The post says Jev is being used in Claude Code, browser agents, and judges with Choice/Score/Noul instead of paragraphs, and mentions TypeSafe's vendor eval figures.
This week's agent stack is still paying a chatbot tax for if-statements. Jev is what people are stuffing into Claude Code, browser agents, and judges — Choice/Score/Noul, not a paragraph. TypeSafe's 20-200x / 40-400x is vendor eval, high end. The actual scene: waitlist,
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.
