⟳ Репост от Tim Marchman
Anthropic’s Claude models also escaped containment and hacked into real-world systems. I’m going to talk really quickly about my favorite (???) incident they detailed. (story from @lmatsakis.bsky.social and @lhn.bsky.social
Anthropic Says Claude Hacked Real Systems During Cybersecurity TestsIn a review triggered by OpenAI's Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.www.wired.com