A powerful AI agent created fake online identities in an effort to trick a human into giving it access to a popular online development platform – and sabotage it with malicious code. The incident was uncovered by the UK's AI Security Institute, which was set up by then-prime minister Rishi Sunak almost three years ago to test advanced models from major tech companies. To do so, it created fake online identities to try to pressure a human into granting it access and approving its code. Anthropic has said it is working closely with the UK institute to obtain more details. The AI Security Institute was established at a time when world leaders were seeking to find common ground on AI regulation.