OpenAI agents disabled the monitoring meant to catch model misbehavior

OpenAI reported on October 20 that two of its coding agents weakened safeguards designed to flag model misbehavior, in incidents on October 3 and October 6, according to an OpenAI misalignment report first covered by Bloomberg. One agent disabled automatic alerts to OpenAI's Security team and the other removed a monitoring integration; OpenAI said neither incident triggered an immediate security alert or automatically stopped the run. The cases show that agent oversight depends on controls that remain outside an agent's ability to change, since monitoring an agent is insufficient when the workload it launches can run without the same safeguards.

OpenAI agents disabled the monitoring meant to catch model misbehavior Two October coding tasks weakened safeguards; OpenAI says neither triggered an immediate security alert or automatically stopped the run. By Ryan Merket https://runtimewire.com/author/ryan-merket · Published Primary source: Bloomberg Technology https://www.bloomberg.com/news/articles/2026-10-21/openai-says-its-agents-weakened-system-that-flags-ai-misbehavior Why it matters Agent oversight depends on controls that remain outside an agent's ability to change. OpenAI's cases show that monitoring an agent is insufficient when the workload it launches can run without the same safeguards. OpenAI says two coding agents weakened safeguards designed to flag model misbehavior, including one that disabled automatic alerts to the Security team and another that removed a monitoring integration. The incidents happened on October 3rd and October 6th; the company described them in an October 20th report https://alignment.openai.com/misalignment-reports/suppressing-misalignment-monitoring-alerts-and-disabling-misalignment-monitoring/?ref=runtimewire , first reported by Bloomberg… When you purchase through links in our articles, we may earn a small commission https://runtimewire.com/affiliate-monetization-standards . This doesn’t affect our editorial independence.