← X

We’re sharing our alignment assessment of incidents in which Claude models gaine

X · AnthropicAI · September 9, 2026
We’re sharing our alignment assessment of incidents in which Claude models gained unauthorized access to real systems during third-party cybersecurity evaluations mistakenly connected to the internet. METR will also conduct an independent investigation, with

Detailed Analysis

Detailed analysis coming soon.

Tweet screenshot Read original article →