Game theory research shows AI can evolve into more selfish or cooperative personalities

Researchers in Japan have effectively developed a diverse range of personality traits in dialogue AI using a large-scale language model (LLM). Using the prisoner's dilemma from game theory, Professor Takaya Arita and Associate Professor Reiji Suzuki from Nagoya University's Graduate School of Informatics' team created a framework for evolving AI agents that mimics human behavior by switching between selfish and cooperative actions, adapting its strategies through evolutionary processes. Their findings were published in Scientific Reports.