Q&A with mathematicians behind the "First Proof" experiment, which tests AI's mathematical competence on questions drawn from the authors' unpublished research (Siobhan Roberts/New York Times)

Siobhan Roberts / New York Times: Q&A with mathematicians behind the “First Proof” experiment, which tests AI's mathematical competence on questions drawn from the authors' unpublished research  —  Large language models struggle to solve research-level math questions.  It takes a human to measure just how poorly they perform.