Introduces TypeSafe AI's Jev model for fast decisions inside agents: classify data, score it, pick an option; the author bets browser automation will be the big use case.
Jev is here: TypeSafe AI's model for fast decisions inside agents. Classify data, score it, pick an option. My bet is browser automation will be the big use case. The demos I've seen look seriously fast.
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.
