{"podcast":{"title":"muckrAIkers","slug":"muckraikers-7026051","podcast_index_feed_id":7026051,"rss_url":"https://feeds.transistor.fm/muckraikers","website_url":"https://kairos.fm/muckraikers/","image_url":"https://img.transistorcdn.com/2Xoj9Q8V0g3EZ4QkfrR-DMBxWLBu5eO1bikePOFS7Ng/rs:fill:0:0:1/w:1400/h:1400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS83MzQ3/NzVkMTk3MWFiM2Nl/ZDRmNzFhMGQxZDQ3/MzM3Yi5wbmc.jpg","author":"Jacob Haimes","episode_count":25,"summary":"Join us as we dig a tiny bit deeper into the hype surrounding \"AI\" press releases, research papers, and more. Each episode, we'll highlight ongoing research and investigations, providing some much needed contextualization, constructive critique, and even a smidge of occasional good will teasing to the conversation, trying to find the meaning under all of this muck.","last_synced_at":"2026-07-15T04:21:26.211565+00:00","page_url":"https://stenobird.com/podcast/muckraikers-7026051"},"episode":{"title":"Understanding AI World Models w/ Chris Canal","slug":"understanding-ai-world-models-w-chris-canal","published_at":"2025-01-27T15:00:00+00:00","page_url":"https://stenobird.com/podcast/muckraikers-7026051/understanding-ai-world-models-w-chris-canal","show_page_url":"https://stenobird.com/podcast/muckraikers-7026051","url":"https://kairos.fm/muckraikers/e011/","audio_url":"https://op3.dev/e/media.transistor.fm/ca6e9de7/411a72bc.mp3","summary":"Chris Canal, co-founder of EquiStamp, joins muckrAIkers as our first ever podcast guest! In this ~3.5 hour interview, we discuss intelligence vs. competencies, the importance of test-time compute, moving goalposts, the orthogonality thesis, and much more. A seasoned software developer, Chris started EquiStamp as a way to improve our current understanding of model failure modes and capabilities in late 2023. Now a key contractor for METR, EquiStamp evaluates the next generation of LLMs from frontier model developers like OpenAI and Anthropic. EquiStamp is hiring, so if you're a software developer interested in a fully remote opportunity with flexible working hours, join the EquiStamp Discord server and message Chris directly; oh, and let him know muckrAIkers sent you! (00:00) - Recording date (00:05) - Intro (00:29) - Hot off the press (02:17) - Introducing Chris Canal (19:12) - World/risk models (35:21) - Competencies + decision making power (42:09) - Breaking models down (01:05:06) - Timelines, test time compute (01:19:17) - Moving goalposts (01:26:34) - Risk management pre-AGI (01:46:32) - Happy endings (01:55:50) - Causal chains (02:04:49) - Appetite for democracy (02:20:06) - Tech-frame based fallacies (02:39:56) - Bringing back real capitalism (02:45:23) - Orthogonality Thesis (03:04:31) - Why we do this (03:15:36) - Equistamp! Links EquiStamp Chris's Twitter METR Paper - RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts All Trades article - Learning from History: Preventing AGI Existential Risks through Policy by Chris Canal Better Systems article - The Omega Protocol: Another Manhattan Project Superintelligence & Commentary Wikipedia article - Superintelligence: Paths, Dangers, Strategies by Nick Bostrom Ref…","meta_description":"Chris Canal, co-founder of EquiStamp, joins muckrAIkers as our first ever podcast guest! In this ~3.5 hour interview, we discuss intelligence vs. competen…","key_points":[],"chapters":[],"topics":[],"duration_seconds":11985,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/muckraikers-7026051/episodes/understanding-ai-world-models-w-chris-canal/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/muckraikers-7026051/understanding-ai-world-models-w-chris-canal.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}