Ambiance: A Unix-Inspired Harness to Free LLMs from the Chat Pane

Towards a Harness That Can Do Anything

I designed Ambiance to liberate LLMs from chat interfaces by leveraging their existing knowledge of Unix systems. By treating everything as files within a familiar hierarchy, this harness reduces cognitive load and enables self-healing agents. The system uses a custom kernel to manage events, ensuring agents operate efficiently without wasting tokens on learning new environments.

"The idea behind Ambiance is simple: the model's priors are the cheapest resource you have, so a harness built out of things the model already knows will always beat one it has to be taught."