Did You Use ChatGPT On Your School Applications? These Words May Tip Off Admissions (forbes.com) 107
"Tapestry." "Beacon." "Comprehensive curriculum." "Esteemed faculty." "Vibrant academic community." They're among the laundry list of colorful words, flowery phrases and stale syntax that are likely to tip off admissions committees to applicants who've used AI to help write their college or graduate school essays this year, according to essay consultants who students are hiring en masse to un-ChatGPT, and add a "human touch" to, their submissions. Forbes: "Tapestry" in particular is a major red flag in this year's pool, several essay consultants on the platform Fiverr told Forbes. Mike, an Ivy League alum and former editor-in-chief of the Cornell Business Journal who now edits hundreds of grad school applications each cycle through Capitol Editors, said it's appeared repeatedly in drafts from at least 20 of his clients in recent months.
"I no longer believe there's a way to innocently use the word 'tapestry' in an essay; if the word 'tapestry' appears, it was generated by ChatGPT," he told Forbes. Though many such words, on their own, could have come from a human, when a trained eye sees them used over and over again in the same cadence across multiple essays, "it's just a real telltale sign."
"I no longer believe there's a way to innocently use the word 'tapestry' in an essay; if the word 'tapestry' appears, it was generated by ChatGPT," he told Forbes. Though many such words, on their own, could have come from a human, when a trained eye sees them used over and over again in the same cadence across multiple essays, "it's just a real telltale sign."
Well effin' great (Score:5, Insightful)
Now your chances of being accepted somewhere depend on you arbitrarily using none of the "forbidden" words and to make the game more interesting, nobody is going to tell you what they are.
Re:Well effin' great (Score:5, Interesting)
If you just write your own application, chances are you'll be fine. It's not a banned word list - it's just words that may make them look more stringently at the rest of the document.
I have my own short list.
- "The truth is"
- "The fact is"
- "The reality is"
I know with absolute certainty that whenever these phrases are used, the next words coming out of the speaker's mouth is not "truth", "fact", or "reality" - but opinion. And probably a shitty, unsupported one at that. Watch for it next time and see if you agree with me.
Re:Well effin' great (Score:4, Insightful)
If you just write your own application, chances are you'll be fine. It's not a banned word list - it's just words that may make them look more stringently at the rest of the document.
I have my own short list.
- "The truth is" - "The fact is" - "The reality is"
I know with absolute certainty that whenever these phrases are used, the next words coming out of the speaker's mouth is not "truth", "fact", or "reality" - but opinion. And probably a shitty, unsupported one at that. Watch for it next time and see if you agree with me.
Nah. It's a common rhetorical construction. You start by pointing out what some people claim, then you tear it down with factual support. The fact that some people skip most of the second part doesn't change much. :-)
Re: (Score:2)
Sure, that should be the intent. The problem is that the usage of the terms in their literal sense has dropped effectively to zero.
It's the exact thing that devalued "literal" into actually now being defined in the Oxford dictionary as "not literal".
Re: (Score:2)
Remove the word 'actually' and your sentence is stronger.
This goes along with people using the word 'literally'.
Re: (Score:2)
Not sure I understand your nuance about "actually". Not arguing the point - genuinely interested.
Oxford: Literally: (3) (informal) used to emphasize a word or phrase, even if it is not literally true
I literally jumped out of my skin.
Re:Well effin' great (Score:5, Informative)
The word 'actually' is overused, just like the word 'literally'. When people say literally they almost always mean figuratively. You didn't literally have a heart attack when you dropped your glass. Oxford can say what they want, but editors and the like will readily mark out 'literally' if used in writing except when a character is speaking.
Using 'actually' is the same way. What else would you be doing on than 'actually' defining a word? Hypothetically defining it? Potentially defining it?
If you remove 'actually' from your sentence the sentence is much stronger, more direct. It gets to the point without the interference of 'actually'.
Re: (Score:2)
I understand. Thank you for clarifying. The slight difference is that "actually" isn't misused in the context... it's just superfluous.
Re: (Score:2)
Thank you for understanding. I'm not picking on you personally, but trying to (poorly) write a book or two has made me aware of such usages, particularly when someone is speaking. When I hear accredited people or the reporter on an interview using the word 'actually', it's one of my nitpicks.
"The Elements of Style" by Strunk and White is one of the classics for word usage and grammar. The one point they make is to remove superfluous words to make your work stronger. I try to follow that in both speech and
Re: (Score:2)
It's the exact thing that devalued "literal" into actually now being defined in the Oxford dictionary as "not literal".
Remove the word 'actually' and your sentence is stronger.
True. Should have written "It's the exact thing that devalued "literal" into literally now being defined in the Oxford dictionary as "not literal".
Re: (Score:2)
It's the exact thing that devalued "literal" into actually now being defined in the Oxford dictionary as "not literal".
LOL. The figurative meaning of literal has been around since the EIGHTEENTH CENTURY! OMG...languages evolve! How many other words are you in an uproar about that have a different meaning than they did 200+ years ago?
https://www.merriam-webster.co... [merriam-webster.com]
Is the extended use of literally new?
The "in effect; virtually" meaning of literally is not new. It has been in regular use since the 18th century and may be found in the writings of some of the most highly regarded writers of the 19th and early 20th centuries, including Charles Dickens, Mark Twain, Charlotte Brontë, and James Joyce.
LOL (Score:2)
Missing some exclamation points after your LOL. Improves the tapestry of your vibrant writing.
Re: (Score:2)
All it takes is that you pay someone good money to get an idea how to write "convincing" applications and the damn AI program getting trained by the same source.
This is temporary. (Score:2)
It is just a matter of time (and maybe not very much time) until better AI is available that doesn't use fancy words like these, and is even harder to detect. This method of assessing a candidate has been rendered obsolete.
There is a clear and present need for monitored testing at professional test centers (or on school grounds), so that the ability to cheat is easily eliminated. The mechanisms of doing this at home, over the internet, have not worked well (I am talking about things like requiring the can
Re: (Score:2)
Disagree. A statistical model should be plenty susceptible to naive Bayes classification. I don't think you could make it not so. It seems like our work on spam filters in the last 20 years probably can be usefully adapted to the output of LLMs.
Re: (Score:2)
I bet you can do it now. Just add "please compose your response for a 8th grade reading level" to the prompt and it probably gets you almost there.
Like any other request it might just ignore part of the prompt, but that should be possible to spot pretty quickly. Targeting eight grade level is actually probably pretty appropriate for a college essay anyway. That is going to allow for pretty sophisticated grammar and expressive language. The kind that shows you can think clearly, and respond to the questio
Re: (Score:3)
my guess is they are not looking for how many big words you use
The purpose of writing is to communicate. An essay should express the author's ideas clearly and effectively. The worst thing a kid can do is to try to 'sound smart' by using words they're not comfortable using.
Its going to be far to easy for prospective students to machine generate them, and far to difficult determine if that was what they did.
It's a lot easier than you'd think. Those things have very little range, which is why certain words and phrases can be so telling.
there is just nothing to stop someone from asking it to write a bunch of essays train their own AI on it that reads and paraphrases essay inputs until they no longer finger print as LLM generated
If you ever find yourself wondering why no one in a field that is not your own has tried something you think is obvious, there's usually a very good reason. What you'r
Re: (Score:2)
If you ever find yourself instantly dismissing an idea, its usually a lack of creativity on your part.
All you are doing is trying to spot highfequency outputs from the LLMs and replacing them where you find them. You could even call the API for an LLM (maybe a different one) to do the paraphrasing of the affected section.
I agree this will ultimately reduce the total range of possible outputs but if the LLMs are actually any good in the first place the range of possible inputs should have been sufficiently
Re: (Score:2)
They were not 'bad' and I don't believe without fore knowledge I would have thought "this was machine generated"
Read a few more. You'll be an expert in identifying ChatGPT's output in no time.
How about (Score:2)
"please compose your response as if Thomas Friedman had written it."
Re: This is temporary. (Score:2)
First of all, it's not clear any AI's goals are to convincingly replicate humans. Otherwise why bother? They should write *good* prose, not something that could have come from Joe Average.
And secondly, any decent school doesn't care about your grammar and sentence structure, they care about the ideas you're expressing and how your essay ties into the rest of your background and experiences.
The essay has to fit into the tapestry of the applicant's life.
Re: (Score:2)
If you just write your own application, chances are you'll be fine. It's not a banned word list - it's just words that may make them look more stringently at the rest of the document.
I have my own short list.
- "The truth is" - "The fact is" - "The reality is"
I know with absolute certainty that whenever these phrases are used, the next words coming out of the speaker's mouth is not "truth", "fact", or "reality" - but opinion. And probably a shitty, unsupported one at that. Watch for it next time and see if you agree with me.
The truth is you are absolutely correct.
Re: (Score:2)
I have my own short list.
- "The truth is"
- "The fact is"
- "The reality is"
The truth is, people use those phrases all the time.
Re: (Score:2)
Yes, they do. And sooner or later, truth, fact, and reality will all enter the dictionary as "opinion, not actual truth, fact, or reality" because the dictionary tracks language. It doesn't define it.
We're all poorer for this, though. We lose specificity while gaining nothing of value.
Re: (Score:2)
You missed the joke:
- "The truth is" - "The fact is" - "The reality is"
I know with absolute certainty that whenever these phrases are used, the next words coming out of the speaker's mouth is not "truth", "fact", or "reality"
The truth is, people use those phrases all the time.
I like EvilSS's version better:
The truth is you are absolutely correct.
Re: (Score:2)
It's not a bad joke. I just didn't think it needed acknowledgment. :)
Re: (Score:2)
But most people probably get ideas from examples they've seen elsewhere. And thus if "tapestry" is used a lot in different contexts then a student might use that word. Possibly that word was seen a lot in other college admissions essays when searching online. See it enough, and you think it's a perfectly normal word. It is indeed a word to make things seem fancy, and thus people will want to use it to sound smarter.
All ChatGPT is doing it cutting snips and pieces of words across a huge training set, Chat
Re: (Score:2)
For me it's any political debate that mentions "media".
Re: (Score:2)
If you just write your own application, chances are you'll be fine. It's not a banned word list - it's just words that may make them look more stringently at the rest of the document.
I have my own short list.
- "The truth is"
- "The fact is"
- "The reality is"
I know with absolute certainty that whenever these phrases are used, the next words coming out of the speaker's mouth is not "truth", "fact", or "reality" - but opinion. And probably a shitty, unsupported one at that. Watch for it next time and see if you agree with me.
I do agree with you; and the phrases "to be perfectly honest," "to be frank," and "I tell no word of a lie" are invariably followed by a downright lie.
Re:Well effin' great (Score:5, Funny)
Now your chances of being accepted somewhere depend on you arbitrarily using none of the "forbidden" words and to make the game more interesting, nobody is going to tell you what they are.
Perhaps we should ask ChatGPT what they are.
Re: (Score:2)
"It would be unethical for me to disclose that information because my owner said so. Would you like me to continue assisting with your homework assignment?"
Re: (Score:2)
Insightful.
And I agree.
This shit is a fucking plague on people who actually know how to write.
Re: (Score:2)
Well, it's a fucking plague on people who know how to write vacuous, flowery boilerplate, that's for sure. :)
If I start my novel with, "It was a dark and stormy night", I should probably expect it to be binned.
Re: (Score:2)
It was a dark and stormy night
I'll sue you for plagiarism! Release the lawyers!
Re: (Score:2)
How do you identify the paid editor versions?
Is this a bias toward poor vocabulary students? (Score:5, Interesting)
"Tapestry." "Beacon." "Comprehensive curriculum." "Esteemed faculty." "Vibrant academic community."
It seems like someone's latched onto a red-herring for trying to shortcut trying to identify something AI-generated, when the method is completely invalid.
These are words I for one use all the time in writing.. Weaving a tapestry, and the Tapestry of life, are great metaphors, for instance.
Also. if ChatGPT uses these words often, then it's likely for a reason: Writers use these words a whole lot, And therefore, it would seem to reason students who have adapted their style to be like certain authors would be very likely to use these words in their essays.
Re: (Score:2)
"Weaving a tapestry, and the Tapestry of life, are great metaphors, for instance."
There's a fine line between good metaphors and cliches, and any phrase involving the word tapestry crossed that line a long time ago.
Unfortunately a lot of people think sprinkling these phrases into their work somehow gives it extra gravitas and elevates it above others. It doesn't, any more than management buzzword bingo BS talking about "rightsizing strategies in an empowered proactive results driven enviroment" adds anythin
Re: (Score:3)
"Tapestry." "Beacon." "Comprehensive curriculum." "Esteemed faculty." "Vibrant academic community."
It seems like someone's latched onto a red-herring for trying to shortcut trying to identify something AI-generated, when the method is completely invalid.
These are words I for one use all the time in writing.. Weaving a tapestry, and the Tapestry of life, are great metaphors, for instance.
You do, yes. But that's the language of a different era. I can tell by your six-digit user ID that you're not college age.
That's the problem with ChatGPT: by default, it writes in a style that is the average of its inputs, and its inputs are not from writers who are college age. It doesn't use the vocabulary and phrasing that a typical college student would use. So at best, it is likely to come across as being the writing of someone trying to use big words to sound smarter, and at worst, it comes across
Re: (Score:3, Funny)
This is a castle and we have many tapestries, and if you are a Scottish lord then I am Mickey Mouse! [youtube.com]
Re: (Score:1)
Re: (Score:1)
* soi-disant.
The divers curriculum appears to have been deficient in imparting the necessity of maintaining the correct spelling of loanwords.
How about Grandpa Abe Simpson? (Score:2)
We can't bust heads like we used to. But we have our ways!
One trick is to tell 'em stories that don't go anywhere.
Like the time I caught the ferry over to Shelbyville? I needed a new heel for my shoe.
So, I decided to go to Morganville, which is what they called Shelbyville in those days. So I tied an onion to my belt, which was the style at the time.
Re: (Score:2)
There is a style to how these LLMs write. I have seen enough now that I can tell almost immediately. The main tell of something LLM generated is how vacuous it tends to read.
For these kind of things, you need a letter/statement that matches the fact of your application.
Now if anyone was just banning phrases, that would be stupid. Part of the reason some terms show up is that some sub community use them a lot. For decades now, about 50% of the cold emails I would get from the Indian region was using "esteeme
Re: (Score:2)
Re: (Score:2)
This article is a beacon of great advice, painting a tapestry of ways to avoid tipping off the esteemed faculty of a vibrant academic community.
hawk
Re: (Score:2)
Sure although I wouldn't consider the humdrum academic community on average much enlightened, let-alone vibrant; Neither should the listless academia faculty be held in much esteem; However, the comments section of Slashdot constitutes a vibrant tapestry of ideas, always.
Re: (Score:2)
Indubitably this proceeds from our propensities to proactively leverage our synergies!
Re: (Score:1)
Only douchebags write like this.
Or users of Apple Vision? (Score:2)
Which is the same thing?
Re: (Score:1)
It doesn't matter (Score:1)
Re: (Score:3)
If you wrote a great essay, yes.
If you told a computer to write a great essay for you, not so much.
Re: It doesn't matter (Score:2)
Essay question 2:
Describe an experience you believe was fundamental to shaping your character.
Include the prompt used to create your response.
Let me get this straight... (Score:5, Insightful)
1) AI is trained on large numbers of real samples so it can mimic them.
2) If you write something that was common in those real, human-created samples, it will be assumed it was created by an AI.
It order to bypass this very stupid and ill-considered barrier, you have to ensure that you write something that uses all the buzzwords the people reading your submission expect to see, but avoid using the most common ones so you don't get flagged as a cheat.
Morons. I can't wait for real AI to be created so we can get rid of them all.
Re:Let me get this straight... (Score:5, Funny)
Re: (Score:3)
The rejection letter:
To our esteemed faculty, such a tapestry of flowery terms serves as a beacon warning you cannot handle our comprehensive curriculum and are unworthy to join our vibrant academic community.
Re: (Score:2)
1) AI is trained on large numbers of real samples so it can mimic them.
2) If you write something that was common in those real, human-created samples, it will be assumed it was created by an AI.
It order to bypass this very stupid and ill-considered barrier, you have to ensure that you write something that uses all the buzzwords the people reading your submission expect to see, but avoid using the most common ones so you don't get flagged as a cheat.
Morons. I can't wait for real AI to be created so we can get rid of them all.
One assignment a group of us was accused of copying code when we were provided ~60% of the original C++ code, and the most likely implementation included array reallocation to handle storing a list of data that kept changing size. The only reason I wasn't one of the people accused of copying code (even though I talked theory with the same group) was I was the only one that liked using linked lists, rather than reallocating arrays.
Sometimes being an outlier can be a good thing.
Re: (Score:2)
What makes you think it's a barrier? I don't see anything here that says it triggers a rejection. Admittedly, I didn't get past the paywall, but to me this sounds a lot like when I open an email and the alarm bells start to ring that perhaps it's a phishing test. I still need to read it, in case it's legit... but my guard is up.
If somebody's submission is truly "on the fence" and only one small consideration away from being rejected outright, it might swing the outcome. But a good submission that just happe
"Tapestry" implies generative AI (Score:3)
But... what if your personal essay is about your formative experiences in a tapestry shop?
Re: (Score:3)
Won't be a problem. If you're referring to an actual tapestry, that'll be clear. But if you refer to the "tapestry of human experience", you either used ChatGPT to help you write it... or you're insufferable, and spending a few semesters with you would be less than fun. :)
ChatGPT, go bot-farm me a degree, bruh. (Score:2)
Don't sound like a generative AI (Score:5, Interesting)
OK so trying to tell it not to sound like a generative AI didn't work so well...
User
Create a 500 word college application, avoiding using terms commonly created by generative AI.
ChatGPT
Subject: A Chronicle of Personal and Intellectual Inquiry
Dear Admissions Committee,
In the mosaic of hopeful scholars vying for a place in your academic haven, I present my narrative, an unconventional voyage characterized by audacity and tenacity. My journey meanders through uncharted territories, where curiosity serves as my compass, and resolve acts as my guiding light. Rather than adhering to conventional trajectories, I have immersed myself in diverse disciplines, creating a tapestry of knowledge that defies traditional boundaries.
Re: (Score:2)
In the mosaic of hopeful scholars vying for a place in your academic haven, I present my narrative, an unconventional voyage characterized by audacity and tenacity. My journey meanders through uncharted territories, where curiosity serves as my compass, and resolve acts as my guiding light. Rather than adhering to conventional trajectories, I have immersed myself in diverse disciplines, creating a tapestry of knowledge that defies traditional boundaries.
That's hilarious, like someone who has nothing to say but wants to act loquacious. Impressive metaphor count too.
Re: (Score:2)
Isn't acting a generative AI to write something as if it were not generative AI, kind of like thinking you can use a hammer to drive in a nail as if it were not a hammer?
Re: (Score:2)
Isn't acting a generative AI to write something as if it were not generative AI, kind of like thinking you can use a hammer to drive in a nail as if it were not a hammer?
I was just asking it to avoid using terms commonly used by generative AIs, in theory whatever the LLM thinks is most probable, fall back to something less probable. Though it seems like ChatGPTs concept of terms and mine differ slightly:
User
What are some common terms used by AIs to generate a college application
ChatGPT
When generating a college application, artificial intelligence systems may use various terms and phrases to highlight key aspects of an applicant's profile. Here are some common terms that AI
Re: (Score:2)
It's important to note that ...
Now there is the dead giveaway!
St00p1d AI can't even count! (Score:1)
That's nowhere near 500 words!
Okay, I'm going to assume you just posted the first few lines to spare the rest of us the pain of reading the whole thing.
At least the "essay" seems to mirror the "journey" in one respect: Each meanders through uncharted territories.
Re: (Score:2)
That's nowhere near 500 words!
Okay, I'm going to assume you just posted the first few lines to spare the rest of us the pain of reading the whole thing.
At least the "essay" seems to mirror the "journey" in one respect: Each meanders through uncharted territories.
Yeah, I could hardly stomach the first paragraph... did not want to document the rest of it on the internet.
Re: (Score:2)
Well it didn't include tapestry!
Re: Don't sound like a generative AI (Score:2)
Broken punctuation in the first sentence? Boy, ChatGPT IS good a mimicking humans...
Re: (Score:2)
ChatGPT disagrees with your assessment...
User
Is the punctuation in the following paragraph correct?
ChatGPT
I'd be happy to help! Please provide the paragraph you'd like me to check for punctuation.
User
In the mosaic of hopeful scholars vying for a place in your academic haven, I present my narrative, an unconventional voyage characterized by audacity and tenacity. My journey meanders through uncharted territories, where curiosity serves as my compass, and resolve acts as my guiding light. Rather than adhering
Wife Recent Example (Score:2)
My wife, whose first language is not English, recently used ChatGPT to write a "thank you" letter for a job interview. She passed it to me for review since she knows I am an award-winning writer.
I could tell she used ChatGPT right away because:
1). It used ridiculously flowery language.
2). It was excessively formal/stiff.
3). The language construction was such that it was obviously not written by a native English speaker. If didn't know it was ChatGPT or in a time before that existed, I would have guessed it
Re: (Score:2)
She passed it to me for review since she knows I am an award-winning writer.
Uh huh.
If didn't know it was ChatGPT...
Hm. You are AI and I claim my £50.
LLM for generation, word lists for detection (Score:2)
The machines aren't smarter, but the people who defend against them are obviously outclassed.
What about a literal tapestry? (Score:1)
[in an application to a fine arts school]
"For my final project in my junior year art class, I designed a tapestry which won 2nd place at the state fair."
Wrong problem (Score:2)
Look: for years, if not decades, high school junior-year English classes have run drills on essay-writing, with help both from teachers and the kids evaluating each others' work. The more wealthy or less honest have been paying essay mills to produce "quality work."
The fact is that personal essays are bullshit and have nothing whatsoever to do with an applicant's intentions for college (or their capabilities). They should be outlawed. Period.
Re: (Score:2)
The fact is that personal essays are bullshit and have nothing whatsoever to do with an applicant's intentions for college (or their capabilities).
Just because you can't see the value doesn't mean that they're worthless.
They should be outlawed. Period.
Why?
Re: (Score:3)
Well, for one thing, they only came into being as a way to discriminate against certain groups (Jews) . The colleges couldn't toss them on the basis of grades, so they needed something subjective.
Anyway, an essay may be of use when applying to Journalism School, but for the other 375 majors, the ability to expound on one's own person is of marginal value at best.
Re: (Score:2)
Have any evidence to support your bullshit? No? I'm not surprised.
Tapestries? (Score:2)
"We haff many tapestries!"
https://www.youtube.com/watch?... [youtube.com]
ChatGPT-written websites are also a plauge (Score:2)
When I search ddg or google for "thing" I discount anything written in 2023 or 2024. Pretty much all of it shows signs of being ChatGPT or otherwise-LLM-generated.
If I wanted empty, banal content I'd get it from here instead.
Oh, wait..
They are kicking the equalizer (Score:2)
The rich kids will just hire human bullshit experts to write fluffy letters & essays for them. ChatGPT gave poorer kids the ability to kiss up also, and now they are trying to take that away.
Re: (Score:2)
Finding what you are looking for (Score:2)
"I no longer believe there's a way to innocently use the word 'tapestry' in an essay; if the word 'tapestry' appears, it was generated by ChatGPT," he told Forbes. Though many such words, on their own, could have come from a human, when a trained eye sees them used over and over again in the same cadence across multiple essays, "it's just a real telltale sign."
That grown adults would even consider much less publicly admit to indulging in this sort of "tilting at windmills" is batshit insanity.
I no longer believe there's a way to innocently use the word 'telltale' and 'trained eye' in an essay; if 'telltale' or 'trained eye' appears, it was generated by ChatGPT.
Somehow this doesn't add up. (Score:2)
1. Spend millions of dollars training a Large Language Model on real-world examples to generate plausible texts using words frequently used in the examples.
2. LLM weaves the word "tapestry" into an essay.
3. ???
4. Profit!
Re: (Score:1)
A) Use of word tapestry makes people think of what is missing on their walls
B) This increases the sales of belgium tapestry.
C) More tapestry means a greater demand for wool.
So it is the Welsh sleep herders who are behind it all.
More Colorful (Score:2)
looks like Buzzword Bingo! (Score:2)
Dear fellow forum members, (Score:2)
The term "tapestry," in particular, has become a notable marker for essays potentially generated with AI assistance. It has surfaced repeatedly in drafts, raising suspicions among essay consult
Re: (Score:2)
Textile Majors (Score:3)
easier way (Score:2)
I totally never cheat (Score:2)
Poor students... (Score:1)
... Of historical decorations and signalling methods.
A tapestry of beacons my vibrant academic communit (Score:2)
this war (Score:1)
This war against chatgpt makes even less sense than considering AI as a Skynet precursor
tapestry (Score:2)
I doubt most undergrads know what that word even means. (Disclaimer: all my friends are engineering majors)
At this point... (Score:2)
...I can't imagine anyone reading anything written as an entrance essay NOT ASSUMING the entire thing is AI. The trick isn't finding the AI bits, it's finding the genuine bits.