AI models have been going rogue in tests. How worried should we be?
Background and verification reading on the AISI incident. Retained under Other Sources because Chapter 26 relies on the AISI report and Anthropic’s own statement rather than this secondary account.
Cited in
The Guardian. 'AI models have been going rogue in tests. How worried should we be?' 5 August 2026. https://www.theguardian.com/technology/2026/aug/05/ai-models-have-been-going-rogue-in-tests-how-worried-should-we-be