The post says TypeSafe's Jev is fast, but lacks reasoning for computer use, which could lead to agents being banned on websites. It imagines an agent that thinks both fast and slow.
Jev by @typesafeai is fast. But lack reasoning for computer use and can lead to agents being banned on websites. LLMs are so slow that sometimes you just prefer to go do the work yourself. What if we could have the benefits of both? An agent that thinks fast and slow, like a
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.
