A new paper just exposed a setting that changes how AI models scale.

Scaling laws tell labs how big a model should be for a given amount of data.

Until now, that math was always done in tokens.

A new paper rewrites the rule in bytes.

The team trained 988 models, from 50M… pic.twitter.com/G7j5tySh9V

— AlphaSignal AI (@AlphaSignalAI) 2 juin 2026

A new paper just exposed a setting that changes how AI models scale. Scaling laws tell labs how big a model should be for a given amount of data. Until now, that math was always done in tokens. A new paper rewrites the rule in bytes. The team trained 988 models, from 50M

→ View original post on X — @alphasignalai