Roman Yampolskiy

Associate Professor of Computer Science, University of Louisville

About

Roman Yampolskiy (born 1979 in Riga, then part of the Soviet Union) is a computer scientist and Associate Professor in the Department of Computer Engineering and Computer Science at the University of Louisville's Speed School of Engineering, where he founded and directs the Cyber Security Lab. He holds a PhD from the University at Buffalo and is credited with coining the term "AI safety" in a 2011 publication, work that helped establish the field as an academic discipline in its own right. His research argues that the standard optimism about AI safety — that with enough time, funding, and careful engineering a superintelligent system could be kept controllable indefinitely — rests on an unproven assumption; his papers on AI unpredictability, unexplainability, and uncontrollability contend that no system smart enough to be useful can be made safe against every possible failure, across every malicious actor and every round of self-improvement. He has authored several books, including Artificial Superintelligence: A Futuristic Approach (2016) and AI: Unexplainable, Unpredictable, Uncontrollable (2024), and continues to publish widely on AI safety, AI boxing, and cybersecurity.

Key Contributions

Coined the term "AI safety" in a 2011 publication, helping establish it as a distinct field of research
Founded and directs the Cyber Security Lab at the University of Louisville's Speed School of Engineering
Argues across a body of peer-reviewed research that controlling a superintelligent AI system is not merely difficult but provably unsolvable — comparable to building a perpetual motion machine that must never fail
Introduced and studied "AI boxing" — strategies for physically and informationally containing a potentially dangerous AI system — and the theoretical limits on how well such strategies can work
Authored Artificial Superintelligence: A Futuristic Approach (2016) and AI: Unexplainable, Unpredictable, Uncontrollable (2024), alongside more than 100 publications on AI safety and cybersecurity

Videos & Interviews

AI Emergency: The AI Labs Are Lying To Everyone, He Says 99% Chance Of Extinction | Roman Yampolskiy

A four-way debate, which the title does not say. Ed Zitron, Andrew McAfee, Nate Soares and Roman Yampolskiy each wrote a probability of extinction in an envelope; the headline takes the highest of the four and hangs it on one name. The spread is the substance — the host reads out 99% and a rounding-error zero within seconds of each other.

View Details

Connections

Nate Soares

In conversation

President, Machine Intelligence Research Institute (MIRI)

They sat on the same side of a four-way debate recorded on this site, and the closeness hides a real difference. Soares argues that no one knows how to align a superintelligence and that building one now kills everyone, a problem of time and method; Yampolskiy argues the problem has the wrong shape, like a perpetual-motion machine, since a system that must never err across every interaction and every round of self-improvement cannot be controlled indefinitely. Both want a ban, and only one thinks more time would help.

youtube.com