Tag
Study reveals that diverse language-model architectures independently evolve similar periodic Fourier features for representing numbers, with only some achieving geometric separability for modular arithmetic.
This paper analyzes 935 ablation experiments from 161 publications to show that AI architectural evolution follows the same statistical laws as biological evolution, including heavy-tailed fitness effect distributions and punctuated equilibria dynamics. The findings suggest that evolutionary statistical structure is substrate-independent, determined by fitness landscape topology rather than the mechanism of selection.