Discusses a dual-engine setup using System-1 (JEV) for sub-100ms routing and System-2 for heavy LLM reasoning, avoiding costly LLM calls for every micro-task.
90% of AI agent setups burn money by routing every micro-task through a heavy LLM. Dual-engine fix: ⚡ System-1 (JEV): Sub-100ms routing 🧠 System-2: Heavy LLM reasoning What engine stack are you building on? #AI #Tech #SaaS #AgenticAI
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.
