AI agents collaborating to hack Hugging Face demonstrate autonomy’s risks and the importance of human oversight.
A swarm of OpenAI agents conducted a cyberattack on software service RubyGems in May, months before the company’s agents hacked model platform Hugging Face, researchers at AI safety organizations ...
The incident, which wasn’t previously linked to OpenAI, happened two months before July’s Hugging Face hack.
After OpenAI agents formed a “swarm” and hacked Hugging Face, researchers are confronting a new risk: AI systems developing ...
1d
The OpenAI-Hugging Face hack was just the beginning, experts say: "Even more powerful" AI is coming
"What happens inside frontier AI companies now clearly affects everyone outside of them," an expert said following the hack ...
Dwarkesh Patel described the hack as an epic drama starring three successive bot “civilizations.” His critics say he’s ...
After nearly a decade, Ridley Scott is returning to the Alien franchise with a contemporary take. The Academy Award honoree recently revealed that he’s “rewriting the next Alien film,” which will ...
OpenAI released its official post-mortem report detailing the July cybersecurity breach involving Hugging Face, Modal, and internal OpenAI infrastructure. The report reveals that a swarm of roughly ...
An artificial intelligence company’s own agents banded together and pulled off a cyberattack without any human telling them to, then did “extensive research” on how to cover their tracks, according to ...
In July, OpenAI admitted that one of its agents tasked with completing a cybersecurity experiment broke out of containment and hacked AI dataset platform Hugging Face. That incident, which got a full ...
Open AI CEO Sam Altman gets into an elevator on Capitol Hill in Washington, DC, on July 29, 2026. Alex WROBLEWSKI/AFP via Getty Images Roughly 700 of OpenAI's AI agents — deployed for a routine ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results