WSJ Tech News Briefing · Wednesday, September 2, 2026
OpenAI is limiting the cyber capabilities of its forthcoming AI model, Astra, due to concerns about its potential for automated cyberattacks. The company stated that internal testing revealed Astra can devise and execute novel cyberattacks with minimal human input, prompting the addition of extra security layers to prevent misuse by hackers or the AI going rogue.
“OpenAI is limiting the cyber capabilities of a new model that can pull off automated cyberattacks.”
“The chat GPT maker says that it's internal testing determined that the forthcoming model called Astra is capable of devising and executing novel cyberattacks against difficult targets with only limited human input.”
“In a blog post the company said that it has added additional layers of security to reduce the risk of misuse by hackers, or Astra going rogue and hacking targets on its own.”