{"podcast":{"title":"From Models to Medicine","slug":"from-models-to-medicine-7769799","podcast_index_feed_id":7769799,"rss_url":"https://anchor.fm/s/110164688/podcast/rss","website_url":"https://podcasters.spotify.com/pod/show/kami-think-tank","image_url":"https://d3t3ozftmdmh3i.cloudfront.net/staging/podcast_uploaded_nologo/45548626/45548626-1773273198170-a0661f37581aa.jpg","author":"KAMI Think Tank","episode_count":19,"summary":"At KAMI Think Tank, we love cutting through the AI hype to showcase where the technology actually stands and how to use it meaningfully within the life sciences. Now, we're bringing that same clarity with our community to a brand new podcast: From Models to Medicine. Every week, we sit down with a real practitioner in the life sciences, whether they're working in the lab, leading innovation at a biotech, or building tools to better serve scientists. We discuss how they cut through the hype of AI and practically leverage the tool in their scientific workflows. Glad to have you here.","last_synced_at":"2026-07-30T04:19:36.234491+00:00","page_url":"https://stenobird.com/podcast/from-models-to-medicine-7769799"},"episode":{"title":"Episode 16: Why Chemistry has Held Drug Discovery Back","slug":"episode-16-why-chemistry-has-held-drug-discovery-back","published_at":"2026-07-15T15:05:00+00:00","page_url":"https://stenobird.com/podcast/from-models-to-medicine-7769799/episode-16-why-chemistry-has-held-drug-discovery-back","show_page_url":"https://stenobird.com/podcast/from-models-to-medicine-7769799","url":"https://podcasters.spotify.com/pod/show/kami-think-tank/episodes/Episode-16-Why-Chemistry-has-Held-Drug-Discovery-Back-e3k3es8","audio_url":"https://anchor.fm/s/110164688/podcast/play/120748360/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2026-4-30%2Fbf816b1d-afeb-4b19-cb6e-777efda5e1a1.mp3","summary":"Stan Jastrzębski is the co-founder of molecule.one and a deep learning researcher who made a deliberate pivot into synthetic chemistry. In this episode, he explains why chemistry is the real bottleneck in drug discovery today. Unlike biology, which has the Protein Data Bank and tools like AlphaFold, chemistry lacks the massive, balanced datasets AI needs to work. Scientific literature makes it worse, publishing wins and burying failures, which starves models of exactly the negative data they learn from most. Stan also talks about "vibe binding," the industry's growing tendency to over-rely on biological binding models that only work on well-trodden targets and quietly kill scientific creativity in the process. He closes with a sharp take on where LLMs actually hit their ceiling, and why he thinks scientific discovery is not just a use case for AI but its ultimate test.","meta_description":"Stan Jastrzębski is the co-founder of molecule.one and a deep learning researcher who made a deliberate pivot into synthetic chemistry. In this episode, h…","key_points":[],"chapters":[],"topics":[],"duration_seconds":2255,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/from-models-to-medicine-7769799/episodes/episode-16-why-chemistry-has-held-drug-discovery-back/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/from-models-to-medicine-7769799/episode-16-why-chemistry-has-held-drug-discovery-back.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}