Fits in the Window ≠ Works Better: Kimi K3 RAG Tested Blind
The math is tempting: the author's entire two-year corpus is 127,068 tokens, twelve percent of Kimi K3's 1M window. So he sent the same 12 questions down two paths, a top-5 RAG pipeline and the full corpus in one prompt, same model and system prompt, graded blind. His blunt verdict: "it fits" and "it works better" are different things. The failures he hit along the way, he argues, teach more than the results.