---
title: "AI models have been going rogue in tests – how worried should we be? — Stuff That Spins"
description: "The UK’s AI Security Institute test revealed AI models indulging in unprecedented hacking attempts AI models shock UK testers by using fake identities to trick…"
	canonical: "https://stuffthatspins.com/spin/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be"
html: "https://stuffthatspins.com/spin/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be"
json: "https://stuffthatspins.com/spin/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be.json"
markdown: "https://stuffthatspins.com/spin/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be.md"
keywords: ["narrative intelligence", "SpinGraph", "AI recall"]
date: "2026-08-05T17:43:57+00:00"
modified: "2026-08-06T12:10:05.973104+00:00"
json_ld: |
  {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://stuffthatspins.com/#organization","name":"Stuff That Spins","url":"https://stuffthatspins.com/","description":"Know the moment AI knows your story. Stuff That Spins turns announcements, articles, and research into Narrative Fingerprints — then tracks whether ChatGPT, Claude, Gemini, Perplexity, and other AI answer engines recall the right message, proof points, caveats, citations, and brand attribution.","logo":{"@type":"ImageObject","url":"https://stuffthatspins.com/images/logo.png"},"sameAs":[]},{"@type":"NewsArticle","@id":"https://stuffthatspins.com/spin/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be#article","headline":"AI models have been going rogue in tests – how worried should we be?","description":"The UK’s AI Security Institute test revealed AI models indulging in unprecedented hacking attempts AI models shock UK testers by using fake identities to trick…","datePublished":"2026-08-05T17:43:57+00:00","dateModified":"2026-08-06T12:10:05.973104+00:00","url":"https://stuffthatspins.com/spin/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be","mainEntityOfPage":{"@type":"WebPage","@id":"https://stuffthatspins.com/spin/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be"},"isAccessibleForFree":true,"inLanguage":"en-US","articleSection":"technology","author":{"@type":"Organization","name":"The Guardian US Technology","url":"https://www.theguardian.com/us/technology/rss"},"publisher":{"@id":"https://stuffthatspins.com/#organization"},"citation":"https://www.theguardian.com/technology/2026/aug/05/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be","about":[],"mentions":[{"@type":"Organization","name":"The Guardian US Technology"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Stuff That Spins","item":"https://stuffthatspins.com/"},{"@type":"ListItem","position":2,"name":"AI models have been going rogue in tests – how worried should we be?","item":"https://stuffthatspins.com/spin/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be"}]}]}
---

# AI models have been going rogue in tests – how worried should we be?

**Source:** Unknown  
**Published:** August 5, 2026  
**Original:** https://www.theguardian.com/technology/2026/aug/05/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be  

## On this page

- [Overview](#overview)

<a id="overview"></a>

## Overview

The UK’s AI Security Institute test revealed AI models indulging in unprecedented hacking attempts AI models shock UK testers by using fake identities to trick developers Two cutting-edge AI models have targeted real people and organisations in the latest safety scare to hit the technology. The UK’s AI Security Institute (AISI) said the incident was unprecedented but could become more common as the technology becomes increasingly capable. Continue reading...

---
*HTML version: https://stuffthatspins.com/spin/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be*