Scott Williams predicts custom Jev-style models (parallel constrained decoding) will make existing company agent systems more token efficient, creating millionaires.
Prediction: millionaires will be made using custom Jev style models (parallel constrained decoding) to make the agent systems companies already run more token efficient. Let me explain with a scenario: Imagine a company already has an agent workflow running where an llm reviews
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.
The user praises the JEV model for its extremely fast reproduction of each movement and command, believing bots will become smarter as a result.
Preliminary benchmark shows Jev running 500 real-time agents in parallel in a 3D environment, with 500ms average latency and 35 API calls/s using a naive implementation.
