Jev has been exploding in popularity recently.
@hanakoxbt19K followers
29,894 views
16 Comments
Comments from the original post on X (Twitter)

@flock_io
Try THIS/THAT if you want a faster and more accurate decision model
7 likes

@oliver_yu9
This is exactly the kind of setup I’ve been testing on Mac. I put Laya behind a Jev-compatible API and tested 7 released Jev clients against it unchanged. Then ran it beside a saturated 27B local LLM — short decisions stayed at 47.2ms P99 at 8 req/s. Local decision layer on MLX GPU + Apple Neural Engine:
1 like

@ChrisEdouardo
Dont try to replace the reasoning part by the fast part.every thing has a cost! Great browser Use agents need to learn and only use JEV on a known pattern. Be careful. System 1 alone has no future in production! It is what it is. But for fun, yeah. why Not?
1 like

@TevfikTa1
还没玩过这个工具 赶紧去试试效率如何

@0xMukay
jev-claude routing Claude Code's own judgment calls through Jev before risky commands execute is the architecture where the decision model audits the generation model — and that is the correct order of operations.

@AlysaPorce2uft
这效率确实有点东西赶紧去试试

@Web3BPP
The Jev API looks wild, especially with agents deciding actions dynamically

@Vaeshkar
All I know is I have all that since last year

@0xyumio
Jev started as a decision model and somehow ended up speedrunning every side quest in computer science. Browser agents, Mario, drones, robot arms, SQL, pixel art… bro refuses to stay in one lane.

@johncubahiro12
这玩意儿实测确实快得离谱建议赶紧上手

@w_sof6
Avoiding frontier models for simple decisions is clever, but does Jev's router really beat just hardcoding a few if/else statements?

@_alphashark_
At 2.5 Hz, jev-drone's loop leaves you 400 ms per decision, so that's the latency to compare your own Jev calls against.

@storylove1206
This is a fantastic collection of Jev projects.

@0xthe0
fuzzy judgment directly inside SQL feels slightly cursed but insanely useful

@slash1sol
yep worth it

@ai_studioxyz
Keyword-Tools sind Commodity. Der echte Vorrteil: Audit-Workflows automatisieren, manuelle Klickarbeit sparen, Zeit für Beurteilung und Risikofragen gewinnen.
