sloptells / bold everywhere

active · formatting · first recorded 2026-07-02 · registers: hn, cooking, parenting

**Bolding** key phrases in contexts where no human would: forum answers, comments, casual replies. Humans in our matched corpora essentially never bold; models do it constantly (90×+ in advice registers).

model specificity: cross-model; declining but still extreme

examples

**Salt, correctly timed** — Salting early and adequately…

evidence

occurrences per 10k words, measured 2026-09-28 (run #15, 3 current + 3 vintage models)

current AIvintage AI (2024/25)humans (matched)canon (great pre-AI prose)
pooled27.0761.120.000.00
hn1.41—0.00
cooking49.52—0.00
parenting31.74—0.00
linkedin56.00——

history

rundateAI /10kvs humans
#22026-07-0230.67only in AI
#32026-07-0231.47only in AI
#42026-07-0641.81only in AI
#52026-07-1339.81only in AI
#62026-07-2023.79only in AI
#72026-07-2730.16only in AI
#82026-08-0324.66only in AI
#92026-08-1023.03only in AI
#102026-08-1726.81only in AI
#112026-08-3126.49only in AI
#122026-09-0726.11only in AI
#132026-09-1424.65only in AI
#142026-09-2131.26only in AI
#152026-09-2827.07only in AI

detector

regex: \*\*[^*\n]{2,80}\*\*

sources

← all tells