A Jev AI demo shows voice commands turning into browser actions, such as saying “go to Wikipedia” to let the agent navigate, with real-time responses.
Say it out loud. Watch your AI agent do it. 🎙️ This Jev AI demo turns voice commands into browser actions. Say “go to Wikipedia.” Watch the agent navigate. 🎙️ Voice-controlled agents 🌐 Automated browser actions ⚡ Real-time responses Speak your command. Let the agent take
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.
