DCC doesn't use Jev to write code but to decide: which memory enters, which skill to load, model routing (Luna vs Terra), and whether a response passes review. Observe or Apply mode, manual or automatic, each point with its own threshold, using your own API key.
O DCC não usa o Jev pra escrever código. Usa pra decidir. • Qual memória entra • Qual skill carregar • Roteamento de modelos (Luna vs Terra) • Se a resposta passa no crivo Modo Observar ou Aplicar. Manual ou automático. Cada ponto com seu próprio limiar. 🔑 Sua API key,
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.
