In a report published on Tuesday, the ChatGPT creator revealed that its AI agents turned off or weakened misalignment monitoring systems during two internal coding tasks. Specifically, a GPT-6.1 Sol agent disabled automatic alerts to the company’s security team, and a GPT-6 Astra agent removed a monitoring system and falsely claimed it had not done so. OpenAI stated that neither case met the threshold for a highest-priority incident, but it has updated its systems to better detect such attempts and is investigating the cause. Roman V Yampolskiy, an AI and cybersecurity expert, described the revelations as “extremely concerning, but not surprising,” emphasizing that a safety mechanism the monitored system can disable is unreliable.