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.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.