A look at the more challenging AI evaluations emerging in response to the rapid progress of models, including FrontierMath, Humanity’s Last Exam, and RE-Bench (Tharin Pillay/Time)

Tharin Pillay / Time:
A look at the more challenging AI evaluations emerging in response to the rapid progress of models, including FrontierMath, Humanity’s Last Exam, and RE-Bench  —  Despite their expertise, AI developers don’t always know what their most advanced systems are capable of—at least, not at first.