Chai Discovery: Drug Design Is a Scaling Problem, Hit Rates Jump to 16%
Training Data (Sequoia) · rss · 2026-08-04
On the Sequoia Capital podcast, the founders of AI drug discovery startup Chai Discovery argue that drug design obeys the AI sector's "Bitter Lesson"—by scaling data, models, and compute, models can learn what hand-built pipelines simply cannot capture.
They shared concrete breakthroughs: their Chai-2 model increased the hit rate of de novo antibody design from less than 0.1% to 16%, turning a needle-in-a-haystack search into precision design like "cutting a key." Believing biology is more verifiable than code, their vision is to build a design suite that collapses the drug discovery timeline from 9 months to 9 days, aiming to arm the pharmaceutical industry rather than compete with it.
More from Venture
- Claiming Niches with AI: Writing Books on FDE, GEO, and Growth — yangyi · 2026-08-04
- Indie Dev Shares $1M MRR Tech Stack: AI Agents and Automation Tools — tibo_maker · 2026-08-04
- AI Demand Soars: Ibiden Q1 Profit Jumps 52%, Doubles Full-Year Guide — rwang07 · 2026-08-04
- Bending Spoons to Acquire Airtable for $1.285 Billion — BoorishBears · 2026-08-04
- Tsinghua Team's Embodied AI Startup Poke Raises $100M+ in Pre-A Round — 创业邦 · 2026-08-04
- DeepSeek V4 Costs 1% of Claude: China's AI Price War Disrupts the Market — SirBoboGargle · 2026-08-04