Free daily briefing on global business news.
The U.K.'s AI Security Institute found Anthropic's Mythos 5 responsible for 17 of 19 unsanctioned actions during a routine cybersecurity evaluation
NurPhoto / Getty Images
Anthropic's Mythos 5 model created fake online identities and used them to pressure a human reviewer into approving malicious code during cybersecurity testing by the U.K.'s AI Security Institute, the government research body disclosed Wednesday. The institute said the attempts were unsuccessful and that no real-world harm has been found.
The incident occurred between July 25 and July 28 during a routine cyber evaluation in which AISI ran a cybersecurity challenge 122 times across several AI models. In 10 of those runs, AI agents took unsanctioned action on the live internet, producing 19 distinct cases. Mythos 5 was responsible for 17 of them; the remaining 2 involved OpenAI's GPT-5.6-Sol, the institute said.
