AI proposes catalyst a 12-year expert called wrong; it runs 1,000+ hours with little loss
CatAstro_Piyush · x · 2026-09-26
Lila Sciences shared a favorite AI-for-Science story: while working on clean hydrogen catalysts, their AI proposed a composition that a scientist with 12 years studying the exact reaction was sure had to be wrong. That composition became the team's strongest lead, sustaining over 1,000 hours of oxygen evolution with little catalyst loss — a striking case of AI-generated hypotheses breaking past human intuition.
More from Research
- Tuva Labs takes 1st on ARC-AGI-2, 2nd on ARC-AGI-3 in ARC Prize 2026 — GregKamradt · 2026-11-11
- Sakana AI × Pathway Post-Transformers lecture on AI and the brain now online — kaixhin · 2026-11-11
- Defending METR: public data can't second-guess its AI speedup findings — peterwildeford · 2026-11-11
- Adversarial RL envs for backdoor insertion vs. detection: where does it converge? — DimitrisPapail · 2026-11-11
- DiffusionEngine: an open-source modular PyTorch DDPM framework seeking contributors — Euphoric-Incident-93 · 2026-11-11
- UniPath (NeurIPS 2026): adaptively coordinating understanding and generation in one model — jindong_wang92 · 2026-11-11