Roman Yampolskiy: AI Can’t Be Controlled — and We’re Building It Anyway - #558

About this episode

Roman Yampolskiy discusses the challenges of controlling superintelligent AI and the implications of his findings on AI safety.

Roman Yampolskiy has spent two decades trying to prove that superintelligent AI can be controlled. He couldn’t. I invited him on to make his case. Subscribe if you want science with evidence, not speculation. Roman is a professor of computer science at the University of Louisville and one of the earliest researchers in AI safety. His book AI: Unexplainable, Unpredictable, Uncontrollable started as an attempt to solve the alignment problem. After decades of work, it became a proof that the problem cannot be solved. Not difficult. Mathematically impossible. I push back hard. We go after the Einstein test: can a large language model trained only on pre-1911 physics reproduce what Einstein did with the same data? We ran that experiment. It failed. Roman and I disagree about what that means. We also get into the halting problem and what it actually tells us about predicting smarter-than-human behavior, whether value alignment is a real problem or a well-funded category error, the case for a government moratorium on frontier model development, and why Roman thinks giving an AI agent access to your computer is the dumbest thing a smart person can do. What you’ll hear: Whether AI control…

People in this episode

Host: Brian Keating

Guest: Roman Yampolskiy

Topics covered

• AI control
• superintelligence
• AI safety
• alignment problem
• halting problem
• government moratorium

Keywords

• AI control
• superintelligent AI
• alignment problem
• halting problem
• AI safety
• government moratorium
• Einstein test

Mentioned in this episode

Organizations: University of Louisville

Books & works: AI: Unexplainable, Unpredictable, Uncontrollable

More episodes of Into the Impossible With Brian Keating

• OpenAI’s Navier–Stokes Claim: Is This What AGI Looks Like? with Emad Mostaque · September 9, 2026 · 1h 19m
• Roman Yampolskiy vs Emad Mostaque: I Was The Only Optimist - #569 · September 1, 2026 · 58 min
• The Universe Didn’t Come From Nothing | The Peter McCormack Show · August 28, 2026 · 1h 46m
• The Physics Reason AI Works When It Shouldn’t - #568 · August 25, 2026 · 1h 18m
• Engineering Chair: Most People Should Not Go To College - #567 · August 18, 2026 · 1h 0m
• John Martinis: The Nobel Physicist Behind Macroscopic Quantum Tunneling - #566 · August 11, 2026 · 49 min