WHAT NEW IN X10.31 SAT

X 上的 AI 合集档案 · 22 个合集 · 63,170 条

jevVIDEO

用 Jev 做即时模型路由:100ms 打分选模型

作者用 Jev 给任务打分,约 100ms 内从 N 个模型中选一个并返回置信度与 needsReview 标记,只把不确定的请求升级给 Claude/GPT。

Francesco
@francescoinweb32026.09.20收录原推发布于 2026.09.20
Francesco @francescoinweb3原推发布于 2026.09.20
在 X 上打开原推

been playing with @typesafeai Jev and honestly - insane. what a time to be a builder found a use case i couldn't stop building: instant model routing. why send every request to your biggest model? Jev scores the task in ~100ms, picks 1 of N, and returns a confidence + a needsReview flag. cheap calls stay cheap - only the uncertain ones escalate to claude/gpt. shipped it as a tiny 0-dep toolkit. jev is the reflex - here's the whole "other half" it plugs into 👇

这条是引用着另一条写的:x.com/francescoinweb3/status/2101258999400116486

x.com/francescoinweb3/status/2101372526513336330采集于 2026.09.20 10:13