Topic

AI

The technology itself — what current models can and cannot do, and how that changes what is worth building.

03 items · all topics

Writing

  1. Evaluations are not testsA test tells you whether the code did what you wrote. An evaluation tells you whether the system is still good enough. Confusing the two produces suites that pass while the product gets worse. · 5 min
  2. Retrieval is not a knowledge baseTeams ship retrieval as though it were search with better manners. It is a data product, and it fails in the ways data products fail — quietly, and mostly on freshness. · 2 min

Building

  1. briefcastA self-hosted podcast library that downloads, transcribes and summarizes episodes — locally, if you want it to. · briefcast