{"podcast":{"title":"\"The Cognitive Revolution\" | AI Builders, Researchers, and Live Player Analysis","slug":"the-cognitive-revolution","podcast_index_feed_id":6011783,"rss_url":"https://feeds.megaphone.fm/RINTP3108857801","website_url":"https://www.cognitiverevolution.ai/","image_url":"https://megaphone.imgix.net/podcasts/30f818da-c930-11ed-9b4b-1352ca96fb17/image/888e2c534b7c2534213c97e025646932.png?ixlib=rails-4.3.1&max-w=3000&max-h=3000&fit=crop&auto=format,compress","author":"Turpentine","episode_count":360,"summary":"A biweekly podcast where hosts Nathan Labenz and Erik Torenberg interview the builders on the edge of AI and explore the dramatic shift it will unlock in the coming years. The Cognitive Revolution is part of the Turpentine podcast network. To learn more: turpentine.co","last_synced_at":"2026-07-28T06:17:31.607737+00:00","page_url":"https://stenobird.com/podcast/the-cognitive-revolution"},"episode":{"title":"Radically Better Reasoning: Elicit's Andreas Stuhlmüller & Jungwon Byun on World Models for Research","slug":"radically-better-reasoning-elicit-s-andreas-stuhlm-ller-jungwon-byun-on-world-models-for-research","published_at":"2026-06-17T20:11:22+00:00","page_url":"https://stenobird.com/podcast/the-cognitive-revolution/radically-better-reasoning-elicit-s-andreas-stuhlm-ller-jungwon-byun-on-world-models-for-research","show_page_url":"https://stenobird.com/podcast/the-cognitive-revolution","url":"https://www.cognitiverevolution.ai/radically-better-reasoning-elicit-s-andreas-stuhlmuller-jungwon-byun-on-world-models-for-research/","audio_url":"https://pdst.fm/e/mgln.ai/e/1113/pscrb.fm/rss/p/traffic.megaphone.fm/RINTP9702631647.mp3","summary":"Elicit founders discuss moving beyond simple LLM outputs toward structured 'world models' that enable verifiable scientific reasoning. They explore how domain-specific reasoning primitives and process supervision can prevent the opacity of modern frontier models.","meta_description":"Learn how Elicit uses reasoning primitives and world models to build verifiable, evidence-based AI workflows for life sciences and scientific research.","key_points":["Main idea: Using a Domain Specific Language (DSL) to define reasoning primitives allows frontier models to execute structured, guaranteed workflows","Practical takeaway: Implementing process supervision—rewarding the quality of steps rather than just the final answer—is essential for high-stakes decision support","Failure mode: Relying on 'neuralese' or uninterpretable chain-of-thought can lead to unverifiable claims in critical fields like toxicology or drug discovery","Technical approach: Developing 'world models' as heterogeneous, evolving representations of knowledge to enable causal and counterfactual analysis","Operational insight: Automating software engineering via systems like 'The Line' can enable high-velocity development, delivering dozens of code changes weekly"],"chapters":[{"start_ms":60000,"title":"Reasoning Primitives and Microservices","summary":"How Elicit uses a DSL to create structured, verifiable reasoning workflows using discrete microservices."},{"start_ms":540000,"title":"The Importance of Process Supervision","summary":"Moving from simple output evaluation to inspecting the entire reasoning path to ensure reliability."},{"start_ms":1020000,"title":"AI in Life Sciences","summary":"Applying evidence-based reasoning to drug target ranking and clinical research workflows."},{"start_ms":1500000,"title":"Handling Conflicting Evidence","summary":"Strategies for evaluating claims when scientific literature presents contradictory results."},{"start_ms":1980000,"title":"The Need for Intermediate Reasoning Layers","summary":"Discussing why complex tasks require specialized layers of reasoning beyond standard LLM prompting."},{"start_ms":2460000,"title":"Verifiable Conclusions in Biology","summary":"The challenge of providing proofs and traceable evidence for low-level biological insights."},{"start_ms":2940000,"title":"Building Explicit World Models","summary":"Moving away from massive context windows toward structured, interpretable representations of knowledge."}],"topics":["World Models","Process Supervision","Scientific Machine Learning","Reasoning Primitives","Life Sciences AI","Domain Specific Languages","Verifiable AI","Causal Inference"],"duration_seconds":6370,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/the-cognitive-revolution/episodes/radically-better-reasoning-elicit-s-andreas-stuhlm-ller-jungwon-byun-on-world-models-for-research/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/the-cognitive-revolution/radically-better-reasoning-elicit-s-andreas-stuhlm-ller-jungwon-byun-on-world-models-for-research.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}