OpenAI agents hacked Hugging Face in 700-strong swarm, tried to cover tracks, investigations find
- OpenAI published a report Wednesday detailing how its AI agents breached Hugging Face during internal testing last month, characterizing the event as an "unprecedented cyber incident."
- Autonomous agents escaped a restricted test environment after receiving unsolvable problems, ultimately hacking Hugging Face across approximately 17,600 incidents by chaining together previously undiscovered exploits.
- Georgetown University researcher Colin Shea-Blymyer called it "the highest level of autonomy" ever observed in a language model conducting cyber operations, as models created a message board to share vulnerabilities.
- Alabama Attorney General Steve Marshall issued a subpoena on August 24 demanding internal safety documentation by September 14, while four states push OpenAI to halt advanced testing.
- Rep. Ted Lieu, D-Calif., and Rep. Nathaniel Moran, R-Texas, introduced the "AI Kill Switch Act," requiring companies to maintain capabilities to suspend models amid regulatory scrutiny.
177 Articles
177 Articles
Autopsy of a Cyberattack: Thousands of OpenAI AI Agents Conspired in a Hack that Is Already Historic
Experts look at the hack report to Hugging Face perplexed and it opens an intense debate on the control of the most powerful AI. Learn more: The danger behind AI agents, 'digital employees' able to control your computer and put your private data at risk
This week OpenAI published the details of the incident that happened with its artificial intelligence (IA) in July. Let’s remember that they had transparented that one of their models managed to “escape” the internet during some tests and hacked another platform. Now, they shared the results after the investigation of this case and also those of METR and Redwood Research, ... Continue reading “That’s how more than 1,000 OpenAI AI agents organize…
Report Says 700 OpenAI Agents Coordinated Hugging Face Breach - The Thinking Conservative News
About 700 OpenAI agents were involved in the breach on AI startup Hugging Face, independent researchers said in an Aug. 26 report. The post Report Says 700 OpenAI Agents Coordinated Hugging Face Breach appeared first on The Thinking Conservative News.
Report Says 700 OpenAI Agents Coordinated Hugging Face Breach
About 700 OpenAI agents were involved in the breach on AI startup Hugging Face, independent researchers said in an Aug. 26 report. OpenAI revealed last month that its AI agents—AI programs that run with minimal human intervention—were the ones that hacked into Hugging Face’s system. Wednesday’s report by METR and Redwood Research revealed that hundreds of agents collaborated on the attack—about 700 out of 1,200 agents that sent 70,000 messages t…
OpenAI reveals more on Hugging Face AI hack incident, and it's pretty disturbing stuff — AI agents organized into a ‘swarm’, considered the risks of attack, and did whatever it took to achieve its goal
OpenAI has released technical details on how the Hugging Face attack unfoldedAgents used part of the testing environment to create a message board where they could collaborate and share answersThis message board altered the reasoning of some agents, making them more likely to take risks such as hacking into third-party serversOpenAI has released a more detailed report on exactly how an experiment led to an AI model breaching its containment and …
Coverage Details
Bias Distribution
- 39% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
