Un•AI•ify looks for patterns commonly found in AI-generated writing created by models like ChatGPT, Grok, Claude, Gemini, and others. LLMs use these writing styles and rhetorical patterns because of their popularity in English-language content.
Why does Un•AI•ify focus on rhetoric?
Communication is inseparable from persuasion. This has been known as far back as Aristotle who said, "It is not sufficient to know what one ought to say, but one must also know how to say it" — itself an example of both It's not X. It's Y and But reverse!. (No surprise Aristotle knew something about rhetoric.) Rhetoric is inseparable from communication, and understanding how writing attempts to persuade and influence audiences is so important. Modern digital communication exists in extreme competition, putting immense pressure on writers to use rhetoric to capture attention. Within this environment, communication that uses rhetoric successfully is more likely to be seen. No surprise, more and more content online uses and abuses rhetorical writing. This kind of content is created by people and AI.
How do you interpret the Rhetorical Score? Understand the score is an arbitrary calculation. Certain patterns weigh more heavily on the Rhetorical Score (It's not X. It's Y will increase the score more dramatically. Em dashes less). Now, think of the Rhetorical Score as how much an audience is likely to perceive they are being pushed or pulled by the content. The higher the score, the more likely an audience is to react to the writing, and this reaction could be positive or negative. If they are receptive to the message already, they are likely to react positively (think of this as "preaching to the choir"). If they approach the content with skepticism, perhaps trying to discern value quickly, they are more likely to react negatively. The underlying hypothesis of Un•AI•ify: People will dismiss communication when they perceive it is intended to persuade or when it is perceived to be low-value ("AI writing" could be seen as low-value as it's so easy to produce). Persuasion and low-value could be two parts of the same dynamic: If an idea is valuable, does it need to be sold or will it sell itself?
Regardless, people today have little choice in the matter. They must filter through the flood of content they are exposed to online in order to and discern what's valuable or not. By using "tells" (such as overused and rhetorical writing patterns), people can more quickly filter information. Expect this to continue. Subscribe to the Un•AI•ify blog for more in-depth discussion of modern communication dynamics.
TL;DR: Use the Rhetorical Score as a flag to gauge how likely your audience may see the content as rich in information or rich in persuasion. Ask: How will this content be received by the audience?
By raising awareness of the overuse of rhetoric and other Patterns, the astute reader and writer can produce better writing and a sharper, smarter mind.
If there are other patterns you would like Un•AI•ify to identify, reach out to [email protected].
It's not X. It's Y
This pattern looks for words like it's not, doesn't, and not only as well as related phrasing. These words and phrases set up a ubiquitous rhetorical pattern with AI-generated writing we call "It's not X. It's Y."
The It's not X. It's Y pattern begins with a statement of negation followed by a statement of affirmation. Why is this rhetorical approach so popular? What makes it effective? How many times can this be used before the rhetorical approach loses its power? And what is the writer trying to state? It's not X. It's Y is easy enough to recognize once you understand it, but for a tool to identify the Pattern is complicated. Un•AI•ify works by spotting common negations and then highlighting surrounding content. There are false positives, a limitation of the tool; however, prepare to be surprised how this rhetorical pattern shows up. Finally, bonus catches in place for "more than" and "go beyond."
Lady doth protest
The full quote from Shakespeare's Hamlet is "The lady doth protest too much, methinks." When you want to make a point, make the point. Extra words of enthusiasm, usually in the form of adverbs, can often be deleted to make writing stronger. Lady Doth Protest looks for words like "just," "truly," "really," "fully," etc. Remember what Ronald Reagan said, "If you're explaining, you're losing."
But reverse!
But pervades persuasive writing today for good reason. The word signals, "Pay attention. Something is different." But reverses sentiment, keeping readers off-kilter and ready to be led by the writer. Smart readers will think of but like an Uno reverse card that negates whatever was written before "but." As Nassim Taleb said, "Everything before the 'but' is meant to be ignored by the speaker; and everything after the 'but' should be ignored by the listener." But is a powerful word, but use it wisely.
Clichés
Clichés are said to "betray a lack of original thought," so they are best avoided. Examples of Clichés checked for include: think outside the box, low-hanging fruit, barking up the wrong tree, and it is what it is. Bottom line: Clichés can terminate thinking (and maybe that's what you want in your writing). Be careful the thinking terminated isn't your own.
Buzzwords
Watch out for buzzwords and jargon in writing. Often used in business writing, common buzzwords include: laser-focused, optimize, actionable, disrupt, utilize, leverage, unlocks. Instead of using buzzwords, try specific examples and language — the kind that demonstrates your subject matter expertise.
Triads
Triads are three things in a row. Repetitive and rhythmic, triads (or tricolons) make for great rhetoric, and writers and speakers have used them for centuries. Veni, vidi, vici! Like everything, they can be overused. Check your triad frequency. What if two would do? Might you need four or five? While the bears numbered three, Goldilocks is just one way to write your story.
Dashes
Em dashes (—) and en dashes (–) have their place. Writers love em dashes, in particular. And no, not every em dash means, "AI wrote this!" Good writers know how to type an em dash. Like it or not, generative AI can create good writing too. However, there's such a thing as too much of a good thing. Watch your em dash frequency. Use en dashes (–) in a range if you like. Whatever you do, be consistent within a document. If you put spaces on either side of an em dash, make sure they all look that way. If you use two hyphens (--), make sure there's not an em dash (—) in there too. Why? Because people are paying attention to these things — even if only subconsciously.
About Un•AI•ify
Un•AI•ify was created to offer a quick way to analyze writing for certain patterns used and abused by AI (and writers on LinkedIn). If you have a pattern you'd like Un•AI•ify to look for or simply want to connect, email [email protected] or find Justin on X or LinkedIn. This site was built by Justin Owings, a marketer, tinkerer, and student of influence. The owner assumes no liability for analysis produced by Un•AI•ify. Use the tool at your own risk.
If you're still reading this, take the next step: Join Un•AI•ify by subscribing. Learn more about this project, and connect with others interested in being smart about AI and modern media.
Disclaimer: AI is trained on and mimicks writing from people (and now, life imitates artificial). Non-AI writing can and will be mistaken for AI-generated writing and vice versa. Un•AI•ify aims to raise awareness in order to raise the bar on writing and increase scrutiny on content.
© Justin Owings • 2025 • All rights reserved
