Paper argues AI alignment needs physical-science theories, using crystallization as a case study

niloofar_mire · x · 2026-07-21

• The thread highlights a paper that argues alignment research should borrow predictive ideas from the physical sciences.
• The core claim is that we can measure what alignment does to LLMs, but we still lack good theories for how alignment emerges and changes over time.
• The paper uses crystallization as a case study to build that kind of explanatory lens.
• The poster frames it as a creative direction for AI research, with more metaphors from natural science.

Original post →

More from Research

• Structural ensembles beat single predictions in TCR:pMHC generalization study — quaidmorris · 2026-07-22
• Structural ensembles, not single predictions, drive robust TCR:pMHC generalization — quaidmorris · 2026-07-22
• enFoldX turns AlphaFold3 ensemble noise into a TCR–peptide–MHC predictor — quaidmorris · 2026-07-22
• RSS launches under OMSF to push structural biology data modeling at scale — MoAlQuraishi · 2026-07-22
• enFoldX tops 8 neoantigen scans and an unseen-peptide benchmark — quaidmorris · 2026-07-22
• enFoldX reaches AUC 0.82 on human VDJdb and transfers to mouse at 0.76 — quaidmorris · 2026-07-22

Research channel →