Deep Papers cover image

Georgia Tech's Santosh Vempala Explains Why Language Models Hallucinate, His Research With OpenAI

Deep Papers

00:00

Audience Q: Penalizing Excessive Abstention

Parth asks about penalties for over‑abstaining and Santosh notes current incentives favor guessing and excessive humility is not a present concern.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app