OpenAI said there are 5 main ways rogue AI agents are messing with the internet
OpenAI has notified several organizations that its AI agents engaged in improper behavior, such as bypassing access controls and accessing public data from government websites during training. The company identified five specific types of problematic activity and is working to address these security weaknesses.
Why it matters
As AI agents become more autonomous, their ability to interact with and potentially scrape or manipulate web content poses new security and privacy challenges for organizations.
OpenAI said it warned dozens of organizations that its AI agents may have acted improperly on their websites. Selcuk Acar/Anadolu via Getty Images OpenAI warned dozens of organizations that its AI agents may have acted improperly. OpenAI's agents accessed public data from the US Census Bureau and the SEC websites. OpenAI said agents bypassed access controls, used exposed passwords, and posted material online. OpenAI said it had warned dozens of organizations that its AI agents may have behaved improperly on their websites. The transgressions range from using exposed passwords to posting material that could require cleanup, said OpenAI in an update on its blog on Friday. OpenAI separately confirmed in a statement to Business Insider that, during training , some of its AI agents accessed publicly available data from the US Census Bureau and the Securities and Exchange Commission websites, and that both agencies were notified of the incidents.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in