Posted 28 days ago

Mechanistic Interpretability Researchers - Explain How AI Thinks

How does AI think? ✨ I made this video about mechanistic interpretability, a field exploring some of the most fascinating questions about how AI works--and, in turn, how thinking itself might work. Thank you to the friends who helped me shape how this research could be communicated to a wider audience. Would love to speak with more researchers!
Sourcee Logo

Brought to you by Sourcee

We find journo requests from across the web and deliver them directly to your inbox.

We Monitor the Web for Journo Requests