Did the Hardest A.I. Problem Just Get Much Easier?
27 October 2026 at 09:03
A prominent researcher claims to have a revolutionary approach to “interpretability,” or the science of why A.I. models do what they do. Other experts aren’t so sure.

© Nicole Craine for The New York Times

© Gabriela Bhaskar/The New York Times

© Bizuayehu Tesfaye/Las Vegas Review-Journal/Tribune News Service, via Getty Images