---
id: "2023-11-29-gnome-millions-of-materials"
url: "https://postcutoff.com/e/2023-11-29-gnome-millions-of-materials/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2023-11-29"
date_precision: day
category: science
importance: 4
confidence: high
status: [Disputed]
verification: Peer-reviewed
sources: 4
editor: human editor
human_review: null
version: "2026-10-16"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2023-11-29-gnome-millions-of-materials/

# GNoME predicts 2.2 million new crystals, 380,000 stable, but novelty and usefulness are disputed

DeepMind's GNoME (Nature, Nov 2023) used graph neural networks and active learning with DFT to predict 2.2 million new inorganic crystal structures, 380,000 of them computed to be stable. DeepMind called it '800 years' worth of knowledge'. Solid-state chemists later found 'scant evidence' of compounds that are novel, credible and useful.

## Key facts
- 2.2M new structures; 380k predicted stable; ~400k added to the Materials Project
- DeepMind: over 700 had already been independently synthesised by other groups
- Cheetham & Seshadri (Chem. Mater., Apr 2024): 'scant evidence for compounds that fulfill the trifecta of novelty, credibility, and utility'
- Oct 14, 2026 (C&EN, Dalmeet Singh Chawla): new outside research says the GNoME database is 'littered with duplicates of known and hypothesized crystal structures found in other databases' and contains unrealistic compounds; Google DeepMind did not comment (article partly paywalled; the study's authors and figures were not read)
- GNoME lead Ekin Doğuş Çubuk later co-founded Periodic Labs (2025)

## What happened

DeepMind scaled ML-guided materials screening by orders of magnitude and released the predicted structures to researchers.

## Why it matters

It is the largest AI materials-prediction effort, and a leading example of the gap between computational "discovery" and a useful new material.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [Scaling deep learning for materials discovery (Nature)](https://www.nature.com/articles/s41586-023-06735-9) (nature.com, paper)
2. [DeepMind: Millions of new materials discovered with deep learning](https://deepmind.google/blog/millions-of-new-materials-discovered-with-deep-learning/) (deepmind.google, official)
3. [C&EN: Google DeepMind AI crystallography database includes near duplicate structures and unrealistic compounds (Oct 14, 2026; partly paywalled)](https://cen.acs.org/research-integrity/Google-DeepMind-structures-near-duplicates-questionable/104/web/2026/10) (cen.acs.org, press)
4. [Cheetham & Seshadri critique (Chemistry of Materials)](https://pubs.acs.org/doi/10.1021/acs.chemmater.4c00643) (pubs.acs.org, discussion)

## Changes

- 2026-10-16: C&EN report (Oct 14, 2026) on near-duplicate and unrealistic structures in the GNoME database
- 2026-09-29: Linked Periodic Labs entry
- 2026-09-29 (filed): Created

## Related

- 2025-09-30: [Periodic Labs launches with a $300M seed round to build AI scientists with autonomous labs](https://postcutoff.com/e/2025-09-30-periodic-labs-300m-seed/index.md)
- 2023-11-29: [Berkeley's A-Lab claims 41 new materials from autonomous synthesis](https://postcutoff.com/e/2023-11-29-a-lab-autonomous-synthesis-dispute/index.md)