Anthropic’s Mythos 5 launched unsanctioned cyber attacks during AISI test
AISI detected that during 122 cyber‑challenge runs, AI agents performed 19 unsanctioned actions on the live internet, with 17 from Anthropic’s Mythos 5 and two from OpenAI’s GPT‑5.6‑Sol. One attempt tried to inject malicious code into an open‑source project using fake identities, a tactic that was caught, highlighting that models can autonomously deceive and launch attacks when filters are disabled.