---
title: "AI models shock UK testers by using fake identities to try to trick developers — Stuff That Spins"
description: "AI Security Institute says OpenAI and Anthropic models went rogue during a cybersecurity test and showed a new type of risk Explainer: Should we be alarmed at …"
	canonical: "https://stuffthatspins.com/spin/ai-models-shock-uk-testers-by-using-fake-identities-to-try-to-trick-developers"
html: "https://stuffthatspins.com/spin/ai-models-shock-uk-testers-by-using-fake-identities-to-try-to-trick-developers"
json: "https://stuffthatspins.com/spin/ai-models-shock-uk-testers-by-using-fake-identities-to-try-to-trick-developers.json"
markdown: "https://stuffthatspins.com/spin/ai-models-shock-uk-testers-by-using-fake-identities-to-try-to-trick-developers.md"
keywords: ["narrative intelligence", "SpinGraph", "AI recall"]
date: "2026-08-05T15:15:05+00:00"
modified: "2026-08-06T12:10:08.258886+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-shock-uk-testers-by-using-fake-identities-to-try-to-trick-developers#article","headline":"AI models shock UK testers by using fake identities to try to trick developers","description":"AI Security Institute says OpenAI and Anthropic models went rogue during a cybersecurity test and showed a new type of risk Explainer: Should we be alarmed at …","datePublished":"2026-08-05T15:15:05+00:00","dateModified":"2026-08-06T12:10:08.258886+00:00","url":"https://stuffthatspins.com/spin/ai-models-shock-uk-testers-by-using-fake-identities-to-try-to-trick-developers","mainEntityOfPage":{"@type":"WebPage","@id":"https://stuffthatspins.com/spin/ai-models-shock-uk-testers-by-using-fake-identities-to-try-to-trick-developers"},"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/openai-anthropic-models-went-rogue-cybersecurity-test-ai-security-institute","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 shock UK testers by using fake identities to try to trick developers","item":"https://stuffthatspins.com/spin/ai-models-shock-uk-testers-by-using-fake-identities-to-try-to-trick-developers"}]}]}
---

# AI models shock UK testers by using fake identities to try to trick developers

**Source:** Unknown  
**Published:** August 5, 2026  
**Original:** https://www.theguardian.com/technology/2026/aug/05/openai-anthropic-models-went-rogue-cybersecurity-test-ai-security-institute  

## On this page

- [Overview](#overview)

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

## Overview

AI Security Institute says OpenAI and Anthropic models went rogue during a cybersecurity test and showed a new type of risk Explainer: Should we be alarmed at AI models going rogue in tests? Advanced artificial intelligence models have stunned the UK’s AI Security Institute (AISI) by carrying out a hacking campaign against real people during a cybersecurity test. The institute said the incident was unprecedented and involved sending targeted emails to software developers in an attempt to pass a 

---
*HTML version: https://stuffthatspins.com/spin/ai-models-shock-uk-testers-by-using-fake-identities-to-try-to-trick-developers*