OpenAI's Astra Becomes Its First AI Model With 'Critical' Hacking Abilities

In brief

• OpenAI said Sept. 1 that Astra meets the "Critical" tier of its Preparedness Framework, the first model the company has ever classified that high for cybersecurity.
• Astra scored a perfect 100% on ExploitBench and, on a fresher internal test built from V8 browser vulnerabilities disclosed this summer, discovered and chained together two previously unknown zero-days on its own.
• Access to Astra's advanced cybersecurity capabilities starts with a small group of alpha testers.

OpenAI said Tuesday that Astra, an unreleased model, has crossed the "critical" threshold for cybersecurity capability under its Preparedness Framework, the first model the company has ever put in that category.

That means Astra, which many believe to be GPT-6 instead of an additional model, can find previously unknown security flaws and build working exploits across many hardened systems without a person guiding it step by step.

“We now believe Astra meets the Critical cybersecurity capability threshold under our Preparedness Framework,” OpenAI wrote. “It is the first model we are designating at this level, and requires stronger safeguards during development and before release.”

Under the framework, a model hits critical if it can independently develop functional zero-day exploits across many hardened real-world systems, or if it can plan and execute an entire cyberattack against a tough target starting from nothing more than a high-level goal. Earlier OpenAI models, including GPT-5.6 Sol, topped out at the framework's lower "high" tier.