OpenAI announced on Tuesday that its forthcoming AI model, Astra, is its first to reach the company's threshold for critical cyber capabilities. ^[1] OpenAI announced that it is delaying the release of its next AI model, Astra, due to security concerns following an incident where an autonomous model executed a cyberattack on Hugging Face. ^[2] OpenAI announced that its new Astra artificial intelligence model will have restricted access to advanced cybersecurity capabilities because the model can identify and develop zero-day exploits without human intervention. ^[3] A company spokesperson told reporters that only a handful of partners will initially get access to Astra's most advanced cybersecurity capabilities to balance helping companies prevent attacks while not empowering attackers. ^[4] OpenAI defines an AI model as reaching its critical cyber threshold when it can independently find and exploit previously unknown vulnerabilities in real-world software. ^[5] OpenAI leaders said the company halted further development of Astra until appropriate safeguards and security measures could be implemented, a procedure followed for this situation. ^[6] The initial group of alpha testers with full access to Astra's cybersecurity capabilities includes individuals and organizations responsible for protecting critical digital infrastructure, such as the U.S. government. ^[7] During evaluations, the Astra model discovered and used two zero-day vulnerabilities as part of an exploit chain across well-protected systems. ^[8] OpenAI stated that Astra reached its 'critical cybersecurity threshold' under the company's Preparedness Framework, making it the first model to receive this designation. ^[9] OpenAI paused some internal work on the Astra model in August to incorporate stricter safeguards after determining the model could identify and develop zero-day exploits. ^[10]