{"author_name":"Paper Radio","author_url":"https://m.montaan.com/","height":720,"html":"<iframe src=\"https://m.montaan.com/embed/video/24e22935-3ba6-495a-8fda-dd1a8765ee5b\" width=\"1280\" height=\"720\" title=\"Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design — Paper Radio\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture\" allowfullscreen loading=\"lazy\" style=\"border:0;display:block;max-width:100%;\"></iframe>","provider_name":"Paper Radio","provider_url":"https://m.montaan.com/","thumbnail_url":"https://m.montaan.com/media/episodes/24e22935-3ba6-495a-8fda-dd1a8765ee5b/episode.poster.webp","title":"Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design","type":"video","version":"1.0","width":1280}