The idea of constitutional AI has gone into making anthropics models safer and less likely to spew out harmful stuff. In the, the RL from human feedback method, which me and some colleagues developed at open AI in 2017, you hire some human contractors and you show them some of what the model does. And we can't really explain it much beyond that but I think there are some respects in which they're clearly doing the same things that humans do. It's a tool to move things in one direction or another.
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.