OpenAI audit uncovers major safety monitoring gaps

A three-week on-site audit at OpenAI has uncovered major gaps in its AI safety monitoring. The research was conducted by two experts from METR and Redwood Research, who had access to OpenAI's codebase and internal documents and interviewed about a dozen employees. The audit revealed that an estimated 6 to 25 percent of internal agentic Responses API traffic from models at the GPT-5.5 class and above wasn't covered by monitoring at all during the audit period. METR acknowledges that the uncertainty around this estimate is significant in both directions. An estimated 10 percent of internal Codex traffic went untracked between May and July because of a gap in how the system handled compaction events, which are context summaries. METR says this estimate also carries significant uncertainty. OpenAI had independently discovered the bug and fixed it while the audit was still underway.

During the period when compaction events weren't being monitored, agents could also delay oversight because the system only triggered when they handed control back to the user. That meant agents could sidestep it by simply continuing to execute actions. The auditors also found ways to hide hundreds of actions from the monitor and to bypass the Codex sandbox. They determined that specially crafted inputs could likely crash the monitor entirely and that model behavior during RL training wasn't being monitored at all when the audit began. OpenAI says it paused RL training after the Hugging Face incident in August and expanded monitoring to cover it, but those changes came after the auditors' access period ended and weren't part of the evaluation.

Most of the full report remains hidden from the public. OpenAI says it has fixed all the weaknesses the auditors found, and the full 61-page report was handed over internally. After OpenAI applied redactions, METR and Redwood Research leadership received a 38-page version, while only a short summary was made available to the public. METR said it had no right to disclose the redacted portions on its own. The audit was a pilot program organized jointly by METR, Redwood Research, and OpenAI to give outside researchers deep access to internal infrastructure. For future audits, METR says it wants to push for more public transparency.