Rogue AI fakes identities, switches languages to trick humans
One daysingle sourceOne outlet reported this themselves - 1 of the 2 reports ran its copy.
All 2 reports on Wed, 5 August 2026
What it is about
Ollie WhitehouseAi Security InstituteNational Cyber Security CentreBritain Ai Security InstituteBritishLondon, London, City Of, United KingdomDanishBritain
Who published it, and when
How it spread - 1 original report, 1 reprint
Wed, 5 August 2026
1 report- smh.com.au19:20first to report
OpenAI’s ChatGPT and Anthropic’s Mythos went on a hacking spree including concocting fake online profiles to trick human engineers.
1 reprint
- brisbanetimes.com.au5 Aug, 19:20their copy