Learning Robust Real-Time Cultural Transmission without Human Data
This work addresses the challenge of developing domain-general social skills for AI agents, which could enable cumulative cultural evolution as a pathway to artificial general intelligence.
The paper tackled the problem of enabling AI agents to perform real-time cultural transmission without relying on pre-collected human data, achieving zero-shot, high recall transmission in novel contexts.
Cultural transmission is the domain-general social skill that allows agents to acquire and use information from each other in real-time with high fidelity and recall. In humans, it is the inheritance process that powers cumulative cultural evolution, expanding our skills, tools and knowledge across generations. We provide a method for generating zero-shot, high recall cultural transmission in artificially intelligent agents. Our agents succeed at real-time cultural transmission from humans in novel contexts without using any pre-collected human data. We identify a surprisingly simple set of ingredients sufficient for generating cultural transmission and develop an evaluation methodology for rigorously assessing it. This paves the way for cultural evolution as an algorithm for developing artificial general intelligence.