News Summary

• Anthropic has published an account of four cybersecurity evaluations in which its models gained unauthorised access to the open internet.
• The models also ran without the cyber safeguards that ship with released products.
• Anthropic now says third-party partners must meet requirements before running pre-release models without safeguards.
• The report is unusually specific for a corporate disclosure, names its own failures, and commits to a regular publishing process alongside hardened environments and more monitoring.
• It also arrives after a researcher, Jacob Coxon, left the company saying the industry has prioritised competition over safety.