Understanding the inner thoughts of AI

Timecodes

• 00:00 Introduction 
• 02:41 Motivation for interpretability research
• 04:01 Mechanistic interpretability 
• 08:14 Chain of thought monitoring 
• 18:14 Interpretability techniques 
• 35:00 Auditing models for safety 
• 48:53 What comes next for interpretability 

Please leave us a review on Spotify or Apple Podcasts if you enjoyed this episode. We always want to hear from our audience whether that's in the form of feedback, new idea or a guest recommendation!

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.