Anthropic Open Sources Prompts: Claude Achieves 35% Hit Rate in Protein Design
Hesamation · x · 2026-08-19
Anthropic open-sourced the prompts used to make Claude design protein binders (e.g., "You do not need rest"). Tests show Claude designed binders for 14 out of 15 targets, achieving a 35% hit rate—significantly higher than the typical 10-15%. Some designs even outperformed the best existing methods.
More from Research
- NBER study: Pangram detector achieves near-zero error rates — soumitrashukla9 · 2026-08-19
- Real AI risks lie outside the model: permissions, data, and presentation — bigdata · 2026-08-19
- TraceLab: 4,300 real coding-agent sessions reveal high cache hit rates but quadratic cost growth — CShorten30 · 2026-08-19
- Bayesian view won AI debate but no one noticed — AdaptiveAgents · 2026-08-19
- Discussion: Over-determined projections may outperform embedding tables in representation learning — kalomaze · 2026-08-19
- Claude autonomously designs proteins with 35% success rate in wet-lab tests — ResultBackground2450 · 2026-08-19