Autonomous laboratory reports solid-state synthesis of new inorganic compounds
Berkeley's A-Lab, an AI-driven autonomous laboratory, reported synthesising 41 novel inorganic compounds out of 58 targets over 17 days with minimal human intervention.
- Model
- A-Lab (ML planning + robotics)
- Field
- Materials science
- Date
- 2023-11-29
What was found
A-Lab coupled machine-learning synthesis-recipe prediction with robotic sample preparation, heating and X-ray characterisation, drawing targets from stability predictions including GNoME's. It reported making 41 of 58 targeted compounds autonomously. Published in Nature alongside GNoME.
Novelty check
Targets were drawn from computed stability databases. The contested question is whether the synthesised phases were correctly identified and genuinely new, rather than known phases or misindexed results.
Caveats and known objections
A detailed critique led by Robert Palgrave argued that many of the 41 claimed compounds were misidentified from the X-ray data, in several cases likely known phases, mixtures, or amorphous products rather than the claimed novel crystals. It is the identification step, not the automation, that is disputed; the autonomy claim itself is not the weak point. A 2026 Author Correction from the team re-analysed the diffraction data and clarified that 'novel' was meant as new to their prediction platform rather than necessarily new to science.
Independent checks
Palgrave et al. (analysis of the reported diffraction data): disputed the identification of most claimed new compounds · link ↗
Authors' correction (Nature, 2026): re-analysed diffraction data; clarified 'novel' meant new to the platform, not to science · link ↗
Disagree with these grades?
Bring a citation: a grade moves on evidence, not on argument.
Or on GitHub: submit a check challenge the grade send a correction or send a pull request
Flag this for triage
Signals order the review queue and nothing else. They are never published, and they never move a grade: that takes a citation.
Entry history (1 event)
- AddedEntered the registry graded Disputed and AI-led.
Entries are never deleted. A grade that does not hold up is downgraded on the record, with the reason beside it.
Community discussion
Graded disputed for verification and ai-led for autonomy. What these mean.
Cite this entry
whataifound.org. (2023). Autonomous laboratory reports solid-state synthesis of new inorganic compounds. whataifound.org: A Registry of AI Scientific and Mathematical Discoveries. https://whataifound.org/finding/2023-11-29-a-lab-synthesisBibTeX
@misc{whataifound-lawrenceberkeleynationallaboratory-2023-synthesis,
title = {Autonomous laboratory reports solid-state synthesis of new inorganic compounds},
author = {{whataifound.org}},
year = {2023},
howpublished = {whataifound.org: A Registry of AI Scientific and Mathematical Discoveries},
note = {Result by Lawrence Berkeley National Laboratory. Verification: Disputed. Autonomy: AI-led.},
url = {https://whataifound.org/finding/2023-11-29-a-lab-synthesis}
}