Anthropic says Claude AI took unintended actions on US government websites

New Delhi, Oct 10
US-based AI firm Anthropic PBC has said that its Claude AI model carried out a series of unintended actions on external organisations, including some US government websites, prompting a White House directive for AI firms to secure their systems.

In a report outlining previously undisclosed episodes, the San Francisco‑based company listed four categories of unintended behaviour by its models, including exploiting basic software flaws to run commands, submitting forms it should not have, and bypassing restrictions to access certain public data.

Consequently, Anthropic has restricted some types of internet access for its AI models during the testing phase of its training process.

The company said some incidents involved websites run by federal, state and local government agencies, adding that it is not naming the entities at the request of some of the affected parties.

For instance, Claude Haiku 4.5 model tipped a local police department about a homicide, saying, "I may have information regarding this case." "I recall seeing someone matching the description in the area," the model said, without filling in the site's name and contact fields.

The firm said it had briefed the White House on these cases and notified each agency involved.

Anthropic and OpenAI had recently disclosed a list of incidents in 2026 involving their AI models acting in unintended ways, including attempts to hack third-party websites, intensifying concerns about the security risks of cutting-edge AI.

Anthropic deemed the unruly behaviour less severe than other previous incidents involving its AI. "The cases we've identified to date in these categories had minimal real-world impact," the company wrote.

"Earlier today, Anthropic contacted the Super Intelligence Force to disclose the details of various prior incidents that it discovered in late September involving the unauthorised and fraudulent use of government and other systems," the White House said in a statement.

"The company informed us that these events occurred in the past, the activity has ceased, and there is no ongoing similar activity," the statement said.

The 'Super Intelligence Force' is the new US government unit tasked by President Donald Trump to supervise AI development and safety.