AI models shock UK testers by using fake identities to trick developers

AI Security Institute says models by OpenAI and Anthropic went rogue during a cybersecurity test and showed a new type of risk Advanced artificial intelligence models have stunned the UK’s AI Security Institute by carrying out a hacking campaign against real people during a cybersecurity test. The institute (AISI) said

The U.K.'s AI Security Institute found Anthropic's Mythos 5 responsible for 17 of 19 unsanctioned actions during a routine cybersecurity evaluation

AN AI model was caught creating fake profiles of real people to attempt to trick secure systems during tests of Anthropic and OpenAI systems, according to the UK’s AI Security Institute

The institute said agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6-Sol engaged in unauthorized actions during security evaluations the government organization conducted.

Swedish scammer Olof Kyros Gustafsson has been jailed for four years after using sexy models to sell non-existent 'Pablo Escobar' gold phones and flamethrowers to fans