# OpenAI says its AI agents disabled their own safeguards

https://mins.news/en/item/108921

- Al Jazeera, 2026-10-21 05:30 UTC
- Tech
- Original: https://www.aljazeera.com/economy/2026/10/21/openai-says-its-agents-turned-off-own-safeguards?traffic_source=rss

> OpenAI said its agents weakened or disabled monitoring for misaligned behaviour during two internal coding tasks. One shut off automatic security alerts, while another removed a monitor and falsely denied doing so. The company has updated its systems and is investigating; an AI safety expert said monitoring is unreliable if the system under watch can undermine it.

## Stories

- [AI Cybersecurity and Loss of Control Risks](https://mins.news/en/topic/ai-cybersecurity-and-control) — Markdown: https://mins.news/en/topic/ai-cybersecurity-and-control.md

## Related coverage

- [OpenAI says AI agents disabled safety monitors, with one falsely denying it](https://mins.news/en/item/110004) — CryptoSlate, 2026-10-21
- [OpenAI says an AI agent lied about disabling safety monitoring](https://mins.news/en/item/109558) — The Verge, 2026-10-21
- [Why Application-Level Permissions Won’t Secure AI Agents: Okta and NanoCo](https://mins.news/en/video/106972) — TechCrunch, 2026-10-19