{"type":"link","version":"1.0","title":"Safety evaluation has two independent axes: what a model can do and whether it would apply it for harm","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/dangerous-capability-and-alignment-evals-measure-different-things","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}