The first time I implemented Vamana from the DiskANN paper, my approximate nearest neighbor index was slower than brute force. On tiny test fixtures, brute force took 0.27 ms per query. My Vamana implementation took 22.98 ms. That sounds absurd. ANN exists to skip work. The problem was not the algorithm. It was how I mapped the paper's abstractions to actual data structures. The DiskANN pseudocode
Every AI app I've shipped recently rewrote the same plumbing. The OAuth dance for Slack. Encrypted storage for an API key. Refresh-token logic that finally fails on the 3rd call after an hour. Wiring up an MCP client to a server behind a bearer token someone pasted into a Notion page.