Slop*Detector

INCONCLUSIVE — slop score 40/100

This one lands as inconclusive, and the evidence explains why: it's a mix of boilerplate template debris and academic citation formatting that got flagged for the wrong reasons. The dead Akismet privacy link and the default Inter font stack both point to an untouched WordPress/Hypotheses theme, which is normal for an academic blog platform and not evidence of AI authorship on its own. The 'punch sentence' and 'stacked short sentence' findings are weaker than they look; the cited evidence is bibliography entries and citation fragments (thesis titles, conference proceedings, author names), not actual prose rhythm from the post body, so those two findings probably misread reference formatting as generated text. Given that the strongest structural finding is just an unfilled plugin default and the writing-style findings rest on citations rather than sentences, the 40/100 score reflects genuine uncertainty rather than a clear pattern of AI generation.”,

Findings

• Untouched shadcn/Tailwind defaults — shadcn components, lucide icons, and Inter/Geist/Space-Grotesk font stacks left at their defaults mean the model picked the design, not a person. Instrument Serif as an accent font is a separate, independently corroborated tell.
• One/two-word punch sentences — Single dramatic words dropped as their own sentence ("Done." "Gone." "Period.") are an LLM emphasis habit, not a human one.
• Stacked short-sentence drumbeat — Three or more clipped sentences in a row ("Important emails buried. Drafts that sound wrong. Labels everywhere.") is the manufactured-rhythm tell.
• Dead Privacy Policy link — The Privacy Policy link exists but leads to an empty or broken page — the template put the link there and nobody wrote the page.