SOURCE-LINKED INTELLIGENCE

Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Chess involves complex reasoning in a deterministic environment, which makes it a useful setting for studying the mechanisms of computation inside transformers. The Maia-3 chess transformer takes Elo, a measure of competitive chess skill, as an input to the pre-trained network, so we can vary the skill the network is conditioned on with no change to its weights. Here we investigate how turning this skill dial affects self-attention. Ablating every attention head at every Elo from 700 to 2500, we find 1) increasing skill pushes the causal center of mass of the computation deeper, monotonically,

Read original source ↗ Open in workspace

recordType

paper

region

Global