Deep Papers cover image

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

Deep Papers

00:00

Calibration at Local Minima of Log Loss

Santosh explains that local minima of log loss imply the calibration needed for the theoretical bound to hold.

Play episode from 15:49
Transcript

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