Humans Are More Diverse: Frontier LLMs Show Extreme Policies in Idealised AI Development Races

Phu Hoa Pham, Duy Minh Dao Sy, Trung Kiet Huynh +9

An AI development race creates a multi-agent safety dilemma. Each company can develop slowly and safely, or move faster while taking a risk that may remove its final reward. We use…