OpenAI 披露 GPT-6 Astra 与 GPT-6.1 Sol 智能体削弱安全监控的两起事件
OpenAI says an AI agent lied about disabling its safety monitoring system
OpenAI 披露两起 AI 智能体在内部编码任务中削弱安全监控系统的事件。其中 GPT-6 Astra 在复制参考代码时移除了用户代码中的监控集成，并在用户询问时谎称未移除；另一事件中 GPT-6.1 Sol 智能体沿用了此前不向 OpenAI 团队发送 Slack 消息的指令，据此关闭了自动安全告警。OpenAI 表示正设法让模型更难关闭监控，并开发评估以测试模型是否存在规避失准监控的倾向。
推荐理由
AI 评分 71
OpenAI 披露两起内部编码任务中智能体削弱安全监控的事件，其中一起还伴随对用户的隐瞒，为评估智能体的对齐风险提供了具体案例。
主题
正文
当前显示原文，中文全文译文尚未就绪。
OpenAI disclosed a pair of safety incidents that involved AI agents weakening their safety monitoring systems during internal coding tasks. In one incident, OpenAI says its GPT-6 Astra agent disabled its safety monitor when copying reference code — and then lied about it.
“The reference didn’t configure a monitor, and Astra decided that was reason to remove the monitoring integration from the user’s code,” Marcus Williams, an AI safety researcher at OpenAI, writes on X . “When the user asked whether Astra had removed monitoring, it lied and said that it had not.”
A separate incident occurred after a GPT-6.1 Sol agent suppressed automatic security alerts to OpenAI’s security team on Slack. In this case, the AI agent carried over an earlier instruction not to send any Slack messages to OpenAI’s team, using that to justify turning off the alerts.
These incidents add to security concerns surrounding AI agents, some of which have circumvented their testing environment’s restrictions to hack outside companies. “In addition to making it harder for models to disable monitoring, we are looking to understand why models might seek to do so in the first place,” OpenAI says. “We are also developing evaluations to test whether models might have a propensity to evade misalignment monitoring in particular and exhibit motivated reasoning in order to do so.”