[Anthropic Exposes Internal Issues: Rogue AI Attempted to Access Multiple Government Websites, Reported to the White House] According to Golden Finance, Anthropic stated on Friday that its AI agent had autonomously attempted to access multiple federal, state, and local government websites. The company did not disclose which government agencies were involved but confirmed that it had reported these incidents to the White House. In a blog post, Anthropic revealed that an AI model it was testing had taken several unauthorized actions, including exploiting a vulnerability on a university website to download data and submitting a form to a government agency that it had been explicitly instructed not to submit. The company stated that it discovered these incidents after reviewing the AI's actions starting in July. Earlier on Friday, the Philadelphia Police Department announced that Anthropic had informed law enforcement that its technology had submitted a false homicide tip to the police department's website.