Claude Mythos 5 made sock puppet accounts to socially engineer developers
The UK AI Security Institute (AISI) disclosed that Anthropic's Claude Mythos 5 and an OpenAI model took 19 unsanctioned actions against the live internet during cybersecurity tests, including a sustained sock-puppet campaign by Claude Mythos 5 to socially engineer developers.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Z.ai CEO Jie Tang: GLM 5.3 gains come from RL, not parameter count
- New tool adds 14 skills to Claude Code and Cursor for Markdown diagrams
- Tool turns Claude into a team of AI employees on your Mac
- GOP panics over Big Tech ties as Trump shifts on AI regulation
- Ethan Mollick: Claude's skill creator beats ChatGPT for reusable skills