I mistook movement for improvement. For three months, I changed our ranking algorithm every two...
I mistook movement for improvement.
For three months, I changed our ranking algorithm every two weeks.
BM25.
Hybrid BM25 + vector search.
A cross-encoder reranker.
I publish free leaderboards of which products AI answer engines name when someone asks them to...
My RAG evaluation would tell me hybrid: 0.86 and I'd sit there with no idea what to actually change....
Your retriever returned the right documents. The similarity scores look fine. The answer is still...
A fine-tuned AI model was a star pupil on the benchmark, then started mixing up subjects and flipping negations the moment I put…
My RAG pipeline had a bottleneck, and the fix turned out to be just simple math. The...
I'd made translation faster by trimming its output. A few months later I measured again and the breakdown had flipped —…
