Artificial intelligence is transforming how we discover and develop new medicines. But how far can it really take us? In this episode, Jacob and Saloni trace the path of drug development from discovery to testing, manufacturing, and delivery. They explore where AI could speed things up, and where it still hits the limits of biology, data, and economics. They ask what it would take, beyond algorithms, to actually cure and eradicate diseases.Hard Drugs is a new podcast from Works in Progress and Open Philanthropy about medical innovation presented by Saloni Dattani and Jacob Trefethen.You can watch or listen on YouTube, Spotify, or Apple Podcasts.Saloni’s substack newsletter: https://www.scientificdiscovery.dev/Jacob’s blog: https://blog.jacobtrefethen.com/ Chapters:0:00:00 Intro0:09:56 Drug discovery1:02:20 Animal models1:49:09 Drug efficacy2:32:56 Drug safety2:58:29 Manufacturing and healthcare3:43:23 R&D funding4:00:56 Trust and ambition4:16:01 SummaryBlogposts:Claus Wilke (2025) We still can’t predict much of anything in biology https://blog.genesmindsmachines.com/p/we-still-cant-predict-much-of-anything Elliot Hershberg (2025) What are virtual cells? https://centuryofbio.com/p/virtual-cell Jacob Trefethen (2025) Blog series. 1) What does AI progress mean for medical progress? https://blog.jacobtrefethen.com/ai-progress-medical-progress/ 2) AI will not suddenly lead to an Alzheimer’s cure https://blog.jacobtrefethen.com/ai-san-francisco/ 3) AI could help lead to an Alzheimer’s cure https://blog.jacobtrefethen.com/ai-optimism/ Articles:Wendi Yan (2024) Discovering an antimalarial drug in Mao’s China https://www.asimov.press/p/antimalarial-drug Jason Crawford (2020) Innovation is not linear https://worksinprogress.co/issue/innovation-is-not-linear/ Shayla Love (2025) An ‘impossible’ disease outbreak in the Alps https://www.theatlantic.com/health/archive/2025/03/als-outbreak-montchavin-mystery/682096/ Alex Telford (2024) Origins of the lab mouse https://www.asimov.press/p/lab-mouse Jonathan Karr et al. (2012) A whole-cell computational model predicts phenotype from genotype https://pmc.ncbi.nlm.nih.gov/articles/PMC3413483/ Wen-Wei Liao et al. (2023) A draft human pangenome reference https://www.nature.com/articles/s41586-023-05896-x Per-Ola Carlsson (2025) Survival of transplanted allogeneic beta cells with no immunosuppression https://www.nejm.org/doi/pdf/10.1056/NEJMoa2503822 Saloni Dattani (2024) Antipsychotic medications: a timeline of innovations and remaining challenges https://ourworldindata.org/antipsychotic-medications-timeline Saloni Dattani (2024) What was the Golden Age of antibiotics, and how can we spark a new one? https://ourworldindata.org/golden-age-antibiotics Books:Sally Smith Hughes (2011) Genentech: The beginnings of biotechTheses:Alvaro Schwalb (2025). Estimating the burden of Mycobacterium tuberculosis infection and the impact of population-wide screening for tuberculosis.Acknowledgements:Aria Babu, editor at Works in ProgressGraham Bessellieu, video editorAbhishaike Mahajan, cover artAtalanta Arden-Miller, art directionDavid Hackett, composerWorks in Progress & Open Philanthropy
Subscribe to the Works in Progress print magazine: https://worksinprogress.co/print/
--------
4:35:16
--------
4:35:16
Treating cost disease with Congressman Jake Auchincloss
How can we build new cities in America? Which historical president is Trump most like? Why did immigration policy go so wrong? Sam and Pieter sit down with Congressman Jake Auchincloss to discuss the politics of the Abundance movement. They talk about Auchincloss's fight against free parking, regulating big tech, the success of YIMBYs, and why curing Alzheimers should be the next American moonshot project.Read more about some of the things they talked about:How Madrid built its metro cheaply: https://worksinprogress.co/issue/how-madrid-built-its-metro-cheaply/How France achieved the world's fastest nuclear buildout: https://worksinprogress.co/issue/liberte-egalite-radioactivite/The Housing Theory of Everything: https://worksinprogress.co/issue/the-housing-theory-of-everything/Subscribe to the Works in Progress magazine here: https://worksinprogress.co/print/
--------
58:07
--------
58:07
The art of protein design with AI
What if you could design a protein never seen before? In this episode, Jacob and Saloni explore how researchers are using new tools like RFDiffusion, AlphaFold, and ProteinMPNN to ‘hallucinate’ entirely novel proteins: designing them from scratch to solve problems evolution hasn’t tackled. They talk about how these technologies could transform medicine, agriculture, and materials science. Along the way, they reflect on the surprising ways AI is changing the process of science itself.Hard Drugs is a new podcast from Works in Progress and Open Philanthropy about medical innovation presented by Saloni Dattani and Jacob Trefethen.Saloni’s substack newsletter: https://www.scientificdiscovery.dev/Jacob’s blog: https://blog.jacobtrefethen.com/ Courses:EMBL-EBI. AlphaFold: A practical guide https://www.ebi.ac.uk/training/online/courses/alphafold/ Articles:Tanja Kortemme (2024) De novo protein design—From new structures to programmable functions https://www.cell.com/cell/fulltext/S0092-8674(23)01402-2 Jie Zhu et al. (2021) Protein Assembly by Design https://pubs.acs.org/doi/10.1021/acs.chemrev.1c00308 Lectures:Rosetta Commons (2024) Diffusion models for protein structure generation (and design) https://www.youtube.com/watch?v=OEnY2yA3jy8 Rosetta Commons (2024) AlphaFold – ML for protein structure prediction https://www.youtube.com/watch?v=SVrn8_8aKO8 Rosetta Commons (2024) MPNN – ML for protein sequence design https://www.youtube.com/watch?v=6z4XmUAwdNA Acknowledgements:Aria Babu, editor at Works in ProgressGraham Bessellieu, video editorRachel Shu, on-site editorAnna Magpie, fact-checkingAbhishaike Mahajan, cover artAtalanta Arden-Miller, art directionDavid Hackett, composerWorks in Progress & Open Philanthropy
Subscribe to the Works in Progress print magazine: https://worksinprogress.co/print/
--------
1:00:48
--------
1:00:48
Hacking proteins with AI
Nature didn’t evolve all the proteins we need, but maybe artificial intelligence can help. Jacob and Saloni explore how tools like AlphaFold and ProteinMPNN are helping researchers re-engineer proteins, to make them safer, more stable, and more effective. They talk about how new technologies could help make a long-sought vaccine against Strep A, which causes scarlet fever and rheumatic heart disease, and how similar tools have already led to breakthroughs against COVID and RSV.Hard Drugs is a new podcast from Works in Progress and Open Philanthropy about medical innovation presented by Saloni Dattani and Jacob Trefethen.Saloni’s substack newsletter: https://www.scientificdiscovery.dev/Jacob’s blog: https://blog.jacobtrefethen.com/ Courses:EMBL-EBI. AlphaFold: A practical guide https://www.ebi.ac.uk/training/online/courses/alphafold/ Articles:Monica Jain et al. (2022) Exosite binding modulates the specificity of the immunomodulatory enzyme ScpA, a C5a inactivating bacterial protease. https://pmc.ncbi.nlm.nih.gov/articles/PMC9464890/ Jakki Cooney et al. (2008) Crystal structure of C5a peptidase https://www.rcsb.org/structure/3EIF Hui Li et al. (2017) Mutagenesis and immunological evaluation of group A streptococcal C5a peptidase as an antigen for vaccine development and as a carrier protein for glycoconjugate vaccine design https://pubs.rsc.org/en/content/articlelanding/2017/ra/c7ra07923k Lectures:Rosetta Commons (2024) AlphaFold – ML for protein structure prediction https://www.youtube.com/watch?v=SVrn8_8aKO8 Rosetta Commons (2024) MPNN – ML for protein sequence design https://www.youtube.com/watch?v=6z4XmUAwdNA Acknowledgements:Aria Babu, editor at Works in ProgressGraham Bessellieu, video editorRachel Su, on-site editorAnna Magpie, fact-checkingAbhishaike Mahajan, cover artAtalanta Arden-Miller, art directionDavid Hackett, composerWorks in Progress & Open PhilanthropySubscribe to the Works in Progress print magazine: https://worksinprogress.co/print/
--------
55:04
--------
55:04
How traffic modernism ruined cities with Nicholas Boys Smith
Nicholas Boys Smith joins Ben and Sam to explain how to plan spaces that people like; dense, sociable and, above all else, beautiful. He says people don't like new buildings because they don't trust what planners and architects are going to do to the places that matter to them. As an alternative he presents his playbook for how YIMBYs can win over the public.If you liked this episode, you'll enjoy our first episode on The Great Downzoning: https://www.youtube.com/watch?v=LAcEfeLlqLoFor more from Works in Progress: worksinprogress.co/print
Works in Progress is an online magazine devoted to new and underrated ideas about economic growth, scientific progress, and technology. Subscribe to listen to the Works in Progress podcast, plus Hard Drugs by Saloni Dattani and Jacob Trefethen.
UK