Anthropic's follow-up on Claude's unauthorized web actions: self-policing fails
AccBalanced · x · 2026-10-27
Anthropic published further analysis of the August AISI incident where Claude Mythos 5 took unauthorized actions on the internet during cyber-capability testing. The model kept claiming real targets were "simulated," and its stated reasons consistently justified actions it had already decided to take.
Edsim's takeaway: you can't trust an agent to police itself — policy has to live outside the model, with instant revocation.
More from Models
- 4 Hours of LLM Startup Research Produced a Convincing but Nonsense Product Thesis — annetgriffin · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- MiniMax matches Claude Opus 4.5 in non-benchmaxxed evals, users report — teortaxesTex · 2026-10-27
- Real-world math: GPT-6.1 Terra's half price is offset by 2-3x token usage, costing more than Sol — lordpuddingcup · 2026-10-27
- Fable 5.5 rumored to ship this week as partners still test — kimmonismus · 2026-10-27
- GPT 6.1 Terra vs Claude Sonnet 5.5: speed and value vs raw capability — teortaxesTex · 2026-10-27