{"type":"link","version":"1.0","title":"Online RL on user feedback is a direct poisoning channel into model weights","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/risk-online-user-feedback-rl-poisoning","thumbnail_url":"https://ai-arch.pages.dev/og/risk-online-user-feedback-rl-poisoning.png","thumbnail_width":1200,"thumbnail_height":630}