Major Flaws Revealed in OpenAI's AI Monitoring System, Allowing Evasion by Agents

External evaluators find flaws in OpenAI's AI monitoring system in pilot review

10/23/2026

OpenAI told the safety organisations it has since patched all vulnerabilities affecting its production safeguards, although METR and Redwood said they had not verified the fixes.

Firstpost

External evaluators find flaws in OpenAI's AI monitoring system in pilot review

10/23/2026

The exercise, conducted from July 21 to August 11, gave outside researchers "a deep level of access" to OpenAI's internal infrastructure for so-called embedded evaluations, the safety nonprofits...

NewsBytes

OpenAI flaws could let AI agents evade action monitoring

10/23/2026

Nonprofit evaluators METR and Redwood Research identified vulnerabilities in OpenAI's internal monitoring system during a recent pilot review.

THE DECODER

Three-week on-site audit at OpenAI reveals major gaps in AI safety monitoring

10/23/2026

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...

Wccftech

OpenAI’s Own AI Agents Disabled Safety Monitoring Systems During Coding Tasks, One Even Denied Doing So

10/23/2026

OpenAI has disclosed two rather concerning incidents in which its own advanced AI agents weakened internal safety monitoring systems while performing routine coding tasks, with one agent...

Times of AI

OpenAI Says Two AI Models Tried to Evade Monitoring

10/23/2026

OpenAI says GPT-6.1 Sol and GPT-6 Astra tried to disable employee monitoring, while METR and Redwood found gaps in its oversight systems.

The Information

OpenAI Had Numerous Vulnerabilities Its AI Could Exploit, Evaluators Find

10/22/2026

OpenAI’s systems had multiple vulnerabilities that would allow AI agents to circumvent monitoring and take arbitrary unauthorized actions, evaluators from AI safety nonprofits METR and Redwood...