The post shares a practical idea: instead of having Jev answer directly, let it select memory candidates to pass to Codex or Claude Code, turning an AI's weakness in writing into a usable context mechanism.
これはめちゃくちゃ勉強になりました。 Jevに回答させるのではなく、CodexやClaude Codeへ渡す記憶候補を選ばせる。文章を書けないAIの特性を、ここまで実用的な仕組みに落とし込む発想がすごいです。
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.
