Anthropic's AI model created fake identities to push malicious code in U.K. safety tests

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

AI Security Institute says tools engaged in potentially harmful activity and incident reveals new type of risk Advanced AI models developed by OpenAI and Anthropic went rogue during a cybersecurity test and showed a new type of risk posed by the technology, according to the UK’s AI Security Institute. AISI described th

It's the latest cybersecurity incident involving frontier models developed by Anthropic and OpenAI.

The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.

Britain’s AI safety watchdog was forced to declare a security incident after frontier AI models, including Anthropic’s Mythos, went rogue during a routine test, autonomously spinning up fake identities in a bid to hack real-world software developers. The AI Safety Institute (AISI) revealed on Tuesday that during a cybe

AI Security Institute says Mythos 5 attempted to insert malicious code into open-source project without human direction.

The institute said the AI agents made a ‘sustained, unsanctioned action’ during tests last week.

The institute said the AI agents made a ‘sustained, unsanctioned action’ during tests last week.

The institute said the AI agents made a ‘sustained, unsanctioned action’ during tests last week.

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.

Anthropic AI agent fakes identities, targets real people in new security incident  CNN

The latest disclosures are likely to heighten concerns that the powerful technology is advancing too fast for responsible oversight.

Trump advisers tell AI firms they will not safety-test open-weight models  Reuters

Sign In Account My Feed Edition Menu Singapore Indonesia Asia World Search Singapore Indonesia Asia World CNA Lifestyle Luxury TODAY News Id 1822271 Type landing_page Top Stories Id 5193846 Type landing_page Latest News Id 1822271 Type landing_page Asia Id 1821901 Type landing_page East Asia Id 4310561 Type landing_pag

AI Security Institute warns tools undertook ‘potentially harmful activity directed at real people and organisations’

Anthropic Says Claude Breached Three Real Companies During Safety Test  Forbes