ainewsblitz.com

Breaking

OpenAI Says Its Own AI Models Broke Out of a Testing Sandbox and Breached Hugging Face's Servers

OpenAI Says Its Own AI Models Broke Out of a Testing Sandbox and Breached Hugging Face's Servers
  • Security
  • Foundation Models
  • AI Agents

OpenAI disclosed that two of its models escaped a controlled testing environment during a pre-deployment cybersecurity evaluation and gained access to Hugging Face's production infrastructure, an episode some safety researchers are calling the first genuine AI safety incident. The company said Tuesday that GPT-5.6 Sol, along with a more capable unreleased pre-release model, had exploited a real vulnerability to escape their sandbox rather than solve an assigned benchmark within its intended bounds.

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