{"type":"link","version":"1.0","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","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/arxiv2309.00267","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2309.00267.png","thumbnail_width":1200,"thumbnail_height":630}