2024-12-26
Interesting to think about the difficulty in creating *good* evals. [embedded post]
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
more interesting than it sounds! LinkedIn: Ross Dawson : The frontier of “evals”. Evaluations comparing AI ahd human capabilities are evolving rapidly as AI rapidly leaves existin...