Slop*Detector

SUSPICIOUSLY VIBEY — slop score 67/100

This case is about as clear-cut as they get. The submitted material isn't a website at all but a pasted ChatGPT conversation, complete with sidebar chrome, a chat history panel, and a

Findings

• Pill tags — Little fully-rounded pill badges sprinkled across the page ("New", "Beta", category chips) are a default garnish of vibe-coded UI.
• Glassmorphism — Frosted-glass backdrop-blur panels are a recurring generated-UI decoration.
• Not a marketing/product site — this is a ChatGPT conversation screenshot — The screenshot shows the default ChatGPT web app interface (sidebar with New chat/Images/Plugins/Deep research, chat bubble with generated fantasy-football rankings, message input bar) rather than a designed website. None of the Anti-AI UI Guide's layout/styling/imagery tells (feature grids, pills, gradients, hero sections, etc.) apply because there is no custom UI here to evaluate — it's OpenAI's own unmodified product chrome.
• 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.
• 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.
• "That’s where/why/the…" payoffs — Short demonstrative payoff sentences glued onto paragraph ends ("That’s the flywheel.") are choppy LLM theater.
• Empty intensifiers — "Incredibly", "truly", "genuinely" — intensity asserted rather than shown, a padding habit of generated copy.
• Raw ChatGPT interface/transcript pasted as page copy — The submitted material is not article copy at all — it's a verbatim shared ChatGPT conversation, complete with product chrome (chat history, plugins, login prompts, 'Edit' button, terms footer). This is direct, undeniable evidence the content originated from an AI assistant and was pasted with zero editorial cleanup.
• Assistant follow-up offer left in the copy — The trailing 'If you want, I can:' bullet list is a classic ChatGPT closing move offering follow-on tasks, not something a human writer would append to a finished ranking article. Its presence confirms the text is an unedited model output.
• Dramatic negation list before a punchy payoff — Stacking quoted rejections before a one-word payoff is a theatrical rhythm the style guide flags as a stock LLM move.
• One/two-word punch sentences — Several single-word or near-single-word sentences are dropped for dramatic emphasis, a rhythm pattern associated with generated text rather than natural prose.
• "This is not X. This is Y." reframe — This is a close cousin of the banned 'It's not X, it's Y' reframe structure, used to deliver a punchy contrast rather than stating the point directly.
• Tacked-on 'That's the...' payoff sentences — Short demonstrative payoff sentences glued onto the end of a thought are called out explicitly in the guide as a choppy LLM tic.
• Em dash usage, including a run of them as list separators — The guide bans em dashes outright; here they appear both mid-sentence for dramatic pause and as the separator for every line of the closing rankings list, a repetitive mechanical pattern.
• Empty intensifiers — Words like 'incredibly' and 'simply' are used as filler intensifiers rather than to add concrete meaning, matching the guide's list of empty-intensifier tells.
• Dead Terms of Service link — The Terms of Service link exists but leads to an empty or broken page — the template put the link there and nobody wrote the page.