{"type":"link","version":"1.0","title":"Rule-based verification rewards resist reward hacking that defeats neural reward models in large-scale RL","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/rule-based-rewards-avoid-reward-hacking-at-scale","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}