The author shares that inserting a Jev (reflexes) card before the LLM lets Jev sort worker reports and pass only necessary info to Commander Astra, drastically cutting token usage from 330k in the same exchange.
Maybe it's time to stop feeding everything to the LLM (brain) The result of inserting one "Jev (reflexes)" card in the front stage is insane ・Jev sorts the workers' reports ・Only passes necessary info to Commander Astra With just this, the same exchange goes from 【330k →
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.
