LLMs fail to learn from atomic coordinates at up to 70 billion parameters and 2 million structures, a paper on nature.com reports. Specialized geometric architectures still win when structure dominates the property, the authors report.
Reality
- Evidence66
- Adoption
- Insufficient
- Hype gap−5
- Incentives
- Insufficient
- Confidence60
Hessian Interatomic Potentials predict molecular Hessians directly and run one to two orders of magnitude faster, their authors report. A cheaper Hessian would make second-order chemistry workflows easier to run routinely, if the reported gains survive independent tests.
Reality
- Evidence45
- Adoption
- Insufficient
- Hype gap+15
- Incentives
- Insufficient
- Confidence55
The analysis argues that a model standing in for people can be sound for one research purpose and unsound for the next, and that the four purposes it identifies each rest on a different claim about human likeness.
Reality
- Evidence52
- Adoption
- Insufficient
- Hype gap+6
- Incentives40
- Confidence54
Its agents interview the user for what the request leaves out, then build and run the modelling. The paper shows this on two enzymes, which demonstrates the pipeline rather than measuring how often it is right.
Reality
- Evidence48
- Adoption
- Insufficient
- Hype gap+30
- Incentives65
- Confidence52
Chen and colleagues report that a single text-prompted model scored highest overall across 16 pathology test sets, measured against baselines their code list names. The abstract publishes the counts; the margins are left out.
Reality
- Evidence45
- Adoption15
- Hype gap+30
- Incentives55
- Confidence55
The UK Biobank study reports generated metabolomic profiles beating every benchmark, and disease models built on synthetic proteomics at AUC 0.72 to 0.83. The check exists only where the assays were run.
Reality
- Evidence58
- Adoption
- Insufficient
- Hype gap+18
- Incentives38
- Confidence55
CrysVCD enforces oxidation-state balance before crystal structures are built, and reports 85 percent metastability and 68 percent phonon stability. The expensive part of the pipeline was always the filter.
Reality
- Evidence70
- Adoption16
- Hype gap+16
- Incentives62
- Confidence68