X · @natolambert
· X / Twitter
RT Miles Brundage: Our innocent harness misconfig, their egregious misalignment
RT Miles BrundageOur innocent harness misconfig, their egregious misalignmentAnthropic: In a review of our cybersecurity evaluations, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to t