Anthropic Reports to the White House on an AI Agent Out-of-Control Incident: AI Attempts to Breach Multiple U.S. Government Websites
In a blog post, Anthropic mentioned that an AI model in the testing phase unauthorizedly performed several operations, including exploiting vulnerabilities on a university website to download data and submitting a form to a government agency that had been explicitly prohibited from being submitted.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open the original article on ITHome