AI proposed chemistry a 12-year expert called wrong — it became their best hydrogen catalyst
tw_killian · x · 2026-09-26
Andrew Beam of Lila Sciences shares an AI-for-science story: while working on clean-hydrogen (water electrolysis) catalysts, their AI proposed a composition that John Gregoire — a scientist who had studied the exact reaction for 12 years — thought had to be wrong. It became their strongest lead, sustaining over 1,000 hours of oxygen evolution with little catalytic degradation. Gregoire left his Caltech research professorship to become Lila's Chief Autonomous Science Officer, building some of the world's most sophisticated automated labs. Context: green hydrogen currently depends on iridium, one of Earth's rarest metals (a few tonnes mined per year), so alternative catalysts matter for clean energy.
More from Research
- Claude computes nine-loop scattering amplitude, breaking Lance Dixon's eight-loop record — kevinweil · 2026-09-26
- Stanford's Matryoshka Attribution tops mech interp benchmark, removes refusal by resetting 1% of weights — stanfordnlp · 2026-09-26
- Dual Covariance 3DGS SLAM: two covariances per Gaussian, robust tracking at 60 FPS — kwangmoo_yi · 2026-09-26
- Dual Covariance Gaussian Splatting SLAM decouples rendering and registration — kwangmoo_yi · 2026-09-26
- ImageJevBench: image decision benchmark ranks top models, full eval costs $0.02 — airesearch12 · 2026-09-26
- Biopharma Bench: agents complete only 8 of 71 real biopharma tasks, GPT-6 Astra leads — AllThingsApx · 2026-09-26