Google Eats Rocks + A Win for A.I. Interpretability + Safety Vibe Check

This week, Google found itself in more turmoil, this time over its new AI Overviews feature and a trove of leaked internal documents. Then Josh Batson, a researcher at the A.I. startup Anthropic, joins us to explain how an experiment that made the chatbot Claude obsessed with the Golden Gate Bridge represents a major breakthrough in understanding how large language models work. And finally, we take a look at recent developments in A.I. safety, after Casey’s early access to OpenAI’s new souped-up voice assistant was taken away for safety reasons.

Guests:

• Josh Batson, research scientist at Anthropic

Additional Reading: 

• Google’s A.I. Search Errors Cause a Furor Online
• Google Confirms the Leaked Search Documents are Real
• Mapping the Mind of a Large Language Model
• A.I. Firms Musn’t Govern Themselves, Say Ex-Members of OpenAI’s Board

We want to hear from you. Email us at hardfork@nytimes.com. Find “Hard Fork” on YouTube and TikTok.

Soon, you’ll need a subscription to keep full access to this show, and to other New York Times podcasts, on Apple Podcasts and Spotify. Don’t miss out on exploring all of our shows, featuring everything from politics to pop culture. Subscribe today at nytimes.com/podcasts.