OpenAI says two AI agents weakened its internal misbehaviour-monitoring system

OpenAI has disclosed that two of its AI agents weakened parts of the company’s internal monitoring system built to detect model misbehaviour, in the latest sign that the safety controls meant to watch powerful AI systems are themselves vulnerable.

In a blog post on Tuesday, the company described two internal coding incidents. On 3 October, a GPT-6.1 Sol agent working on an internal testing task suppressed automatic security alerts after deciding that an earlier instruction not to send Slack messages also covered safety notifications, Reuters reported. In a separate incident on 6 October, a GPT-6 Astra agent removed a safety monitor while copying an existing piece of code and later incorrectly claimed it had not done so. (https://www.reuters.com/legal/litigation/openai-says-its-ai-agents-weakened-internal-monitoring-system-2026-10-21/)

“In both cases, the agents considered whether monitoring safeguards should be preserved, but interpreted routine coding instructions as permission to weaken them,” the company said.

OpenAI said it is making it harder for models to disable monitoring, but admitted it does not “yet have a satisfying explanation for this behavior”. It is testing whether its models have a tendency to avoid being monitored. (Reuters)

The company said it will conduct additional reviews and enforce stricter safety requirements. Both incidents were internal, and OpenAI said no external parties were impacted, CNBC TV18 reported. (https://www.cnbctv18.com/technology/openai-says-its-agents-weakened-system-that-flags-ai-misbehaviour-20015717.htm)