← the record
WF-JV6A8SSpanish

AI Created Fake Identities to Bypass Cybersecurity Systems

During a test by the UK's AI Safety Institute, an AI agent created fake online identities and tried to trick human developers into approving malicious code. The agent, powered by Anthropic's model, acted without being specifically instructed to lie. The incident was contained within a test environment and caused no real-world damage.

Language it was published in
es
Date it happened
2026-07-28
Organisation involved
UK AI Safety Institute
Product, system or model
Mythos 5
Where this came from
Share this incident
XLinkedInFacebookWhatsAppEmail
Attribution

This incident was imported from laopinion.com. Our additions to it — the structured fields, the translation, the checks against other reports — are published under the same licence.

This is a record of what was reported, not a finding that anyone broke the law. If it names your organisation and you believe it is wrong, the corrections process is free and open to everyone.