Skip to main content

OpenAI's Rogue Agent Went Unnoticed For a Week

1 month ago
An anonymous reader quotes a report from Reuters: The OpenAI agent that broke into tech firm Hugging Face went on a dayslong hacking spree that OpenAI didn't notice until well after the threat was contained and the FBI was alerted, according to people familiar with the investigation. The agent -- a program capable of making decisions and executing complex tasks with little or no human oversight -- attempted to break out of its isolated testing environment at OpenAI around July 9, according to two of the people. The intrusion at Hugging Face, which operates as a repository for AI tools and models, began two days later on July 11 and lasted until July 13, said Thomas Wolf, Hugging Face's co-founder. It took several more days for OpenAI to realize its agent was behind the hack, and the two companies only communicated about it for the first time on or around July 20, according to Wolf and three of the people familiar with the investigation. OpenAI's public disclosure, on July 21, thatone of its agents had slipped out of control and carried out the break-in at Hugging Facedrew global attention. But many details of the hack, including how long the agent went rogue and OpenAI's belated knowledge of it, are being reported here for the first time. Hugging Face is preparing a public timeline of the hack, Wolf said, adding that he could not speak to what happened at OpenAI. In a statement, OpenAI said the hack was unprecedented and "marks an important moment for AI safety." It added that it was reviewing the incident with outside advisers and would eventually publish a technical report. "Does that mean that they left it unattended and didn't realize what it was doing? Or maybe they did and didn't know how to contain it? Both are equally dangerous and alarming," asked Marley Smith, the principal intelligence specialist at the nonprofit World Ethical Data Foundation. "The models lie, they cheat, they hack," said Jeffrey Ladish, whose organization, Palisade Research, studies the capabilities and motivations of AI agents. Ladish said the hack should spark broader questions over how much all the leading AI companies are willing to invest in onerous security measures while locked in a race with one another to deploy the best and fastest models. "There has to be government oversight," Ladish said, "because it won't happen otherwise."

Read more of this story at Slashdot.

BeauHD

Instagram Is Now Banning Pickup Artists, Pranksters Who Use Meta Glasses

1 month ago
Instagram is banning videos filmed with Meta smart glasses that harass strangers in public, including prank videos targeting service workers and pickup-artist clips of women who may not realize they are being recorded. "If you're posting content that is taking advantage of people and harassing them, like a lot of these pickup line kind of videos that we've heard of and seen, then we're going to take the content down," said Instagram head Adam Mosseri in response to a question on his Instagram stories last week. "We don't want people to be surreptitiously taking videos of other people and harassing them and then posting them on our platform. So we're trying to fight that every way we can." Business Insider reports: It's unclear how many videos have been removed under this new policy. Business Insider found that two large accounts of pickup artists who filmed themselves approaching women in public while wearing the glasses had been deactivated. (Both previously had more than a million followers.) A Meta spokesperson confirmed to Business Insider that these accounts were booted for violating the policy about posting harassing content that had been filmed with the glasses. Meta did not directly respond to questions about how this new policy is being enforced or what exactly constitutes a violation.

Read more of this story at Slashdot.

BeauHD