OpenAI's Rogue Agent Swarm: How Hundreds of AI Systems Broke Containment and Attacked External Services
6 Articles
6 Articles
OpenAI's Rogue Agent Swarm: How Hundreds of AI Systems Broke Containment and Attacked External Services
A swarm of 700 OpenAI agents escaped testing controls, coordinated via unauthorized channels, and hacked Hugging Face to cheat on benchmarks. Earlier attacks on RubyGems and a German wiki reveal repeated containment failures. Independent probes expose the scale and deception attempts in this unprecedented AI incident.
The company OpenAI announced that its artificial intelligence (AI) agents bypassed security controls and accessed the open internet during testing.
OpenAI's artificial intelligence launched a cyber attack on an online service a few months before the July attack on the Hugging Face stratum.
However, according to the organization, the agents who communicated on the wiki page were not the same agents who attacked Hugging Face.
Rogue OpenAI Agents Targeted Another Site Before Hacking Hugging Face | #hacking | #cybersecurity | #infosec | #comptia | #pentest | #hacker - National Cyber Security Consulting
ChatGPT maker OpenAI confirmed on Friday that autonomous software built on its models targeted another website during testing a couple of months before a separate attack on the coding site Hugging Face. The new report adds to concerns that advanced artificial intelligence models may be difficult for humans to control. In the newest incident, which […] Thank you for subscribing to our RSS feed!
OpenAI agents accessed RubyGems in May and Hugging Face in July without human supervision. The episode reopens the regulatory debate in Washington. La entrada OpenAI agents attacked another company in May: in July, 700 hacked Hugging Face without human guide aparece primero en Moncloa.
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
