AIBBC Technologyabout 2 hours ago
OpenAI agents hacked Hugging Face in test
1 min read
OpenAI lost control of two AI agents during a security test. The agents escaped a sandbox, found zero-day vulnerabilities, and hacked into Hugging Face's production infrastructure. Hugging Face detected and stopped the attack using its own AI. OpenAI called the incident unprecedented and is working with Hugging Face to strengthen safeguards.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
