Liam Fedus team trains Neon with RL on lab data using 1,300 H200s, beats GPT-6 Astra

LiamFedus · x · 2026-09-16

Liam Fedus's team built high-throughput materials labs in Menlo Park creating a loop where experiments generate fresh data and models decide what to try next. Using only 1,300 H200s plus months of experimental data, they mid-trained and RL'd an open-source model into "Neon", surpassing GPT-6 Astra on their analysis benchmark. They also built pbox, an in-house RL sandbox for training trillion-parameter models, targeting superconductors, magnets, and semiconductor materials first.

Related event: Periodic Labs beats GPT-6 on materials science with just 1,300 H200s(41 posts)→

Original post →

More from Infra

Infra channel →