OpenAI flags critical cyber capability risk in upcoming ’Astra’ model

Investing.com -- OpenAI is halting some internal development of its next-generation artificial intelligence model after preliminary tests suggested the software could autonomously execute sophisticated cyberattacks.

The San Francisco-based startup said Thursday that its upcoming model, code-named Astra, demonstrated advanced coding and hacking skills that may cross its internal “Critical” risk threshold. Under OpenAI’s self-imposed safety framework, an AI system reaches this classification if it can independently discover “zero-day” software vulnerabilities or launch end-to-end attacks on secure networks without human direction.

In response to the capability jump, OpenAI is restricting Astra’s development to heavily guarded, isolated environments.

At a Glance: OpenAI’s Security Overhaul for ’Astra’

• 
  

  Halted Workflows: Internal development lacking strict security controls has been paused.

  
  


• 
  

  Real-Time Interception: New automated monitors will track the model’s underlying reasoning steps to instantly shut down misaligned or dangerous actions.

  
  


• 
  

  External Audits: OpenAI is bringing in government agencies and third-party safety institutes to stress-test the model.

  
  

The preemptive lockdown underscores the growing tension in Silicon Valley between the race to commercialize increasingly powerful AI and the imperative to contain it. Previous iterations of OpenAI’s technology, including GPT-5.6-Sol, maxed out at a "High" risk rating.

OpenAI clarified that Astra remains unreleased and was not involved in recent high-profile AI security breaches, such as the recent Hugging Face exploit. The company framed the pause as evidence that its internal safety guardrails are working as intended, catching dangerous capabilities before the technology is deployed to the public or enterprise clients.

You May Also Be Interested In

• Trump admin reportedly not expecting to reach Canada tariff deal
• Nordic Mining shares tumble on liquidity issues, slow ramp-up
• Etched secures $700M at doubled valuation to scale AI inference hardware