Claude runs 64-hour autonomous research: 318k protein designs, 17 binders validated
kimmonismus · x · 2026-10-20
Anthropic's internal Claude research model carried out much of a research project autonomously, with results confirmed in the lab.
- Given one starting prompt and four follow-ups, Claude used specialized tools to generate 318,000+ protein designs in 64 hours, choosing attachment sites on scorpion toxins and selecting candidates for testing
- Labs tested 211 candidates, including human-assisted additions; 17 successfully bound their target toxins as small-protein "binders"
- Claude handled choosing the approach, coordinating tools, and deciding what deserved physical experiments — a step toward autonomous AI scientists
Related event: Claude Autonomously Designs 318K Proteins in 64 Hours, Lab-Validated(2 posts)→
More from AGI Musings
- John Smart's new talk: Biostasis drops to $36K as AI reshapes the future of self — Chris_Armstrong · 2026-10-20
- Mathematicians aren't immune to sycophantic AI; weak verification is the culprit — gerardsans · 2026-10-20
- noOS: the OS's only job will be handing flops to the agent, says Papailopoulos — DimitrisPapail · 2026-10-20
- The problem with the "AI as a normal technology" slogan — intellectronica · 2026-10-20
- AI existential dread has a cognitive core that soothing emotions won't fix — zetalyrae · 2026-10-20
- Scoble: As AI Makes Everyone Look Like an Expert, Advantage Shifts to Judgment and Taste — Scobleizer · 2026-10-20