Waypoint Bio argues AI in biology has a data problem before a model problem
anshulkundaje · x · 2026-09-21
Waypoint Bio's second essay argues AI in biology faces a data problem before a model problem.
- Using AI to speed up drug discovery is easy; the hard part is finding impactful medicines humans would never have discovered.
- Models are only as good as their training data, and the field's biggest goals—curing incurable diseases, designing unprecedented therapeutics—are by definition out-of-distribution.
- The essay outlines the data needed to build out-of-distribution medicines, highlighting spatial biology and spatial pooled screening.
More from AGI Musings
- Kevin Roose: 'Stochastic Parrot' Discourse Blinded Millions to AI Progress — bigblueboo · 2026-09-21
- Publication norms force AI-jobs papers to overclaim causality, scholars say — danielrock · 2026-09-21
- How to read imperfect AI-job-impact studies: update Bayesian-style as signals pile up — danielrock · 2026-09-21
- With 60,000+ ML Conference Submissions, How Do You Spot a Good PhD Student? — AnkaReuel · 2026-09-21
- TechCrunch Equity podcast: are AI execs serious about slowing down? — TechCrunch AI · 2026-09-21
- Opinion: Terence Tao owes no stance on AI deployment — mathematicians should do their art — akbirthko · 2026-09-21