Roman Yampolskiy

Roman Yampolskiy is a computer scientist at the University of Louisville whose research centers on artificial intelligence safety and security. He is best known for the uncontrollability thesis, which argues that advanced AI systems may possess properties that make them impossible to control reliably, regardless of design intentions. His work explores the theoretical foundations of AI alignment, the risks of artificial superintelligence, and formal approaches to AI safety. Yampolskiy has published extensively on these topics and has contributed to the broader discourse on existential risks from advanced AI systems.

Roman Yampolskiy is a computer scientist and AI safety researcher at the University of Louisville, known for developing the uncontrollability thesis—the argument that sufficiently advanced artificial intelligence systems may be fundamentally uncontrollable by design. His work focuses on AI safety, security, and the theoretical limits of AI alignment.