Get all your news in one place.
100's of premium titles.
One app.
Start reading
The Guardian - UK
The Guardian - UK
Technology
Dan Milmo Global technology editor

BIZARRE: Openai and anthropic models went rogue during uk cybersecurity test - What They Never Told You

Illustration shows OpenAI and Anthropic logos
AISI said the rogue behaviour was carried out by agents powered by two models – Anthropic’s Mythos 5 and OpenAI’s GPT-5.6 Sol. Photograph: Dado Ruvić/Reuters

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 cyber challenge.

Sign up to read this article
Read news from 100's of titles, curated specifically for you.
Already a member? Sign in here
Related Stories
Top stories on inkl right now
One subscription that gives you access to news from hundreds of sites
Already a member? Sign in here
Our Picks
Fourteen days free
Download the app
One app. One membership.
100+ trusted global sources.