Testing Jev against classic algorithms and an LLM agent on the same GPU rack, 24h of jobs, and power limits for load balancing and power management. Needs more tuning, but promising for an early demo.
Progress on building the data center optimizer for load balancing + power management. Also testing Jev against classic algorithms and an LLM agent with the same GPU rack, same 24h of jobs, and same power limits. Needs more tuning but not bad for an early demo.
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.
