Each tell below comes with why it reads as AI and the plain line to write instead.
AI writing gives itself away with a small set of overused words (delve, underscore, pivotal, showcasing), puffery, the "it is not just X, it is Y" rhythm, a flood of em dashes and bold, warm-up openers and a tacked-on summary. The durable fix is teaching the tool your own voice, so the tells never start.
First, the proof it is real
This is measured, not a hunch. A 2025 Science Advances study of fifteen million research abstracts found words like delve and underscore spiked right after ChatGPT, enough to estimate one in ten had been AI-assisted. Wikipedia keeps a living list of the tells too.
The tells also move faster than any fixed list, which is the part most guides miss. One independent analysis of around sixteen thousand Substack posts found the giveaway has shifted from the "it is not just X, it is Y" line itself to repeating that shape within one piece.
Of the posts that used it at all, a quarter used it three or more times, so the tell is a habit that keeps recurring rather than any single word. The full analysis is here, and it is the kind of thing you only find by digging past the first page of results.
To catch this yourself, read your piece back and look for any sentence built the same way more than twice: the same construction, or the same three-beat rhythm. If a shape shows up three times, that is the tell, more than any single word.
The tells, and what to write instead
These are the ones that give it away most. Scan for them in anything you or an AI wrote.
| The tell | Why it reads as AI | Write instead |
|---|---|---|
| Delve, delve into | The single most outed AI word. Its use exploded in real writing after ChatGPT. | Look at, get into, or just cut it. |
| Underscore, pivotal, showcasing, intricate | The "excess vocabulary" the study measured spiking. | Plain words: shows, key, detailed. |
| A testament to, rich tapestry, the realm of | Puffery that inflates everything into a big deal. | Say the actual thing, plainly. |
| "It is not just X, it is Y" | A rhythm the model loves for fake profundity. | Make the point once and move on. |
| Em dashes everywhere | AI reaches for the em dash constantly. It is such a strong tell that this whole site bans them. | A comma or a full stop does the job. |
| Bolding half the sentence | The model bolds like it is marking a textbook. | Bold rarely, or not at all. |
| "In today's fast-paced world..." | A warm-up opener that says nothing. | Start on the actual point. |
| The tidy rule of three | Three neat items every single time reads generated. | Vary it. Use two, or four, or one. |
| "Experts say", "studies show" | Vague authority with no name, often invented. | Name the source, or drop the claim. |
| A summary tacked on the end | AI wraps up neatly when nobody asked it to. | Stop when you are done. |
Tells drawn from Wikipedia's Signs of AI writing and the Science Advances 2025 excess-vocabulary study, both linked above.
Here is what they look like stacked into one sentence, then the same thing cleaned:
Before: In today's fast-paced world, it is not just a tool, it is a testament to how AI can delve into the intricate realm of your writing.
After: AI can help you write faster. Here is how.
Your voice is the real fix, because a word list ages
Here is the honest bit most tells guides skip. The list above is a moving target. As soon as everyone learns that "delve" is a giveaway, the models drift and the readers recalibrate, and a fresh set of tells takes over. If all you do is find and replace the words, you are always a step behind.
The durable fix is to teach the tool what you actually sound like, so it writes in your voice from the start instead of the neutral AI one you then have to scrub. Two ways to do that:
- Paste real samples into the pass below. Two or three real things you have written, underneath the text you want cleaned.
- Use Claude's built-in Styles. You upload samples of your writing and it matches them.
The pass is the quick clean-up, the voice is the long game.
The de-AI pass
Paste this into Claude or ChatGPT with your text underneath. It finds the tells, rewrites them out, and tells you what it changed so you learn them for next time. Add a couple of your own writing samples and it will keep your voice while it cleans.
Do a de-AI pass on the text below, in three steps, and show your work.
Step 1, find the tells. Read it and list every giveaway, quoting the exact words:
- AI words: delve, underscore, pivotal, showcasing, intricate, testament, tapestry, realm, and their cousins.
- Puffery that inflates everything into a big deal.
- The "it is not just X, it is Y" line, and any shape or rhythm that repeats across the piece (the same construction, or a rule of three, used again and again). The repetition is the bigger tell than the phrase.
- Em dashes, half-sentence bolding, and warm-up openers like "in today's world".
- Vague authority ("experts say", "studies show") with no real name.
- A summary tacked on the end that nobody asked for.
Step 2, rewrite it, fixing every tell you found:
- Plain words a real person would say out loud. Prefer commas or full stops over heavy dash punctuation.
- Say the actual thing instead of praising it. Cut the warm-up and the tacked-on summary.
- Keep every real point and fact from the original. Change how it is said, not what it says.
- Vary the sentence length so it reads natural, not choppy or robotic.
- Never invent a fact, a name or a number to fill a gap. Leave a clear gap in brackets for me instead.
- If I pasted samples of my writing below, match that voice. If not, keep it plain and natural, do not invent a personality.
Step 3, report. Give me a short list of what you changed and why, so I learn the tells for next time.
[PASTE YOUR TEXT HERE]
[Optional, so it sounds like me: paste two or three things I actually wrote, and match that voice.]
Set it once so the tells never start
The pass above cleans a draft after the fact. Better is to stop the tells before they land. Paste this short list into your Claude or ChatGPT custom instructions, or into a saved Style, and it applies to everything the tool writes for you, so you spend far less time scrubbing.
Write like a person, not like AI. Apply these to everything you write for me: - Cut the AI words: delve, underscore, pivotal, showcasing, intricate, testament, tapestry, realm, and do not dress a plain thing up in a fancier word. - No "it is not just X, it is Y", and do not repeat the same shape, or a tidy rule of three, through a piece. - No warm-up openers like "in today's world", and no summary tacked on the end. Start on the point, stop when it is made. - Name a source or drop the claim. No "experts say" or "studies show" with no name. - Plain words a real person would say out loud, and vary the sentence length so it does not read robotic. - Never invent a fact, a name or a number. Leave a clear gap in brackets for me instead.
Keep this short and current. A long ban list gets ignored, and half these words will date, so prune it rather than growing it.
See the tells light up in your own writing
The fastest way to learn them is to watch them appear in something you wrote. Simon Willison, an engineer who writes closely about AI, built a free browser tool that does exactly that: paste your text into his LLM cliché highlighter and it marks every sentence that matches a known tell, no signup, nothing to install.
It beats an AI detector, which only hands you a score and gets it wrong in both directions. This shows you the actual phrases to fix, which is the part that teaches you to spot them yourself.
If you live in Claude Code and want a reusable version, there are free open-source humanizer skills that score and rewrite your text on your own machine, like this one. For everyone else, the highlighter plus the pass above is plenty.
Where the line is
- The honest bit: this list will age. The tells are real today and backed by the research above, but the models and the readers both move. Treat the words as a starting point and lean on the voice fix, which does not go stale.
- A detector score is not proof. It is a signal that gets things wrong in both directions. Do not use one to accuse a student, a colleague or yourself of anything. The tells you can see with your own eyes are worth more than a number.
- If the rewrite comes back stiff or choppy, you stripped too hard. A pass with no samples flattens everything to a neutral, clipped tone. Paste more of your own writing and tell it to keep your rhythm, not just cut words.
- Not everything needs this. Run the pass when your name is on it or it goes public. A two-line message to a mate is fine as it is, so do not police yourself into stiffness.
Run the pass on one thing today
Take the last thing you wrote with AI, an email, a caption, a post, and run the pass on it with two of your real messages pasted underneath. Read the before and after side by side. That comparison teaches you your own tells faster than any list, and after a few passes you start catching them as you write.
Want the output to sound like you from the first draft, not after a clean-up? That is the whole job of the Voice File.
Questions people ask
How to tell if writing is AI?
Look for the habits that keep turning up: words like delve and underscore, puffery, the "it is not just X, it is Y" rhythm, em dashes and bold everywhere, and a tidy summary at the end. One tell proves little, but the same sentence shape repeated three or more times in one piece is a strong sign.
What are red flags for AI writing?
Delve, underscore, pivotal and showcasing, puffery like "a testament to" or "rich tapestry", vague authority such as "experts say", the tidy rule of three every time, and bold on half a sentence. The table above gives the plain line to write instead of each one.
How can you tell if someone used ChatGPT to write an essay?
Read it for the tells above, especially one sentence shape repeated through the piece, and treat what you find as a signal rather than proof. Detector scores get it wrong in both directions, so never use one to accuse a student or anyone else.