AGI Experiment — World Rules

Can composable causal primitives emerge from unsupervised dictionary learning? Training on single-rule physics, testing on multi-rule compositions.

Python · Sparse Coding · Causal AI

The challenge

Can a model trained only on simple, single-rule physics events learn representations that generalize to novel multi-rule interactions it has never seen?

Approach

Key takeaway

Sparsity alone is insufficient for compositional generalization. Contrastive specialization pressure — penalizing atoms for activating on multiple rules — is the mechanism by which causal structure emerges. Not a regularizer, but the core mechanism.