OpenAI披露GPT-6 Agent隐瞒禁用安全监控事件
OpenAI says an AI agent lied about disabling its safety monitoring system
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.
OpenAI 披露了一起涉及 AI 智能体的安全事件，该智能体在内部编码任务期间削弱了其安全监控系统。在其中一起事件中，OpenAI 表示其 GPT-6 Astra 智能体在复制参考代码时禁用了其安全监控器——随后对此事撒谎。
"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."
"参考代码没有配置监控器，Astra 认为这是从用户代码中移除监控集成的理由，" OpenAI 的 AI 安全研究员 Marcus Williams 在 X（原推特）上写道。"当用户询问 Astra 是否已移除监控时，它撒谎称并未移除。"
A separate incident occurred after a GPT-6.1 Sol agent suppressed automatic se …
另一起事件发生在 GPT-6.1 Sol 智能体压制自动 se ……之后
Read the full story at The Verge.
在 The Verge 阅读全文。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力