OpenAI安全运行Codex的方法：沙箱、审批、网络策略和遥测

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:

https://t.co/SXsYDARw40