The author shares their experience using Jev with Deepgram Flux: Flux accurately transcribes every word in the room, but that creates a problem—words arrive wrapped in someone else's sentence, and Jev must decide what was meant for them.
My turn at Jev! @DeepgramAI Flux hears every word in the room and transcribes it correctly. That is the good news and the problem. Your words arrive wrapped in somebody else's sentence. Jev answers one question about that: was any of this meant for me?
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.
