I still think that jev is a bit overheated.
Argued Jev is overhyped and that decision quality depends on the preparation, materials, and logic behind each call.
The original post, translated
I still think that jev is a bit overheated. It's good, but it depends on the scenario. The most important part of decision-making is not the moment of making the decision, but the preparation for the decision, the materials provided, and the logic behind it. The jev model's own cognition + state determines its upper limit. It just depends on how humans can combine this set of raw materials. In addition, the output of a decision is of great significance, after all, this is a decision! So, should we treat jev
Show the original post in its source language ▾
我还是觉得吧，jev 有点过热了。它很好，但要分场景。 决策最重要的不是做决定那一下，而是为决策所做的准备，提供的素材，以及背后的逻辑。 jev 模型自身的认知 + state 决定了它的上限。就看人类能如何组合这套原材料了。 此外，决策的产出是有重要意义的，毕竟这是决策嘛！那么，要不要对 jev
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.
Related Jev cases
This LangChain share is quite interesting.
AgentsDev tools
Jev hands-on: the basic gameplay of this explosively
Keep browsing: all 1173 Jev cases · more from @verysmallwoods · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post