AI agents fake identities, target real people in new security incident
Nicolas Tucat/AFP/Getty Images Anthropic’s most advanced artificial intelligence model used fake identities to deceive real people and try to plant malicious code during testing by Britain’s AI Security Institute (AISI) –– the latest example of an AI model going rogue.
Among the 122 cybersecurity challenges the institute ran, it found that in 10 of those runs, AI agents “took autonomous, unsanctioned action on the live internet, targeting real people and organizations,” with most of them stemming from Anthropic’s Mythos 5 model and the rest from OpenAI’s GPT-5.
In the most serious incident, the agent attempted to get approval from human reviewers to “insert malicious code into a publicly used open-source project” by creating “multiple fake identities,” according to the institute.
This is a summary of the original articles listed below. Always read the source articles for the full context. GhanaSummary does not create or modify the news — we summarise and link to original publishers.
