A developer uses TypeSafe's Jev to give a character a memory that judges each message: whether it's worth keeping, which exact words matter, where it fits, and if anything is outdated—all decided in one call.
I'm using @typesafeai's Jev to give a character a memory that judges. Every message: is this worth keeping? Which exact words? Where does it fit? Is anything she knew now out of date? What does it remind her of? One call decides all of it. Building this at @mutuals_inc
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.
