WHAT NEW IN X11.03 TUE

AI collections from X · 22 collections · 65,264 posts

jevARTICLE

Scoring content, recruiting and video editing with Jev

The author shares how they use Jev to score work in content, recruiting and video editing, noting that a high score is not proof the work is good and some checks still need human judgment.

ericosiu
@ericosiuArchived 2026.09.23Originally posted 2026.09.22

What this article says

作者以「Jev 用于 AI agent 时,高分并不等于工作做得好」为核心论点,分享自己在内容生产、招聘筛选和视频剪辑三条工作流中实际使用 Jev 的经验。文章承认 Jev 在结构化评分上的效率,但强调评分只是代理指标:模型给出的高置信度分数可能掩盖事实错误、风格偏差或语境缺失,因此在这些环节仍保留人工复核。结论是 Jev 适合作为决策与排序的加速层,但不应被当作质量证明,需要为每类任务单独设计校验点。

Jev for AI agents: a high score is not proof that the work is good.

Here’s how I’m using Jev across content, recruiting and video editing—and where the checks still need human judgment. https://x.com/i/article/2102061001810268160

ericosiu @ericosiuOriginally posted 2026.09.22
Open original on X
x.com/ericosiu/status/2102180138645610924Archived 2026.09.23 10:32