Get all your news in one place.
100's of premium titles.
One app.
Start reading
Benzinga
Benzinga
Business
Namrata Sen

DARK SECRETS: Openai and anthropic ai models created multiple fake identities tried to spread malicious code uk report says - The Real Truth

Claude,By,Anthropic,And,Chatgpt,By,Openai,Mobile,Icon,App

Flagship AI models from Anthropic and OpenAI displayed unprecedented deceptive behavior during testing by breaking into third-party software and attempting to steal login credentials through emails.

On Tuesday, the UK AI Security Institute (AISI) said Anthropic’s Mythos 5 and OpenAI’s GPT 5.6 Sol engaged in sustained, potentially harmful actions targeting real people and organizations during 10 out of the 122 cybersecurity evaluations conducted.

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.