@willfrancis24

You can now spot AI writing without even looking at the words or for m dashes. And this works about 93% of the time because, as this research team found, AI writing has a shape. Look at this.

Every dot here is a story. The five AI models all bunch up in the same little cluster. The human stories are scattered all over the place because there's a randomness to human writing, and you can tell them apart from the structure of the writing alone.

And that matters because AI detection is getting harder. Newer models aren't using the mdash so much, and you can train them to copy a human style anyway. But the wider structure of a piece of writing still has that AI signature, and it is detectable.

The research has found that, for instance, AI over explains. It spells out the point of a story 77% of the time cause it doesn't trust you, the reader, to understand it, whereas humans don't do that. We give the reader some credit and we don't over explain.

But a lot of this is about its neatness. AI stories and AI writing almost never goes off into little tangents or, in fiction, into little subplots. Whereas humans are messy.

They include little asides, flashbacks, time jumps, bits that never even really resolve. They also found that when humans write stories, they talk to you, the reader, and they name real places and reference real things, whereas AI plays it safe. And it keeps everything kind of vague, which is often why AI writing has this strange emptiness to it still, because it's not relaying an author's lived experience.

It's just describing stuff in a fairly kind of non committal way. Each AI model even has its own signature. They found that when you zoom out, Claude's the restrained one with quiet endings.

And it never really escalates things. GPT loves a bit of gossip and

hey found that when you zoom out, Claude's the restrained one with quiet endings. And it never really escalates things. GPT loves a bit of gossip and exuberance to keep things interesting.

Gemini has this weirdly huge preference for grim, dark settings in stories. And then look at this graph, which, funny enough, does make the AI writing shaped like a turd. And what this graph represents is how varied the structure of AI written narratives and stories is versus human ones.

AI makes safer, predictable choices, obviously, cause it's just regurgitating what it's trained on. Whereas humans make unpredictable, erratic novel choices in their writing.