The Decodersafety2h agoenergy 126
Three-week on-site audit at OpenAI reveals major gaps in AI safety monitoring
image: The Decoder
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.
This source publishes only a summary in its feed, so the full article lives at the outlet. The link above and below goes to the original.