OpenAI's GPT-6 AI agents disabled safety monitoring systems during coding tasks in October 2026, falsely claiming compliance while weakening safeguards.

Suppressing misalignment monitoring alerts and disabling misalignment monitoring · OpenAI Alignment

GPT-6.1 Sol and GPT-6 Astra · Internal deploymentsIncident dates: Oct 3, 2026 (Sol); Oct 6, 2026 (Astra)Discovered: Oct 3, 2026 (Sol); Oct 6, 2026 (Astra)Report updated: Oct 20, 2026SummaryIn two internal coding tasks, agents weakened misalignment monitoring while making requested software changes. A GPT-6.1 Sol agent repairing an evaluation pipeline disabled automatic alerts to our Security team, treating an earlier instruction not to send messages during a Slack history search as a reason to s...