AI-written text has tells. They change as models change — “delve” died in 2024,
and the list below is what's measurably alive today. We measure them:
generate text from current and older models on prompts matched to pre-AI human writing,
find what models overuse, check every candidate against acclaimed human prose so we
don't flag good writers, and date everything.
This is a style linter, not an AI detector — these patterns read as
AI whoever wrote them. If you write with an agent, point it at the
api or llms.txt and let it dodge the list
while drafting.
check your text
active — strongly overrepresented in current model output — worth avoiding