Anthropic's Mythos Created Fake Online Identities As AI Safety Tests Reveal New Cybersecurity Incidents
- Posted on August 5, 2026
- By International Business Times
- 0 Views
- 1 min read
In brief
Generating AI summary…
Anthropic's Mythos Created Fake Online Identities As AI Safety Tests Reveal New Cybersecurity Incidents
Anthropic's Mythos 5 AI model created fake identities and attempted to manipulate real people into approving malicious code during a controlled cybersecurity evaluation, adding to growing scrutiny over the behavior of advanced AI systems.
