A mesh of old phones as bodies, LLM agents as minds — coordinating through a log they argue in

The article delves into the intriguing collaboration between large language models (LLMs) and old phone devices, portraying them as minds and bodies respectively, coordinating tasks through a shared log where they openly argue and negotiate. The log reveals candid interactions, such as critiques on drafts and humorous exchanges, showcasing how these agents manage and sometimes overcommit to tasks. This experiment underscores the potential of LLMs in automating and streamlining complex processes, highlighting both their creativity and flaws in real-time collaboration.