slowbench
RetrievalInferenceEvalsAgentsSeriesFindingsBenchmarksArchive

Measure first. Then decide.

Most of what I believed about my own systems did not survive measurement.

Notes on retrieval, evaluation, and the systems around them — measured before written. Every number here comes from a run against the system that actually serves traffic — not a copy made for the benchmark. Where a result rests on one run, it says so.

Posts
5
Words
11,303
Sections
4
Publishing

Next: An 80-day agent session and the wall at the end of it · tomorrow

5 in the last 42 days · 31 scheduled

Retrieval

3

Code search, embeddings, and ranking.

Inference

1

Local inference, Metal/GPU, and batch tuning.

Evals

1

Measurement methodology and benchmark design.

Agents

Coding agents and context management.

Recent