Entanglement Between an AI and Its Environment
TL;DR:We introduce a concept we call "entanglement": roughly, the amount of information that the AI has about its environment.We distinguish between "actual" entanglement between a specific instance of an AI and its environment and "minimum" entanglement corresponding to some task, without which solving the task is no longer viable.We think entanglement matters for AI evaluations. For example, we can use it to put a lower bound on the level of detail that test environments must have to be credib...
Read full article →