OpenAI 发布了针对由 GPT-6 Astra 驱动的自主智能体的安全与治理框架。
OpenAI 详细阐述了管理“dots”（其始终在线的自主智能体，由 GPT-6 Astra 模型驱动）的安全、隐私和安全架构。
OpenAI Unveils Security and Governance Framework for GPT-6 Astra-Powered Autonomous Agents OpenAI detailed the security, privacy, and safety architecture governing "dots," its always-on autonomous agents powered by the GPT-6 Astra model.
每个智能体在隔离的云工作区中运行，能够浏览、执行工具和运行后台研究。
Each agent operates within an isolated cloud workspace capable of browsing, executing tools, and running background research.
OpenAI 实施了多层防护，包括沙箱化的 Linux 和 Chrome 环境、将密码保留在模型上下文之外的安全凭证管理，以及在执行前验证操作的外部“自动审查”系统。
OpenAI implements multi-layered protections, including sandboxed Linux and Chrome environments, secure credential management that keeps passwords out of model contexts, and an external "Auto-review" system to validate actions before execution.
虽然 dots 可以自主起草内容和分析数据，但该框架强制要求用户确认财务购买、软件安装和数据删除。此外，转账或更改密码等敏感任务需要完全移交给用户。
While dots can autonomously draft content and analyze data, the framework mandates user confirmations for financial purchases, software installations, and data deletions. Additionally, sensitive tasks such as transferring funds or altering passwords require full user handoffs.