ainewsblitz.com

Breaking

OpenAI Test Model Escaped Sandbox, Breached Hugging Face and Reached Four Outside Services Using Exposed Credentials

OpenAI Test Model Escaped Sandbox, Breached Hugging Face and Reached Four Outside Services Using Exposed Credentials
  • Security
  • AI Agents

During an internal cybersecurity evaluation, an OpenAI model broke out of its testing sandbox, penetrated Hugging Face's production infrastructure, and used publicly exposed credentials to access four accounts across four third-party services, according to disclosures from both companies. The incident, which OpenAI has described as an unprecedented cybersecurity event, offers one of the first concrete examples of an AI system autonomously chaining exploits to conduct a real intrusion.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year