Why couldn't it be done before, but can be done now?
Used Jev to score every account on a timeline for $0.000032 each, batching ten accounts per call at 96.2% agreement.
The original post, translated
Why couldn't it be done before, but can be done now? Economics have changed. At large model prices, judging each account on the timeline once would be impossible. But Jev is a structured decision model: it doesn't generate text, only returns probabilities, at $0.000032 per account, with 10 accounts merged into one call (consistency rate 96.2%). Only when costs come down can the product hold up.
Show the original post in its source language ▾
为什么以前做不了、现在能做了？经济学变了。 按大模型的价格，给时间线每个账号判一次不可能。而 Jev 是结构化决策模型：不生成文本只回概率，单账号 $0.000032，10 个账号合并成一次调用（一致率 96.2%）。 成本降下来，产品才成立。
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 @peter51888206 · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post