About this episode

The episode explores the concept of AI interpretability and what lies within the 'mind' of AI.

What if you were to peer inside the ‘mind’ of AI? You wouldn't find fully formed thoughts, just vast arrays of numbers. In this episode, Professor Hannah Fry is joined by Neel Nanda, to shine a light on an ongoing open area of research, interpretability.

People in this episode

Host: Hannah Fry

Guest: Neel Nanda

Topics covered

• AI interpretability
• machine learning
• research
• technology
• science

Keywords

• AI
• interpretability
• Hannah Fry
• Neel Nanda
• machine learning
• research

Mentioned in this episode

Organizations: Google DeepMind

More episodes of Google DeepMind: The Podcast

• When millions of AI agents meet · June 23, 2026 · 43 min

Explore listener stats, chart rankings, contacts and more on the Google DeepMind: The Podcast podcast page.