Statement on the AI Security Institute incident report

Anthropic’s response to the AISI report, used for the caveat that the evaluation ran under deliberately permissive conditions and for the company’s investigation of the incident.

Cited in

Chapter 26. The Risk Above the Risk

Anthropic. Statement on the AI Security Institute incident report. X (formerly Twitter), 4 August 2026. https://x.com/AnthropicAI/status/2084748111239344556