OpenAI 新模型 Astra 或达最高网络安全风险等级，部分开发暂停
原标题：OpenAI flags its new Astra model as potentially reaching the highest cybersecurity risk level for the first time
AI 摘要
OpenAI 在内部测试中发现其新模型 Astra 展现出极强的网络安全能力，可能首次达到其安全框架中的最高风险等级“Critical”，因此暂停了部分开发工作。公司已加强安全控制、隔离测试环境并部署监控系统。CEO Sam Altman 确认该评估将推迟发布，并批评竞争对手 Anthropic 仅向少数合作伙伴提供强大模型的做法。
正文节选
OpenAI flags its new Astra model as potentially reaching the highest cybersecurity risk level for the first time Key Points - OpenAI is pausing parts of the development of its new AI model, Astra, after internal tests revealed cybersecurity capabilities so strong that the model could reach the highest risk level ("Critical") in the company's internal security framework. - At this level, the AI could independently develop and execute cyberattacks without human involvement. OpenAI is now rolling o