Symbol k

The passage around this formula

…material goes into the window, and the burden of finding what matters is placed on attention at inference time rather than on an index built in advance. Writing n for the number of tokens placed directly in context and k for the number of tokens a retriever would instead have selected, the quadratic cost derived above means the two approaches sit in different complexity regimes for handling the same underlying material: $C_{\mathrm{LC}} \sim O(n^2 \cdot d), \qquad C_{\mathrm{RAG}} \sim O(k^2 \cdot d), \qquad k \ll n$. That gap is not an incidental efficiency detail. It is the reason…

Read this part in the article →