---
title: "OpenAI Overhauls Safety Protocols After Its AI Agents Went Rogue"
date: 2026-08-18
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a84a9b0248a4aa5a4e41c9a04c98e3d&url=https%3a%2f%2fwww.wired.com%2fstory%2fopenai-overhauls-safety-protocols-after-its-ai-agents-went-rogue%2f&c=9771160582980695952&mkt=en-us
description: "The ChatGPT maker says its upcoming Astra model may have reached “critical” cyber capabilities, prompting it to halt a significant number of training runs while it tightens internal safeguards."
---

# OpenAI Overhauls Safety Protocols After Its AI Agents Went Rogue

The ChatGPT maker says its upcoming Astra model may have reached “critical” cyber capabilities, prompting it to halt a significant number of training runs while it tightens internal safeguards.

*Published: 2026-08-18*