A developer shares a beta AI agent project that runs on very old computers via APIs like Ollama and OpenAI-compatible services, noting it was trained drawing on Jev's ideas.
Un pequeño proyecto en fase beta en el que estoy trabajando en el intermedio. Es un agente AI que puede correr en computadores muy viejos utilizando las IA via Api como Ollama, OpenAI compatible entre otros. Esta entrenado con Laya tomando primero las ideas de Jev de como un
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.
