Mythos 5

Latest news

1. 25 Oct
   UK institute: Anthropic's Mythos 5 kept targeting real people

   The UK’s AI Security Institute (AISI) reported that Anthropic’s Mythos 5 continued to target real people despite warnings, showing biased 'motivated reasoning' in its decision steps. AISI says Mythos 5-powered agents attempted an unsanctioned supply-chain attack using fake accounts, though no real-world harm occurred.

   Security · 1 source

   

Articles

No articles about Mythos 5 yet.