Results
6 articlesSort
47:22EN
Sequoia Capital· Aug 4, 2026PodcastFrom One in a Thousand to 15 Percent: Chai Discovery Treats Drug Design as a Scaling ProblemJoshua Meier and Matthew McPartlon tell Sequoia’s Training Data why antibody design is an engineering problem, not a bespoke science, and why they sell a molecular CAD suite instead of their own drugs.
1:29:30EN
Cognitive Revolution "How AI Changes Everything"· Oct 14, 2025Podcast2,500 Compounds and a 51 Percent Hit Rate: How a Small Graph Net Found New AntibioticsHost Nathan LabenzMIT's Jim Collins tells Nathan Labenz how a bootlegged 2018 project, a binary growth-inhibition label, and Chemprop graph networks pulled novel antibiotics out of chemical space that labs could never screen by hand.
57:52EN
Unsupervised Learning: With Jacob Effron· Aug 13, 2025PodcastThey Aimed for 1%. The Lab Hit 20%. Chai Discovery Moved Antibody Design Onto the Computer.Host Jacob EffronJoshua Meier on three waves of AI drug discovery, why Chai-2 behaves like Photoshop for molecules, and why a 1% hit rate was supposed to be enough to change the industry.
49:27EN
No Priors: AI, Machine Learning, Tech, & Startups· Jul 3, 2025Podcast · 2 speakersFrom 0.1% to 20%: Chai-2 Turns Antibody Design Into Prompt EngineeringHost Sarah Guo, Elad GilChai Discovery co-founders Joshua Meier and Jack Dent tell Sarah Guo how a generative model now designs antibodies that bind on the first 24-well plate.
55:40ENSequoia Capital· Apr 29, 2025PodcastTo Solve All Diseases, Isomorphic Labs Needs a Half-Dozen AlphaFoldsMax Jaderberg on turning DeepMind's game-playing research into a general AI engine for drug design—and why prediction alone cannot search a 10^60 molecular universe.
57:41ENNo Priors: AI, Machine Learning, Tech, & Startups· Feb 25, 2025Podcast · 2 speakersA Hundred Million Cells, Four People, Three Days: Biology's ImageNet MomentHost Sarah Guo, Elad GilVevo Therapeutics and the Arc Institute open-sourced Tahoe-100M and a 230-million-cell atlas in the same week — and argued that virtual cells, not just protein folders, are the next language model of biology.