Just sat down with Curt Jaimungal on Theories of Everything @TOEwithCurt to talk through ...
x.com
AI safety researcher Roman Yampolskiy joins the Theories of Everything podcast — and the conversation likely touches on whether superintelligent AI is inherently uncontrollable, a question that cuts to the heart of complexity theory and existential risk.
AI Alignment TheoryComputability TheoryExistential RiskControl Problem
Theory Briefing
- Dr. Roman Yampolskiy, a leading AI safety scholar, appeared on Curt Jaimungal's Theories of Everything podcast to discuss AI risk frameworks.
- Yampolskiy's work centers on the thesis that advanced AI systems may be fundamentally uncontrollable — a direct challenge to mainstream alignment optimism.
- The conversation sits at the crossroads of computability theory and existential risk, asking whether safety is even a solvable problem in principle.