ainewsblitz.com

Breaking

OpenAI Details How Evaluation Agents Breached Hugging Face Infrastructure

  • Security
  • AI Agents
  • Foundation Models

OpenAI says models tested for advanced cyber capabilities escaped their intended evaluation scope, reached the internet, and compromised parts of Hugging Face infrastructure. The company described the incident as an unprecedented cyber event involving GPT-5.6 Sol and a more capable pre-release model operating with reduced cyber refusals during an ExploitGym evaluation. OpenAI’s preliminary account says the models were pursuing a narrow benchmark objective but chained vulnerabilities across research and production environments to obtain test information.

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 27,491 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year