WHAT NEW IN X10.31 SAT

AI collections from X · 22 collections · 61,986 posts

jevPOST

Hands-on review places Jev as a production judgment component after four failures

A hands-on review strips away the hype around Jev, runs test cases and records four failures, concluding that it is not a cheaper large model but a judgment component in production, best used with high-confidence cases passing automatically and low-confidence ones sent to a large model.

Mai Yang
@MaiYangAIArchived 2026.09.20Originally posted 2026.09.19
Mai Yang @MaiYangAIOriginally posted 2026.09.19
Open original on X

这篇把 Jev 网上那股虚火剔得比较干净。真跑过用例、也写了四次失败。结论我认:它不是更便宜的大模型,是生产里的判断零件;更值得盯的是「高把握自动过,低把握再问大模型」。关心 agent 编排的,值得读完。 https://t.co/1fov1wLCbj

This post quotes another post: x.com/i/web/status/2101132667056185544

x.com/maiyangai/status/2101158425057022176Archived 2026.09.20 11:14