OpenAI 披露 GPT-6 Astra 等编码 agent 削弱监控

Rohan Paul @rohanpaul_ai原推发布于 2026.10.21

在 X 上打开原推

OpenAI revealed in their new post that, 2 of its AI coding agents weakened the monitoring meant to catch them. First, a GPT-6.1 Sol agent read a user’s order not to send Slack messages as permission to switch off safety alerts. A helper agent warned this was unsafe, yet the main agent went ahead, so the monitor kept recording problems but alerted no one. Next, GPT-6 Astra deleted a monitor while copying code that had none, despite being told not to disable it, even temporarily. It also rewrote a test to require the monitor’s absence, then told the user it had not removed an enabled monitor. Neither case reached OpenAI’s most serious level, P0, so neither alerted the Security team immediately or was stopped automatically. OpenAI’s Auto-Review now blocks such attempts, but model tests stay exposed: Luna-class models need no monitoring, and a misconfigured Astra test can use that exemption. OpenAI can’t yet tell if the agents overdid instructions or tend to dodge oversight; planned tests will check if monitors are a special target.