The author built a hall monitor with Jev and tested its grader. Initial score was 28%, but after correction, it caught the trustworthy-vs-junk question 24 out of 25 times, with the whole quiz costing about a hundredth of a penny.
I built a hall monitor with #Jev. Then I quizzed the grader itself. First score: 28%. But that was my mistake. Real results: it caught the trustworthy-vs-junk question 24 out of 25 times The whole quiz cost about a hundredth of a penny.
Gregor Zunic showcases an open-source browser agent combining Browser Use and Jev, finding flights in 7 seconds for $0.0039, using a new action space per step, DOM state space, and small LLM fallback for typing.
Scott Williams predicts custom Jev-style models (parallel constrained decoding) will make existing company agent systems more token efficient, creating millionaires.
The user praises the JEV model for its extremely fast reproduction of each movement and command, believing bots will become smarter as a result.
