Mathematical paradoxes unearth the boundaries of AI
Matthew J. Colbrook, Vegard Antun, Anders Hansen · TheScienceBreaker · 2022
Instability is AI's Achilles’ heel. We show the following paradox: there are cases where stable and accurate AI exists, but it can never be trained by any algorithm. We initiate a foundations theory for when AI can be trained - such a programme will shape political and legal decision-making in the coming decades, and have a significant impact on markets for AI technologies.