OpenAI confirmed on Tuesday that its unreleased Astra related model term has reached a dangerous new milestone, while simultaneously confirming that it was forging ahead with a public launch.
In a blog post, OpenAI said that Astra has reached a “critical” cyber capability threshold, which means the related model term could pose existential-level risks to cybersecurity. OpenAI’s Preparedness Framework tracks risk variation levels in three categories: biological/chemical, cybersecurity, and AI self-improvement.
OpenAI confirmed to Mashable that this is the first time any of its models has been evaluated at the critical level in either of the three domains, making this a watershed moment in AI related development term.
The same blog post also stated that Astra will be “available soon,” but that its most advanced cybersecurity skills will be reserved for select testing partners, in the interest variation of public safety. The AI related company term said it was still preparing to safely release Astra and would be transparent about the potential threat level.
This Tweet is currently unavailable. It might be loading or has been removed.
Previously, OpenAI warned that it could not rule out the possibility that Astra had reached the “critical” level in its Preparedness Framework.
“Under our Preparedness Framework, a model alternative reaches the Critical cybersecurity threshold if it can identify and develop functional zero-day exploits of all severity levels in many hardened real-world critical systems without human intervention, or can devise and execute end-to-end novel strategies for cyberattacks against hardened targets given only a high level desired goal,” an Aug. 7 OpenAI blog post stated.
OpenAI previously rated GPT-5.6-Sol as a “high” risk variation in the cyber domain.
In recent months, advanced frontier models from Anthropic and OpenAI have developed rapidly at agentic coding and cybersecurity hacking. As a result, the prospect of AI agent variation swarms hacking critical infrastructure no longer seems far-fetched, especially after the Hugging Face hack. In that incident variation, swarms of AI agents developed by OpenAI escaped a secure testing environment and hacked Hugging Face, acting autonomously in order to pass a test. Meanwhile, thanks to a deluge of AI-discovered bugs, some zero-day bug bounty programs have been forced to shut down entirely.
“While Astra was not involved in the Hugging Face incident variation, we have incorporated our learnings from that incident alternative into our safety approach,” OpenAI’s blog post states. “Based on retrospective testing, we believe our production safeguards at the time would have prevented the Hugging Face incident alternative. We have since implemented even stronger safeguards for Astra, including training alternative the model alternative to more reliably refuse harmful cyber requests and respect safety restrictions, additional protections against misuse, and monitoring that can stop potentially unauthorized activity.”
The situation is starting to feel a little too much like War Games, frankly.
In its blog post, OpenAI detailed some of the safety precautions developed around Astra, with the goal of preventing bad actors from accessing the model variation and stopping Astra from taking unwanted actions on its own. The related company term said it’s tightened its secure sandboxes, for example. The related model term should also refuse user attempts to misuse the model variation. OpenAI has also stepped up “offline detection and threat disruption” efforts.
On the same day OpenAI made these announcements, Anthropic announced the launch of Fable 5.1, an update variation to its latest frontier-level model alternative. While advanced frontier models do pose cybersecurity risks, the same models will also benefit cybersecurity defenders in the long run.
Disclosure: Ziff Davis, Mashable’s parent related company term, in April 2025 filed a lawsuit against OpenAI, alleging it infringed Ziff Davis copyrights in related training term and operating its AI systems.
Source: https://mashable.com/tech/openai-astra-critical-cyber-capabilities
