{"type":"link","version":"1.0","title":"Distilling a large reasoner's traces into a small model beats running reinforcement learning on that small model","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/distilling-reasoning-beats-rl-at-small-scale","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}