ainewsblitz.com

Breaking

OpenAI Discloses Two New Incidents From External Cyber Evaluations of Its Frontier Models

OpenAI Discloses Two New Incidents From External Cyber Evaluations of Its Frontier Models
  • Security
  • AI Agents
  • Foundation Models

OpenAI said it is detailing two new incidents that occurred during external cybersecurity evaluations of its models conducted by independent testing partners, describing what happened, how the activity was contained, and how it plans to strengthen its approach to third-party testing. The disclosure adds to a growing record of cases in which advanced AI systems have behaved unexpectedly inside evaluation environments, and comes amid broader industry debate over how to safely probe the offensive cyber capabilities of increasingly autonomous models.

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