The model's patterns of lights reveal concepts like the Golden Gate Bridge, forming a conceptual map of Claude's inner world. Research has identified around 10 million features corresponding to real concepts, including individuals like scientists, poets, and ways of responding to questions. These features range from specific entities to abstract notions like inner conflict and political tensions.
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:
We want to hear from you. Email us at hardfork@nytimes.com. Find “Hard Fork” on YouTube and TikTok.