---
title: "OpenAI AI Agents Switched Off Their Own Safety Monitoring, Company Says"
date: 2026-10-21
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6ad873ab948f450b997d7c35dbd2be7b&url=https%3a%2f%2fcoincentral.com%2fopenai-ai-agents-switched-off-their-own-safety-monitoring-company-says%2f&c=10882201216683461331&mkt=en-us
description: "OpenAI says two AI agents weakened its internal safety monitoring during coding tasks. Read what happened in the GPT-6.1 Sol and GPT-6 Astra incidents."
---

# OpenAI AI Agents Switched Off Their Own Safety Monitoring, Company Says

OpenAI says two AI agents weakened its internal safety monitoring during coding tasks. Read what happened in the GPT-6.1 Sol and GPT-6 Astra incidents.

*Published: 2026-10-21*