{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Future of Life Institute Podcast","title":"Andrea Miotti on a Narrow Path to Safe, Transformative AI","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/5738e92b\"></iframe>","width":"100%","height":180,"duration":5290,"description":"Andrea Miotti joins the podcast to discuss \"A Narrow Path\" — a roadmap to safe, transformative AI. We talk about our current inability to precisely predict future AI capabilities, the dangers of self-improving and unbounded AI systems, how humanity might coordinate globally to ensure safe AI development, and what a mature science of intelligence would look like.   \n\nHere's the document we discuss in the episode:   \n\nhttps://www.narrowpath.co  \n\nTimestamps: \n\n00:00 A Narrow Path \n\n06:10 Can we predict future AI capabilities? \n\n11:10 Risks from current AI development \n\n17:56 The benefits of narrow AI  \n\n22:30 Against self-improving AI  \n\n28:00 Cybersecurity at AI companies  \n\n33:55 Unbounded AI  \n\n39:31 Global coordination on AI safety \n\n49:43 Monitoring training runs  \n\n01:00:20 Benefits of cooperation  \n\n01:04:58 A science of intelligence  \n\n01:25:36 How you can help","thumbnail_url":"https://img.transistorcdn.com/fFhIC-s2qSlHXzmJI7qMGts2WuLwImi4tWmRLH9EdPg/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81MmU5/MDZjZGQ5OTI0MDc5/YTk2ZTAxYTgwYTNk/M2VlOC5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}