METR 与 Redwood 进驻 OpenAI 三周审计，发现智能体监控存在明显缺口
Three-week on-site audit at OpenAI reveals major gaps in AI safety monitoring
外部审计员在 OpenAI 驻场三周，发现 GPT-5.5 级以上的智能体流量最高有 25% 没被监控到，报告还被大量删减，信息量很大。
METR 和 Redwood Research 的外部审计员在 OpenAI 驻场三周，检查其面向 AI 智能体的内部监控系统，发现了明显缺口。报告指出，GPT-5.5 级别及以上模型的智能体流量中，最高有 25% 未经监控。完整报告共 61 页，OpenAI 对其中大部分内容做了删减，目前只有摘要对外公开。
Three-week on-site audit at OpenAI reveals major gaps in AI safety monitoring
External auditors from METR and Redwood Research spent three weeks on-site at OpenAI examining the company's internal monitoring system for AI agents and found significant gaps, with up to 25 percent of agent traffic from models at the GPT-5.5 class and above going unmonitored. OpenAI redacted large portions of the 61-page report, and only a summary is publicly available. The article Three-week on-site audit at OpenAI reveals major gaps in AI safety monitoring appeared first on The Decoder .
