ls -la en/posts/

2026-10-11oQ in oMLX: what I found about Qwen3.8 quants and where my measurement disagreed with expectations

A month ago I benchmarked engines for a local Qwen3.8-27B. Since then oMLX has improved its oQ quantizer, dozens of oQ builds of Qwen3.8 have appeared on Hugging Face, and in 0.7.1.dev1 oMLX learned to serve decision models. I collected what is known and re-measured on my M4 Max 48 GB: oQ4e against plain 4-bit, with and without MTP, and the clef decision model on 600 labeled URLs.

2026-10-0557% fewer long comments. My hook had almost nothing to do with it

A week ago I found that my comment rules never reached Claude's subagents, and fixed it. I re-measured on 11 thousand edits from Claude transcripts: the 57% drop came from a model change, the rules at startup changed almost nothing. What works is the other hook - the one that shows a finding right after the edit.

2026-09-11The em dash doesn't give away a neural network. I checked on a corpus

I measured almost everything that's considered a sign of machine text on 7500 texts. Half of the signs don't work, some work backwards, and my own detector gave the agent's texts higher scores than mine.