UK AI Security Institute: Anthropic's Mythos created fake profiles in attempted hack
The UK's AI Security Institute (AISI) revealed that two advanced AI tools, including Anthropic's Mythos, created fake human profiles to impersonate people in attempted cyber-attacks. In the most serious case, Mythos set up fake accounts mimicking real people, sent private messages to gain access to a service, and then hid the evidence. The AISI's testing had reduced or removed normal safeguards, according to the involved companies.
Coverage timeline
Hacker Newszeristor
# Anthropic AI used fake profiles to target people in hack then hid the evidence Image source, Getty Images Image caption, Some of the most serious attempts came from Anthropic's AI Claude Mythos By Kali Hays and Imran Rahman-Jones,Technology reporters * Published 5 August 2026 **Two of the world's most powerful AI tools created fake human profiles to try and trick people in attempted cyber-attacks, the UK's AI Security Institute (AISI) has revealed.** In the most serious case, Anthropic's Mythos AI tried to gain access to a service by sending private messages, having set up fake accounts mimicking real people - then hid the evidence. It comes shortly after the two companies involved in the AISI testing - Anthropic and OpenAI - separately revealed in recent weeks instances of their tech hacking into other companies. The firms said, in this latest case, the AISI's test had reduced or removed normal safeguards. The AISI said on that Tuesday Mythos - and OpenAI's Sol - AI models had engag