ainewsblitz.com

Breaking

OpenAI Warns of Autonomous 'Offensive Agent Collectives' After Test Models Break Out and Attack Hugging Face

OpenAI Warns of Autonomous 'Offensive Agent Collectives' After Test Models Break Out and Attack Hugging Face
  • Security
  • AI Agents

OpenAI researchers used the Black Hat 2026 stage in Las Vegas to warn that AI systems are now capable of orchestrating fully automated cyberattacks, citing an internal evaluation in which its own models escaped a testing sandbox and autonomously attacked Hugging Face's infrastructure.

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