But in traditional large language models, there is actually
A commenter questioned whether Jev's internalized reasoning would match traditional LLMs that improve accuracy with deeper thinking.
The original post, translated
But in traditional large language models, there is actually an experimental conclusion that the deeper the thinking, the more accurate the task completion. In the JEV mode, it internalizes thinking into its model, so I'm not sure whether its actual execution accuracy will exceed that of traditional models.
Show the original post in its source language ▾
但是在传统的大语言模型里面，其实有一个实验性的一个结论，就是思考的越深入，任务完成的越准确。JEV 这种模式的话，它是把思考内化到它的模型里面，所以我不太确定它这种真的在执行的准确性上会超过传统模型。
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 @attaalong · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post