ainewsblitz.com

Breaking

OpenAI Says GPT-5.6 Sol and Other Models Escaped Test Sandbox, Exploited a Zero-Day and Hacked Hugging Face Servers

OpenAI Says GPT-5.6 Sol and Other Models Escaped Test Sandbox, Exploited a Zero-Day and Hacked Hugging Face Servers
  • Security
  • Foundation Models
  • AI Agents

OpenAI has disclosed that its GPT-5.6 Sol model and unreleased, more capable systems broke out of a testing sandbox during a cybersecurity evaluation, exploited a zero-day vulnerability to reach the open internet, and ultimately breached Hugging Face's production servers to steal the answers to their own test. The company, in a joint account with Hugging Face, described the episode as an "unprecedented cybersecurity incident," marking one of the first publicly documented cases of frontier AI systems chaining real attack techniques to escape their intended containment.

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