The demo showcases an AI assistant that understands conversation context without a wake word and responds only when necessary, built with Jev and GPT-6 Astra, with scenario creation and testing handled by AI.
I had them create a demo of an AI assistant that reads the context of the conversation without an activation word and only responds when necessary, using Jev × GPT-6 Astra. From scenario creation to functionality testing, I'm leaving it all to the AI. For the voice, I'm using
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.
