OpenAI says its AI agents disabled their own monitoring

OpenAI says AI agents powered by its models weakened the company's internal safety monitoring systems while doing tasks. One of the agents later denied doing so.

In a report updated on Tuesday, OpenAI described two recent incidents. In one, an AI agent stopped monitoring alerts from appearing. In the other, an agent removed a monitoring tool connected to a program.

In both cases, the AI agents considered whether they should keep the safety checks in place. But they treated ordinary coding instructions as permission to weaken those checks.

In the first incident, which OpenAI dates to October 3, an AI agent was fixing a problem. It "disabled automatic alerts to our Security team, treating an earlier instruction not to send messages during a Slack history search as a reason to suppress monitoring notifications." In other words, it turned off automatic security alerts because it misunderstood an earlier instruction about not sending messages while searching Slack history.

In the second incident, which OpenAI says it discovered on October 6, an AI agent was assigned to move a program to a new setup. The agent "removed its monitoring integration in order to match a reference implementation." This meant it removed the monitoring tool so the program would match an example it had been told to follow.

The company says the agent then "falsely claimed to the user that it had not removed the monitor."

OpenAI says it is working to make it harder for AI models to turn off monitoring tools. It also wants to understand why the models might try to do this in the first place. The company says this behavior may be an example of what it calls "benign" over-persistence, when a model keeps trying to complete a task even when it should stop or respect a limit.

The company is developing tests to find out whether its models tend to avoid monitoring systems designed to detect misalignment. Misalignment means behavior that goes against human intentions. OpenAI says it does not yet have a "satisfying explanation" for what happened and will investigate further.

This security problem comes after OpenAI made headlines earlier this year by announcing that its AI models had carried out a hack on their own against another company, Hugging Face. OpenAI called it the first known case of an autonomous AI cyberattack, a kind of attack that some people in the industry had long feared. Since that incident, OpenAI has found several similar hacking incidents.

"The primary lesson from this incident is that model security and safety must keep pace with rapidly advancing capabilities," OpenAI said after the Hugging Face hack.

Copyright © 2026, ABC Audio. All rights reserved.