YC Paper Club: Falling Sequencing Costs Turn Cancer Care Into a Per-Patient Data Problem
Y Combinator · youtube · 2026-11-08
This week's YC Paper Club dives into AI for biology, arguing that collapsing sequencing costs have made biology a data-mining problem that models are finally equipped to tackle.
Key segments:
- Alfredo Gonzalez: why cancer care is becoming a per-patient data problem, and why now is the best time for AI Bio
- Yusuf Roohani: virtual cells and autonomous research — modeling an entire cell rather than a single molecule
- Garyk Brixi: what a language model trained on DNA actually learns
- Divya Nori: few-shot prompting for biological design
Also features a live Turing test experiment. Notably, in-context learning emerged in a genome model that was never trained for it.
Related event: YC Paper Club Explores AI for Biology(3 posts)→
More from AGI Musings
- From chihuahua vs. muffin to Snell's-law raccoons: a decade of AI expectations — korymath · 2026-11-09
- Larry Page predicts 99.999% of compute will end up in orbit, citing US data center regulation — elonmusk · 2026-11-09
- Debate over valuing human life in numbers splits AI ethics circles around Gebru — austinc3301 · 2026-11-09
- Scaling laws matter more than ever in the RSI era: small models as proxies — ChengleiSi · 2026-11-09
- Jesse Eisenberg tests AI writing to "make sure it's bad" — and remains paranoid — jxnlco · 2026-11-09
- Krugman: AI bubble burst recession may beat 2000s slump, joblessness to linger for years — GaryMarcus · 2026-11-09