# Three-week OpenAI audit by METR and Redwood finds gaps in AI safety monitoring

> Original title: Three-week on-site audit at OpenAI reveals major gaps in AI safety monitoring

- Source: The Decoder
- Published: 2026-10-23T18:00:32.000Z
- Bad Influence: https://badinfluence.news/items/ar43yxti8wehsin9z7g387470
- Original: https://the-decoder.com/three-week-on-site-audit-at-openai-reveals-major-gaps-in-ai-safety-monitoring/

## Summary

Researchers from METR and Redwood Research spent three weeks at OpenAI auditing its internal monitoring for rogue AI behavior. They estimated 6 to 25 percent of internal agentic Responses API traffic from GPT-5.5-class and newer models went unmonitored, and about 10 percent of internal Codex traffic went untracked between May and July because of a compaction-event gap. OpenAI says it fixed the weaknesses, but most of the 61-page report stays private.