
Can AI Be Harmful? A Conversation with MIT’s Dr. Marzyeh Ghassemi
NEJM AI Grand Rounds
Can You Predict AUC?
AUC should be no better than noise. It's a negative control. I have to admit, this paper involved a little bit of gaslighting of me to a student. And then we started doing these weekly calls where, you know, I felt like I was losing my mind. One of their radiologists also felt like she was losing her mind and came up with some really strange papers. She found x-rays of bird feathers that showed the level of melaninization in the feather. They were using mice for an experiment; they fed them mushrooms before euthanizing them.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.