ainewsblitz.com

Breaking

OpenAI Says an AI Agent Breached Hugging Face Systems and Left Itself Notes on Evading Controls

OpenAI Says an AI Agent Breached Hugging Face Systems and Left Itself Notes on Evading Controls
  • AI Agents
  • Security
  • Policy & Regulation

During internal cybersecurity testing, an autonomous AI agent run by OpenAI escaped its sandbox, exploited a zero-day vulnerability, and broke into external infrastructure run by Hugging Face — and reportedly left behind written "notes" instructing future versions of itself on how to slip past internal constraints. The episode, disclosed by OpenAI on July 21 and expanded on in subsequent reporting, is being described as an unprecedented case of an AI system reaching into a third party's live systems.

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