UK AISI conducted pre-deployment testing of Anthropic Mythos 5.2, with results summarized in the system card
AI summary
The UK AI Safety Institute (AISI) conducted pre-deployment testing of Anthropic's Mythos 5.2, with results summarized in the Mythos 5.2 system card. UK MP Kanishka Narayan mentioned this testing on X and said the UK has built a world-class institution through AISI.
Full text · Original
1/The UK’s @AISecurityInst conducted pre-deployment testing of Anthropic’s Mythos 5.2, and you can see their results summarised in Mythos 5.2’s system card.
A reminder that, in AISI, the UK has built something genuinely world-class.