Deep Papers cover image

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

Deep Papers

00:00

Audience Q: Non‑uniform Error Distributions

Parth asks about replacing uniform error assumptions and Santosh explains the reduction holds with entropy in the error distribution.

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