Updated Feb 2025

Compression-Aware Intelligence

Contradiction Density (CD):

$$CD = \frac{\text{Number of contradictions detected}}{\text{Total outputs evaluated}}$$

Coherence Delta (CoD):

$$CoD = \text{Coherence(before)} - \text{Coherence(after)}$$

Entropy Risk Score (ERS):

$$ERS = - \sum_i p_i \log(p_i)$$

Composite CAI Score:

$$CAI\_Score = \alpha \cdot CD + \beta \cdot CoD + \gamma \cdot ERS$$

CAI is about one thing: test stability across semantically equivalent but differently phrased prompts to detect internal model contradictions and compression failures. Brittleness arises when meaning-preserving transformations induce semantically incompatible internal states under compression, and hallucinations are the forced collapse of that incompatibility.

Every system compresses. If you can see the compression, you can predict where the answer will drift, route before failure, and ship safer systems.