{"type":"link","version":"1.0","title":"A findability task that reuses a category's own words primes users to it and inflates apparent success","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/evaluation-tasks-must-not-echo-the-labels-being-tested","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}