Old AI writing tells are gone, but new verbal tics keep appearing
Vendors have stamped out famous tells like em-dashes, yet every model version grows its own high-frequency phrases, so no single feature reliably flags AI text.
A study by the marketing firm Graphite says the old AI writing tells have been stamped out, but every model version grows new verbal tics of its own.
The study used 10,000 pre-ChatGPT articles as a human control, had models rewrite them from summaries, and compared word frequencies, finding 13,000 phrases at least twice as common in AI text. The study was designed and run by Graphite itself.
Claude Opus 5.5's biggest tell is "this matters," 116 times more frequent than in human writing; OpenAI's Astra favors "not simply X" corrective framing, over 100 times more common. Old tells like em-dashes have been largely eliminated.
Graphite chief AI officer Greg Druck told TechCrunch that models only remove the best-known tells, new ones keep popping up, and every version has its own.
Sources:https://graphite.io/five-percent/research/ai-tells-opus-5-5-updatehttps://techcrunch.com/2026/10/01/opus-5-5-loves-to-tell-you-this-matters-and-other-ai-writing-tells