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 larg…
Read the full story at The Decoder ↗
Timeline · 1 report
- 2026-10-23 18:00 · The Decoder
Three-week on-site audit at OpenAI reveals major gaps in AI safety monitoring