AI, Mathematics

LLMs are bad at solving math problems not in their training data

For the experiment, the authors — representing a diversity of mathematical fields — each contributed one test question that arose from research they had in the works but had not yet published. They also determined the answers; these solutions are encrypted online and will be released on Feb. 13. “The goal here is to understand the limits — how far can A.I. go beyond its training data and the existing solutions it finds…