Posted on 08/29/2026 9:04:49 PM PDT by SeekAndFind
A GHOST WRITER is haunting the English language. The linguistic spectre can turn its hand to prose, poetry, journalese and corporate jargon. It is frightfully versatile: you can get it to mimic Shakespeare’s sonnets or a schlocky beach read; Ernest Hemingway’s taut prose or the office-printer manual. It is frightfully fast, churning out thousands of words a minute. (Hemingway rarely produced as many in a day, and required much more booze.) Wordsmiths are spooked.
AI writing is everywhere. It is in your inbox and on your LinkedIn feed. It is all over the internet, drafting more than a third of new websites by one count. Large language models (LLMs) are helping students write essays and probably helping scientists write papers. Some allege AI-generated prose won the Commonwealth Short Story prize this year, with judges praising its “quiet authority”. (The Commonwealth Foundation denied the claim.)
LLMs have stylistic quirks. They are thought to maximise the use of long em-dashes—and the use of words like “maximise”. They like to “deep dive” (and, better yet, “delve”) into the “rich tapestry” of the world. AI writing is not about a single word or phrase, but a rich tapestry of things.
Spotting AI texts can be tricky. This is in part because you need evidence beyond a few words or dashes: claiming that a text is by an LLM because it uses the word “delve” is like claiming one is by Jane Austen because it uses “imprudence”. Bots also write in slightly different ways.
There is no single style of AI writing, explains Karolina Rudnicka, a linguist at the University of Gdansk in Poland, just as there is no single style of human writing. Writers have idiosyncrasies—Emily Dickinson, for instance, loved em-dashes—and bots may do, too. But there are a few ways to identify LLM-generated text.
One is to use detection algorithms that are trained to spot the texture of human or AI prose. Pangram, a leading firm, claims to have 99.98% accuracy. (It has partnered with Substack, a blogging platform, on such a tool.)
Detectors, however, are black-box algorithms that can give false positives. They do not give reasons for why they reach their conclusions.
Researchers have also tried scouring texts for suspicious words or comparing papers from before and after LLMs were made available to the public. But these approaches have drawbacks too, not least because it is hard to disentangle AI quirks from other language trends.
You can discover AI’s hallmarks by comparing the writing of man and machine. To do this you need a baseline that is distinctive and familiar. The Economist turned to prose that we’re sure is human and that readers will recognise: our own. We designed a study to ask top LLMs—OpenAI’s ChatGPT, Anthropic’s Claude, Google’s Gemini and xAI’s Grok—to write versions of our articles without consulting the web. (As a prompt, we gave them the AI-generated summaries that we have experimentally added to some of our articles.)
This gave us a corpus of human and AI creations and we compared them across 55,940 sentences and 1.2m words. To make sure we were detecting AI quirks rather than our own, we also checked the AI texts against journalism from CNN, the New York Times and the Washington Post. Excerpts from hit novels published between 1950 and 2022 offered another test.
Our findings are surprising. AI prose is distinguishable by word and punctuation choice as well as sentence and paragraph structure. But its hallmarks are not what you might expect, partly because its writing style has changed with software updates. That does not mean that LLMs are great writers: their prose lacks lucidity and elegance and is often formulaic. So those aspiring to be impressive (human) storytellers should avoid the following peculiarities in their own prose.
First, consider words. The vocabulary that bots overuse has changed: they no longer “delve” and there are not as many “tapestries”. Instead they offer a significant number of polysyllables like “significant”, “increasingly” and “consequences”. They use more rare words (“interdependence”, “reindustrialisation”) and scientific lingo (“parameter”, “methodology”) than humans, and are fond of nominalisations (making nouns from verbs, such as “expansion” from “expand”). All the LLMs in our study use such words, but particularly Gemini and Claude.
Much of this language could be described as what George Orwell called “pretentious diction”. He railed against writers who “dress up simple statements” with complicated words and jargon to sound clever. Such pontificating penmen, Orwell observed, also believe that “Latin or Greek words are grander than Saxon ones”. (Bots agree: more Latinate suffixes crop up in their writing than in human texts.)
Then look at punctuation. Many believe LLMs stuff their prose with em-dashes, but that is not true after the most recent updates. Today only Claude uses more em-dashes than human writers, with ChatGPT using markedly fewer than any other writer in our study. Humans rejoice—and start using dashes again.
A better way to spot AI-generated writing would be to look for texts without much punctuation at all. LLMs are very Joycean about it: they use fewer commas and semicolons than humans (and hardly any parentheses). They use less punctuation in part because they write longer sentences—“and” is their most overused word—and in part because they do not quote experts.
Finally, study the sentence. Bots’ sentences tend to be long; paragraphs are rarely interrupted with short, punchy statements. How dull. When LLMs want to make their sentences more lively, they often reach for a rhetorical device. Their favourites include: “not X but Y”, “not only but also” and the “rule of three”. (Grouping ideas in threes makes them more engaging, as we did just then.) ChatGPT and Claude use more of these constructions per 1,000 sentences than other LLMs and humans.
So if you want to spot AI writing, look for bland, pretentious prose lavished with Latinate words—at least for now. With every update, our study shows, AI writing is becoming more similar to human prose. Pangram successfully detected AI-generated copy, but may struggle in future. LLMs are trained on human writing and learn from human feedback, notes Tommie Juzek of Florida State University, picking up things people find impressive and dropping things they do not.
Bots learn fast, too. Take ChatGPT: until very recently it used an em-dash in almost every sentence. When your correspondent asked an older model whether it thought AI overused the dash, it said: “Ha—great question!” Ask the bot the same thing today and it soberly says “they’re best used sparingly.” Only a ghost could shapeshift so quickly. ■
Hahaha, I know...it is my programmed BIDI (Bot Identification Deflection Interaction) meant to throw humans...er...people off my...er...the trail of discovery.
And so was that...:)
Oh, absolutely.
I just retired last year, but I was working with a guy, a real genius IMO, who was into that early on.
He demonstrated to me how he could tell an AI agent what he wanted to do, and it would spit out the structure for his programming. It wasn’t perfect, but he could insert his own elements into that structure and syntax that it handed to him, and instead of spending weeks trying to tweak the syntax and framework to get it to work, it would take him days...or hours.
Remarkable. I don’t think I would have believed it that devoutly until he actually showed me how he did it.
I was very impressed, I can tell you, and when I heard that AI was going to have a great impact on programming, I believed it implicitly.
> While I am wary of the potential abuses that could come about in using AI, I also see how it can be very useful.<
I’ve been sporadically using ChatGPT. I find it a bit humorous that the first answer makes a definitive statement. When I ask a follow-up question, most of the time it responds with “My earlier answer was inaccurate “. Sometimes it carries into the third follow-up question.
It’s almost a game at this point. Try it.
EC
I see this as one of the things that very few people are focused on. We all focus on the positive, good, and helpful things AI can do for us, in the same way a drug addict might focus on the things they find good about a particular drug.
But they don't pay any attention to the potential deleterious effects that drug might have, in the same way we are tempted to paper over the negative effect offloading our intellect wholly onto machines might have.
I have heard it said often that the mind is like a muscle that needs to be exercised regularly, otherwise, like muscles it will become flabby and soft.
I believe that is a real, significant, and serious danger.
When I saw the movie "Idiocracy", it was hilarious, but I wondered how it could come to pass (I know, it was just a comedy) that everyone was completely brainless. Was it this? 
Possibly.
I see that as one pathway. But this issue of offloading our human intellect to AI might carry us to the same end..
Well. I'm going back to my television now.
Leave me alone. Baitin'.
—
They also start with long, drawn out stories of how things are before telling you, here's the kicker, what you don't know, what's running quietly in the background...
They do also start a lot of statements with AND.
A lot of the YT bots mispronounce names or say the year by digit. I’d say it’s twenty twenty-six and the bot will say it’s two zero two six. Then many are just a handful of pictures, or file videos with a fruity narrating voice very short on facts.
That sentence made my head hurt.
And they tell you that the best part is last; and remind you numerous times to be sure and wait for the end. (Do they get ‘points’ for viewers who wait for the end, and how would YouTube know that?)
I appreciate the people who undermine the system by giving a summary in the comments.
On the other hand, there are some that are done very well. They may mispronounce a word now and then, but they do very well at compiling information and conveying it in an efficient and engaging way. I’ve recently streamed a lot of the better ones - most on bird behavior, and some from a series on Spinoza. they’re very good.
It does seem odd to me that the AI voice will often pronounce the same word incorrectly in one place but correctly in another...
Yes, and youtube can tell where you stop watching.
So can the guy who put up the video.
It allows them to see where you lost interest.
There is a guy who debunks a lot of urban myths and such. He tells the story and then says, "That is the story, but, is it accurate?" He says he can watch the viewership drop off a cliff at that point.
People are there for the story, not for reality.
AI can’t be subdued.
Every time the letter combination ‘ai’ appears, AI capitalizes it.
I have had AI “apologize” to me. Have not had any incidents with Grok, though.
Don’t really have time to play games with it.
But here is an AI incident I had last month. Pretty creepy.
I had a knee replacement in July, and some genius in the hospital system decided it would be a good idea for me to have a follow-up, 3 days later with my PCP.
I was able to get into the truck for my husband to drive me there, but, about a mile from home, I asked him to turn around. I just could not take the pain the bumps in the road were causing in my surgical leg.
As soon as I got home, I called my doctor’s practice to let them know I would not be there and why.
Instead of a human, I was communicating with a robot with an annoying female-sounding fry vocal voice. I would have been okay with this if the robot had just taken my information, but it went on with a voice filled with compassion to tell me how “sorry” it was that I was in pain.
Long story short: When it asked if I had any questions, I responded with something like, “Why are you talking in a fry-vocal voice?” I was pretty grumpy at this point.
It actually went on to explain that it had been programmed to present a pleasant-sounding voice. It’s not pleasing in a human, for pete’s sake! 😲 Then it told me that it could “spice up” the voice if I wanted. What!!?? I ended the call.
It’s too long and repetitive. It’s also vague at times. Sometimes the grammar is awful.
I sometimes read a post and check to see if you were the poster. Does that make me AI, too?
(Psssst...what chip you got?)
Ah, my other FRiend with a distinctive writing style!
It is “long-winded”, but...I am not changing at this late point in life!!!
And back at you!
And ... a good mushroom!
Hahahahaha...it is a source of family fun and pride!
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.