In terms of anthropic itself, one thing I wanted us always to look at the safety component of this first and foremost. And so mechanistic interpretability, which probably does have too long a name, is the science of figuring out what's going on inside the models. The hope is that if we're worried about an AI system behaving in ways very different than we would expect or with motivations very different than they would expect, could we think of it a little like an X-ray or a brain scan?
Dario Amodei has been anxious about A.I. since before it was cool to be anxious about A.I. After a few years working at OpenAI, he decided to do something about that anxiety. The result was Claude: an A.I.-powered chatbot built by Anthropic, Mr. Amodei’s A.I. start-up.
Today, Mr. Amodei joins Kevin and Casey to talk about A.I. anxiety and why it’s so difficult to build A.I. safely.
Plus, we watched Netflix’s “Deep Fake Love.”
Today’s Guest:
- Dario Amodei is the chief executive of Anthropic, a safety-focused A.I. start-up
Additional Reading:
- Kevin spent several weeks at Anthropic’s San Francisco headquarters. Read about his experience here.
- Claude is Anthropic’s safety-focused chatbot.