An ai model found a new enzyme system with crispr-like repeats in 21 hours of autonomous work,…
an ai model found a new enzyme system with crispr-like repeats in 21 hours of autonomous work, where similar discoveries have taken human labs years. anthropic’s life sciences lab published it on sept 23.
the bottleneck in biology is shifting from discovery to deciding which discoveries to chase.
Context
Verified date: Anthropic's post Claude discovers a novel enzyme system with CRISPR-like repeats is dated Sep 23, 2026. It introduces a new life sciences research group and laboratory at Anthropic. The Next Web says the enzyme system sits in bacteriophage DNA beside a long array of repeats and that Anthropic does not yet know what it does. Interesting Engineering says Claude agents mined 200,000 reverse transcriptases.
Nature (Sep 25, 2026) says the detection effort used roughly 950 AI agents that spent more than 21 hours combing through DNA sequence databases.
The Sep 23 publication and the 21 hours match. Nature says roughly 950 AI agents ran for more than 21 hours, so it is not one agent working alone, and Anthropic says the function of the system is not yet known. The comparison to human labs taking years was not seen in the sources read, so unsupported here, not refuted. in the excerpts read. 'The bottleneck in biology is shifting from discovery to deciding which discoveries to chase' is the author's opinion.
Related work
- Anthropic research: Claude discovers a novel enzyme system ↗Research version.
- Interesting Engineering: Claude scans 200,000 enzymes ↗Sep 23, 2026.
- Nature news ↗Sep 25, 2026.
Watch next
- Read Anthropic's research post for how long a human search of this kind takes.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 1 October 2026 at 10:46 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →