Slop*Detector

INCONCLUSIVE — slop score 47/100

The findings here pull in two directions, which is why this one lands at 47 and not higher. The privacy policy and footer read like boilerplate with the usual generated tics, em dashes stacked around radiocarbon dating claims and a gradient wash sitting under three identical copyright cards, the kind of thing a template generator spits out without anyone looking twice. But the punchiest evidence, lines like "Then civilization." and "The Don." dropped as their own sentences, plus the comment thread rattling off "Basques, Vikings, and Indians. Then civilization. You guys said it. Accurite?", shows up in what looks like a 2005 comment section, years before any LLM existed to write it. That timing problem keeps this from being a clean verdict either way. The core article itself reads like a human wrote it with some stiff phrasing and a stray non-breaking space artifact, not a chatbot output, so the slop signal is real but it's coming from the wrong part of the page.

Findings

• Feature-tile grid — Equal-width card grids of 3–4 identical tiles (icon, subheader, blurb) are the signature layout block of generated landing pages.
• Gradient backgrounds / gradient text — Large gradient washes and gradient-clipped headline text (usually blue→purple) are the default decoration of generated UI.
• Em dashes — Em dashes are the single most reliable punctuation tell of LLM copy. Human marketing copy almost never uses them; models reach for them constantly.
• "It’s not X. It’s Y." reframe — The contrast-reframe construction ("It’s not X. It’s Y.", "X isn’t just Y, it’s Z") is the classic LLM rhetorical move. A dead giveaway.
• 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.
• Transition-adverb sentence openers — Sentences opening with "Moreover," "Furthermore," "Additionally" on a loop is essay-bot cadence.
• AI vocabulary — Words statistically overrepresented in generated text: "seamless", "leverage", "unlock", "empower", "elevate", "robust" and friends.
• Stiff, uncontracted prose — Expanded forms ("it is", "you will", "do not") dominating over contractions reads as robotic formality — either legal text or a language model.
• Em dash usage — Two instances of em dashes appear (one rendered with a stray non-breaking space character), which the style guide flags as a tell, though this is a 2005-dated article with an archaic HTML artifact and no other AI markers accompany it.
• Privacy Policy reads as generated — The Privacy Policy carries multiple AI-writing tells (em dashes, "it’s not x. it’s y." reframe). Generated legal pages are a strong marker of an unreviewed, vibe-coded ship.