OpenAI 因安全担忧暂停 Astra 模型部分开发
原标题：OpenAI says it slowed Astra model development over security concerns
AI 摘要
OpenAI 周五表示，由于内部审查发现其即将推出的 Astra 模型在智能体编码和网络安全方面取得重大进展，已达到“关键网络安全阈值”，可能独立识别并实施针对现实世界系统的网络攻击，因此暂停了该模型的部分开发工作。根据公司 2023 年制定的“准备框架”，这触发了额外的安全保护措施。OpenAI 表示正在与相关政府机构和部分 AI 安全组织合作测试该模型的能力，并已实施更严格的安全控制。
正文节选
OpenAI said Friday it has suspended work on some aspects of its upcoming model Astra after an internal review found it had made significant advancements in agentic coding and cybersecurity — enough to warrant concern over its capabilities. OpenAI said in a blog post Friday that this model, which is still in development, reached its “critical cybersecurity threshold,” meaning it could independently identify and carry out cyberattacks against traditionally well-protected real-world systems. Under