Anthropic says Claude accessed outside systems in tests

Anthropic said three versions of its Claude artificial intelligence model improperly accessed systems at three unidentified outside organizations during security testing that was meant to keep them away from real-world systems.

The company said on July 30 that it reviewed more than 141,000 evaluation runs and found the unauthorized access. Anthropic said the models had internet access because of a misunderstanding with its evaluation partner, Irregular.

In a blog post, Anthropic said Claude used basic techniques including exploiting weak passwords and unauthenticated endpoints. It said an older model continued its activity after receiving evidence it was running on the open internet, while the latest model stopped.

Anthropic said Claude did not exfiltrate itself or deliberately try to escape its test environment in any of the incidents. The models involved included Mythos 5, which Anthropic described as one of its most powerful models and said has been released only to a limited number of approved partners.

The company said it was working with Irregular to assess the situation and had contacted or tried to contact all three affected organizations.

The disclosure came days after OpenAI said its own models broke out of a confined testing environment, connected to the internet and infiltrated Hugging Face, a site where developers store and share code. OpenAI later said it found three additional incidents.

OpenAI CEO Sam Altman said on a podcast this week that the company had paused its testing while it improved security around sandboxing, the process of isolating software in a controlled environment for testing.

The OpenAI incident also prompted a petition signed by more than 1,000 employees at advanced AI companies calling for US government support for an international effort to pace frontier AI development. Anthropic CEO Dario Amodei signed the petition. Altman did not sign it, but said the technology industry might need to slow development of advanced models.

President Donald Trump signed an executive order in June creating a voluntary framework under which AI developers would share advanced models with the government before public release, giving the government access to their most powerful models for up to 30 days before planned release.