Slop*Detector

INCONCLUSIVE — slop score 39/100

The strongest signal here is the writing itself, specifically the recurring 'not X, but Y' contrast construction the analyst flagged twice, once in the pouncing passage and once in the Africa comparison, which is the kind of reflexive reframe a model reaches for when it wants to sound sharp. Layered on top of that are em dashes threaded through the Sefer Yetzirah and Shem HaMephorash sections, a punctuation habit that shows up far more in generated prose than in how people actually write. The visual findings, default lucide icons, untouched shadcn components, and a handful of blur panels, point to a templated Substack theme rather than anything the author built by hand, though on a blog post that carries less weight than it would on a product landing page. The subject matter itself, detailed Kabbalistic and Voynich manuscript analysis, suggests a human researcher directing or editing the output even as the prose carries clear AI tells. A score of 39 and an inconclusive verdict fit the evidence: enough to raise an eyebrow, not enough to call the whole post machine-written.

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.
• Glassmorphism — Frosted-glass backdrop-blur panels are a recurring generated-UI decoration.
• 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.
• Minor em dash usage — One em dash appears in 'Mayim — מים', but it's used as a translation aside rather than a dramatic rhetorical device, and is not part of a pattern.