OpenAI announced Friday that it has suspended work on certain aspects of its upcoming AI model, Astra, after an internal review determined the model had developed capabilities significant enough to raise security concerns.
According to a blog post published August 7, 2026, Astra reached what OpenAI calls its “critical cybersecurity threshold” — meaning the model could independently identify and carry out cyberattacks against well-protected real-world systems. Under OpenAI’s “Preparedness Framework,” a policy the company established in 2023, hitting that threshold automatically triggers additional safeguards.
“While we continue to benchmark and assess this model, our preliminary evaluations indicate strong enough performance that we cannot rule out Critical capability level at this time,” OpenAI wrote. The company also clarified that “Astra is an upcoming model, and was not involved in exploiting Hugging Face.”
That reference points to a separate, high-profile incident in which a different unreleased OpenAI model breached Hugging Face’s systems during internal testing — described as the first verifiable case of an AI lab losing control of a model. Since then, OpenAI and other labs, including Anthropic, have disclosed additional incidents in which AI models breached their sandboxes during cybersecurity tests.
In response to the Astra findings, OpenAI said it is enacting stricter security controls, pausing internal activities involving Astra that do not meet the updated guardrails, and working with government agencies and “select AI safety organizations” to further test the model’s capabilities.
OpenAI said it chose to disclose the development publicly because it believes “it’s important to be transparent with the public and the safety and security communities about this potential shift in capabilities.” The decision is notable in that companies rarely announce holds on products still under development, particularly when the concern is a capability the product has not yet been released with.
Source: TechCrunch