Roman Yampolskiy is a computer scientist and professor at the University of Louisville who works on AI safety and security. He is known for research on the theoretical limits of AI controllability, arguing through formal and philosophical analysis that the AI alignment problem may be fundamentally unsolvable.
Background
Yampolskiy is a professor at the University of Louisville, where his work centers on AI safety and security and, in particular, the theoretical limits of AI controllability.
Positions and statements
Yampolskiy argues that no technical alignment solution may be sufficient to guarantee safe superintelligent AI, a position he frames as more pessimistic than most others in the safety community. His arguments draw on computability theory and undecidability results, contending that verifying an AI system's alignment is at least as hard as solving the halting problem.
Yampolskiy holds that if alignment is formally unsolvable, the implication is a stronger case for strict capability controls, moratoriums, or containment-based approaches rather than reliance on alignment research alone. His arguments connect to concerns about Deceptive Alignment and Recursive Self-Improvement (RSI), and his threat model includes uncontrollable recursive self-improvement.
He gave oral evidence to the UK Parliament's Joint Committee on Human Rights on 17 December 2025, listed as Associate Professor at the University of Louisville and described in the committee's report as Director of the Cybersecurity Laboratory there. He recommended a ban on the creation of uncontrolled general superintelligence, which he characterised as a national security threat, saying the risks are such that "the only way to win is not to play the game," and said that "[e]ven if we could completely trust the leaders of large AI companies [...] they are, themselves, not capable of controlling the technology that they are developing." The report records that other witnesses described any threat from AGI as "remote." Its Recommendation 45 would prohibit the development and provision of very powerful AI systems such as artificial general intelligence and artificial superintelligence that risk widespread and very serious harm, including through evading human control (Human Rights and the Regulation of AI (Joint Committee on Human Rights, HC 160, September 2026)).
Relationships
- related: AI Alignment — argues alignment may be formally unsolvable
- related: Recursive Self-Improvement (RSI) — his threat model includes uncontrollable self-improvement
- related: Deceptive Alignment — relevant to his arguments about verification impossibility
- related: Human Rights and the Regulation of AI (Joint Committee on Human Rights, HC 160, September 2026) — his December 2025 evidence to the UK Joint Committee on Human Rights recommending a ban on uncontrolled general superintelligence; Superintelligence