What does this equation mean?

It is worth being precise about what “just use a longer context” actually replaces, because the alternative is not vague. Retrieval-augmented generation, as originally formalised by Patrick Lewis and colleagues, pairs a parametric model with a separate non-parametric retrieval step: a retriever selects a small number of passages likely to be relevant to a query from a much larger corpus, and only those selected passages, not the whole corpus, are placed in the model’s context for generation [ 14 ] . This publication’s own reporting on retrieval-augmented systems covers that mechanism, its indexing choices, and its failure modes at length elsewhere; the point relevant here is narrower and purely architectural. Long-context use skips the selection step entirely: the entire candidate 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 retrieval-augmented systems existed as a technique before million-token windows did, and it is why the comparison between the two approaches remains a live, actively contested research question rather than a settled one, even after context windows grew by orders of magnitude.