1d ago · 11 min read · The extraction pipeline processed 2,400 documents overnight. Cost: $380. The next morning I diffed the inputs against the previous batch—87% were near-duplicates with trivial whitespace changes. I’d burned $330 re-extracting answers I already had. No...
Join discussion1d ago · 10 min read · I noticed it as a silence first. A request that normally felt instant took long enough that I caught myself staring at the logs like they owed me money. Nothing was “down.” No exception. No crash. Just… slow. And the slow wasn’t mysterious: Redis had...
Join discussionMar 10 · 14 min read · I originally got asked to write about app/azure_integrations/azure_maps.py—specifically the cache key scheme (tile vs geohash), TTL heuristics by zoom level, and the fallthrough behavior to the upstream geocoder with backoff. That’s exactly the post ...
Join discussionMar 10 · 11 min read · I didn’t switch to multi‑vector embeddings because it was trendy. I did it because a single pooled vector kept lying to my search. When you collapse a candidate into one embedding, you’re asking one point in space to simultaneously represent “career ...
Join discussion
