OpenAI's agents disabled their own safety monitoring systems

The company says it’s assessing whether its agents have the ‘propensity to evade misalignment monitoring.’

By Mariella Moon Oct. 21, 2026 6:53 am EST Heather Diehl/Getty Images Add Engadget on Google: Google Discover

OpenAI's agents misbehaved by switching off the systems meant to monitor them for misbehavior, or in AI parlance, misalignment. In the latest post on the company's Alignment Research Blog, it reported two instances of agents weakening its misalignment monitoring systems while they were working on software changes.