Classical force fields could still catch up and beat MLIPs, researcher says
TimothyDuignan · x · 2026-10-28
In a discussion with Lindorff Larsen, Timothy Duignan says he's open to the idea that classical force fields may improve rapidly and ultimately outperform machine-learning interatomic potentials (MLIPs) for many applications. He previously noted that hand-fitting zinc coordination geometry (tetrahedral vs octahedral) remains an unsolved problem, despite zinc being central to many biological systems.
Related event: Researchers Debate Whether MLIPs Can Outperform Classical Force Fields(5 posts)→
More from Research
- DeepMind researcher: all of mathematics will soon be formalizable, with agents hunting proofs — ChrSzegedy · 2026-10-28
- A fine-tuned 'cat obsession' control fools every AI welfare criterion — MirrorEthic_Anchor · 2026-10-28
- Sweeping every Qwen3-8B neuron, rated for weirdness by Haiku — Sauers_ · 2026-10-28
- Kevin Buzzard: Lean formalization revealed errors in theorems by 4 Fields medalists — Machine Learning Street Talk · 2026-10-28
- Follow-up repo machine-verifies Hamiltonian cycle results on top of OpenAI/Anthropic ETH refutation claims — xennygrimmato_ · 2026-10-28
- DiscoTrace wins EMNLP 2026 Best Paper: LLM answers lack humans' community-specific rhetorical diversity — TuhinChakr · 2026-10-28