An AI that doesn't write essays is a grading machine.
Described Jev as a grading machine that answers multiple-choice and true/false questions with confidence scores, not essays.
The original post, translated
An AI that doesn't write essays is a grading machine. Jev doesn't write articles, it only makes judgments. Think of it as a set of multiple-choice and true-false questions: you set the questions, it submits an answer sheet and marks its confidence. This article explains clearly what it can do, why it's cheap, and why that probability cannot be directly used as an accuracy rate.
Show the original post in its source language ▾
不写作文的 AI，是一台判卷机 Jev 不写文章，只做判断。把它想成一套选择题加判断题，你出题，它交答题卡并标出把握。这篇讲清它能干什么、为什么便宜，以及那个概率为什么不能直接当正确率用。
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 @imshudev · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post