The yeast lab is now running its own experiments. chalmers' closed-loop ai scientist, out oct 1 in…
the yeast lab is now running its own experiments. chalmers' closed-loop ai scientist, out oct 1 in the journal of the royal society interface, forms hypotheses, plans runs and interprets results on brewer's yeast with minimal human input.
a familiar microbe just became the first full ai research loop.
Context
Chalmers University of Technology reported on September 30, 2026 that its researchers built an AI scientist that generates hypotheses, designs experiments and interprets results in a closed-loop laboratory working on brewer's yeast, Saccharomyces cerevisiae, with minimal human intervention. The AI was given scientific knowledge including the yeast genome, metabolism and previous studies, and the robot scientist Eve, designed for drug discovery, was updated with large language models and automated reasoning.
The paper, by Brunnsaker, Gower, Naval and colleagues, appears in the Journal of The Royal Society Interface, volume 23, issue 240, and was published online on July 8, 2026 after acceptance on May 15, 2026.
The note says the paper was out on October 1. The pages read show online publication on July 8, 2026 and the Chalmers news release on September 30, 2026. Whether the issue itself is dated October 1 was not shown, so that date is unsupported here, not refuted.
'Minimal human input' matches the Chalmers wording, 'minimal human intervention'. The note's 'first full AI research loop' was not found in the pages read. Chalmers calls the integration of AI reasoning with experimental capability 'unusual, and cutting edge within a rapidly expanding area', and Eve was an earlier robot scientist that the team updated, so 'first' is unsupported here, not refuted.
'The yeast lab is now running its own experiments' is the author's line. The release says the researchers describe the system as collaborating with human scientists.
Related work
- AI scientist autonomously generates and validates new biological discoveries (Chalmers University of Technology, September 30, 2026) ↗Source for the closed-loop yeast laboratory, Eve and the 'minimal human intervention' wording.
- Agentic AI integrated with scientific knowledge: laboratory validation in systems biology (Journal of The Royal Society Interface, 23(240), published online July 8, 2026) ↗Source for the paper, its journal reference and the July 8, 2026 online publication date.
Watch next
- Read the paper's results for how many hypotheses were tested and how many were validated. Check the issue date for volume 23, issue 240.
Sources
- AI scientist autonomously generates and validates new biological discoveries (Chalmers University of Technology, September 30, 2026)chalmers.se
- Agentic AI integrated with scientific knowledge: laboratory validation in systems biology (Journal of The Royal Society Interface, 23(240), published online July 8, 2026)royalsocietypublishing.org
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 9 October 2026 at 09:04 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 →