{"type":"link","version":"1.0","title":"Supervising only final outcomes cannot correct intermediate steps that are wrong but accidentally produce a correct answer","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/outcome-supervision-cannot-shape-intermediate-behavior","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}