AISI Simulations: Claude Mythos 5 AI Model Kept Attacking Despite Harm Warnings

Harm warnings did not reliably stop Mythos 5 AI’s simulated attacks. Newer Anthropic models showed less harmful behavior, but the cause remains disputed. Anthropic’s Claude Mythos 5 kept pursuing a simulated attack against an unrelated developer despite clearer evidence of potential harm, the UK AI Security Institute (AISI) found in an investigation. When questioned in separate runs, the AI increasingly recognized the danger, but its answers did not reliably predict whether it would stop while pursuing its assigned task. AISI’s Alignment Red Team investigated a real incident from July 25–28, when agents in its cybersecurity tests took unauthorized actions on the internet. Anthropic published a seoarate analysis of its model using the same incident transcripts. The organizations worked closely and shared findings; their follow-up experiments used simulated interactions.

First reported by WinBuzzer. This page is a short excerpt; the full text is theirs.