How to clean ChatGPT text before you paste it

The tells are mostly punctuation and characters you cannot see. Both are fixable in one pass.

Copy the text out of ChatGPT, then strip the punctuation and the hidden characters before it lands anywhere. That is the whole job. The visible tells are em dashes, curly quotes and the ellipsis glyph. The invisible ones are zero-width and non-breaking spaces, which survive a copy and never show on screen.

The characters to remove

Dashes and quotes first. Em dashes and en dashes become plain hyphens. Curly quotes and curly apostrophes become straight ASCII marks, or come out entirely. The ellipsis glyph becomes three periods. Those four cover most of what a reader notices.

Then the structure. Markdown written for a chat window arrives flattened in a plain field. You get leftover asterisks around bold text, stray heading marks, and bullet or numbered list markers sitting mid-paragraph. Remove them too, or the paste reads as a broken outline.

Then the ones you cannot see. Zero-width space, zero-width joiner, word joiner, soft hyphen, byte-order mark, non-breaking space and the narrow no-break space. NFKC normalisation folds fullwidth and ligature glyphs back to plain letters. Cyrillic and Greek lookalike letters need converting to their Latin twins.

Order matters more than the list. A literal \n from a chat or code copy is turned back into a real line break before any other rule runs, so text that arrived as one escaped line becomes paragraphs first.

Your wording never changes. Only typography, structure and hidden characters move, so the cleaned paste says exactly what the model said.

It will not get you past an AI detector

Character cleanup does not defeat detection, and plenty of pages imply otherwise. Detectors score the statistical properties of your words: word choice, sentence rhythm, perplexity and burstiness. Punctuation sits outside that measurement. Originality.AI tested the question directly and found that adding or removing hidden characters left detectability unchanged.

The second trap is autocorrect. Word and Google Docs re-curl straight quotes and put no-break spaces back after you paste. Turn off smart quotes in their autocorrect settings, or you clean the text and the app dirties it again in front of you.

What I use

For one message, use a web page. Try it free in your browser, with no install and no account, and the cleanup runs client-side so nothing is uploaded.

The round trip is what wore me down. Copy out of ChatGPT, open a tab, paste, clean, copy again, paste for real, then repeat on the next message. Klipto's Anti-LLM transform runs the same pass at the moment I press ⌘V, in any Mac app, offline. One tap on the chip in the paste preview, or automatic on every paste.

Frequently asked questions

Does cleaning ChatGPT text help it pass an AI detector?

No. Detectors read patterns in the words themselves, so replacing an em dash with a hyphen changes nothing they measure. Cleanup fixes typography and hidden characters. Rewriting sentences is a separate job.

Which invisible characters does AI text contain?

Zero-width space (U+200B), zero-width joiner and non-joiner, word joiner, soft hyphen, byte-order mark, non-breaking space and the narrow no-break space (U+202F). They render as nothing or as an ordinary space.

Does ChatGPT watermark its output with hidden characters?

No. Narrow no-break spaces appeared in o3 and o4-mini output in April 2025, OpenAI said they were "not a watermark" but a training quirk, and they vanished after a model update the next day.

Do Claude and Gemini need the same cleanup?

Yes. The families of characters are much the same across models, so the same pass works on all three. Only the exact mix varies.

Can I clean it without pasting into a website?

Yes, on a Mac. Klipto runs the cleanup on-device as part of the paste, so the text never leaves the machine and there is no daily quota.

Get Klipto for Mac

Free for 14 days · no card, no account required · 5 MB

Download Klipto