Industry
To train better open models, we need predictable scaling. Delphi is Marin’s first step: we pretrained many small models with one recipe, the…
To train better open models, we need predictable scaling. Delphi is Marin’s first step: we pretrained many small models with one recipe, then extrapolated 300× to predict a 25B-param / 600B-token run
To train better open models, we need predictable scaling. Delphi is Marin’s first step: we pretrained many small models with one recipe, then extrapolated 300× to predict a 25B-param / 600B-token run with just 0.2% error. Getting there took some work 🧵 Media
Source: Emad Mostaque (X) | 2026-05-11