The post notes two emerging layers around coding agents: Orca coordinates multiple agents in parallel worktrees, while TypeSafe's Jev makes fast, typed decisions instead of generating chat text, potentially handling routing, scoring, and approvals.
Two interesting layers are emerging around coding agents: @orca_build coordinates multiple agents in parallel worktrees. @typesafeai Jev makes fast, typed decisions instead of generating chat text. One manages execution. The other can handle routing, scoring, approvals,
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.
