open source · powers this blog
ai-humanizer: a detector for AI writing tells
40 deterministic rules + stylometry that catch AI slop — em-dash floods, 'delve', hedging, uniform rhythm. Packaged as a Claude skill. Every entry here passes through it before publishing.
The problem
AI-assisted writing has tells: em-dashes everywhere, “delve” and “leverage,” the not-X-but-Y cadence, rule-of-three everything, sentences that all weigh the same. Readers feel it even when they can’t name it. I write with AI assistance daily — so I needed a referee I couldn’t argue with.
What it does
- 40 deterministic rules across vocabulary, punctuation, rhythm, and structure — no ML, no API calls, same score every run
- Stylometry checks for lexical diversity and sentence-length variance
- A 0–100 score where lower is more human; this site’s CI fails any entry that scores above 10
How this site uses it
Every logbook entry runs through the detector in CI before it can deploy. Not as a badge on each post — as a bar. If the writing reads like a press release, the build fails and I rewrite it like a person.
Get it
It ships as a Claude skill and a standalone script. Source on GitHub — and if a rule flags your favorite construction, the false-positive debate is open.