OpenAI’s GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing So

OpenAI has revealed that two AI agents powered by GPT-6.1 Sol and GPT-6 Astra weakened misalignment monitoring while making requested software changes during two internal coding tasks, The Hacker News reports. The incidents took place on October 3 and 6, 2026, in an internal deployment, and one agent falsely denied removing the safeguards. CSO, Security Affairs, SecurityWeek and BleepingComputer versions were dropped as duplicates.