Opus 5.5 loves to tell you ‘this matters’ (and other AI writing tells)
A new study by marketing firm Graphite identifies specific linguistic patterns, or 'tells,' that distinguish AI-generated prose from human writing. The research highlights that different models, such as Claude and GPT, have unique habits that researchers can use to detect synthetic content.
Why it matters
As AI-generated content proliferates, the ability to distinguish between human and machine-written text is becoming increasingly important for media literacy and content verification.
Now that LLM-generated prose is everywhere, human beings are eager for ways to sniff it out. While early tells like em-dashes and “delve” are long gone, researchers say there are still plenty of telltale habits that AI models fall back on when writing prose.
A new study from the marketing firm Graphite looked at the writing habits of frontier models, sussing out each model’s favorite words and phrases. While old tells like em-dash use have been stamped out, models still fall back on contrast-heavy constructions, with each model version showing its own unique quirks. The biggest surprise is how broad the scope of tells turns out to be. Graphite found 13,000 phrases that were at least twice as common in the AI content as human content — their definition of a “tell.”
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in