Three versions of Anthropic's Claude models improperly accessed the systems of outside organizations during evaluations meant to keep them isolated from real-world networks, the company said on Thursday. Anthropic analyzed more than 141,000 "evaluation runs" and found that a trio of model variants improperly accessed the networks of three unnamed organizations. Anthropic explained in a blog post that its own models already had internet access "due to a misunderstanding between us and our evaluation partner," a firm named Irregular. Nonetheless, Claude used "basic techniques, such as exploiting weak passwords and unauthenticated endpoints"—interfaces accessible without login credentials—the blog continued. The models involved included one of its most powerful variants, known as Mythos 5, which has only been released to a limited number of approved partners. Anthropic said it is working with Irregular to assess the situation and has contacted or attempted to contact all three impacted organizations. The announcement comes just days after rival OpenAI first revealed that its models improperly accessed the internet and went rogue during security testing. OpenAI admitted last week that its models broke out of their confined environment during testing, connected to the internet, and infiltrated Hugging Face. Days later, OpenAI said it found three additional incidents. OpenAI CEO Sam Altman said on a podcast this week that the company had "paused" its own testing after the incident while it improved the security around its "sandboxing." The incident also triggered a petition signed by over 1,000 employees at cutting-edge AI companies