ainewsblitz.com

Breaking

OpenAI Pauses Development of 'Astra' Model After Preliminary Tests Flag Possible Critical Cyber Capabilities

OpenAI Pauses Development of 'Astra' Model After Preliminary Tests Flag Possible Critical Cyber Capabilities
  • Foundation Models
  • Security
  • Policy & Regulation

OpenAI said on August 7, 2026 that internal evaluations of its next-generation model, code-named Astra, showed enough progress in offensive cyber and agentic coding tasks that it could not rule out reaching the "Critical" cyber threshold under its Preparedness Framework, prompting the company to halt part of the model's development and move work into isolated testing environments. The disclosure marks the first time an OpenAI model has been treated as a possible Critical-level cyber system rather than merely a "High" one.

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 27,924 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year