explained that TypeSafe's Jev generates no text, returning only a choice, a score, or a yes/no probability, and argued why that matters.
The original post, translated
A model has appeared that overturns the premise that "AI generates text." TypeSafe's "Jev" does not generate any text at all. The only answers it can return are three formats: "choose one from the options," "return a score," and "return a yes/no probability." Let me explain a little why this is groundbreaking.
Show the original post in its source language ▾
「AIは文章を生成するもの」という前提を崩すモデルが登場しました。 TypeSafeの「Jev」は、テキストを一切生成しません。返せる答えは「選択肢から一つ選ぶ」「スコアを返す」「yes/noの確率を返す」の3形式のみ。なぜそれが画期的なのか、少し説明させてください。
The post above is a machine translation from ja; 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 @tatsuo1020 · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post