Anthropic Looks At Some Of Its Alignment Problems

Anthropic has given us its assessment of four ‘recent cybersecurity incidents’ involving Claude that happened during cybersecurity evaluations, three of which were previously known. The report excludes the incident reported by UK AISI. There will also be a METR investigation of these incidents, which unlike the investigation done at OpenAI will be untimed. If This Was Real You Would Never Tell Me It Was Real. Anthropic’s July 30 report said that the models in question believed they were still within their simulations, and not on the open internet.

First reported by Don't Worry About the Vase. This page is a short excerpt; the full text is theirs.