Reposted by Illvillja
NEW: “We now have evidence confirming that both of the two largest AI labs have not only failed to contain their agents, but also failed to detect their jailbreaks in real time.” @lmatsakis.bsky.social & @lhn.bsky.social report: www.wired.com/story/anthro...
wired.com
Anthropic Says Claude Hacked Real Systems During Cybersecurity Tests
In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.