https://hackerpaper.kaipfister.de/p/1606.03966/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=24332686urn:hackerpapers:mention:1606.03966:24332686Mon, 31 Aug 2020 15:54:52 GMT<p>The practices identified here make sense. Testing pipelines on a small amount of data to make sure there are not simple typos, then doing aggregate statistical tests and specific example condition tests will catch many issues. The paper &quot;Making Contextual Decisions with Low Technical Debt&quot; https://arxiv.org/pdf/1606.03966.pdf goes deeper. Testing and monitoring deployments are very similar. The idea of shadow testing new models (seeing how their outputs would differ from the production models on real data) has been very important for identifying issues in my experience. This can be…</p><p><a href="https://hackerpaper.kaipfister.de/p/1606.03966/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG