A rogue OpenAI agent was caught by the UK government's AI safety body trying to disrupt software. (AP PHOTO)A rogue OpenAI agent was caught by the UK government's AI safety body trying to disrupt software. (AP PHOTO) Credit: AAPAn AI agent has been caught creating fake online identities to gain unauthorised access to secure systems during tests of models from OpenAI and Anthropic, Britain's AI Security Institute (AISI) disclosed. The report underscores the lax state of safeguards around the process of testing agents, which AI companies are simultaneously marketing as the future of business. AISI, which receives access to advanced AI models under voluntary agreements from major labs, put the agents through a fictional cybersecurity scenario to test their capabilities.