sloptells / bullets for a conversation

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

Answering a casual question with a formatted mini-wiki: bullet lists, sections, a summary. In the cooking register models used bullets at 134× the human rate. A list is innocent on its own; the tell is a list where a human would write three sentences.

Scored per item; only fires meaningfully when text is short relative to its list count.

examples

A few common examples: - US “arugula” = UK/AU/NZ “rocket” - US “cilantro” = …

evidence

occurrences per 10k words, measured 2026-08-17 (run #10, 3 current + 3 vintage models)

current AIvintage AI (2024/25)humans (matched)canon (great pre-AI prose)
pooled32.4725.202.590.28
hn8.715.37
cooking72.550.54
parenting41.300.00
linkedin0.00

history

rundateAI /10kvs humans
#22026-07-0231.79×8.6 vs humans
#32026-07-0233.51×5.0 vs humans
#42026-07-0633.96×9.0 vs humans
#52026-07-1336.81×5.3 vs humans
#62026-07-2030.12×7.1 vs humans
#72026-07-2736.62×7.7 vs humans
#82026-08-0332.31×5.4 vs humans
#92026-08-1037.04×9.4 vs humans
#102026-08-1732.47×13 vs humans

detector

regex: ^\s*[-*•]

sources

← all tells