AI Dynamics

Global AI News Aggregator

About

Empirical Evidence of Stable Scaling Laws Across Model Architectures

Here’s the wildest part… The same scaling law held across different model sizes, tasks, and sequence lengths. 8B dense model? 17B×16 MoE? Math + code RL tasks? Even 32k-token reasoning traces stayed on-curve. Stable scaling across everything.

→ View original post on X — @godofprompt