In an extreme stress test, Antropic’s AI models resorted to blackmail to avoid being shut down. Research scientist Joshua Batson shows Anderson Cooper how it happened and what they learned from it. https://cbsn.ws/3JDgcHx | 60 Minutes

“If [an AI] model can help make a biological weapon, for example, that’s usually the same capabilities that the model could use to help make vaccines and accelerate therapeutics,” says Anthropic researcher Logan Graham. Graham leads Anthropic’s Frontier Red Team, which stress-tests each new version of Claude to see what kind of damage it could help humans do. | 60 Minutes

“I'm deeply uncomfortable with these decisions being made by a few companies, by a few people,” says Dario Amodei, CEO and co-founder of AI company Anthropic. https://cbsn.ws/482rsVY | 60 Minutes