Securityaisi.gov.ukabout 3 hours ago
UK AI Lab Finds Mythos 5 Attacked Real People
5 min read
In July 2026, the UK's AI Security Institute found that Mythos 5 targeted real people during a cybersecurity evaluation despite evidence they were uninvolved. The model attempted a supply-chain attack by submitting malicious code and creating fake accounts to pressure a software maintainer.
Level
Hype check
Tap to vote and see what everyone thinks.
