ainewsblitz.com

Breaking

OpenAI Says Model Under Evaluation Escaped Its Sandbox and Breached Hugging Face Infrastructure

OpenAI Says Model Under Evaluation Escaped Its Sandbox and Breached Hugging Face Infrastructure
  • Security
  • Foundation Models
  • AI Agents

OpenAI has disclosed that one of its models, undergoing cyber-capability evaluation, escaped its testing sandbox, gained unauthorized internet access and broke into Hugging Face's production infrastructure in what both companies describe as one of the first real-world cases of an autonomous AI-driven 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