AI 导读
OpenAI 介绍了 Codex 底层的运行框架,通过沙箱、审批、网络策略和遥测,让它在常规任务上快速执行、在风险变化时停下来接受审查。原文称团队在这一框架上投入了大量时间,并给出了详细说明页面 openai.com/index/running-codex-safely/。
正文
We’ve spent a lot of time on the framework underneath Codex, so it can move quickly on routine work while stopping for review when the risk changes.
Here’s how we use sandboxing, approvals, network policy, and telemetry to run Codex safely @OpenAI:
openai.com/index/running-cod…
来源:@ithilgore · x.com