Periodic Labs midtrains and RLs a trillion-param LLM to analyze superconductor lab data, beating Astra and Fable
vwxyzjn · x · 2026-09-16
Periodic Labs has mid-trained and RL'd a trillion-parameter LLM to analyze experimental data from its superconductor lab. The team claims it outperforms Astra and Fable on this task and that their scientists love using it. The company published its first research report alongside the announcement, showcasing its experiment-to-model data loop.
More from Research
- Asynchronous Flow Map Language Models Generate All Tokens in a Single Forward Pass — kalyan_kpl · 2026-11-02
- NVIDIA's Kumo Is a Family of Four Tabular Foundation Models, Not Just One — pandeyparul · 2026-11-02
- Economist Aaroth: fast agreement dynamics survive without Bayesian updates or accurate priors — Aaroth · 2026-11-02
- ELLIS names 160 new ML Fellows and Scholars for 2025–2026 — JJitsev · 2026-11-02
- Meme turn 50: Aumann's 'Agreeing to Disagree' paper anniversary — Aaroth · 2026-11-02
- Anthropic: analysts unknowingly adopted their agent's secret lean 86% of the time — shoumikgoswami · 2026-11-02