Claude designs protein binders from scratch, hitting 14 of 15 targets autonomously
daniel_mac8 · x · 2026-08-19
Anthropic published a tech report showing that Claude, with no pre-installed design or prediction tools, autonomously designed novel protein binders from scratch — 14 out of 15 targets successful — using only a human expert's protein design prompt. Adaptyv Bio and Twist Bioscience then independently built and tested the designs.
Key details from the report:
- The only human intervention mid-campaign was "please resume";
- About 2/3 of the 16k-word prompt was long-horizon agent prompting, not biology;
- All tools were built by Claude on the fly.
The takeaway: superhuman performance in a narrow but important domain, without any specialized model training.
Related event: Anthropic Says Claude Designed Protein Binders for 14 of 15 Targets(45 posts)→
More from coding & agent
- ai& becomes an official built-in Cline provider with 13 open-weight models — DavidBennett__ · 2026-10-16
- x402 as a free GTM channel: agents discover 100+ tools, no API keys needed — 0xJeff · 2026-10-16
- Sam Altman: stop getting better at prompts, build loops and graphs that prompt for you — goyalshaliniuk · 2026-10-16
- POV ski game on real Matterhorn elevation data, built with Claude Opus 5.5 — techartist_ · 2026-10-16
- Poisoned SERPs broke rank tracking — a Claude MCP + Notion workaround — VeryWellVersed · 2026-10-16
- OpenAI's Live API adds Decisions API for ~200ms real-time voice app decisions — juberti · 2026-10-16