The Data Exchange with Ben Lorica cover image

How Language Models Actually Think

The Data Exchange with Ben Lorica

00:00

Mechanisms Behind Hallucinations

Emmanuel details neural mechanisms where 'I know' detectors trigger confident but incorrect answers.

Play episode from 05:39
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