This prototype observes conversations in real time in Jev, updating exploration↔convergence, resolution↔pending, and disagreement↔agreement with each utterance to visualize the meeting state.
I prototyped a sensor in Jev that observes conversations in real time. With each utterance, ・Exploration ↔ Convergence ・Resolution ↔ Pending ・Disagreement ↔ Agreement are updated to visualize the state of the meeting. It could also be used for real-time
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.
