Citrini Used Anthropic's Internal Model to Design Scorpion Antivenom Proteins Overnight
citrini · x · 2026-10-20
Citrini Research spent three months testing whether Anthropic's internal research model could do real drug design, under the project name Citrini Therapeutics.
Key details:
- Prompted from an Anthropic conference room, Claude ran an autonomous campaign overnight: spawning 300+ sub-agents on 300+ concurrent GPUs to design, score, and deliver a set of proteins, then sent them to a physical lab for synthesis and testing with no further human input
- The team finished with a package ready for wet-lab submission, waking to a Slack notification that the campaign had concluded
- Context: the stock-research shop pivoted to life sciences in June, betting on a neglected sector at cyclical lows with AI-driven drug discovery upside
The full piece is paywalled, but it's a rare third-party, hands-on test of a frontier internal model's ability to drive an end-to-end autonomous drug design campaign.
More from AGI Musings
- Claude runs 64-hour autonomous research: 318k protein designs, 17 binders validated — kimmonismus · 2026-10-20
- China's thinkers have very different answers to what's left for humans after AI — sudoraohacker · 2026-10-20
- Do UIs still matter when AI agents become the main consumers of your data? — DanielLockyer · 2026-10-20
- What disruptive event could flip public sentiment in favor of AI? — Mr-and-Mrs · 2026-10-20
- No kings, just a few techno lords: AI platforms as the new means of production — bakraofwallstreet · 2026-10-20
- Frontier lab refusals vs retail giants are opening real demand for open weights — curious_vii · 2026-10-20