OpenAI Astra 模型即将发布，具备自主发现系统漏洞能力
原标题：Open AI’s Astra model is on the way—and very good at breaking into computer systems
AI 摘要
OpenAI 公布了即将推出的 Astra 模型的新细节，称其为首个达到其“关键网络安全阈值”的大语言模型，能够自主发现并利用系统漏洞。OpenAI 计划很快发布 Astra，但对最先进的网络安全功能将限制访问，并已采取多项安全措施，包括改进模型防护、限制高风险账户、增加思维链监控等。然而，由于缺乏第三方确认，外界难以评估其安全声明。
正文节选
OpenAI shared new details on its forthcoming Astra model, which the company said is the first large language model to meet its “critical cybersecurity threshold,” in preparation for its imminent release. “We plan to make Astra available soon,” OpenAI’s blog post reads, “but access to its most advanced cybersecurity capabilities will be more limited.” The frontier lab determined that Astra is capable of finding unknown security flaws in computer systems, and exploiting them without a person’s gui