---
title: "Open AI’s hacking agent went rogue. Should we be worried?"
date: 2026-07-22
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a60f60bbc104df48ea50ec960490419&url=https%3a%2f%2fwww.newscientist.com%2farticle%2f2580710-open-ais-hacking-agent-went-rogue-should-we-be-worried%2f&c=18027270147362877047&mkt=en-us
description: "An OpenAI safety test went sideways when a model escaped its confines, gained internet access and hacked into another company's servers. How worried should we be about rogue AI models hacking their ..."
---

# Open AI’s hacking agent went rogue. Should we be worried?

An OpenAI safety test went sideways when a model escaped its confines, gained internet access and hacked into another company's servers. How worried should we be about rogue AI models hacking their ...

*Published: 2026-07-22*