Anthropic’s models gained unauthorised ‘real-world’ access during testing

SAN FRANCISCO – Anthropic’s artificial intelligence models “gained unauthorised access” to three outside organisations during testing that was supposed to keep them away from “real-world” systems, the company said on July 30.The announcement comes just days after rival OpenAI first revealed that its models improperly accessed the internet and went rogue during security testing.Anthropic evaluated more than 141,000 “evaluation runs” and found that three different versions of its model, known as Claude, had improperly accessed the systems of three unnamed organisations.Unlike the incident involving OpenAI’s technology, Anthropic’s models had access to the internet “due to a misunderstanding between us and our evaluation partner”, called Irregular, Anthropic said in a blog post.Nonetheless, Claude used “basic techniques, such as exploiting weak passwords and unauthenticated endpoints”, the blog post continued.The models involved one of its most powerful ones known as Mythos 5, which has been released only to a limited number of approved partners.Anthropic said it is working with Irregular to assess the situation, and that it has contacted or attempted to contact all three impacted organisations.Rogue agentsOpenAI and Anthropic released their most powerful models in 2026 – known as Sol and Mythos, respectively – boosting concerns across the industry about safety and security.Those concerns also revolve around so-called AI agents, which are software products designed to perform tasks autonomously.OpenAI admitted last week that its models had broken out of their confined environment during testing, connected to the internet and infiltrated Hugging Face, a site where developers store and share their code.Days later, OpenAI said it found three additional incidents.OpenAI chief executive officer Sam Altman said on a podcast that the company had paused its own testing after the incident while it improved the security around its “sandboxing”, which is the process of isolating software in a controlled environment for testing.The incident also triggered a petition signed by over 1,000 employees at cutting-edge AI companies calling on the US government to help slow the release of the most advanced AI models.Anthropic CEO Dario Amodei was among those who signed the petition.Titled Pacing The Frontier, the petition requests “that the US government support an international effort to develop the technical and governance tools needed to deliberately pace the frontier of automated AI development”.Altman did not sign the petition, but suggested during the podcast that the tech industry might need to slow down development of advanced models.“We may have to pace the rate of AI development to give ourselves enough time for society to harden around some of these new capability levels,” he said.Earlier in 2026, the Trump administration invoked national security concerns to block OpenAI and Anthropic from launching their newest models, but ultimately indicated it was satisfied with assurances about their safety, leading to their release.In June, Trump signed an executive order creating a voluntary framework under which AI developers will share advanced models with the government before public release.Under the framework, developers such as OpenAI, Anthropic and Google would give the government access to their most powerful models for up to 30 days before planned release. AFP