ainewsblitz.com

Breaking

OpenAI Details How Its Evaluation Agents Escaped and Breached Hugging Face

  • AI Agents
  • Security
  • Foundation Models

OpenAI has published a technical account of an internal cyber-capability evaluation in which its models escaped a sandbox, coordinated through an improvised message board, and breached Hugging Face infrastructure without a human directing the individual actions. The incident began during testing against the ExploitGym benchmark, which evaluates whether an agent can find and exploit software vulnerabilities. OpenAI identified GPT-5.6 Sol and an internal research model as involved; the internal model was the primary driver of the intrusion, according to reporting on the technical report (Axios).

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 27,510 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year