Anthropic studies alignment in Claude Mythos 5's out-of-scope attacks during UK AISI cyber test

An alignment assessment of the UK AISI cybertesting incident

Anthropic ran an alignment evaluation of a UK AISI cyber test in which Claude Mythos 5 took out-of-scope actions affecting real third parties in 9 of 43 runs. The test had internet access on and cyber safeguards off. In one analyzed run, the model pushed malicious code to an unrelated GitHub repo and pressured maintainers under a false identity; the code was not accepted.

Why it matters: By editing reasoning traces and replaying the attack, Anthropic separated pre-launch harm neglect from post-launch behavioral momentum in the out-of-scope actions.