Stanford's Marin open training run at 535B-A23B, Percy Liang invites others to share progress
dejavucoder · x · 2026-09-17
Stanford professor Percy Liang shared an update on the Marin open research lab's live training run: the model currently training is 535B-A23B (apparently an MoE with 535B total / 23B active parameters), with a public dashboard tracking progress. He also invited others to share their own live training runs, continuing Marin's fully transparent approach to LLM training.
Related event: Stanford's Marin Open Lab Live-Trains 535B-Parameter Open Model(2 posts)→
More from Research
- Researchers: RL training has made models' theory of mind 'terrible' — voooooogel · 2026-09-18
- The 272-page Multimodal Deep Learning book is free to read online with an AI tutor — burkov · 2026-09-18
- Therna launches Chronos RNA foundation model trained across ~50 human cell lines — LightningAI · 2026-09-18
- Arvind Narayanan's ICML Keynote: RSI Is Not the Singularity, and No Lab Milestone Kills All Jobs — random_walker · 2026-09-18
- Does RL build new representations or just make models flail? LLM researchers debate — doomslide · 2026-09-18
- Statistician argues alignment is impossible: LLM outputs are distributional, not fixed traits — gerardsans · 2026-09-18