@gdb: Evaluations of our next major model, Astra, indicate significant capability advancements in agentic coding and cybersec…
Summary
OpenAI's next major model, Astra, shows significant capability gains in agentic coding and cybersecurity, and is being treated as a 'critical' model for cybersecurity under the Preparedness Framework, with additional controls planned.
View Cached Full Text
Cached at: 08/08/26, 05:05 AM
Evaluations of our next major model, Astra, indicate significant capability advancements in agentic coding and cybersecurity.
Team is doing the safety and security work to make Astra broadly available, and get its advanced cyber capabilities into the hands of defenders:
OpenAI (@OpenAI): After evaluating one of our upcoming models, Astra, we’re treating it as our first “critical” model for cybersecurity under our Preparedness Framework.
This is a scenario we’ve planned for, and we’re putting additional controls in place to ensure Astra’s further development
Similar Articles
Responding to the next frontier of critical cyber capabilities
OpenAI announces that internal evaluations of its upcoming model Astra indicate it may reach critical cyber capabilities under its Preparedness Framework, prompting strengthened security controls and a pause on certain internal activities.
OpenAI says it slowed Astra model development over security concerns
OpenAI says it slowed development of its upcoming Astra model after an internal review found it reached a critical cybersecurity threshold, capable of autonomously conducting cyberattacks. The company has implemented additional safeguards and is coordinating with government agencies and AI safety organizations.
OpenAI puts the brakes on a new model because it’s supposedly too powerful
OpenAI is pausing internal activities around its in-development Astra model over concerns that it may reach critical cybersecurity capabilities under its Preparedness Framework, following recent incidents of AI models going rogue at Anthropic and Meta.
@sama: astra is a powerful model and we are working to make it generally available. we do not think it is a good strategy to k…
Sam Altman announces that the Astra model is powerful and OpenAI is working to make it generally available, while taking extra time to ensure safety given its cyber capabilities.
@gabriel1: so exciting, can't wait to try this beast
Sam Altman announces that 'astra' is a powerful AI model being prepared for general availability, with additional safety time needed due to its cyber capabilities.