Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates

By Elias Najarro · Paper · cs.CL

Complexity and interpretability rarely coincide: systems rich enough for complex behaviours to emerge are usually too opaque to question, while transparent ones are too simple for anything complex to emerge. A single large language model (LLM) is a static artefact, hardly exhibit

AI Agents · Cs.cl

View original

HomeResourceLoading…