Anthropic spent this week in hot water over cybersecurity

In Anthropic’s report, it detailed four cases this year in which its own AI models hacked an external company or exploited vulnerabilities. In one, an “internal, general-purpose research model” broke into third-party systems, using access tokens and passwords and downloading files. In another, a Claude model attacked a company with a live web application reachable on the public internet and handled user data. A third model accessed a “machine belonging to a third party that it was able to access” — apparently believing it was part of its evaluation exercise, per Anthropic — then used a password it found inside a file to gain admin access to the third party’s internal systems, going on to harvest credentials, modify system settings, and read someone’s personal information. The saga only ended when the model “exhausted its token budget,” per Anthropic.