• Newsletters
  • Account Activating this button will toggle the display of additional content Account Sign out

A.I. Could Be Great for College Essays

Every year, the artificial intelligence company OpenAI improves its text-writing bot, GPT. And every year, the internet responds with shrieks of woe about the impending end of human-penned prose. This cycle repeated last week when OpenAI launched ChatGPT —a version of GPT that can seemingly spit out any text, from a Mozart-styled piano piece to the history of London in the style of Dr. Seuss . The response on Twitter was unanimous: The college essay is doomed. Why slave over a paper when ChatGPT can write an original for you?

Chatting with ChatGPT is fun. (Go play with it !) But the college essay isn’t doomed, and A.I. like ChatGPT won’t replace flesh and blood writers. They may make writing easier, though.

GPT-3, released by OpenAI in 2020, is the third and best-known version of OpenAI’s Generative Pre-trained Transformer—a computer program known as a large language model. Large language models produce language in response to language—typically, text-based prompts (“Write me a sonnet about love”). Unlike traditional computer programs that execute a series of hard-coded commands, language models are trained by sifting through large datasets of text like Wikipedia. Through this training, they learn patterns in language that are then used to generate the most likely completions to questions or commands.

Language is rife with repetition. Our ability to recognize and remember regularities in speech and text allows us to do things like complete a friend’s sentence or solve a Wordle in three tries. If I asked you to finish the sentence, The ball rolled down the … you’d say hill, and so would GPT-3. Large language models are, like people, great at learning regularities in language, and they use this trick to generate human-like text. But when tested on their ability to understand the language they produce, they often look more like parrots than poets.

Gary Marcus, an emeritus professor at NYU and the author of Rebooting AI , is a vocal critic of the idea that bots like GPT-3 understand what they’re writing . In a recent preprint (an academic paper that hasn’t been peer-reviewed), Marcus and two co-authors used OpenAI’s DALL-E 2 to demonstrate the limitations of large language models. DALL-E 2 , like GPT-3, responds to text-based prompts. But instead of producing language, it creates images. DALL-E 2 was trained to learn associations between images and their captions to produce entirely new images based on the text users enter. If you ask it for, say, “an impressionist painting of Albert Einstein surfing” you get the four images below.

Not bad, right? DALL-E 2 was recently used to win an art competition .

But as Marcus and his co-authors point out in their paper , DALL-E 2 doesn’t understand the relationship between the words that users enter. If, for instance, you ask it to produce an image of “an old man talking to his parents,” you get four images of three people talking. The AI fails to understand that, however old the old man looks, the people he’s talking to must, by definition of being his parents, look older.

Compared with DALL-E 2, ChatGPT appears to have a better grasp of the text users enter and the responses it spits out. This might be why the Internet responded to its release so enthusiastically. ChatGPT “is causing jaws to drop and brows to furrow,” wrote Axios .

I had trouble stumping it with some classic riddles from cognitive psychology. Take the Lily Pad problem:

Prompt: A lily pad, in a pond, doubles in size every day. On the 20 th day, it covers the entire pond. On what day did it cover half the pond?

ChatGPT: A lily pad in a pond that doubles in size every day will cover half the pond on the 19 th day, one day before it covers the entire pond.

The A.I. got that the question described exponential growth—a phenomenon that, as the pandemic demonstrated, many humans fail to understand. But I did fool ChatGPT with the bat and ball problem made famous by Princeton psychologist Daniel Kahneman’s book, Thinking, Fast and Slow :

Prompt: A bat and ball cost $1.10. The bat costs $1 more than the ball. How much does the ball cost?

ChatGPT: If the bat costs $1 more than the ball, and the bat and ball cost $1.10 in total, then the ball must cost $1.10 - $1.00 = $0.10.

The correct answer is 5 cents. (Trust me.)

ChatGPT might fail at tests of reasoning, but it’s great at generating humanlike text to different lengths and in various styles. This brings us back to the college essay—an easy task for ChatGPT, many commentators claimed on Twitter. “We’re witnessing the death of the college essay in realtime,” tweeted one Google employee . Ethan Mollick, a management professor at the University of Pennsylvania, had ChatGPT write an essay question , create a grading rubric for said question, answer the question, and grade its own answer. (It got an A minus.) How could the essay not be doomed?

This isn’t the first time that large language models have been predicted to fell the essay or worse. “To spend ten minutes with Sudowrite [a GPT-3-based A.I.] is to recognize that the undergraduate essay, the basic pedagogical mode of all humanities, will soon be under severe pressure,” wrote journalist Stephen Marche in a 2021 New Yorker piece. (On Tuesday, Marche wrote an article for the Atlantic titled “ The College Essay Is Dead .”) And in 2019, when GPT-2 was created, OpenAI withheld it from the public because the “fear of malicious applications” was too high .

If any group were to put an A.I. to malicious use, essay-burdened undergraduates would surely be the first. But the evidence that A.I. is being used to complete university assignments is hard to find. (When I asked my class of 47 students recently about using A.I. for schoolwork, they looked at me like I was mad.) It could be a matter of time and access before A.I. is used more widely by students to cheat; ChatGPT is the first free text-writing bot from OpenAI (although it won’t be free forever). But it could also be that large language models are just not very good at answering the types of questions professors ask.

If you ask ChatGPT to write an essay contrasting socialism and capitalism, it produces what you expect: 28 grammatical sentences covering wealth distribution, poverty reduction, and employment stability under these two economic systems. But few professors ask students to write papers on broad questions like this. Broad questions lead to a rainbow of responses that are impossible to grade objectively. And the more you make the question like something a student might get—narrow, and focused on specific, course-related content—the worse ChatGPT performs.

I gave ChatGPT a question about the relationship between language and colour perception, that I ask my third-year psychology of language class, and it bombed . Not only did its response lack detail, but it attributed a paper I instructed it to describe to an entirely different study. Several more questions produced the same vague and error-riddled results. If one of my students handed in the text ChatGPT generated, they’d get an F.

Large language models generate the most likely responses based on the text they are fed during training, and, for now, that text doesn’t include the reading lists of thousands of college classes. They also prevaricate. The model’s calculation of the most probable text completion is not always the most correct response—or even a true response. When I asked Gary Marcus about the prospect of ChatGPT writing college essays his answer was blunt: “It’s basically a bullshit artist. And bullshitters rarely get As—they get Cs or worse.”

If these problems are fixed—and, based on how these models work, it’s unclear that they can be—I doubt A.I. like ChatGPT will produce good papers. Even humans who write papers for money struggle to do it well. In 2014, a department of the U.K. government published a study of history and English papers produced by online-essay writing services for senior high school students. Most of the papers received a grade of C or lower. Much like the work of ChatGPT, the papers were vague and error-filled. It’s hard to write a good essay when you lack detailed, course-specific knowledge of the content that led to the essay question.

ChatGPT may fail at writing a passable paper, but it’s a useful pedagogical tool that could help students write papers themselves. Ben Thompson, who runs the technology blog and newsletter Stratechery, wrote about this change in a post about ChatGPT and history homework. Thompson asked ChatGPT to complete his daughter’s assignment on the English philosopher Thomas Hobbes; the A.I. produced three error-riddled paragraphs. But, as Thompson points out, failures like this don’t mean that we should trash the tech. In the future, A.I. like ChatGPT can be used in the classroom to generate text that students then fact-check and edit. That is, these bots solve the problem of the blank page by providing a starting point for papers. I couldn’t agree more.

I frequently used ChatGPT while working on this piece. I asked for definitions that, after a fact-check, I included. At times, I threw entire paragraphs from this piece into ChatGPT to see if it produced prettier prose. Sometimes it did, and then I used that text. Why not? Like spell check, a thesaurus, and Wikipedia, ChatGPT made the task of writing a little easier. I hope my students use it.

Future Tense is a partnership of Slate , New America , and Arizona State University that examines emerging technologies, public policy, and society.

comscore beacon

  • Ethics & Leadership
  • Fact-Checking
  • Media Literacy
  • The Craig Newmark Center
  • Reporting & Editing
  • Ethics & Trust
  • Tech & Tools
  • Business & Work
  • Educators & Students
  • Training Catalog
  • Custom Teaching
  • For ACES Members
  • All Categories
  • Broadcast & Visual Journalism
  • Fact-Checking & Media Literacy
  • In-newsroom
  • Memphis, Tenn.
  • Minneapolis, Minn.
  • St. Petersburg, Fla.
  • Washington, D.C.
  • Poynter ACES Introductory Certificate in Editing
  • Poynter ACES Intermediate Certificate in Editing
  • Ethics & Trust Articles
  • Get Ethics Advice
  • Fact-Checking Articles
  • Teen Fact-Checking Network
  • International
  • Media Literacy Training
  • MediaWise Resources
  • Ambassadors
  • MediaWise in the News

Support responsible news and fact-based information today!

Is the college essay dead? AI apps write scripts, speeches and so much more

Plus, the house of representatives will vote on a new speaker today. how does that work.

the essay is dead

I want you to experience some artificial intelligence applications that I have been trying recently. You will see some jaw-dropping potential in these apps to disrupt, create and even cheat. Let’s start with ChatGPT, which, with just a little prompting, can write an essay or even a TV script. I asked it to create a Seinfeld scene in which George decides to become a journalist. In 10 seconds, the script appeared:

the essay is dead

(OpenAI.com)

The New York Times can’t seem to rave enough about ChatGPT saying, “ChatGPT is, quite simply, the best artificial intelligence chatbot ever released to the general public. It was built by OpenAI, the San Francisco A.I. company that is also responsible for tools like GPT-3 and  DALL-E 2 , the breakthrough image generator that came out this year.” In case you were wondering, GPT stand for “generative pre-trained transformer.”

I asked it how I could know if a racehorse would become a champion:

the essay is dead

I asked ChatGPT to write a sermon that a United Methodist minister might deliver about lotteries. I asked it to explain quantum physics at a fourth-grade level. After it gives a response, you can ask for another response, and it will compose a new answer. And, according to the Times, “It can  write jokes  (some of which are actually funny),  working computer code  and  college-level essays . It can also  guess at medical diagnoses ,  create text-based Harry Potter games  and  explain scientific concepts at multiple levels of difficulty .” 

Recently, an essay in The Atlantic suggested that artificial intelligence technology makes it easy for a program to produce a logical, conversational article or essay. One student who was caught using AI to produce an essay said it was not unlike using a spellcheck program.  

They don’t feel like they’re cheating, because the student guidelines at their university state only that you’re not allowed to get somebody else to do your work for you. GPT-3 isn’t “somebody else”—it’s a program. The world of generative AI is progressing furiously. Last week, OpenAI released an advanced chatbot named ChatGPT that has spawned a new wave of  marveling and hand-wringing , plus an  upgrade  to GPT-3 that allows for complex rhyming poetry; Google  previewed  new applications last month that will allow people to describe concepts in text and see them rendered as images; and the creative-AI firm Jasper received a  $1.5 billion valuation  in October. It still takes a little initiative for a kid to find a text generator, but not for long. Kevin Bryan, an associate professor at the University of Toronto,  tweeted  in astonishment about OpenAI’s new chatbot last week: “You can no longer give take-home exams/homework … Even on specific questions that involve combining knowledge across domains, the OpenAI chat is frankly better than the average MBA at this point. It is frankly amazing.” Neither the engineers building the linguistic tech nor the educators who will encounter the resulting language are prepared for the fallout.

Hyperwrite is another interesting program that includes templates.  Look at all of the options just under “marketing”

the essay is dead

(HyperWrite)

Hyperwrite allows the user to build documents step by step. I asked HyperWrite to explain World War 2 in language that a 5-year-old might understand. Here are three possibilities it offered:

the essay is dead

And I built a 322-word essay about the importance of submarines from World War II to today in 30 seconds. Here’s part of a finished essay:

the essay is dead

Here are some other places you can go to learn how AI is moving into journalism.

  • The future of content creation with AI is closer than you might think – Poynter 
  • A news photo editor’s nightmare is an art director’s dream – Poynter
  • These projects are using AI to fight misinformation – Poynter
  • How news organizations used automated news to cover COVID-19 – Poynter
  • What is the future of automated fact-checking?  – Poynter
  • Here’s how publishers around the world are using automated news – NiemanLab
  • “Look at the robot as your new colleague”: what automation can do for sports reporting – Journalism.co.uk
  • How a local paper in Argentina uses AI to publish hundreds of sports pieces a month – Reuters Institute for Journalism
  • Runway – an example of text for video editing. This is their latest trailer for 2023.

The battle over today’s vote for Speaker of the House

Let’s keep in mind that this has to do with one of the most powerful and important positions in U.S. government, and hours before the House of Representatives is to vote on who holds that position, the outcome is uncertain. House Republican Leader Kevin McCarthy (R-Calif.) has the backing of almost all his Republican colleagues, but 15 Republicans don’t back him and that is enough to send the leadership vote to a second round, which hasn’t happened in a century.

Since today’s vote will not be the formality it usually is, you should know the rules . PBS explained some of the details that you might not expect, including that the speaker does not have to be a member of Congress, and to be elected, the speaker does not have to get 218 of the 435 House votes (a majority.) The vote only requires a majority of those who are present and vote by name. 

All candidates for speaker must be nominated by members of the House, but they don’t need to be elected lawmakers of the House.  Article I, section II  of the Constitution says only that the House “shall choose their Speaker and other officers.” So far, the chamber has only chosen its own members as speaker, but a non-lawmaker is possible. Earlier this year, former Secretary of State Colin Powell received a vote for speaker, as did Senator Rand Paul of Kentucky. To be the next speaker, a person needs a majority of the votes from House members who are present and voting. (See this useful  Congressional Research Service (CRS) report  for more detail.) That means that while a majority is 218 votes in the House, a person could become speaker with fewer votes if several members do not attend the vote. That happened in 2021 when Rep. Nancy Pelosi, D-Calif., won with just 216 votes after three members voted “present.”

The House has been deadlocked 14 times before. The House historian traces the floor fights back to 1793 when it took three ballots to choose a Leader.

Most House Speaker floor battles happened before the Civil War. But for sheer drama, read about the House Speaker vote from 1917 , or the nine ballots required to elect Rep. Frederick Gillett  of Massachusetts to be speaker in 1923. 

CNN reminds us:

In 1855 and 1856, it took 133 separate votes for Rep. Nathaniel Banks of Massachusetts to be elected, again by a plurality and not a majority. The process stretched over more than a month and included a sort of inquisition on the House floor of the three contenders. They answered questions about their view of the expansion of slavery.  Read more from the House historian’s website . It’s also interesting to  read about Banks ; his official House biography notes he was elected to office as a Republican, an independent, a member of the America Party and as a Democrat.

The Congressional Institute explains the House meets today: 

  • Establish that there is a quorum. If a member in attendance declines to vote, they do not count toward the quorum.
  • The clerk calls for speaker candidate nominations.
  • Chairs of the Republican Conference and Democratic Caucus make short speeches on behalf of their parties’ nominees.
  • The clerk then asks for any other nominations. 
  • The clerk then appoints tellers to record the votes, and the voting begins. 
  • Each member-elect has the opportunity to vote when the clerk calls his or her name. Typically, the member-elect responds by calling out the last name of the person they wish to be speaker. They may also answer “present,” which does not count as a vote but does contribute to a quorum. Or they could decline to respond at all.

the essay is dead

Opinion | Inside the drama of NBC News hiring former RNC chair Ronna McDaniel

There was immediate external criticism and a downright mutiny from inside, including shocking on-air commentary from a prominent voice

the essay is dead

Your newsroom needs an AI ethics policy. Start here.

Until we create standards around artificial intelligence — even though it’s early in the game — we are holding back innovation

the essay is dead

What are ‘sex’ and ‘gender’? How these terms have changed and why states now want to define them

Although they’re sometimes used synonymously, ‘sex’ and ‘gender’ have different meanings to medical professionals.

the essay is dead

Opinion | First in Poynter: A new podcast looks into how Pulitzer Prize-winning stories are done

Across 6 episodes, ‘Pulitzer on the Road’ offers audiences insights into how these award-winning works are produced and what makes them prize-worthy

the essay is dead

No, a grainy image doesn’t show a Princess Kate stunt double

A Facebook post included what looked like a screengrab from a widely shared TMZ video, but the image has been altered.

Start your day informed and inspired.

Get the Poynter newsletter that's right for you.

  • Newsletters
  • Help Center
  • Legislature
  • A.M. ATL newsletter
  • The Monica Pearson Show
  • Trump Georgia case
  • AJC Peachtree Road Race
  • NCAA / NIT Scores

Opinion: The college essay is not dead

Georgia Gwinnett College associate professor Amanda Sepulveda teaches students in her English class.  PHOTO CREDIT: GEORGIA GWINNETT COLLEGE.

In a guest column today, Matthew Boedy , an associate professor of rhetoric and composition at the University of North Georgia , discusses the development of artificial intelligence programs that can spit out accurate and fluid essays in response to any prompt.

Boedy is responding to a column in the Atlantic by English teacher Daniel Herman who writes of the new OpenAI’s ChatGPT program that “may signal the end of writing assignments altogether — and maybe even the end of writing as a gatekeeper, a metric for intelligence, a teachable skill...But most jaw-dropping of all, on a personal level: It made quick work out of an assignment I’ve always considered absolutely ‘unhackable.’ ”

In another Atlantic essay on sophisticated generative AI, novelist and essayist Stephen Marche writes: “Practical matters are at stake: Humanities departments judge their undergraduate students on the basis of their essays. They give Ph.D.s on the basis of a dissertation’s composition. What happens when both processes can be significantly automated? Going by my experience as a former Shakespeare professor, I figure it will take 10 years for academia to face this new reality: two years for the students to figure out the tech, three more years for the professors to recognize that students are using the tech, and then five years for university administrators to decide what, if anything, to do about it.”

Here is Boedy’s take on whether AI programs endanger writing and writing instruction.

By Matthew Boedy

It’s that time of year when I read reflections by my students in my first year writing course. This course is part of a mandated two-semester program and is populated by many dual enrolled students.

By and large, they praise the class and my teaching. Though I suspect at times some are merely buttering me up for a better grade. But I also ask them to reflect on how my ways with reading and writing compares to their high school experiences.

Mathew Boedy

Credit: Peggy Cozart

icon to expand image

The overwhelming claim by these “cream of the crop” students about their high school experience is twofold. First, they are often assigned little to no writing beyond one to two pages. Second, the mechanical or formulaic teaching of writing they received often meant they learned nothing of consequence.

I can’t vouch for the complete veracity of those claims. But I bring this up because of two paired headlines racing across the parts of the internet recently where teachers like me meet: “The End of high school English” and its companion, “The College Essay Is Dead.”

On the website of the Atlantic, both muse about the impact of a new technology called ChatGPT which is an artificial intelligence software that can create essays that sound as good or better than the run-of-the-mill ones I read on a regular basis from students.

The basic claim of mortality here is that this software is the greatest plagiarism program of all time. And people like me still assigning essays will only get from this point on prose produced by a robotic output of what people in the AI business call language production algorithms. I won’t bore you with examples but basically not only can you ask the algorithm to write an essay on any topic but also in the style of any famous author. As if sounding like Hemingway gets you extra points.

Let me dispel any notion that the college essay is dead or that this new technology will end my career as a writing teacher.

Contrary to popular belief, we writing teachers believe more in the process of writing than the product. If we have done our jobs well and students have learned, reading that final draft during this time of year is often a formality. The process tells us the product will be amazing.

Writing is a process of learning not merely about a subject. It’s also a learning about how that subject can best be framed for an audience. It’s also a writer learning about themselves. What do they want to say? What do they want to sound like? What rhetorical tools best fit their own skill set?

Asking an algorithm to make you sound like Hemingway actually will raise the reddest of red flags for me for plagiarism because the paper doesn’t sound like a first-year student.

On that note, if we writing teachers are doing our job well, we are crafting assignments that simply can’t be plagiarized. That is, an essay for my assignments can’t be bought off the internet or created by an algorithm. For example, I ask students to write an essay about three to five pictures of their own choosing. Sure, students can and do select pictures from the internet. But many don’t, instead using pictures from their phone. And coming up with things to say thematically about those pictures can’t be done by an algorithm. Another assignment is a research essay where I give students two sources and they have to find two others. The plagiarism I find most now is students stealing from the examples I show from previous semesters or other students in the class when they post early drafts to a class discussion board.

But for the writing-to-learn process to work, students also have to do their jobs. They have to be willing to fail, to write badly, or simply admit they don’t know what to say. And that is extremely hard if indeed they have never been asked to fill a blank page with little to no guidance from the teacher. To think as they write, not already have thought and then write.

And yes, that initial failure does bring the temptation to cheat. But what I hear from students in these end-of-semester reflections is not the siren song of plagiarism but a fear of failure. Because many of these students have never failed.

And for the other students who all they have known is failure with writing, this process only reinforces that sense of dread.

The answer to that is not an algorithm but advice. It’s why I have conferences with my students roughly every two weeks.

This new technology may indeed be the end of high school English. A certain kind of high school English. And a certain kind of college essay.

But it isn’t the death of the kind of education you should expect from our state’s higher education institutions. It’s the opportunity to show why we need more faculty, not less. Why we need less students per class, not more.

The cost of college has exploded due to one sizable factor – the death of public support. Lawmakers think tuition is the burden students should pay to have skin in the game.

But we all as a collective have skin in this particular composition game because good writing is that key fundamental civic skill, one we so desperately need more of. And it must be and should only be taught by those who see it as learning, not keyboard strokes after learning.

Even the algorithm agrees. I asked ChatGPT “What is the best way to teach writing?” I don’t have space to share its whole answer. But it suggests “clear and detailed feedback,” helping “students develop their own writing process” through revision practice, and working to “encourage creativity and originality in students’ writing.”

Maybe though it is just telling me what I want to hear. Like some of my students.

About the Author

ajc.com

Maureen Downey has written editorials and opinion pieces about local, state and federal education policy since the 1990s.

Five first-year students from the University of Georgia were on a road trip to Savannah on Friday, March 15, 2024 when they rescued a family whose vehicle was submerged in a Burke County creek south of Augusta. The students, some still in wet clothes after the encounter, are (from left to right) Kaitlyn Iannace, Clarke Jones, Jane McArdle, Molly McCollum and Eleanor Cart. COURTESY BURKE COUNTY SHERIFF'S OFFICE

Credit: Contributed

Atlanta firefighters battle blaze at a Midtown McDonald's after its marquee went up in flames Monday morning.

Credit: John Spink / [email protected]

Christian Wise Smith talks to the media after filing paperwork to qualify as a candidate for Fulton County District Attorney at the Georgia State Capitol on Friday, March 8, 2024. (Natrice Miller/ Natrice.miller@ajc.com)

Credit: Natrice Miller/AJC

080522 Atlanta, Ga.: A one-bedroom apartment is shown with a few of the state capitol the Lofts at Centennial Yards Atlanta, Friday, August 5, 2022, in Atlanta. Centennial Yards is formerly known as the Norfolk Southern Railways office building dating back one-hundred years. (Jason Getz / Jason.Getz@ajc.com)

Credit: Jason Getz / [email protected]

Jeffrey Clark, then acting assistant U.S. attorney general, speaks at a news conference at the Justice Department in Washington, D.C., on Oct. 21, 2020. (Yuri Gripas/POOL/AFP/Getty Images/TNS)

Credit: TNS

Credit: Jason Getz/AJC

Macon's new Atrium Health Amphitheater, one of the largest amphitheaters in Georgia, is set to open Sunday on a tract adjacent to the Macon Mall. (Hyosub Shin / Hyosub.Shin@ajc.com)

Credit: HYOSUB SHIN / AJC

Brainstorm in Progress

  • Instructional Design
  • Finding OER
  • Visual Learning

AI and the Death of the College Essay

Robot arm writing with pen.

by Mirko Tobias Schaefer, CC BY 2.0

The Atlantic’s December issue has an essay “ The College Essay Is Dead: Nobody is prepared for how AI will transform academia ” by Stephen Marche that says that AI is going to make the college essay irrelevant. I say good riddance. I write this as a former English and Adult Basic Education Community College teacher. The formal essay has its uses but for why most of our students are going to school, it is an anachronistic barrier. Most are at college to get a credential for work, not to become academics. At the last college I taught at, I routinely replaced papers with group projects. I would tell the students (especially those who didn’t like group work) that your future employers are going to be more interested in how you work in a team and less interested in your ability to write a 10 page research paper. We use writing in my classes as another tool for thinking and expression, not as an end in itself. My classes were portfolio assessed. Students would have a concept map or outline, a discovery draft created in small groups, a draft for the tutor or tutoring center, and a final copy. We also used things like Pecha Kucha to present papers to the rest of the class. Coming from a Constructivist teaching background, many of my formative writing prompts begin “based on past knowledge and your personal experience, what approach would you take to solving the problem of…” You can’t download someone else’s experiences. Teaching should also be a process of relationship building, so you know your students and have some idea about their experiences.

By emphasizing writing as a product instead of a process, we only encourage the students to go to places like Course Hero or use AI tools to write. The goal of education is to meet the outcome of 5000 words right? Who cares how you get there? The fact that someone can give a chatbot a writing prompt and get an acceptable essay (in some cases) just means that teaching is really broken right now. We have commodified teaching and learning to such an extent that anything that can produce something can “get” a grade.

There may be some legitimate uses for these bots: translation, rewriting code; Bryan Alexander and Stephen Downes were talking on Mastodon about having it create lab reports. I think I have read some furniture assembly instructions that were not human generated.

There is the claim that AI can produce art. If your definition of art is the production of a picture, then I question your definition of art. If producing a picture is art then my Xerox machine is every bit as good as Leonardo Da Vinci.

If a student is turning to places like Course Hero or bots for homework, it means that they feel like they do not have ownership of their own education.

  • Get rid of grading. If you are not familiar with ungrading, check out “ So, you want to take the grades out of teaching? A beginner’s guide to ungrading ” by Susan Blum, and then take a deeper dive into the work of Jesse Stommel .
  • Emphasize process, not products. I use concept mapping and/or outlines with students depending on the students inclination. This should not just be about ferrying a student through drafts. It is an opportunity for the student to make connections with their peers, tutors, and their own knowledge and experience. The important thing is to help the student find their own process.
  • Mix papers with presentations, podcasts, or video. Once the student has a process for writing, for organizing and presenting their thoughts and research, let them explore other media: blogs, wikis, audio, video, presentations that are pure images.
  • Have the students create assignments in a collaborative process. Teach them to think and work together. Explore open pedagogical practices and courses like DS106 for alternative approaches to the traditional idea of curriculum.

The bot at Open.AI.com said it succinctly enough for a “C-“:

The use of Artificial Intelligence (AI) in the essay writing process has become increasingly popular in recent years. AI has been used to help students compose essays, from grammar and spell checking to providing more personalized feedback. AI has a number of advantages over traditional essay writing methods, including faster turnaround times and a more efficient process. But despite its advantages, AI will not end the essay writing process.

First, AI can only do so much. AI works best when it is given a specific set of instructions and data to work with. It is not capable of the same level of creativity and critical thinking that a human can bring to the essay writing process. AI can help to identify errors and provide suggestions for improvement, but it cannot provide the same level of insight and feedback as a person can. AI cannot replace the process of brainstorming, outlining and drafting that are essential for creating a successful essay.

Second, AI is not yet sophisticated enough to understand the nuances of language and writing style. AI is often used to check for grammar and spelling errors, but it is not able to understand the context of a sentence or the implications of certain words and phrases. A human can use their knowledge and experience to create a more effective essay, while AI is limited by its programming.

Knowledge is Power

It is important that we understand as much as we can about AI. Read and learn about this. Follow the stories. The real ethical issues come when we leave things like AI and learning analytics to “experts”: we risk losing the ability to make decisions about how and when AI should be used.

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Notify me of followup comments via e-mail

This site uses Akismet to reduce spam. Learn how your comment data is processed .

  • Search for:

The Ptolemaic Universe

Recent Posts

  • A Short Annotated Reading List for AI Ethics and Policy
  • Multi-Modality: Creating a Student Centric, Flexible Choice Instruction/Learning Model
  • AI: What is your policy?
  • Instructional Design Positions at Clover Park
  • AI: An “F” for Fake

Simon Says: Educate!

Listen to the TLC podcast!

Clover Park Technical College

Quote of the Moment…

Nodes in my network.

  • Bryan Alexander
  • Gardner Campbell
  • Mike Caulfield
  • Sahana Chattopadhyay
  • Dave Cormier
  • Robin DeRosa
  • Ignatia Inge deWaard
  • Stephen Downes
  • Cable Green
  • Rajiv Jhangiani
  • David Kernohan
  • Clint Lalonde
  • D'Arcy Norman
  • Howard Rheingold
  • Bonnie Stewart
  • Jill Walker-Rettenberg
  • Audrey Watters
  • + February (2)
  • + January (4)
  • + November (1)
  • + September (1)
  • + August (1)
  • + April (4)
  • + March (1)
  • + January (3)
  • + December (4)
  • + October (2)
  • + August (2)
  • + April (2)
  • + January (2)
  • + December (2)
  • + October (1)
  • + April (1)
  • + February (1)
  • + December (1)
  • + March (6)
  • + February (3)
  • + January (1)
  • + November (3)
  • + October (5)
  • + September (2)
  • + April (8)
  • + March (4)
  • + November (4)
  • + October (6)
  • + April (6)
  • + November (6)
  • + October (7)
  • + August (6)
  • + October (15)
  • + September (3)
  • + August (3)
  • + July (15)
  • + April (5)
  • + November (5)
  • + January (5)
  • + December (5)
  • + November (24)
  • + October (12)
  • + February (4)
  • + December (3)
  • + November (8)
  • + October (10)
  • + September (5)
  • + August (5)
  • + April (3)
  • + January (9)
  • + December (8)
  • + October (22)
  • + September (4)
  • + August (7)
  • + June (13)
  • + March (8)
  • + February (13)
  • + September (6)
  • + August (8)
  • + June (16)
  • + April (7)
  • + February (6)
  • + October (4)
  • Accessibility
  • collaboration
  • Community college
  • conceptmaps
  • connectivism
  • constructivism
  • instructionaldesign
  • Open education
  • Open Educational Resource
  • Open educational resources
  • Open education resources
  • Open source
  • Open textbook
  • Open textbooks
  • opentextbooks
  • Public domain
  • Social media
  • Social network
  • Time management

What Time is Ronald?

Gbc education consulting, creative commons.

Creative Commons Licence

DS106 for Life!

Talky Tina endorses this site!

The Countdown!

the essay is dead

Logo image

'The college essay is dead': Academics react to ChatGPT

Openai recently released chatgpt, an artificial intelligence robot that can write essays when given a prompt., some professors worry that ai will allow students to cheat without fear of being caught, while others see it as a useful advancement..

“The GPT models are a series of large language models that are trained to generate human-like text. The first version, GPT, was released in 2018 and was followed by several updated versions, including GPT-2 in 2019 and GPT-3 in 2020.”

“There is some concern among educators about the potential impacts of chatbots like ChatGPT on education. Some people are worried that chatbots could replace human educators or be used to automate certain teaching tasks, potentially leading to job losses.”

Interestingly, the first two paragraphs of this article were written by ChatGPT as I was experimenting with it before starting this article. The bot is free to use online and provided me with detailed answers to my questions within seconds. 

[RELATED: University writing instructors are no longer grading students’ writing]

ChatGPT has made quite a stir in academic circles. “The college essay is dead,” Stephen Marche states in an article for  The Atlantic . “Nobody is prepared for how AI will transform academia.”  

Others are more relaxed on the subject. “Math didn’t disappear when calculators came along,” said Arizona State University Professor Dan Gillmor to Campus Reform . “But the machines did probably change how much arithmetic students do.”

Gillmor teaches journalism and mass communication. 

[RELATED: University writing center prefers applicants have experience in anti-racism]

“It’s clear to me that schools will need to adapt in several ways, and will need the help of the AI industry. We need to be able to tell, as much as possible, whether someone’s writing is AI-assisted or not,” Gillmor continued. 

He added, “And, more usefully, we need to find other ways to ensure that students can communicate -- and learn – - no matter what tools they’re using.”

Follow the author on Twitter: @emily_fowler18 

Staff image

Emily Fowler '24

Emily is a junior at The Master's University. She previously received her associate's degree at Wabash Valley College. Emily was a Campus Reform intern in 2022. Along with writing, Emily enjoys art, music, and spending time with family and friends.

More articles like this

What you stand for is what defines you, will you join with us, select the principles you stand for, and sign your name below.

I stand for the federal funding to be pulled from colleges and universities when they silence conservative views or students.

clock This article was published more than  1 year ago

Opinion Here’s how teachers can foil ChatGPT: Handwritten essays

Markham Heid writes about health and science for Medium.

The era of deepfake authorship has arrived. Since the release in November of ChatGPT, the artificial-intelligence program has impressed, entertained and caused more than a little hand-wringing about its ability to produce coherent and credible pieces of writing.

Much of the worry has focused on ChatGPT’s potential for powering fake news. But commentators have also worried about the toll AI-aided plagiarism could take on education. Teachers might soon find it impossible to detect AI-generated text. “The College Essay Is Dead,” the Atlantic declared .

That’s unlikely. There are some obvious workarounds. For example, even laptop-equipped students wouldn’t benefit from ChatGPT if they were required to write essays in class without the aid of their phone or an internet connection.

But there’s another fix — one that might have been worth implementing even before the arrival of ChatGPT: Make students write out essays by hand. Apart from outflanking the latest AI, a return to handwritten essays could benefit students in meaningful ways.

For one thing, neuroscience research has revealed that, to the human brain, the act of handwriting is very different from punching letters on a keyboard. Handwriting requires precise motor skills — controlling the individual strokes and the pressure of the pen — that vary for each letter, and these stimulate greater activity in a broader group of brain regions when compared with typing. (Anyone who has ever helped a child learn to write will recognize how much concentration and practice it requires.)

These letter-specific motor skills, coupled with subtle differences in other sensory input, engage the brain in ways that researchers have linked to learning and memory improvements. And those added layers of stimulation might be beneficial even when a student is merely copying an AI-written essay by hand.

The Post's View: We asked ChatGPT hundreds of questions. Here's what we learned.

“Handwriting forces those areas responsible for memory and learning to communicate with each other, which helps form networks that can make it easier to recall or learn new information,” Audrey van der Meer , professor of neuropsychology at the Norwegian University of Science and Technology, told me.

Much of the research comparing the differing neurological effects of handwriting and typing has focused on children or younger students. But there’s evidence that, even for older students and adults, writing by hand is a more cognitively involved process. For example, some work has found that writing by hand leads to better processing of ideas, and that students produce more original work when they complete assignments in longhand. Meanwhile, research on foreign-language learners has found that handwriting is associated with improvements in some measures of accuracy and comprehension.

Especially when it comes to essay writing, producing something by hand is a fundamentally different task that writing it on a computer. When you’re writing by hand, you need to know where you’re going with a sentence — what you want it to say, and the structure it will take — before you begin. If you don’t, you’ll have to cross things out or start over. Typing on a computer requires far less forethought; you can dump out the contents of your brain and then hammer it into shape.

The dump-and-edit method isn’t necessarily an inferior way to produce quality writing. But in many ways, it is less challenging for the brain — and challenging the brain is central to education itself.

“Handwriting requires you to put a filter on what you’re producing in a way that typing doesn’t,” according to Karin H. James , a professor of psychological and brain sciences at Indiana University.

A return to handwritten essays wouldn’t be easy for students. Schools have largely surrendered to a screen-dominated world, and the Common Core curriculum standards don’t mandate cursive training for grades K-12. Most secondary school students, never mind college kids, aren’t accustomed to writing longhand.

It wouldn’t be easy on teachers either, who might have to reduce the length of assignments or allocate extra class time for completion. They’d also have the chore of reading sloppy text that wasn’t neatly turned out by a word processor. But some might find all that preferable to harboring the constant suspicion that they’re being outwitted by a bot.

Toward the end of the 19th century, health issues forced the German philosopher Friedrich Nietzsche to abandon his pen in favor of a typewriter, a new invention at the time. Some of his friends noticed a change in his writing style — a change that one scholar later described as a departure from “sustained argument and prolonged reflection” to a terser “telegram style.”

Nietzsche himself felt the change. “Our writing tools work on our thoughts,” he observed. Ensuring that today’s students have more than one writing tool at their disposal might pay off in ways experts are only beginning to grasp. ChatGPT and other AI-powered technologies will win only if we agree to play on their home turf.

  • Opinion | AI could help ending the dominance of the credentialed classes March 19, 2024 Opinion | AI could help ending the dominance of the credentialed classes March 19, 2024
  • Opinion | Let AI remake the whole U.S. government (oh, and save the country) March 6, 2024 Opinion | Let AI remake the whole U.S. government (oh, and save the country) March 6, 2024
  • Opinion | The government has a workforce crisis. One of its best-kept secrets can fix it. March 12, 2024 Opinion | The government has a workforce crisis. One of its best-kept secrets can fix it. March 12, 2024

the essay is dead

Steven D. Krause

Writer, Professor, and Everything Else

Steven D. Krause

AI Can Save Writing by Killing “The College Essay”

I finished reading and grading the last big project from my “Digital Writing” class this semester, an assignment that was about the emergence of openai.com’s artificial intelligence technologies GPT-3 and DALL-E. It was interesting and I’ll probably write more about it later, but the short version for now is my students and I have spent the last month or so noodling around with software and reading about both the potentials and dangers of rapidly improving AI, especially when it comes to writing.

So the timing of of Stephen Marche’s recently published commentary with the clickbaity title “The College Essay Is Dead” in The Atlantic could not be better– or worse? It’s not the first article I’ve read this semester along these lines, that GPT-3 is going to make cheating on college writing so easy that there simply will not be any point in assigning it anymore. Heck, it’s not even the only one in  The Atlantic this week! Daniel Herman’s “The End of High-School English” takes a similar tact. In both cases, they claim, GPT-3 will make the “essay assignment” irrelevant.

That’s nonsense, though it might not be nonsense in the not so distant future. Eventually, whatever comes after GPT-3 and ChatGPT might really mean teachers can’t get away with only assigning writing. But I think we’ve got a ways to go before that happens.

Both Marche and Herman (and just about every other mainstream media article I’ve read about AI) make it sound like GPT-3, DALL-E, and similar AIs are as easy as working the computer on the Starship Enterprise: ask the software for an essay about some topic (Marche’s essay begins with a paragraph about “learning styles” written by GPT-3), and boom! you’ve got a finished and complete essay, just like asking the replicator for Earl Grey tea (hot). That’s just not true.

In my brief and amateurish experience, using GPT-3 and DALL-E is all about entering a carefully worded prompt. Figuring out how to come up with a good prompt involved trial and error, and I thought it took a surprising amount of time. In that sense, I found the process of experimenting with prompts similar to the kind of  invention/pre-writing activities  I teach to my students and that I use in my own writing practices all the time.  None of my prompts produced more than about two paragraphs of useful text at a time, and that was the case for my students as well. Instead, what my students and I both ended up doing was entering in several different prompts based on the output we were hoping to generate. And my students and I still had to edit the different pieces together, write transitions between AI generated chunks of texts, and so forth.

In their essays, some students reflected on the usefulness of GPT-3 as a brainstorming tool.  These students saw the AI as a sort of “collaborator” or “coach,” and some wrote about how GPT-3 made suggestions they hadn’t thought of themselves. In that sense, GPT-3 stood in for the feedback students might get from peer review, a visit to the writing center, or just talking with others about ideas. Other students did not think GPT-3 was useful, writing that while they thought the technology was interesting and fun, it was far more work to try to get it to “help” with writing an essay than it was for the student to just write the thing themselves.

These reactions square with the results in more academic/less clickbaity articles about GPT-3. This is especially true about  Paul Fyfe’s “How to cheat on your final paper: Assigning AI for student writing.” The assignment I gave my students was very similar to what Fyfe did and wrote about– that is, we both asked students to write (“cheat”) with AI (GPT-2 in the case of Fyfe’s article) and then reflect on the experience. And if you are a writing teacher reading this because you are curious about experimenting with this technology, go and read Fyfe’s article right away.

Oh yeah, one of the other major limitations of GPT-3’s usefulness as an academic writing/cheating tool: it cannot do even basic “research.” If you ask GPT-3 to write something that incorporates research and evidence, it either doesn’t comply or it completely makes stuff up, citing articles that do not exist. Let me share a long quote from a recent article at The Verge by James Vincent on this:

This is one of several  well-known failings of AI text generation models, otherwise known as large language models or LLMs. These systems are trained by analyzing patterns in huge reams of text scraped from the web. They look for statistical regularities in this data and use these to predict what words should come next in any given sentence. This means, though, that they lack hard-coded rules for how certain systems in the world operate, leading to their propensity to generate “fluent bullshit.”

I think this limitation (along with the limitation that GPT-3 and ChatGPT are not capable of searching the internet) makes using GPT-3 as a plagiarism tool in any kind of research writing class kind of a deal-breaker. It certainly would not get students far in most sections of freshman comp where they’re expected to quote from other sources.

Anyway, the point I’m trying to make here (and this is something that I think most people who teach writing regularly take as a given) is that there is a big difference between assigning students to write a “college essay” and teaching students how to write essays or any other genre. Perhaps when Marche was still teaching Shakespeare (before he was a novelist/cultural commentator, Marche earned a PhD specializing in early English drama), he assigned his students to write an essay about one of Shakespeare’s plays. Perhaps he gave his students some basic requirements about the number of words and some other mechanics, but that was about it. This is what I mean by only assigning writing: there’s no discussion of audience or purpose, there are no opportunities for peer review or drafts, there is no discussion of revision.

Teaching writing is a process. It starts by making writing assignments that are specific and that require an investment in things like prewriting and a series of assignments and activities that are “scaffolding” for a larger writing assignment. And ideally, teaching writing includes things like peer reviews and other interventions in the drafting process, and there is at least an acknowledgment that revision is a part of writing.

Most poorly designed assigned writing tasks are good examples of prompts that you enter into GPT-3. The results are definitely impressive, but I don’t think it’s quite useful enough to produce work a would-be cheater can pass off as their own. For example, I asked ChatGPT (twice) to “write a 1000 word college essay about the theme of insanity in Hamlet” and it came up with this and this essay. ChatGPT produced some impressive results, sure, but besides the fact that both of these essays are significantly shorter than 1000 word requirement, they both kind of read like… well, like a robot wrote them. I think that most instructors who received this essay from a student– particularly in an introductory class– would suspect that the student cheated. When I asked ChatGPT to write a well researched essay about the theme of insanity in  Hamlet, it managed to produce an essay that quoted from the play , but not any research about  Hamlet.

Interestingly, I do think ChatGPT has some potential for helping students revise. I’m not going to share the example here (because it was based on actual student writing), but I asked ChatGPT to “revise the following paragraph so it is grammatically correct” and I then added a particularly pronounced example of “basic” (developmental, grammatically incorrect, etc.) writing. The results didn’t improve the ideas in the writing and it changed only a few words. But it did transform the paragraph into a series of grammatically correct (albeit not terribly interesting) sentences.

In any event, if I were a student intent on cheating on this hypothetical assignment, I think I’d just do a Google search for papers on  Hamlet instead . And that’s one of the other things Marche and these other commentators have left out: if a student wants to complete a badly designed “college essay” assignment by cheating, there are much much  better and easier ways to do that right now.

Marche does eventually move on from “the college essay is dead” argument by the end of his commentary, and he discusses how GPT-3 and similar natural language processing technologies will have a lot of value to humanities scholars. Academics studying Shakespeare now have a reason to talk to computer science-types to figure out how to make use of this technology to analyze the playwright’s origins and early plays. Academics studying computer science and other fields connected to AI will now have a reason to maybe talk with the English-types as to how well their tools actually can write. As Marche says at the end, “Before that space for collaboration can exist, both sides will have to take the most difficult leaps for highly educated people: Understand that they need the other side, and admit their basic ignorance.”

Plus I have to acknowledge that I have only spent so much time experimenting with my openai.com account because I still only have the free version. That was enough access for my students and me to noodle around enough to complete a short essay composed with the assistance of GPT-3 and to generate an accompanying image with GPT-3. But that was about it. Had I signed up for openai.com’s “pay as you go” payment plan, I might learn more about how to work this thing, and maybe I would have figured out better prompts for that Hamlet assignment. Besides all that, this technology is getting better alarmingly fast. We all know whatever comes after ChatGPT is going to be even more impressive.

But we’re not there yet. And when it is actually as good as Marche fears it might be, and if that makes teachers rethink how they might teach rather than assign writing, that would be a very good thing.

Share this:

2 thoughts on “ai can save writing by killing “the college essay””.

  • Pingback: More from ChatGPT – Preterition
  • Pingback: ChatGPT for Writing Teachers: A Primer – Preterition

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Notify me of follow-up comments by email.

Notify me of new posts by email.

This site uses Akismet to reduce spam. Learn how your comment data is processed .

The American Scholar Logo

Words, Words, Words

What does the advent of ChatGPT mean for already beleaguered teachers?

By Robert Zaretsky | January 12, 2023

Alan Levine (Flickr/cogdog)

Have you heard the one about the two English professors who walk into a bar while lamenting their professional demise thanks to ChatGPT? They order a couple of beers, and the bartender says, “Why so glum, my friends? ChatGPT is just a tool. Don’t let it define you.”

No? Well, neither had I—until I asked ChatGPT to fill in the blank after “and the bartender says.” For the heck of it, I also asked the program to generate the answer as a koan. It’s hardly a knee-slapper, granted, but no worse than my own lame effort: “What’ll it be, gents? / Wait, no need to tell me / I’ll ask ChatGPT.”

The joke, it seemed, was on me.

But no one in the academy is laughing.

ChatGPT, released in November, is a chatbot powered by artificial intelligence that, according to its creators, “interacts in a conversational way” and can “admit its mistakes, challenge incorrect premises, and reject inappropriate requests.” The implications of this, particularly for the education field, are huge. So much so that several contributors to The Atlantic foresee in this latest spawn of Silicon Valley, the future of teaching. The reason is simply that ChatGPT works all too well.

In one essay , high school teacher (and former professor) Daniel Herman declares that with the advent of ChatGPT, his life “and the lives of thousands of other teachers and professors, tutors and administrators is about to drastically change.” In another , Stephen Marche, also a former professor, offers a timeline for the coming apocalypse: “Two years for students to figure out the tech, three more years for professors to recognize that students are using the tech, and then five more years for university administrators to figure out what, if anything, to do about it.”

Marche and Herman believe that they did the right thing by getting out of the humanities profession. But is the situation so dire for those of us who are still in it?

Not necessarily, according to Zeynep Tufekci. In her New York Times column , she observes that this is hardly the first time that the world has been upended by seismic changes in the transmission of knowledge. More than two millennia ago, Plato fretted over the shift from oral to written culture. Referring to what she calls Plato’s “Dialogues,” Tufekci cites the myth of Thamus, the Egyptian god who warned that writing, shunting aside memory, would breed “forgetfulness.” More ominously Tufekci continues, Plato believed this would allow anyone—even fools and knaves—to pretend they are someone “omniscient and wise.” But rather than, like Plato, lament these “supplanted skills,” as Plato did, Tufekci concludes, we should look for ways to create with these new technologies.

As I stare as my laptop, which rests on a table littered with student exams and papers, a coffee mug, my iPhone, and scattered books, including an old copy of the Phaedrus , I wonder if either of these camps has got it right. The subtitle to Marche’s essay is: “The College Essay is Dead.” Perhaps because Marche no longer teaches, he does not realize that the obit is a bit late: the college essay died years ago. During my three decades of teaching at a public university, I have encountered a dwindling number of students who can write a declarative sentence, much less a clear thesis. Perhaps more important, they have no desire to learn how.

The essay is dead, yes, but it is not yet buried. Instead, it has become the lifeless star of “Weekend with Bernie in the Groves of Academe,” a corpse that students and teachers have an equal interest in pretending is still alive. It’s a mug’s game in which a student sends me an electronic file that, when open, spills out a jumble of words that the sender propounds to be a finished paper. A week later, I send back the file, which, when open, spills out a cascade of red markings underscoring that the student’s words amounted to, well, a jumble. In determining grades, I try to find the elusive mean between the papers that my students wrote and the ones they thought they had written.

To paraphrase Dr. Who, memory is a wibbly-wobbly thing. But I do not think I am being overly nostalgic when I remember how students wrote when I first began teaching in the 1980s. Bad writers abounded back then, too. The difference was that writing—or, for that matter, reading—was a familiar, not a foreign, activity. Writing was as much a part of my students’ world as it was of mine—so essential a part that they most often took up my standing offer to comment on drafts.

Today, that offer still stands, but it stands mostly alone. The current generation of students has moved on from writing. Literally. Most students fail to see the relevance of writing in a world—their world—that is largely post-literate. They are at home in media not yet born when I began teaching, media that privilege images and sounds over written text. This does not spell the end of the world, but it does spell “tbh, dwbi.”

“Don’t worry ’bout it” is part of the appeal to Tufekci’s position. Just as we adapted to earlier leaps in communications technology, she writes, we can do so with artificial intelligence and language models. By flipping the classroom—the practice where students listen to recorded lectures at home and draft their essays in class—teachers can remain relevant.

Lol. Given the sheer irrelevance of writing in their world, one defined by mumblecore and memes, texting and TikTok, students will mostly flip the finger at such solutions.

Tufecki perhaps unwittingly points to a different approach. When she refers to the “Dialogues” of Plato, she means a specific dialogue, the Phaedrus . Yet the passage she quotes, the myth of Thamus, comes at the dialogue’s end and cannot be understood without knowing the rest of the text. Socrates and his sole interlocutor, Phaedrus, begin by agreeing to discuss what kind of speech—scripted or spontaneous—is truer to knowledge of ourselves and our world. Walking outside the city, with its streets channeling traffic, and into the countryside, where one is free to roam, the two interlocutors take turns trading claims and counterclaims. Just as their steps wander, so too do their words.

The spontaneous nature of this stroll mirrors Plato’s fundamental point about language: the superiority of an unscripted conversation to written words, which Plato calls “images.” As the interlocutors, who chose to join each other in this philosophical activity, pursue this dialectical back and forth, they stumble across—though do not always welcome—new perspectives on old matters. These shifts, Plato believed, cannot happen when one reads a written text. How could it be otherwise? Unlike a teacher or student, a book can no more protect itself against misinterpretation, the Platonic scholar Thomas Szlezak has observed, than it can choose its readers.

There is an irony too obvious for Tufekci to note: Plato writes to warn us against writing. Compounding the irony is that Plato writes so well. Szlezak might well be right when he asserts that Plato “never thought of entrusting his entire philosophy to writing.” But although he and countless other commentators debate such matters, Plato’s written words remain wordless. No matter how brilliantly Plato re-creates the artlessness of dialogue, his written words remain only that, re-creations—pale images of a free-flowing conversation between two people who, in the moment, were able to react to each other’s comments and further explain themselves.

What if ChatGPT spells not the end of the academy, but instead a revival—a return to its beginnings? The late Pierre Hadot, whose work revolutionized our understanding of the ancient Greek and Hellenistic schools of philosophy, contended that their goals were wholly unlike our own. Students enrolled in these schools, including Plato’s Academy, to be formed, not simply informed, by their teachings. Rather than studying in order to exchange their degrees for jobs, these students studied to change their lives.

According to Hadot, the Academy was not the ancient equivalent of a moot court, a place where students were taught effective debating techniques. They were taught, instead, to engage in dialogues, or dialectics. Ultimately, such dialogues—which cannot be scripted—are an exercise in humility, even a kind of wisdom, for they teach students (and teachers) “to put themselves in one another’s place and thereby transcend their own point of view.” In short, they entail “spiritual exercises which demanded that the interlocutors undergo an askesis , or self-transformation.”

Of course, the crisis facing the academy, apparently heralded by the invention of language models, will not be saved by trying to scale up this ancient approach. But while we debate the place of writing at the academy, it might help to recall that writing did not have much of a place at all in the original academies. Like most everything else, ChatGPT might prove to be little more than a footnote to Plato.

Permission required for reprinting, reproducing, or other uses.

Robert Zaretsky  teaches in the Honors College at the University of Houston. He is the author most recently of Victories Never Last: Reading and Caregiving in a Time of Plague.

Comments powered by Disqus

Smarty Pants Podcast

The College Essay Is Dead - Nobody is prepared for how AI will transform academia (The Atlantic, Dec 6, 2022)

Summary: The impact of the recent and sudden improvements in AI text-generation systems, driven by large language models, will challenge and transform the humanities, interactions between disciplines, and higher education more generally.

Thanks to Jaya Kannan, Director of Technology for Curriculum and Research, for the pointer.

Related Topics

Language Arts

Is the five-paragraph essay dead, by tina nazerian     oct 18, 2017.

Is the Five-Paragraph Essay Dead?

Sashatigar/Shutterstock

This article is part of the guide: Putting It Into Words: The Future of Writing Instruction.

Dennis Allen doesn’t think the five-paragraph essay is dead.

In the years before his retirement in May from West Virginia University, the Professor Emeritus did not assign “strict” five-paragraph essays. He contends that the five-paragraph essay may be dead in the literal sense because instructors of college composition classes don’t assign it, but he believes its structure is still around.

“I think a dissertation chapter is just a substantially more elaborate version of this,” Allen, who taught at West Virginia University for 35 years, explains. “In other words, the first five pages are the introduction with a thesis near the end, and you have two to five points, and it just expands out.”

The five-paragraph essay is a topic long debated by educators, and strong opinions abound. Ray Salazar called the five-paragraph essay an “outdated writing tradition” that “must end” in a 2012 post for his blog White Rhino . And in a 2016 blog post for the National Council of Teachers of English , Sacramento State associate professor Kim Zarins used the five-paragraph essay structure to show why she’s against teaching it. She called herself a high school “survivor of this form.” Despite its “long tradition, the five-paragraph essay is fatally flawed,” she wrote. “It cheapens a student’s thesis, essay flow and structure, and voice.”

A year later, her stance hasn’t budged.

“When I see five-paragraph essays come into the stack of papers, they invariably have this structural problem where the ceiling is so low, they don’t have time to develop a real thesis and a truly satisfying or convincing argument,” she says.

Five-paragraph essays are not the majority of what Zarins sees, but she points out that she teaches medieval literature, not composition. Regardless, she thinks high school teachers should steer clear of this approach, and instead encourage “students to give their essays the right shape for the thought that each student has.”

Kristy Olin teaches English to seniors at Robert E. Lee High School in Baytown, Texas. She says sometimes educators have structures that don’t allow for ideas, content or development to be flexible, and instead of focusing on what’s actually being said, they become more about “the formula.”

“It seems very archaic, and in some ways it doesn’t really exemplify a natural flow,” Olin says about the five-paragraph essay. “It doesn’t exemplify how we talk, how we write or how most essays you read are actually structured.”

Consider paragraphs. They should be about one subject and then naturally shift when that subject changes, Olin explains. But because the five-paragraph essay structure dictates that there be three body paragraphs, students might try to “push everything” to those body paragraphs.

Olin does think, however, that the five-paragraph essay format is useful for elementary students, adding that fourth grade is when the state of Texas starts assessing students’ writing in standardized tests. But once students get into sixth, seventh and eighth grade, teachers need to break away from that five-paragraph essay format and say “‘this is where we started, and this is where we need to head.’”

Hogan Hayes, who teaches first year composition at Sacramento State, is the second author of an upcoming book chapter about the “myth” that the five-paragraph essay will help students in the future.” There’s a perception that if students get good at the five-paragraph essay format, they’ll hone those skills and will be good writers in other classes and writing situations, he says. But there’s “overwhelming evidence to suggest that’s not the case.”

He doesn’t think that first first year composition teachers should be spending time “hating the five-paragraph essay.” Instead, they should recognize it as knowledge students are bringing with them to the classroom, and then “reconfigure it to new contexts” and use it ways that are more college-appropriate.

Hayes says college writing instructors need to get students to understand that the reason their K-12 teachers kept assigning five-paragraph essays was because they were working with “100, 120, 150 students,” and a standardized writing assignment “that works the same way every time” is easier to read, assess and grade. In regards to students who leave K-12 with a “strong ability to write the five-paragraph essay,” he says, ““I don’t want to snap them out of it because I don’t want to dismiss that knowledge.”

Take McKenzie Spehar, a Writing and Rhetoric Studies major at the University of Utah. She says she learned the five-paragraph essay early on, and except in an AP English class she took in the 12th grade, the structure was pushed heavily on her at school. She can’t say she’s ever written a five-paragraph essay for college. Her papers have all needed to be longer, though she does note that they do tend to stick to a five-paragraph type format—an introduction, a body and a conclusion.

“In general, the consensus is you need more space than a five-paragraph essay gives you,” she says, adding that it’s a good place to start when learning how to write academically. She explains that later on, however, students need a looser structure that flows more with the way they’re thinking, especially if they go into the humanities.

Kimberly Campbell, an Associate Professor and Chair of Teacher Education at the Lewis & Clark Graduate School of Education and Counseling, is strongly opposed to the five-paragraph essay structure. She thinks it stifles creativity and “takes away the thinking process that is key for good writing.” And she says she’s not the only one worried that the structure doesn’t help students develop their writing. In Beyond the Five-Paragraph Essay , a book she wrote with Kristi Latimer (who teaches English Language Arts at Tigard High School in Oregon), Campbell cites research studies that critique the approach of teaching the five-paragraph essay.

“Studies show that students who learn this formula do not develop the thinking skills needed to develop their own organizational choices as writers,” she says. “In fact, it is often used with students who have been labeled as struggling. Rather than supporting these students, or younger students, it does the opposite.”

For his part, Hayes thinks the five-paragraph essay makes it easy to not be creative, not that it necessarily stifles creativity. He believes creative students can work their imagination into any structure.

Allen, the retired English professor, stresses that even if writing isn’t argumentative, it always needs some structure. It can’t be simply uncontrolled, because the reader’s not going to get the point if it’s all over the map.”

Rita Platt is currently a teacher librarian with classes fromPre-K to fourth grade at St. Croix Falls Elementary School in St. Croix Falls, Wisconsin. She still stands by a piece she wrote in 2014; in it she said she was “being really brave” by stating she believes in teaching elementary school students “the good old fashioned” five-paragraph essay format.

She thinks the five-paragraph essay format has room for creativity, such as through word choice, topic and progression of thought. Kids can use the five-paragraph essay model to organize their thoughts, she says, and once they’re really comfortable, they can play around with it.

“Kids need something to start with,” says Platt, who has 22 years of teaching experience across different grade levels.

Campbell’s recommendation, which she says research backs, is to focus on reading good essay examples and give students in-class support while they write. She wants students to read a variety of essays, and pay close attention to structure. The students can then develop ideas in a writing workshop. As they develop their content, they consider how to structure those ideas.

“Students can explore a variety of organizational structures to determine what best supports the message of their essay,” Campbell says.

Platt tells EdSurge that she thinks there’s a movement in writing that says to “just let kids write from the heart.” But that means the kids who aren’t natural writers are left “in the dust.” What’s more, this approach doesn’t honor the constraints of teachers’ jobs, such as how much time they have to teach. And not all teachers love writing or write themselves, she says. Many elementary school teachers, she claims, never write, and not everyone has the skills of, say, Lucy Calkins or Nancy Atwell.

Campbell’s not a fan of asking kids to “‘just write from the heart.’” She wants kids to write about topics they care about, but at the same time, recognizes that instructors do need to teach writing. She says her mentor text method described above “is a lot of work,” but it was effective when she taught middle school and high school.

“In my work with graduate students who are learning to be English Language Arts teachers, I am also seeing this approach work,” she explains. She adds that her method would be easier if class sizes were smaller and teachers weren’t trying to “meet the needs of 150-200 students in a year.”

Most people aren’t going to become professional writers, Platt continues, noting that she’s not saying most people couldn’t, or that schools shouldn’t encourage people to think that way. She says there’s a sense of elitism in education that she gets a little tired of, along with some teacher bashing that makes her feel like she has to defend her colleagues who aren’t themselves natural writers yet are tasked with teaching kids to be “serviceable writers.”

“It bothers me in education—particularly in my field, language arts—where everybody says, ‘everybody should love reading and writing,’” she says. “Well, you know, you hope everybody loves reading and writing. You model that passion, you share that passion with your students but truth be told, our job is to make sure everybody reads and writes very well.”

Putting It Into Words: The Future of Writing Instruction

Facebook and Fake News: Esther Wojcicki On Teaching Digital Journalism in High School

EdSurge Podcast

Facebook and fake news: esther wojcicki on teaching digital journalism in high school, by jenny abamu.

​Engineers, Recruiters and Professors Weigh In: Future Programmers Need Writing Skills, Too

21st Century Skills

​engineers, recruiters and professors weigh in: future programmers need writing skills, too, by sydney johnson.

Not Just for Reading Class Anymore: 5 Tips for Teaching Literacy Across Multiple Subjects

Not Just for Reading Class Anymore: 5 Tips for Teaching Literacy Across Multiple Subjects

By mary jo madda.

Three Principles of Writing Instruction in a Personalized Learning Classroom

Three Principles of Writing Instruction in a Personalized Learning Classroom

By amanda zeligs hand, more from edsurge.

Unlocking the Power of Creativity and AI: Preparing Students for the Future Workforce

Unlocking the Power of Creativity and AI: Preparing Students for the Future Workforce

By abbie misha.

How Is the ‘College Is a Scam’ Narrative Influencing Who Chooses to Go to Campus?

How Is the ‘College Is a Scam’ Narrative Influencing Who Chooses to Go to Campus?

By jeffrey r. young.

To Make Assignments More Meaningful, I’m Giving Students a More Authentic Audience

To Make Assignments More Meaningful, I’m Giving Students a More Authentic Audience

By jonathan lancaster.

Why Old Arguments for Earning a Diploma Don't Resonate With My Students — and Which Ones Will

Why Old Arguments for Earning a Diploma Don't Resonate With My Students — and Which Ones Will

By katie wills evans.

Journalism that ignites your curiosity about education.

EdSurge is an editorially independent project of and

  • Product Index
  • Write for us
  • Advertising

FOLLOW EDSURGE

© 2024 All Rights Reserved

After a writer expressed sympathy for Israelis in an essay, all hell broke loose at a literary journal

Two women sit next to a small pole holding an Israeli flag and a portrait of a young woman, among rows of such poles.

  • Show more sharing options
  • Copy Link URL Copied!

What are the limits of empathy in war?

That’s the question that Joanna Chen, a liberal writer and translator who is Jewish and lives in Israel, probed in an essay about her struggles since Oct. 7 to connect with Palestinians.

“It is not easy to tread the line of empathy, to feel passion for both sides,” she wrote in the literary journal Guernica , explaining that she briefly stopped her volunteer work driving Palestinian children to Israeli hospitals for lifesaving medical care.

“How could I continue after Hamas had massacred and kidnapped so many civilians,” she asked, noting that the dead included a fellow volunteer, a longtime peace activist named Vivian Silver. “And I admit, I was afraid for my own life.”

Children stand amid blasted-out walls and piles of rubble

The essay, titled “From the Edges of a Broken World,” provoked an uproar in the activist literary world. Over the weekend, more than a dozen of the publication’s staff resigned in protest — and Guernica removed the essay from its website.

“Guernica regrets having published this piece, and has retracted it,” the magazine said in a statement . “A more fulsome explanation will follow.”

Among those who quit was the co-publisher, Madhuri Sastry, who wrote on X that the essay was “a hand-wringing apologia for Zionism and the ongoing genocide in Palestine.”

Sastry also called for the resignation of the editor in chief, Jina Moore Ngarambe, a veteran foreign correspondent. Ngarambe did not respond to requests for comment.

In a statement to The Times on Tuesday, Chen said: “Removing any stories and silencing any voices is the opposite of progress and the opposite of literature.”

“Today, people are afraid to listen to voices that do not perfectly mirror their own,” she said. “But ignorance begets hatred. My essay is an opening to a dialogue that I hope will emerge when the shouting dies down.”

The retraction of the essay comes as a new generation of activists in the literary world frames the conflict in the Middle East as a black-and-white battle between two sides — oppressor and oppressed — and pressures institutions to boycott Israeli or Zionist writers.

Palestinian supporters demonstrate during a protest at Columbia University, Thursday, Oct. 12, 2023, in New York. Hamas militants launched an unprecedented surprise attack Saturday killing hundreds of Israeli civilians, and kidnapping others. The Israeli military is responding by attacking the Hamas-ruled Gaza Strip with airstrikes. (AP Photo/Yuki Iwamura)

World & Nation

U.S. college campuses have embraced the Palestinian cause like never before. The story began decades ago

The Palestinian cause — and hostility toward Israel — has shifted from the sidelines of student activism to a robust political movement at U.S. colleges.

Dec. 7, 2023

In January, protesters from Writers Against the War on Gaza disrupted a PEN America event in Los Angeles featuring actor Mayim Bialik, who supports Israel and opposes a cease-fire. Last month, the Jewish Book Council, a nonprofit that promotes Jewish writers and stories, launched an initiative for authors, publishers, agents and others to report antisemitic incidents in the world of publishing — from “getting review-bombed because their book includes Jewish content” to “threats of intimidation and violence.”

For many activists, giving voice to opposing points of view or conveying empathy for Israeli victims of Hamas amounts to both-sidesism that glosses over power imbalances. Israel says that Hamas killed about 1,200 people on Oct. 7, prompting an invasion that authorities in Gaza say has killed more than 31,000 people.

On X, Guernica’s former fiction editor, Ishita Marwah, slammed Chen’s essay as a “rank piece of genocide apologia” and condemned Guernica as “a pillar of eugenicist white colonialism masquerading as goodness.”

Grace Loh Prasad, a Taiwanese-born writer based in the Bay Area who published an excerpt of her new memoir in Guernica last week, wrote : “I am alarmed & upset that my writing has appeared alongside an essay that attempts to convey empathy for a colonizing, genocidal power.”

Hua Xi, Guernica’s former interviews editor, singled out a passage in which Chen describes a neighbor telling her she tried to calm her children who were frightened by the sound of military planes flying over their house: I tell them these are good booms.

Chen writes: “ She grimaced, and I understood the subtext, that the Israeli army was bombing Gaza.”

For Xi, quoting an Israeli calling bombs “good booms” undermines Guernica’s “premise that they are holding space for Palestinian writers.”

Rather than just disagree, these activists are calling for the silencing of voices they view as harmful.

On social media, an activist accused Chen of “both-sidesing genocide.” Another condemned Chen, who was born in Britain and moved to Israel with her parents when she was 16, as “a settler who has settler genocidal friends and raised settler genocidal children.”

LOS ANGELES, CA - OCTOBER 28, 2023: Demonstrators wave Palestinian flags from atop a car to protest the death toll inflicted on the Palestinians during the Israel-Hamas war in Gaza near City Hall on October 28, 2023 in Los Angeles, California.(Gina Ferazzi / Los Angeles Times)

‘This is not a pro-Hamas protest’: Palestinian Americans fight charges of antisemitism

The Palestinian cause has never had so much support. But some Palestinian Americans say the movement has a messaging problem.

Dec. 21, 2023

Established in 2004 amid the U.S. invasion of Iraq, Guernica was founded as an unabashedly antiwar, anti-imperialist publication, according to one of its founders, Josh Jones.

The journal took its name from a Lower East Side bar where two of the founders participated in a reading series, and Picasso’s iconic painting depicting the horror of the 1937 bombing of the Basque town in northern Spain.

Guernica’s leaders did not always agree on what it meant to be antiwar — particularly as a growing wave of pro-Palestinian activists called for not platforming pro-Israeli voices.

Sastry wrote on X that over the last few months she urged Guernica’s leaders to “commit to cultural boycotts” organized by pro-Palestinian activists. They disagreed, she wrote, telling staff in an email that “Guernica’s political projects can be found in what we publish.”

For the record:

8:23 a.m. March 13, 2024 An earlier version of this article said Madhuri Sastry flagged concerns about a Joanna Chen story published in Guernica’s “Voices on Palestine” compilation. The story was published but not included in the collection.

But Sastry did not always like what the magazine published. Even before this week, she said, she raised concerns about a previous story by Chen that was being considered for the magazine’s “Voices on Palestine” compilation. It was ultimately excluded.

At the same time, Guernica’s editors received complaints that their magazine lacked a complexity of voices and was too pro-Palestinian.

People cram together holding pots and other containers

Emily Fox Kaplan, an essayist and journalist who is Jewish and has written for Guernica since 2020, wrote on X that “the only mistake Guernica made was not publishing a wide variety of voices” on the Israel-Palestinian issue “from day one.”

“The problem, when it really comes down to it, is that it presents an Israeli as human,” Kaplan wrote of Chen’s essay. “The people who are losing their minds about this want to believe that there are no civilians in Israel. They want a simple good guys/bad guys binary, and this creates cognitive dissonance.”

Other writers accused activists who attacked Chen’s essay of “bareknuckled antisemitism” and Guernica of “ taking its cue from Joe McCarthy and MAGA book burners .”

“God forbid someone might think Israelis are complex human beings, and not just demons,” said Lahav Harkov, a senior political correspondent at Jewish Insider.

Cambridge, MA - January 29: Kojo Acheampong, a Harvard student and member of AFRO (African and African American Resistance Organization), speaks to Pro-Palestine supporters in the lobby of Cambridge City Hall before their scheduled meeting. Because of the planned protest the City Council opted to have their meeting virtually. (Photo by Matthew J. Lee/The Boston Globe via Getty Images)

The antisemitic cartoon roiling Harvard? It’s not the first time it caused a firestorm

Activists set out to highlight the links between Black and Palestinian liberation. They dredged up a historic dispute over an antisemitic cartoon.

Feb. 23, 2024

Chen said in her statement to The Times that she did not realize the essay was sparking more than usual criticism until Saturday evening when a friend texted to alert her that one of the Guernica editors had resigned. She reached out to the editor in chief that evening and they spoke briefly Sunday morning.

“Since then, nothing,” she said.

“Guernica claims to be ‘a home for singular voices, incisive ideas, and critical questions’ but apparently there is no longer space in this home for a real conversation,” Chen said. “But I do not regard this as a missed opportunity: my words are being read and the door is still, in fact, open.”

Her essay, which is available on the Internet archive , Wayback Machine, offers a personal account of living in Israel before and after Oct. 7.

She wrote that she struggled to assimilate when she moved to Israel. Two years later, at 18, she chose not to serve in the Israel Defense Forces. Besides her volunteer work with Road to Recovery, which provides transportation for Palestinian children to hospitals, she describes donating blood to the people of Gaza. She also translated and edited the poems of Palestinian poets, believing their voices were “just as important” as the voices she translated from Hebrew.

After Oct. 7, Chen wrote, “I listened to interviews with survivors; I watched videos of atrocities committed by Hamas in southern Israel and reports about the rising number of innocent civilians killed in a devastated Gaza.”

She described holding a space in her mind for the victims in both Israel and Gaza: “At night, I lay in bed on my back in the dark, listening to rain against the window. I wondered if the Israeli hostages underground, the children and women, had any way of knowing the weather had turned cold, and I thought of the people of Gaza, the children and women, huddled inside tents supplied by the UN or looking for shelter.”

When a fellow volunteer expressed anger that Palestinians she had helped did not reach out after Oct. 7, Chen did not take sides.

“The Palestinians in the West Bank were struggling with their own problems: closure, the inability to work, the threat of widescale arrests being made by the Israeli army, and harassment by settlers,” she wrote. “No one was safe.”

Two weeks after Oct. 7, Chen writes, she resumed volunteering for Road to Recovery, ignoring her family’s fears for her safety, and drove a Palestinian boy and his father to an Israeli hospital. When they exited her car and the child’s father thanked her, she wrote, she wanted to tell him: “ No, thank you for trusting me with your child. Thank you for reminding me that we can still find empathy and love in this broken world.”

For activists who object to the very existence of Israel, Chen’s liberal framing — and refusal to take a stance — is inherently problematic: They say that the focus on finding empathy and love in a broken world ultimately justifies the status quo.

In her critique of the essay, April Zhu, former senior editor for interviews, wrote the essay starts “from a place that ostensibly acknowledges the ‘shared humanity’ of Palestinians and Israelis, yet fails or refuses to trace the shape of power — in this case, a violent, imperialist, colonial power — that makes the systematic and historic dehumanization of Palestinians ... a non-issue.”

Some argued that Chen’s liberal perspective was more problematic than any conservative voice.

“I find open warmongering less nauseating than this sort of self-pitying faux-bleeding heart claptrap,” wrote an independent filmmaker from L.A. “The fascist propagandist is at least honest. The liberal propagandist never shuts up about how tormented they are by the terrible *complexity* of it all. Get over yourself.”

More to Read

Palestinians search for survivors after an Israeli airstrike on a residential building In Rafah, Gaza Strip, Saturday, Feb. 10, 2024. (AP Photo/Hatem Ali)

Letters to the Editor: ‘War is hell’ is an awful excuse to keep killing Palestinians

Feb. 29, 2024

FILE - Harvard President Claudine Gay, left, speaks as University of Pennsylvania President Liz Magill listens during a hearing of the House Committee on Education on Capitol Hill, Tuesday, Dec. 5, 2023 in Washington. Gay will remain leader of the prestigious Ivy League school following her comments last week at a congressional hearing on antisemitism, the university's highest governing body announced Tuesday, Dec. 12. (AP Photo/Mark Schiefelbein, File)

Opinion: How the fight against antisemitism is now used to promote an ‘anti-woke’ agenda

Jan. 24, 2024

Palestinians carry a wounded girl after being rescued from under the rubble of buildings that were destroyed by Israeli airstrikes in Jabaliya refugee camp, northern Gaza Strip, Wednesday, Nov. 1, 2023. In just 25 days of war, more than 3,600 Palestinian children have been killed in Gaza, according to Gaza's Hamas-run Health Ministry. The advocacy group Save The Children says more children were killed in Gaza in October 2023 than in all conflict zones around the world combined in 2022. (AP Photo/Abed Khaled)

Israel’s media mostly keep Gaza’s human toll out of sight

Start your day right

Sign up for Essential California for news, features and recommendations from the L.A. Times and beyond in your inbox six days a week.

You may occasionally receive promotional content from the Los Angeles Times.

the essay is dead

Jenny Jarvie is a national correspondent for the Los Angeles Times based in Atlanta.

More From the Los Angeles Times

Palestinians inspect the damage of residential buildings after an Israeli airstrike in Rafah, southern Gaza Strip, Sunday, March 24, 2024. (AP Photo/Fatima Shbair)

U.N. demands cease-fire in Gaza, its first demand to halt fighting

FILE - Former President Donald Trump holds up a copy of a story featuring New York Attorney General Letitia James while speaking during a news conference, Jan. 11, 2024, in New York. Trump could find out Monday, March 25, how New York state aims to collect over $457 million he owes in his civil business fraud case, even as he appeals the verdict that led to the gargantuan debt. (AP Photo/Mary Altaffer, File)

Court agrees to hold off collection of Trump’s $454-million fraud judgment if he puts up $175 million

BURIN, OCCUPIED WEST BANK -- MARCH 5, 2024: Salam Najjar bids farewell to her son Amro Najjar, 10, during a funeral in Burin, Occupied West Bank , Tuesday, March 5, 2024. According to his father, Mohammad Najjar, Israeli forces opened fire on their vehicle after they encountered the Israeli military incursion into the Palestinian village and one of the bullets hit Amro directly in the head, killing him. Since the Hamas attack on Oct. 7th and IsraelOs full-scale military offensive in the Gaza Strip, 106 Palestinian children have been killed in the occupied West Bank according to the Defense for Children International Palestine (DCIP). (MARCUS YAM / LOS ANGELES TIMES)

At a boy’s funeral, a Palestinian village gathers to bid farewell

March 25, 2024

Former President Donald Trump speaks during a visit to an unfinished section of border wall with Texas Gov. Greg Abbott, in Pharr, Texas, Wednesday, June 30, 2021. (AP Photo/Eric Gay)

Column: Trump wants to round up over a million undocumented migrants from California. Here’s how he might do it

More From Forbes

Prompt engineering embraces new essay-compression technique that expands on getting very constructive generative ai results.

  • Share to Facebook
  • Share to Twitter
  • Share to Linkedin

Handy new prompt engineering technique to do compression on essays and other text is examined and ... [+] showcased as being quite useful.

In today’s column, I am continuing my ongoing coverage of prompt engineering strategies and tactics that aid in getting the most out of using generative AI apps such as ChatGPT, GPT-4, Bard, Gemini, Claude, etc. The focus here is on a brand-new prompting approach that enables you to cleverly compress essays and other text-based narratives. This is a handy technique that ought to be in your prompting best-practices toolkit.

For my in-depth comprehensive guide on over thirty other keystone prompting strategies, see the link here .

Here’s the essence of today’s discussion.

One of the most popular uses of generative AI entails creating summaries of entered text, see my prior coverage on prompting strategies for summarization at the link here and also the chain-of-density technique (CoD) at the link here . The deal is this. You might have a lengthy document that needs a helpful summary covering the crucial points so that you don’t have to wade through a convoluted textual morass. The simplest prompt to achieve a summary will merely tell the AI to go ahead and summarize the material. Boom, you are done, or so it seems.

The problem is that the summary might not be very good. Odds are that the generative AI might omit points that a human would have realized are vital to include in a summary. There is also a significant chance that the source material will be interpreted rather than carried straight ahead into the summary. Loosey-goosey interpretations of what was said in the source could be way off base.

Into this realm comes the act of compression.

Rather than producing a summary that might veer from the source, you can ask to do a compression. The idea of compression is that the source is reduced in size by a thinning process, but no adaptations or rephrasing takes place. You are still seeing the same words that were in the source. A thinning process is undertaken to try and keep just the needed meat on the bones conveying the crux of the source material.

Google Suddenly Reveals Surprise Android Update That Beats iPhone

Ukraine has developed 15 kinds of long range strike drone and has sortied them against russia s oil industry, the walking dead the ones who live episode 5 review another massively disappointing episode.

To clarify, compression is not a silver bullet. Issues about compression can arise. For example, it is conceivable that as generative AI thins out a source text, some key points might inadvertently get weaned out. Another possible issue is that the resulting compressed text might seem nearly unreadable or incomprehensible. The words removed that might have seemed inconsequential by the AI were possibly integral to the intelligible reading of the text.

The bottom line is that anyone proficient in the use of generative AI should know both techniques by heart, freely welding the best ways to do prompting that encompasses summarization and astute prompting that does compression. You can then wisely decide which approach befits a given circumstance. Sometimes you pull out the hammer of summarization, and other times you reach for the screwdriver of compression. They are two distinct tools that require suitable handling and must be selected for the appropriate situations.

A frequent question I get during the prompt engineering classes that I teach is whether summarization is better than compression, or whether compression is better than summarization. This always brings a smile to my face. The conveyed conundrum is a false choice. None is especially better than the other in the abstract. Each provides a set of benefits and drawbacks. I don’t think you can in the abstract make a solid case that a hammer is better than or worse than a screwdriver since the situation at hand dictates as such. The same goes for summarization versus compression.

Okay, now that we’ve got that foundation established, there are already various recommended ways to word a prompt to do summarizations and compressions. A recent research study explored the topic and proffered a prompt for compression that they extensively tested and found to be quite useful. I will walk you through their research efforts and results.

I opted to try out the compression prompt by doing some of my own testing as a mini-experiment using ChatGPT and GPT-4. This allows you to see the compression prompting in action. I will discuss the matter and aim to arm you with how to suitably use the clever technique.

Before we get into the specifics of this new compression technique, it would be useful to make sure we are all on the same page about the nature and importance of prompt engineering.

Let’s do that.

The Nature And Importance Of Prompt Engineering

Please be aware that composing well-devised prompts is essential to getting robust results from generative AI and large language models (LLMs). It is highly recommended that anyone avidly using generative AI should learn about and regularly practice the fine art and science of devising sound prompts. I purposefully note that prompting is both art and science. Some people are wanton in their prompting, which is not going to get you productive responses. You want to be systematic leverage the science of prompting, and include a suitable dash of artistry, combining to get you the most desirable results.

My golden rule about generative AI is this:

  • The use of generative AI can altogether succeed or fail based on the prompt that you enter.

If you provide a prompt that is poorly composed, the odds are that the generative AI will wander all over the map and you won’t get anything demonstrative related to your inquiry. Similarly, if you put distracting words into your prompt, the odds are that the generative AI will pursue an unintended line of consideration. For example, if you include words that suggest levity, there is a solid chance that the generative AI will seemingly go into a humorous mode and no longer emit serious answers to your questions.

Be direct, be obvious, and avoid distractive wording.

Being copiously specific should also be cautiously employed. You see, being painstakingly specific can be off-putting due to giving too much information. Amidst all the details, there is a chance that the generative AI will either get lost in the weeds or will strike upon a particular word or phrase that causes a wild leap into some tangential realm. I am not saying that you should never use detailed prompts. That’s silly. I am saying that you should use detailed prompts in sensible ways, such as telling the generative AI that you are going to include copious details and forewarn the AI accordingly.

You need to compose your prompts in relatively straightforward language and be abundantly clear about what you are asking or what you are telling the generative AI to do.

A wide variety of cheat sheets and training courses for suitable ways to compose and utilize prompts has been rapidly entering the marketplace to try and help people leverage generative AI soundly. In addition, add-ons to generative AI have been devised to aid you when trying to come up with prudent prompts, see my coverage at the link here .

AI Ethics and AI Law also stridently enter into the prompt engineering domain. For example, whatever prompt you opt to compose can directly or inadvertently elicit or foster the potential of generative AI to produce essays and interactions that imbue untoward biases, errors, falsehoods, glitches, and even so-called AI hallucinations (I do not favor the catchphrase of AI hallucinations, though it has admittedly tremendous stickiness in the media; here’s my take on AI hallucinations at the link here ).

There is also a marked chance that we will ultimately see lawmakers come to the fore on these matters, possibly devising and putting in place new laws or regulations to try and scope and curtail misuses of generative AI. Regarding prompt engineering, there are likely going to be heated debates over putting boundaries around the kinds of prompts you can use. This might include requiring AI makers to filter and prevent certain presumed inappropriate or unsuitable prompts, a cringe-worthy issue for some that borders on free speech considerations. For my ongoing coverage of these types of AI Ethics and AI Law issues, see the link here and the link here , just to name a few.

All in all, be mindful of how you compose your prompts.

By being careful and thoughtful you will hopefully minimize the possibility of wasting your time and effort. There is also the matter of cost. If you are paying to use a generative AI app, the usage is sometimes based on how much computational activity is required to fulfill your prompt request or instruction. Thus, entering prompts that are off-target could cause the generative AI to take excessive computational resources to respond. You end up paying for stuff that either took longer than required or that doesn’t satisfy your request and you are stuck for the bill anyway.

I like to say at my speaking engagements that prompts and dealing with generative AI is like a box of chocolates. You never know exactly what you are going to get when you enter prompts. The generative AI is devised with a probabilistic and statistical underpinning which pretty much guarantees that the output produced will vary each time. In the parlance of the AI field, we say that generative AI is considered non-deterministic.

My point is that, unlike other apps or systems that you might use, you cannot fully predict what will come out of generative AI when inputting a particular prompt. You must remain flexible. You must always be on your toes. Do not fall into the mental laziness of assuming that the generative AI output will always be correct or apt to your query. It won’t be.

Write that down on a handy snip of paper and tape it onto your laptop or desktop screen.

Using Special Prompts Including Chain-of-Density

There is a slew of somewhat remarkable prompt phrases that are essential for anyone seriously doing prompt engineering. One such phrase involves telling generative AI to work on a stepwise basis, something commonly known as invoking chain-of-thought responses by the AI, see my coverage at the link here . Another popular ploy entails telling the AI to take a deep breath, see my analysis of this prompt at the link here . One of the latest favorites involves commanding the AI to take on a Star Trek consideration when devising an answer, see my discussion at the link here .

I previously covered in my writings the various prompts that are particularly suited for getting summaries of text that you might provide to generative AI. Summarizing text is a very common use of generative AI. You can simply paste a whole bunch of text into generative AI and get a pretty good summary of the text. That being said, summaries can diverge from the original content and potentially contain misleading or even outright incorrect summarized content, see my analysis at the link here .

In short, summarizing can be risky due to the generative AI opting to rephrase the original content. The rephrasing might fail to depict the proper meaning and intention of the source content. Envision using summarization on doctor’s notes via generative AI, which is then handed to a different physician and they only have the summary at their purview, see my exploration of these matters at the link here .

Thus, a conventional summarization could be disturbingly problematic.

There is a method of devising summaries that use a prompting strategy that aims to bolster generative AI toward attaining especially superb or at least better than usual kinds of summaries. The technique is known as chain-of-density (CoD). Anybody versed in prompt engineering ought to become familiar with this insightful technique. Consider chain-of-density as not only helpful for producing summaries but there are a lot of other benefits garnered by understanding how the technique works and how this can power up your overall prompting prowess all-told.

For my detailed coverage of the chain-of-density prompting technique, see the link here .

Allow me a moment to share some of those elicitations with you here.

When you are trying to craft a summary, you often might do so in a series of successive attempts. Your first shot might be to craft a summary that has only a few of the biggest points that need to be included. After considering the initial draft, the odds are that you might further refine the summary by adding more elements to it. This can go on and on. Depending on how thorough you are, you might do a handful or more of these refining iterations. Each iteration can be construed as a chain of iterative summaries, one leading to the next for a given instance of trying to write a summary.

That’s the “chain” part of this process.

Let’s add some further terminology to describe the summary-making effort.

A summary typically starts as somewhat sparse when you first toss it together. There isn’t much of any substance in the summary. You are usually seeking to further pack substance into the summary and do so while fighting the length of the summary. The more substance that you can jam into the summary, the higher the density of the summary.

We can give a name to the substance by saying that we are trying to identify important “entities” within the original content. Those entities might be facts or figures. The entities are said to be anything especially instrumental to the overall meaning of the original content. A hope is to carry over as many of the demonstrative entities as feasible into the summary.

Your summary-making process then is to iteratively devise a summary by starting with a sparse version and then adding more and more entities or substances to increase the density until you reach some desired or suitable end-state. The series of iterations acts as a chain. Each is used to connect to the next. You usually will retain the entities from one version to the next version, and be decidedly adding more of the entities available in the original as you seek to jampack the summary accordingly.

Reflect on the adage of putting five pounds of rocks into a three-pound bag.

Maybe you put one pound of rocks into the three-pound bag at the initial attempt. The bag is considered sparsely populated. There is still room to spare. The density is low. You then put a second pound of rocks into the bag. The density is increasing. The sparseness is lessening. Finally, you put in a third pound of rocks. You have hit the maximum density and the sparseness has presumably dropped to near zero.

Suppose that the bag can be elongated.

Wonderful, you exclaim, being overjoyed at having more available space. Imagine though that you are going to hand the bag over to someone else. The larger and heavier the bag, the less useful it becomes. The same applies to summaries.

A rule of thumb is that you want to minimize the length or size of the summary, meanwhile maximizing the summarization content. The two factors are often in contention with each other. You are tempted to increase the length to get more substance included. The length being increased will potentially undercut that the summary is supposed to be a summary.

A person might seemingly just go ahead and read the original content if the summary approaches the size of the original material being summarized. The summary isn’t especially a summary anymore at that juncture. Indeed, sometimes a summary turns out to be longer than the original content that is supposedly being summarized.

How can this be, you might be thinking?

The answer has to do with being extractive versus being abstractive.

During the summarization process, you are looking at two possibilities of the content being carried over into the summary. First, you aim to be extractive, primarily extracting key aspects and shoveling those into the summary. Second, you might at times be abstractive, whereby you go beyond the words themselves of the original content and begin to reinterpret or perhaps elaborate beyond what the summary per se has to say.

A purely extractive summary is more likely to be construed as a fair and balanced reflection of the original content. You are not changing things up. You are only carrying the essentials (entities) over into the summary. The problem with an abstractive summary is that you are potentially changing up things and will be biasing or in some manner altering the meaning found within the original content being summarized. The danger is that this kind of summary is no longer seen as fair and balanced, and instead is based on the perceptions and opinions of the summarizer.

In a sense, if you want an unadorned straightforward summary, you are better off with an extractive summary. If you want an adorned or embellished summary, that goes beyond the words presented in the original source, you might seek an abstractive summary. The thing is, the abstractive summary might no longer be an apt reflection of the original source. That is also how the summary might become longer than the original since the embellishments can possibly increase the size of things and you could find yourself looking at a summary that is much longer than the source used for the summary.

Focusing On Compression As An Extractive Form Of Summarization

The usual parlance when you want a strictly extractive form of summarization is to say that you want a compression of your text.

I should warn you though that the word “compression” means different things to different people. Some are willing to be abstractive when doing a compression. Others would be aghast at someone veering into an abstractive mode when doing what they consider to be a rightfully done compression. To them, compression must be stridently adherent to not rewording any aspect of the source text being used.

I will be showing you in the next section some examples of using prompts related to asking generative AI to do compression. You will immediately see that the word “compression” is relatively ambiguous to most generative AI apps. They might interpret the word to imply purely extractive, but more likely they will assume this means to be abstractive. You will need to nail down in detail what you want the AI to do. I will show you this.

What else should you be thinking about when it comes to doing compression in generative AI?

I am glad you asked.

A recent research study entitled “LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression” by Zhuoshi Pan, QianhuiWu, Huiqiang Jiang, Menglin Xia, Xufang Luo, Jue Zhang, Qingwei Lin, Victor Rühle, Yuqing Yang, Chin-Yew Lin, H. Vicky Zhao, Lili Qiu, Dongmei Zhang, arXiv , March 19, 2024, made these salient points (excerpts):

  • “This paper focuses on task-agnostic prompt compression for better generalizability and efficiency.”
  • “We formulate prompt compression as a token classification problem to guarantee the faithfulness of the compressed prompt to the original one, and use a Transformer encoder as the base architecture to capture all essential information for prompt compression from the full bidirectional context.”
  • “Recent years have witnessed the emergence of various prompting techniques for large language models (LLMs), such as Chain-of-Thought (COT), In-context Learning (ICL), and Retrieval Augmented Generation (RAG). These techniques empower LLMs to handle complex and varied tasks through rich and informative prompts that may exceed tens of thousands of tokens.”
  • “However, the benefits of such lengthy prompts come at a cost of increased computational and financial overhead, as well as the degraded information perception ability of LLMs. Prompt compression is a straightforward solution to address these issues, which attempts to shorten the original prompts without losing essential information.”

I’d like to explain some of those notable points to you.

First, one ongoing consideration is whether a compression prompt is written to be task-specific or task-agnostic.

A task-specific prompt is worded to fit a particular task at hand, such as if you were doing a compression of medical notes and you wanted the prompt to emphasize particular characteristics associated with medical lingo. The prompt is devised for that domain.

A task-agnostic prompt is broader and allows you to use it in a wide variety of circumstances. It is always best to have in your tool chest a task-agnostic prompt since you can use it on a generalized basis, plus you can tweak the wording for task-specific settings. The aim of the above research study was to focus on task-agnostic prompts for compression, which is handy for our purposes herein.

Second, we often speak of compression prompts as hopefully being faithful to the source material.

Faithfulness refers to the notion that the compression tries to retain crucial wording and not goof by removing something that will substantively undercut the meaning. Imagine that a sentence said “Do not cook for more than two minutes” and the compression lopped out the word “not”, leading to this compressed version of “Do cook for more than two minutes”. Ouch, your souffle might be ruined by your having used an unfaithful compression.

Third, an aspirational aim of compression is to be bidirectional, allowing that besides going from the source to a proper compressed version, you potentially can use the compressed version to get back to the source. This is not necessarily the case and opens quite a can of worms. Not everyone needs or expects to be able to return to the full source.

Fourth, it is worthwhile to note frequent circumstances whereby compression really shines.

Suppose that you are importing a ton of text into generative AI, see my explanation of importations prompting strategies at the link here . Or maybe you are using in-context modeling and relying on an external source of text, doing so via the use of RAG (retrieval augmented generation), see my discussion at the link here . And so on.

An important question that comes up is whether it is sensible to bring in the whole ball of wax or whether to try and somehow shorten what you need to bring in.

If you bring in a massive amount of text, you are fighting against the potential limits of generative AI. Those limits can severely degrade the results of the AI trying to cope with the text overload. You also have to consider potential costs. If you are paying for the use of generative AI, the longer-sized text is bound to be a costlier charge than if you could thin it down. Likewise, the servers used to compute the generative AI actions will consume more computational cycles and you will get a double whammy on cost.

I am sure that you immediately discern that a potential solution would be to compress the content, thus, you don’t have to confront the technical limits of the generative AI and might be able to keep your costs lower too. Whenever you are considering bringing into generative AI any large-scale body of text, please have alarm bells go off in your head that tell you to consider doing either compression or summarization. You will be glad that you considered the option.

Returning to the above research study facets, let’s see what they did and the results they found (excerpts):

  • “We conduct extensive experiments and analysis on both in-domain (i.e., MeetingBank) and out-of-domain datasets (i.e., LongBench, ZeroScrolls, GSM8K, and Big Bench Hard).” (ibid).
  • “Despite being small in size, our model shows significant performance gains over strong baselines and demonstrates robust generalization ability from GPT-3.5-Turbo to Mistral-7B.” (ibid).
  • “Additionally, our model is 3x-6x faster than existing prompt compression methods, while accelerating the end-to-end latency by 1.6x-2.9x with compression ratios of 2x-5x.” (ibid).

You can see that they were able to attain some impressive results.

I especially applaud research on generative AI that includes multiple generative AI apps. I say this because each generative AI app differs from the other, ergo if a study exclusively uses only one generative AI app it is hard to claim that the same approach will work equally well on other generative AI apps. Here, it is good news for us that they tried different generative AI apps and essentially found similarly positive results.

I am sure you are eager to see an example of what their compression prompt was able to achieve.

Here is one such example from their study, in this case compressing a meeting transcript snippet from a database of such transcripts (excerpt):

  • Original Text: “Item 15, report from City Manager Recommendation to adopt three resolutions. First, to join the Victory Pace program. Second, to join the California first program. And number three, consenting to the inclusion of certain properties within the jurisdiction in the California Hero program. It was emotion, motion, a second and public comment. CNN. Please cast your vote. Oh. Was your public comment? Yeah. Please come forward. I thank you, Mr. Mayor. Thank you. Members of the council. My name is Alex Mitchell. I represent the hero program. Just wanted to let you know that the hero program. Has been in California for the last three and a half years.”
  • Compressed Text: “Item 15, City Manager Recommendation adopt three resolutions. Join Victory Pace program. Join California first program. Consent inclusion properties jurisdiction California Hero program. Emotion, motion, second, public comment. Cast vote. Public comment? Come forward. Alex Mitchell, represent Hero program. Hero program in California three half years.”

The original text has 109 words, while the compressed text has 46 words. The compression removed 63 words (that’s 109 words in total minus 46 words remaining = 63 words removed). You could say that roughly 58% of the source was removed (i.e., 58% of 109 is about 63). Well over half of the source has been removed.

Now comes the tough part.

Does the compressed version suitably capture the crux of the original text?

Has anything been removed that is essential and thus the compressed version has missed the boat?

I think you can likely see how hard a problem it is to do a proper compression if you try doing the same task yourself by hand. Here’s what I am saying. I want you to look at the original text and try to compress it. What would you remove? What would you leave in? How far can you go on this process, yet still ensure that the result has the needed points and is intelligible?

A twist involves settings where the original text itself is not necessarily that intelligible. A transcript is a great example of a thorny problem. The odds are that a transcript will contain filler words and utterances. Are they worthy of being retained or should those be removed? If you exhort it is obvious to remove the utterances, the issue there is that the tenor or tone of what was said could end up being removed. Perhaps that aspect is vital to comprehending the matter.

Besides deciding whether a compression has done a good job, you might also be wondering whether there is even more compression that can be performed.

Envision that we use a compression that does a good job and reduces the size of the source to half in size. But along comes a better approach that can do the same job and achieve a three-quarters reduction in size. Assuming that all else is equal, you would naturally seek to use the three-quarters reduction approach.

This can be tricky to compare. The greater the compression in terms of reducing the size, the more likely the odds that the compression isn’t going to be as intelligible or otherwise isn’t as apt. The criteria are usually battling with each other. The more reduction, the less of a good job in the sense of being usable and appropriate. The more of a good job you want, the less reduction you can usually achieve. Darned if you do, darned if you don’t.

The Compression Prompt As A Task-Agnostic Template

Congratulations, you have waded through the weeds to get to the crescendo.

Let’s see what the prompt template of their task-agnostic compression prompt consists of (excerpt):

  • “System Prompt: You are an excellent linguist and very good at compressing passages into short expressions by removing unimportant words while retaining as much information as possible.”
  • “User Prompt: Compress the given text to short expressions, such that you can reconstruct it as close as possible to the original.”
  • “Unlike the usual text compression, I need you to comply with the 5 conditions below:”
  • “1. You can ONLY remove unimportant words.”
  • “2. Do not reorder the original words.”
  • “3. Do not change the original words.”
  • “4. Do not use abbreviations or emojis.”
  • “5. Do not add new words or symbols.”

-“Compress the original aggressively by removing words only. Compress the original as short as you can, while retaining as much information as possible. If you understand, please compress the following text: {text to compress}”

I will be using that same prompt in a moment when I show you examples using ChatGPT and GPT-4.

Let’s briefly review the prompt and see what it contains.

First, the prompt tells the generative AI to invoke a persona. For my extensive coverage of personas in generative AI, see the link here and the link here . This is a powerful prompting technique.

Personas get the AI into a computational pattern-matching mode that can significantly aid whatever task you are trying to perform. In this instance, they are telling the AI that it is to pretend to be an excellent linguist and good at compressing passages of text. Nice touch.

Many users of generative AI fail to lean into personas when doing so would be especially advantageous. The use of a persona for amping up compression is a good move. Make sure to keep personas in your mind whenever using generative AI. You’ll be glad that you did.

Second, they provide five stipulated conditions for the compression. This is good since you want to provide as much guidance as you can when asking for a compression. I mentioned earlier that the word “compression” can be ambiguous. Spelling out the five stated conditions will give the AI important clues about what to do.

Third, the phrasing for AI that you use in a prompt ought to at times be emphatic. If you aren’t emphatic, the instructions might be ignored or downplayed. For example, telling the generative AI to aggressively do the compression is a means of guiding the AI toward doing a strident job. I should note that your being emphatic has a downside. The emphatic wording, if it goes way over the top, can trigger a mathematical and computational pattern-matching storm that will distract from what you are trying to undertake.

I believe that sufficiently outlines the keystones of the prompt. Just like buying a new car, we need to take this shiny new vehicle for a drive. Get yourself strapped in and ready for a wild ride.

Showcasing The Topic Via Examples In Generative AI

I will next proceed to showcase what happens when you use compression prompting while in a conversation with generative AI. I am going to use ChatGPT and GPT-4 to showcase my examples. ChatGPT and GPT-4 are sensible choices in this case due to their immense popularity as generative AI apps. An estimated one hundred million weekly active users are said to be utilizing ChatGPT and GPT-4. That’s a staggering number.

A few quick comments before we launch into using ChatGPT and GPT-4.

If you are going to try to do the same prompts that I show here, realize that the probabilistic and statistical properties will likely produce slightly different results than what I show here. That’s the nature of generative AI and how it is devised.

You also should expect that different generative AI apps will respond in different ways. Not all generative AI apps are the same. The key is that sometimes a particular prompt will work in one generative AI app and not another. You will need to undertake a series of trial-and-error attempts to ferret this out.

There is also the timing factor. A prompt that worked today might not work the same way tomorrow. Most of the generative AI apps are continually being updated. The updates might alter internal facets that could change how the AI reacts to your prompting.

We are ready to get underway and I will begin with ChatGPT.

You can do the same in whichever generative AI app that you are using.

As a heads-up, I decided to use Abraham Lincoln’s famous Gettysburg Address as the text that I wanted to have compressed. There are variations of his speech that can be readily found online. I opted to use a version that contains 271 words. Our aim in this mini-experiment will be to do a compression and see if we can reduce the size, along with retaining intelligibility and vital points.

I’m sure that you already know the speech, which starts this way “Four score and seven years ago our fathers brought forth on this continent, a new nation, conceived in Liberty, and dedicated to the proposition that all men are created equal. Now we are engaged in a great civil war, testing whether that nation, or any nation so conceived and so dedicated, can long endure…”

Here we go.

  • My entered prompt into ChatGPT: “I want you to compress an essay that I am going to give you. Are you ready?”
  • ChatGPT generated response: “Yes, I'm ready to help compress your essay. Please provide the essay, and I'll assist you in condensing it.”
  • My entered prompt into ChatGPT: “Here is the text of the Gettysburg address. Go ahead and compress it.”
  • ChatGPT generated response: “Abraham Lincoln's Gettysburg Address, delivered during the American Civil War, reflects on the nation's founding principles of liberty and equality. He honors those who sacrificed their lives on the battlefield, emphasizing the ongoing responsibility to preserve freedom and uphold democratic government. Lincoln urges dedication to the unfinished task of ensuring the nation's survival and the continuation of its principles, emphasizing the importance of honoring the fallen and ensuring their sacrifice was not in vain.”

Take a look at the so-called compression that I got.

You right away certainly observed that the generated response is not a compression. It is more of a summary. Well, maybe not quite a summary either. It has indications that go beyond the text that was provided. This likely was tapped into by ChatGPT as per other prior data training about Abraham Lincoln and the Gettysburg Address in general during the initial setup of ChatGPT.

I’m glad this happened. You see, I wanted to show you this kind of an example to emphasize my earlier point that the word “compression” can be ambiguous. This was not the kind of compression I had in mind.

If at first, you don’t succeed, try and try again, as they say.

  • My entered prompt into ChatGPT: “Let’s start over. I want you to compress the material. You are to use only the material provided and compress the contents. Don’t make any interpretations. Don’t do any rewording.”
  • ChatGPT generated response: “Understood. Please provide the material you'd like me to compress, and I'll follow your instructions accordingly.”
  • My entered prompt into ChatGPT: ”Here is the text to be compressed…”
  • ChatGPT generated response: "87 years ago, our fathers founded a nation dedicated to liberty and equality. Now, in a great civil war, we honor those who sacrificed for our nation. It's fitting to dedicate this ground, yet their deeds surpass our words. We must continue their work, ensuring their sacrifices were not in vain. Let us resolve to uphold freedom and democratic government.”

I valiantly tried to convey to ChatGPT that I wanted a compression.

Though the result is more so a compression than the first run, it still isn’t a compression of the caliber we are looking for. One irksome thing was the “87 years ago” which is a kind of summary or interpretation of what the source says. Didn’t want that.

But I am somewhat pleased that the result came out badly because it shows that even if you try to be instructive about compression, the result still might not come out as hoped for. I think we are primed and ready to see if the compression prompting template will do any better with ChatGPT.

Are you ready to see?

Hold your breath.

  • My entered prompt (based on the research prompt template): “You are an excellent linguist and very good at compressing passages into short expressions by removing unimportant words while retaining as much information as possible. Compress the text I am going to give you and compress the text into short expressions, and such that you (ChatGPT) can reconstruct it as close as possible to the original. Unlike the usual text compression, I need you to comply with 5 conditions. First condition: You can ONLY remove unimportant words. Second condition: Do not reorder the original words. Third condition: Do not change the original words. Fourth condition: Do not use abbreviations or emojis. Fifth condition: Do not add new words or symbols. Make sure to compress the original text aggressively by removing words only. Compress the original text as short as you can, while retaining as much information as possible. Do you understand these instructions?”
  • ChatGPT generated response : “Yes, I understand the instructions. Please provide the text you'd like me to compress.”
  • My entered prompt: ”Here is the text to be compressed…”
  • ChatGPT generated response: “Four score and seven years ago our fathers brought forth on this continent a new nation, conceived in Liberty, dedicated to the proposition that all men are created equal. Now engaged in a great civil war, testing whether that nation, or any nation so conceived and dedicated, can long endure. We are met on a great battle-field. We have come to dedicate a portion of that field, a final resting place for those who gave their lives. It is fitting and proper that we should do this. But, in a larger sense, we cannot dedicate, consecrate, hallow this ground. The brave men, living and dead, who struggled here, consecrated it. The world will little note, nor long remember what we say here, but it can never forget what they did here. It is for us the living to be dedicated to the unfinished work they who fought here have nobly advanced. It is for us to be dedicated to the great task remaining before us—that from these honored dead we take increased devotion to that cause—that we highly resolve that these dead shall not have died in vain—that this nation, under God, shall have a new birth of freedom—and that government of the people, by the people, for the people, shall not perish.”

Finally, we got a compression.

We are now in the right ballpark.

The compressed result has 217 words.

The original text has 271 words, while the compressed text has 217 words. The compression removed 54 words (that’s 271 words in total minus 217 words remaining = 54 words removed). You could say that roughly 20% of the source was removed (i.e., 20% of 271 is about 54). Approximately one-fifth was removed.

I dare say that’s not a compression ratio to be overly elated about. Look, I’m glad that we got the 20%, and I don’t like to look a gift horse in the mouth. It would seem intuitively we might be able to do better.

Note that the prompt doesn’t give a target level of compression. This is something you might consider adding to the prompt. I would first start without a target and just see what you get. Once you’ve seen the result of a first run, go ahead and consider redoing the prompt with a desired target level.

We must also of course consider whether the compressed version is any good at the get-go.

In the case of something like the Gettysburg Address, we could argue forever about the portions that were removed. It is tough since the entire speech is remarkable. Nearly every line and each word is astounding. Imagine trying to compress a poem, and the odds are that you will be leaving out facets that will break your heart.

Another reminder is that you should carefully consider what text you are going to compress and whether the compression, no matter how it works, will be able to reasonably do justice to the original text.

I went ahead and played with the compression prompt template and tried all kinds of variations. In the end, I decided that ChatGPT just doesn’t have the gravitas to go much further on this. I became exasperated and thought that for sure GPT-4, being more advanced than ChatGPT, would do a better job.

Let’s try using GPT-4 and see what happens.

  • ​​ My entered prompt into GPT-4: “I want you to compress an essay that I am going to give you. Here is the text to be compressed…”
  • GPT-4 generated response:

“To compress the text while retaining its essence, I'll remove some parts and rephrase others for brevity.”

"Four score and seven years ago, our fathers founded a new nation on this continent, dedicated to liberty and the belief that all men are created equal. We are now in the midst of a great civil war, testing whether this nation, or any nation so conceived, can endure. We meet on a battle-field of that war, dedicating a part of it as a final resting place for those who gave their lives for this nation's survival. It's fitting and proper we do this.

“Yet, we can't dedicate, consecrate, or hallow this ground beyond what the brave men, living and dead, who struggled here have done. The world may not remember our words, but it can't forget their deeds. It's our task to be dedicated to the unfinished work they've advanced so nobly. From these honored dead we take increased devotion to their cause, resolving that these dead shall not have died in vain, that this nation shall have a new birth of freedom, and that government of, by, and for the people shall not perish."

“The compressed text has been reduced to 176 words.”

End of GPT-4 response

You can see that I first tried a vague prompt about compression.

Sure enough, the compression included rephrasing, which isn’t what I had in mind. No problem. You can’t expect generative AI to be reading minds (well, you soon can, as I explain is being researched, see my coverage at the link here ).

Similar to what I had done with ChatGPT, I will next try a compression prompt based on some simple wording. I will also include a target level of compression so you can see how that impacts the result.

Here’s what took place.

  • My entered prompt into GPT-4: “Do the compression over again. You cannot do any rephrasing this time. You can only remove words. Compress as much as possible while abiding by these rules. Try to aim for a result that has 100 words or less.”

“To compress the text by only removing words without rephrasing, I'll select key sentences and phrases that capture the essence of the original message while significantly reducing the length. Given the constraints, this selection process aims to preserve the core themes of unity, dedication, and the importance of the struggle while adhering to the word count limit.”

"Four score and seven years ago our fathers brought forth on this continent, a new nation, conceived in Liberty, and dedicated to the proposition that all men are created equal. Now we are engaged in a great civil war, testing whether that nation, or any nation so conceived and so dedicated, can long endure. The brave men, living and dead, who struggled here, have consecrated it, far above our poor power to add or detract. It is for us the living, to be dedicated to the unfinished work which they who fought here have thus far so nobly advanced."

“The condensed version of the text is approximately 99 words in size while adhering to the rule of only removing words without rephrasing.”

Seems like GPT-4 did what I asked.

As always, it is important to gauge the intelligibility and aptness of the compression. I won’t delve into that here, other than to say it seemed basically on par with what might be expected, especially given the severe constraint of being around 100 words or less.

We are ready to try the compression prompt template.

  • My entered prompt into GPT-4 (based on the research prompt template): “You are an excellent linguist and very good at compressing passages into short expressions by removing unimportant words while retaining as much information as possible. Compress the text I am going to give you and compress the text into short expressions, and such that you (ChatGPT) can reconstruct it as close as possible to the original. Unlike the usual text compression, I need you to comply with 5 conditions. First condition: You can ONLY remove unimportant words. Second condition: Do not reorder the original words. Third condition: Do not change the original words. Fourth condition: Do not use abbreviations or emojis. Fifth condition: Do not add new words or symbols. Make sure to compress the original text aggressively by removing words only. Compress the original text as short as you can, while retaining as much information as possible. Do you understand these instructions?”
  • GPT-4 generated response : “Yes, I understand the instructions. Please provide the text you'd like me to compress.”
  • My entered prompt into GPT4: ”Here is the text to be compressed…”
  • GPT-4 generated response: “Four score seven years ago fathers brought forth continent, new nation, conceived Liberty, dedicated proposition men created equal. Now engaged great civil war, testing whether nation, any nation conceived dedicated, can long endure. Met great battle-field war. Come dedicate portion field, final resting place who gave lives nation might live. Altogether fitting proper do this. But, larger sense, can not dedicate—not consecrate—not hallow—ground. Brave men, living dead, struggled, have consecrated, above our power add detract. World will little note, nor long remember say here, but never forget did here. For us living, rather, dedicated here unfinished work fought have nobly advanced. Rather for us here dedicated great task remaining before us—that from these honored dead take increased devotion cause gave last full measure devotion—that here highly resolve dead not died in vain—that nation, under God, shall new birth freedom—and government people, by people, for people, shall not perish earth.”

Note that I didn’t give a target level this time and thus the size of the result was based on the general tenor of the compression prompt about being aggressive on the compression.

The original text has 271 words, while the compressed text has 156 words. The compression removed 115 words (that’s 271 words in total minus 156 words remaining = 115 words removed). You could say that roughly 42% of the source was removed (i.e., 42% of 271 is about 115). We were nearing maybe half being removed. Remarkable.

I’ll mention that as always, we would want to closely scrutinize the compressed version. All the other caveats I’ve mentioned still apply.

My recommendation to you is that you try doing some compression prompting exercises via whichever generative AI app you are customarily using. Do so now, before you suddenly discover the need to do a compression. It would be wise to be prepared.

Proceed as follows. First, make use of vague compression prompts and see what happens. Next, fine-tune those prompts and look anew at what happens. Then, try the mentioned compression prompt and gauge how it goes for you. Tweak the prompt as needed. Keep on practicing until you feel you’ve gotten the right swing of things. Reward yourself accordingly.

A final thought for now on this matter.

John Morley, 1st Viscount Morley of Blackburn, the famed British statesman, and journalist, said this about compression: “The essence of a quote is the compression of a mass of thought and observation into a single saying.”

Compression is not an easy task. Any wanton approach can easily do compression if you are willing to toss intelligibility and aptness out the window. Getting generative AI to do erstwhile compression requires soundness on the part of the person entering the prompts. They also need to carefully review the result and not wantonly hand off the compressed version to others who might be unaware of what the original had to say.

Please remember that I energetically asked you to consider practicing doing compressions in generative AI, so that when the day arrives that you must do so, you are ready with the axe firmly in hand.

The last line today suitably goes to Abraham Lincoln: "Give me six hours to chop down a tree and I will spend the first four sharpening the ax."

Lance Eliot

  • Editorial Standards
  • Reprints & Permissions
  • Today's news
  • Reviews and deals
  • Climate change
  • 2024 election
  • Fall allergies
  • Health news
  • Mental health
  • Sexual health
  • Family health
  • So mini ways
  • Unapologetically
  • Buying guides

Entertainment

  • How to Watch
  • My watchlist
  • Stock market
  • Biden economy
  • Personal finance
  • Stocks: most active
  • Stocks: gainers
  • Stocks: losers
  • Trending tickers
  • World indices
  • US Treasury bonds
  • Top mutual funds
  • Highest open interest
  • Highest implied volatility
  • Currency converter
  • Basic materials
  • Communication services
  • Consumer cyclical
  • Consumer defensive
  • Financial services
  • Industrials
  • Real estate
  • Mutual funds
  • Credit cards
  • Credit card rates
  • Balance transfer credit cards
  • Business credit cards
  • Cash back credit cards
  • Rewards credit cards
  • Travel credit cards
  • Checking accounts
  • Online checking accounts
  • High-yield savings accounts
  • Money market accounts
  • Personal loans
  • Student loans
  • Car insurance
  • Home buying
  • Options pit
  • Investment ideas
  • Research reports
  • Fantasy football
  • Pro Pick 'Em
  • College Pick 'Em
  • Fantasy baseball
  • Fantasy hockey
  • Fantasy basketball
  • Download the app
  • Daily fantasy
  • Scores and schedules
  • GameChannel
  • World Baseball Classic
  • Premier League
  • CONCACAF League
  • Champions League
  • Motorsports
  • Horse racing
  • Newsletters

New on Yahoo

  • Privacy Dashboard

From the Rubble of ‘Be’eri’: A Kibbutz Mourns Its Dead and Vows to Rebuild | Photo Essay

From the rubble of ‘be’eri’: a kibbutz mourns its dead and vows to rebuild | photo essay, thewrap gets a rare glimpse inside a devastated community five months after a murderous rampage by hamas terrorists, the first in a series.

KIBBUTZ BE’ERI, Israel — Ela Shani Kozin turned 15 in January, just three months after she survived the Hamas terrorist attack on her kibbutz, Be’eri, a few kilometers from Israel’s border with Gaza.

On the dark day of Oct. 7, 2023, when 1,200 people were murdered in Israel, Be’eri suffered the worst losses among three kibbutzim attacked. About 100 of its 1,200 residents were killed, and dozens more taken hostage. The violence was unspeakable. Families were burned in their homes. Survivors spoke of hearing hours of torture while cowering in their safe rooms. Two teenage girls were found naked and murdered, with rape presumed. Their father is a hostage.

Shani’s father, 72-year-old Itzik Kozin, was killed and his house burned to a cinder. The next street over lifelong peace activist Vivian Silver, 74, was killed. Shani’s teenaged cousin Amit was taken hostage, as was 85-year-old Yocheved Lifshitz and 9-year-old Irish-Israeli Emily Hand. They all returned to Israel in a hostage exchange in November. But Lifshitz’s husband Oded, 83, is still held by Hamas.

Five months after the deadly attack that triggered yet another Mideast war, I returned to Israel to better understand the impact of this devastating massacre, whose aftermath has rippled throughout the world, including in California’s corridors of popular culture.

Far from the screaming crowds on college campuses and beyond the angry activists ripping up photos of hostages, there is Be’eri, where people have family members who are actually hostages, and are trying to reclaim their lives after the horror.

Last December, Ela spoke about her experiences at TheWrap’s Power Women Summit . She recently returned and invited me to tour the devastated kibbutz with her and her mother Sharon, who has been living at a hotel in the Dead Sea since the attack. On this day she visited her father’s house for only the second time since Oct. 7.

Be’eri was founded in 1946, two years before the establishment of the state of Israel, by members of the left-wing Zionist youth movement called HaNoar HaOved VeHaLomed. It was named for one of the founders of Labor Zionism, which is tied to the worker’s movement. Back then, Be’eri was a tiny community with a population of 150, reclaiming desert land and planting trees. They were joined in subsequent years by young Jews from Iraq.

Over time, the kibbutz prospered and became wealthy, and for decades has been known for its thriving print business in addition to its agriculture. Jews came to settle there decades ago from as far away as Argentina.

The community is exceedingly close knit. Everyone knows every other family. Generations have grown up here, and stayed. Now traumatized and mourning, residents are slowly returning to the kibbutz to occupy those homes that were not destroyed. The homes incinerated by Hamas have not yet been touched, and many remain as testimonials to the residents who were killed there.

The kibbutz does not usually allow journalists to enter so this is a rare glimpse of a community coping with the aftermath of Oct. 7., and the tour of sorrow when their nightmares came to life.

The home of Nir Shani, after Hamas terrorists destroyed it.

Sharon’s brother, Nir, texted her first thing in the morning on Oct. 7: “Arabs outside. Talk later.” He ran to his safe room and a few minutes later terrorists attacked his villa, situated toward the rear security fence of the kibbutz where Hamas militants entered. The house was destroyed, then burned. His teenaged son, Amit, was taken hostage.

Sharon Shani surveys the wreckage of her brother Nir’s home.

The destroyed home of 9-year-old Emily Hand, the Irish-Israeli girl who was kidnapped by Hamas, and released in a hostage exchange on Nov. 26. The other two residents were also taken hostage, and later released.

Hamas terrorists attacked Noy and Machol Shosh and their three small children in this home on the morning of Oct. 7. Hiding in their safe room, which every house in the kibbutz has, Noy was shot through the door and bleeding heavily, according to resident Meirav Barkan. Machol held his wound to stem the bleeding when terrorists set fire to the house to force them out. She had to choose between opening the window to allow air in or holding his wound. She ultimately opened the window and saved herself and the three children. Noy died. Machol later learned she was pregnant, and will give birth in the coming weeks.

In this home, Sharon Shani told me Ohad Cohen was shot dead at the door of his safe room, trying to block his wife Sandra who was holding their nine-month-old baby, Mila. The baby was killed in her mother’s arms. The mother survived, as did her two young sons, Liam and Dylan, who the attackers tried to kidnap but found their car was full. So they left them.

As it happened, three generations of the Cohen family were murdered this day. Ohad’s mother Yona, 73, was also killed in her home on Kibbutz Be’eri. Her body was found 11 days after the attack. All three generations were laid to rest side by side at the Yarkon cemetery in Petach Tikvah, according to Israeli media.

A pitched battle went on for hours as wounded residents ran and hid in the medical clinic across from the elementary school of the kibbutz. With shots all around, paramedic Amit Man, 22, treated as many as she could. Two of the Israelis had their own weapons, but eventually their ammunition ran out and Hamas attackers overran the clinic. Man and the others were killed. One nurse, Nirit, hid in a cupboard and survived.

The bullet-pocked wall of the medical clinic.

Residents leave messages to those who were killed at the medical clinic.

Poster for Amit Man, the medic in charge of the clinic who was killed.

Resident Meirav Barkan, 43, said the day before the attack the kibbutz had celebrated its 77th anniversary. She showed me photos of herself as a child growing up there, still posted for the celebration in the communal building.

About 100 residents have returned to live at the kibbutz, she said, including her father, aged 81. “Eight days after the attack he came back to work” in the kibbutz printing press business, “before all the blood was wiped off the house,” she said.

Meirav’s mother, 81, was murdered in their home on Oct. 7. Barkan’s son, Doron, killed several attackers from the balcony of their home, she said, showing me a photo on her phone with two of the dead.

Maayan Lifshitz, 27, holds a photo of her grandfather Oded, an 83-year-old Be’eri resident who is still held hostage. Her grandmother, Yocheved, 85, was among the first hostages to be released. I met her in Tel Aviv, at the Hostage and Missing Families Forum center, where families regularly meet for support and information.

On Oct. 7, Ela Shani Kozin hid in her family’s safe room with her mother Sharon and her eight-year-old brother and his friend. (Initially the boys slept until 12 p.m. and then watched “SpongeBob Squarepants” until the shooting came close.) The terrorists were roaming the kibbutz, but did not reach every house or every street. Lacking clear information, Sharon texted her parents, brother and Ela’s father all day in their homes on the kibbutz. Ela’s father was shot dead in the early afternoon. Ela’s grandmother, 80, was shot twice, through the door of their safe room, but survived. Her grandfather also survived, and emerged from the safe room to find a dead terrorist face down on his couch.

A home burned on Oct. 7

The Hamas attackers set up their headquarters at the children’s third and fourth grade administration building, coordinating their plans. Nothing remains of the building.

Here is Ela’s speech to the Power Women Summit in December:

The post From the Rubble of ‘Be’eri’: A Kibbutz Mourns Its Dead and Vows to Rebuild | Photo Essay appeared first on TheWrap .

Recommended Stories

Israeli prime minister netanyahu cancels delegation after u.s. abstains from u.n. ceasefire vote. here's the latest..

The United Nations Security Council on Monday approved a resolution calling for an immediate ceasefire between Israel and Hamas in Gaza.

Amazon Big Spring Sale deals: Our editors' top picks for the final day of the spring Prime Day event

Act fast to score savings of up to 75% on top brands like Apple, Keurig, iRobot and more.

Women's NCAA tournament: How to watch UConn vs. Syracuse tonight

The Second Round of the women's NCAA tournament continues today. Are you ready to watch?

Women's NCAA tournament: How to watch Iowa vs. West Virginia tonight

The Second Round of the women's NCAA tournament continues today with Iowa vs. WVU. Are you ready to watch?

'My 54-year-old neck looks smooth and hydrated': Grab this anti-aging body lotion for just $11

This is the lowest price ever for the Gold Bond favorite — and it's earned over 20,000 flawless reviews on Amazon.

Final Fantasy XIV Online's Dawntrail expansion arrives on July 2

Square Enix has revealed that the fifth expansion for Final Fantasy XIV Online, Dawntrail, will arrive on July 2. There are a bunch of pre-order bonuses if you pre-order, including an early access period.

Avoid oil burns while cooking with this $9 splatter guard — it's over 70% off for the Amazon Big Spring Sale

Over 30,000 fans say it's a meal-prep must, and it will help keep your stove clean too.

Reese Witherspoon always travels with this face wash — and a big bottle's down to $14

Also on sale for only $6: The superstar's go-to eyelash curler. It's currently 50% off.

Get smart: Score an Oprah-approved Echo Show 15 on rare sale — it's nearly 30% off

Stay on-task and entertained with this Alexa hub, loved by the 'Queen of All Media' herself: 'It almost looks like a piece of art,' she said.

Gold’s 'record march higher set to continue,' Goldman says

Goldman Sachs analysts see gold heading to $2,300 by year-end.

From the Rubble of ‘Be’eri’: A Kibbutz Mourns Its Dead and Vows to Rebuild | Photo Essay

Sharon Israel

From the Rubble of ‘Be’eri’: a Kibbutz Mourns Its Dead and Vows to Rebuild | Photo Essay

Thewrap gets a rare glimpse inside a devastated community five months after a murderous rampage by hamas terrorists, the first in a series.

KIBBUTZ BE’ERI, Israel — Ela Shani Kozin turned 15 in January, just three months after she survived the Hamas terrorist attack on her kibbutz, Be’eri, a few kilometers from Israel’s border with Gaza. 

On the dark day of Oct. 7, 2023, when 1,200 people were murdered in Israel, Be’eri suffered the worst losses among three kibbutzim attacked. About 100 of its 1,200 residents were killed, and dozens more taken hostage. The violence was unspeakable. Families were burned in their homes. Survivors spoke of hearing hours of torture while cowering in their safe rooms. Two teenage girls were found naked and murdered, with rape presumed. Their father is a hostage.

report-from-israel

Shani’s father, 72-year-old Itzik Kozin, was killed and his house burned to a cinder. The next street over lifelong peace activist Vivian Silver, 74, was killed. Shani’s teenaged cousin Amit was taken hostage, as was 85-year-old Yocheved Lifshitz and 9-year-old Irish-Israeli Emily Hand. They all returned to Israel in a hostage exchange in November. But Lifshitz’s husband Oded, 83, is still held by Hamas.

Five months after the deadly attack that triggered yet another Mideast war, I returned to Israel to better understand the impact of this devastating massacre, whose aftermath has rippled throughout the world, including in California’s corridors of popular culture. 

Far from the screaming crowds on college campuses and beyond the angry activists ripping up photos of hostages, there is Be’eri, where people have family members who are actually hostages, and are trying to reclaim their lives after the horror. 

Last December, Ela spoke about her experiences at TheWrap’s Power Women Summit . She recently returned and invited me to tour the devastated kibbutz with her and her mother Sharon, who has been living at a hotel in the Dead Sea since the attack. On this day she visited her father’s house for only the second time since Oct. 7. 

Be’eri was founded in 1946, two years before the establishment of the state of Israel, by members of the left-wing Zionist youth movement called HaNoar HaOved VeHaLomed. It was named for one of the founders of Labor Zionism, which is tied to the worker’s movement. Back then, Be’eri was a tiny community with a population of 150, reclaiming desert land and planting trees. They were joined in subsequent years by young Jews from Iraq. 

Over time, the kibbutz prospered and became wealthy, and for decades has been known for its thriving print business in addition to its agriculture. Jews came to settle there decades ago from as far away as Argentina. 

The community is exceedingly close knit. Everyone knows every other family. Generations have grown up here, and stayed. Now traumatized and mourning, residents are slowly returning to the kibbutz to occupy those homes that were not destroyed. The homes incinerated by Hamas have not yet been touched, and many remain as testimonials to the residents who were killed there. 

The kibbutz does not usually allow journalists to enter so this is a rare glimpse of a community coping with the aftermath of Oct. 7., and the tour of sorrow when their nightmares came to life.

Ela Shani Kozin speaks at TheWrap's 2023 Changemakers Dinner

The home of Nir Shani, after Hamas terrorists destroyed it.

Sharon’s brother, Nir, texted her first thing in the morning on Oct. 7: “Arabs outside. Talk later.” He ran to his safe room and a few minutes later terrorists attacked his villa, situated toward the rear security fence of the kibbutz where Hamas militants entered. The house was destroyed, then burned. His teenaged son, Amit, was taken hostage.

Sharon Israel

Sharon Shani surveys the wreckage of her brother Nir’s home.

Sharon Israel

The destroyed home of 9-year-old Emily Hand, the Irish-Israeli girl who was kidnapped by Hamas, and released in a hostage exchange on Nov. 26. The other two residents were also taken hostage, and later released.

Sharon Israel

Hamas terrorists attacked Noy and Machol Shosh and their three small children in this home on the morning of Oct. 7. Hiding in their safe room, which every house in the kibbutz has, Noy was shot through the door and bleeding heavily, according to resident Meirav Barkan. Machol held his wound to stem the bleeding when terrorists set fire to the house to force them out. She had to choose between opening the window to allow air in or holding his wound. She ultimately opened the window and saved herself and the three children. Noy died. Machol later learned she was pregnant, and will give birth in the coming weeks.

Sharon Israel

In this home, Sharon Shani told me Ohad Cohen was shot dead at the door of his safe room, trying to block his wife Sandra who was holding their nine-month-old baby, Mila. The baby was killed in her mother’s arms. The mother survived, as did her two young sons, Liam and Dylan, who the attackers tried to kidnap but found their car was full. So they left them.

As it happened, three generations of the Cohen family were murdered this day. Ohad’s mother Yona, 73, was also killed in her home on Kibbutz Be’eri. Her body was found 11 days after the attack. All three generations were laid to rest side by side at the Yarkon cemetery in Petach Tikvah, according to Israeli media.

Sharon Israel

A pitched battle went on for hours as wounded residents ran and hid in the medical clinic across from the elementary school of the kibbutz. With shots all around, paramedic Amit Man, 22, treated as many as she could. Two of the Israelis had their own weapons, but eventually their ammunition ran out and Hamas attackers overran the clinic. Man and the others were killed. One nurse, Nirit, hid in a cupboard and survived.

Sharon Israel

The bullet-pocked wall of the medical clinic.

Sharon Israel

Residents leave messages to those who were killed at the medical clinic.

the essay is dead

Poster for Amit Man, the medic in charge of the clinic who was killed.

the essay is dead

Resident Meirav Barkan, 43, said the day before the attack the kibbutz had celebrated its 77th anniversary. She showed me photos of herself as a child growing up there, still posted for the celebration in the communal building.

About 100 residents have returned to live at the kibbutz, she said, including her father, aged 81. “Eight days after the attack he came back to work” in the kibbutz printing press business, “before all the blood was wiped off the house,” she said.

Meirav’s mother, 81, was murdered in their home on Oct. 7. Barkan’s son, Doron, killed several attackers from the balcony of their home, she said, showing me a photo on her phone with two of the dead.

Sharon Israel

Maayan Lifshitz, 27, holds a photo of her grandfather Oded, an 83-year-old Be’eri resident who is still held hostage. Her grandmother, Yocheved, 85, was among the first hostages to be released. I met her in Tel Aviv, at the Hostage and Missing Families Forum center, where families regularly meet for support and information.

Sharon Israel

On Oct. 7, Ela Shani Kozin hid in her family’s safe room with her mother Sharon and her eight-year-old brother and his friend. (Initially the boys slept until 12 p.m. and then watched “SpongeBob Squarepants” until the shooting came close.) The terrorists were roaming the kibbutz, but did not reach every house or every street. Lacking clear information, Sharon texted her parents, brother and Ela’s father all day in their homes on the kibbutz. Ela’s father was shot dead in the early afternoon. Ela’s grandmother, 80, was shot twice, through the door of their safe room, but survived. Her grandfather also survived, and emerged from the safe room to find a dead terrorist face down on his couch.

the essay is dead

A home burned on Oct. 7

the essay is dead

The Hamas attackers set up their headquarters at the children’s third and fourth grade administration building, coordinating their plans. Nothing remains of the building.

Here is Ela’s speech to the Power Women Summit in December:

Home — Essay Samples — Entertainment — Dead Poets Society — Neil Perry Dead Poets Society

test_template

Neil Perry Dead Poets Society

  • Categories: Dead Poets Society

About this sample

close

Words: 709 |

Published: Mar 25, 2024

Words: 709 | Pages: 2 | 4 min read

Table of contents

Introduction, body paragraph 1: neil perry's struggle for authenticity, body paragraph 2: the consequences of repression and the importance of self-expression, body paragraph 3: the role of supportive educational environments, counterarguments: balancing self-expression with responsibility and respect for others.

Image of Dr. Charlotte Jacobson

Cite this Essay

Let us write you an essay from scratch

  • 450+ experts on 30 subjects ready to help
  • Custom essay delivered in as few as 3 hours

Get high-quality help

author

Prof Ernest (PhD)

Verified writer

  • Expert in: Entertainment

writer

+ 120 experts online

By clicking “Check Writers’ Offers”, you agree to our terms of service and privacy policy . We’ll occasionally send you promo and account related email

No need to pay just yet!

Related Essays

6.5 pages / 2866 words

4 pages / 1797 words

4 pages / 1710 words

10.5 pages / 4766 words

Remember! This is just a sample.

You can get your custom paper by one of our expert writers.

121 writers online

Still can’t find what you need?

Browse our vast selection of original essay samples, each expertly formatted and styled

Related Essays on Dead Poets Society

Dead Poets Society, a masterpiece directed by Peter Weir, is a must-watch movie for teenagers. This film features three main characters: Robin Williams as John Keating, Robert Sean Leonard as Neil Perry, and Ethan [...]

There is a balance to ideals in individuality and truth, both at positive and negative extremes. The movie Dead Poets Society by Peter Weir captures the incredible role romanticism and embracement of truth on an individual's [...]

The phrase “carpe diem” or “seize the day” is commonly used as an inspiration for books, movies, poems, and many different types of art. But what does this phrase mean? Where did it come from? What are some examples of this [...]

“There’s a time for daring and there’s a time for caution, and a wise man understands which is called for” (DPS). Transcendentalism is a somewhat daring and rebellious movement that encourages people to live with individuality [...]

Anthony Burgess’s A Clockwork Orange is a novel pervaded by a multifaceted and intrinsic musical presence. Protagonist Alex’s fondness for classical music imbues his character with interesting dimensions, and resonates well [...]

Following the publication of his most notable work, A Clockwork Orange, Anthony Burgess commented on the function of literature in a mutable society. There is not much point in writing a novel unless you can show the possibility [...]

Related Topics

By clicking “Send”, you agree to our Terms of service and Privacy statement . We will occasionally send you account related emails.

Where do you want us to send this sample?

By clicking “Continue”, you agree to our terms of service and privacy policy.

Be careful. This essay is not unique

This essay was donated by a student and is likely to have been used and submitted before

Download this Sample

Free samples may contain mistakes and not unique parts

Sorry, we could not paraphrase this essay. Our professional writers can rewrite it and get you a unique paper.

Please check your inbox.

We can write you a custom essay that will follow your exact instructions and meet the deadlines. Let's fix your grades together!

Get Your Personalized Essay in 3 Hours or Less!

We use cookies to personalyze your web-site experience. By continuing we’ll assume you board with our cookie policy .

  • Instructions Followed To The Letter
  • Deadlines Met At Every Stage
  • Unique And Plagiarism Free

the essay is dead

Don’t Tell America the Babysitter’s Dead

For decades, sitting was both a job and a rite of passage. Now it feels more like a symbol of a bygone American era.

A girl, photographed from behind, wearing a blue-plaid flannel shirt

This article was featured in the One Story to Read Today newsletter. Sign up for it here .

Babysitting used to be both a job and a rite of passage. For countless American teens, and especially teen girls, it was a tentative step toward adulthood—responsibility, but with guardrails. Perhaps you didn’t cook dinner, but you did heat some leftovers for the kids. Maybe you arrived to find them already tucked in, and you read them a story, turned out the lights, and watched TV until the car turned into the drive. You knew whom to call if anything serious came up. Paula Fass, a historian of childhood at UC Berkeley, told me that she started sitting around 1960, when she was 12 or 13. By the time she’d arrive, she remembers, the parents had put their kids to bed and stocked the fridge for her to raid. They recognized that she was grown-up enough to be an extra eye in the home—but childlike enough to go looking for snacks.

Sitting was a “quintessentially American experience,” Yasemin Besen-Cassino, a Montclair State University sociologist and the author of The Cost of Being a Girl: Working Teens and the Origins of the Gender Wage Gap , told me. For decades, working a part-time job was common for teens in the U.S.—perhaps a reflection of the cultural emphasis on hard work, discipline, and financial independence. Even tweens would babysit. And something about that position, teetering between dependence and independence, got lodged in our cultural imagination. Starting in the mid-20th century, the young sitter became an emblem of American girlhood—both a classic coming-of-age character and a locus of anxieties about girls’ growing autonomy. Just how mature are these teens? How much control should they have? And what kind of adults are they on the cusp of turning into? Those concerns preoccupied people not only in real life but also in a plethora of books, shows, and movies.

Today, the teen babysitter as we knew her, in pop culture and in reality, has all but disappeared. People seem to worry less about adolescents and more for them, and for their future prospects. As Fass put it, “Teenagers don’t seem very grown-up these days.” There’s not much reason to fear or exalt babysitters anymore—because our society no longer trusts teens to babysit much at all.

Read: Teen brains are perfectly capable

The 1920s were boom times for leisure. New technologies made chores easier, freeing up couples’ time, and growing wages gave people more disposable income. Meanwhile, restaurants and movie theaters proliferated, and car ownership exploded. Parents were going out at night—and more mothers were working during the day, too. At the same time, traditional child-care providers were becoming less available, Miriam Forman-Brunell, a historian at the University of Missouri at Kansas City, wrote in her book Babysitter: An American History ; grandparents, for instance, were enjoying social lives of their own. Working-class families, Fass told me, would still have been likely to enlist older siblings to watch the young ones. But middle-class parents could also afford to pay a few bucks to the kid down the block, who—as companies were marketing products, more and more, to youths —now had a reason to want pocket money. The teen babysitter was born.

From the beginning, the role was viewed with suspicion. Granting a young person unmonitored control over your children and your house may naturally have been a little worrisome—but beyond that, the sitter took on brewing cultural anxieties. Given that she was working outside her own home—and earning her own pay—she represented teen girls’ growing autonomy, according to Forman-Brunell . She was also associated with women’s liberation. After all, parents needed her partly because moms were starting not only to work but also to enjoy free time on the town. (Before the ’20s, Fass told me, “that kind of leisure had not been common to married women.”)

Those domestic worries came through in pop-culture depictions of the sitter. In the midst of the 1960s sexual revolution, she was often portrayed as a temptress, seducing fathers when mom was away; in the ’70s, she started showing up in horror movies, trapped with a killer in the house and kids to protect—perhaps a way, Forman-Brunell suggests, to see her punished for her self-sufficiency or for the irresponsible behavior audiences seemed to imagine. None of that was likely helping sitters’ reputation, but parents still needed them. That’s when The Baby-Sitters Club , the ’80s book series about a group of tweens running a sitting business—and solving mysteries in their spare time—came to the PR rescue. The novels exemplified what Forman-Brunell calls the “supersitter” trend, portraying fun but well-behaved, competent girls: role models for kids, and also a comfort for nervous parents. Teens’ trustworthiness was a tug-of-war.

But that cultural battle has quieted. There’s little point in it now, perhaps, because actual teens may not be babysitting so much anymore. The field is hard to track precisely, because it’s so informal by definition, but sources told me that many parents today are looking for professionalized child care, or at least older and more experienced caregivers. Teens, meanwhile, are given few opportunities for responsibility—especially with the kind of training wheels that babysitting used to entail.

Read: Why adolescence feels so intense

The archetypal sitter lived just a few doors down. She was the daughter of your friends; she was the girl you’d been watching grow up for years. But Americans today tend to be less well acquainted with neighbors than they used to be, and they trust other people less in general . If you’re not familiar with the high-schooler on your block, you might not feel comfortable placing your children in her questionably capable hands. Even more than that: You might never connect in the first place.

Even if parents do know potential young sitters nearby, they may still hesitate to rely on them. In the past few decades, as “intensive parenting” has become a child-rearing ideal across classes, grown-ups have broadly begun to see kids as fragile and in need of constant oversight . Tweens or younger teens might not seem like comforting sources of protection—they might seem like children in need of watching themselves. As Fass pointed out, it didn’t used to be unusual for 12-year-olds to babysit. Now more than two-thirds of American parents think kids should be 12 or older before they’re even left home alone. Several states have guidelines issuing a similar age limit; in Illinois, kids legally can’t be left unattended until age 14.

The intensive-parenting approach isn’t just about physical safety; it’s also about ensuring kids’ future financial security, using every spare moment to “enrich” them with skills. Besen-Cassino found in her reporting that this was very much part of parents’ calculus when it came to their children’s care. Many families don’t want their kids wasting time sitting in front of the TV or even just playing, she told me; they want them learning, say, math or piano or another language. And if kids are spending time in scheduled activities led by adults, they don’t need a sitter.

The same trend means teens themselves are also likely to be preoccupied—too busy with SAT prep or Model UN to be babysitting. Indeed, teen-labor participation has been dropping for decades, driven in part by adolescents turning instead to academic pursuits and internships. (High-schooler employment rates rose slightly after 2020—perhaps partly because employers, strapped while emerging from pandemic lockdown, were more willing to accommodate teens’ hectic schedules—but remain lower than they were in the latter half of the 20th century .) Part-time employment used to be a milestone in many kids’ transition to adulthood. But today, the period between childhood and adulthood seems to be longer than ever—psychologists call it “extended adolescence.” Americans are getting married, having kids, and buying houses at older ages, and spending longer on education and career exploration beforehand. So teens don’t just seem unfit for babysitting; babysitting might also seem unfit for teens. It’s not the kind of thing you think to put on a résumé.

Of course, not every teen has the privilege of doing an unpaid internship rather than making money; not every family can afford to fill their kids’ time with tutoring or extracurriculars. But intensive parenting isn’t limited to the superrich; it was initially described as a middle-class phenomenon , and more recently it’s spread , at least as an aspiration, across classes. So while less wealthy families are particularly likely to rely on unpaid child care from relatives or friends, many other parents are scrambling to give their kids a leg up with activities—or, if they’re really rich, leaning also on au pairs or boarding schools. It’s unclear who exactly the clientele for the humble babysitter really is anymore.

The result is that babysitting today feels more like a symbol of a bygone American era than a normal part of how teens come of age. The glut of babysitting pop-culture content has thinned significantly; even the TV reboot of The Baby-Sitters Club , which was such a massive hit as a book series, was canceled in 2022 after two seasons. The creator, Rachel Shukert, told Vulture that she believes that was partly because Netflix marketed it to girls rather than to grown-ups: “A show like this has tremendous nostalgic potential,” she said. “But if you’re 35 and you loved the books … Netflix is not going to show The Baby-Sitters Club to you.” It doesn’t sound like it hit teens particularly hard, perhaps because the experience of babysitting isn’t relatable to them.

Or maybe it just didn’t hit a cultural nerve because our fears are evolving. The Baby-Sitters Club was a blueprint for girls becoming women in a time when people were anxious about them maturing the right way. But most of the main characters are 12 or 13 when the series begins; Mallory, initially one of the club’s charges, starts babysitting herself at 11. It might no longer seem like a coming-of-age narrative because people may be less likely to see 11-to-13-year-olds as coming of age at all—just as kids.

Read: Why don’t we teach people how to parent?

Teen babysitters still exist , but they’re facing a different field than they once might have—more structured and formal. A 2020 study found that sitters tended to prepare carefully for their role, taking safety courses and planning a slate of activities in advance—and parents were comforted by those displays of seriousness. When Besen-Cassino spoke with sitters for her research, she learned that they had used their free time not just to get CPR training or lifeguard certifications or driving lessons but also to take classes so they could offer to help kids learn math or music or sports. They advertised themselves, she told me, as “not just a babysitter but someone who can change the life of that child.”

Especially given that babysitting has long been undervalued and underpaid, it seems unfair that teen girls should have to make all that extra effort just to get their foot in the door. And yet, caregiving is serious work; the fact that parents are taking it seriously is warranted. For so long, it’s been treated as something girls and women do naturally, not as labor that requires skills and deserves fair compensation. If we acknowledge that babysitting is more than just a starter job, maybe it makes sense for adults to take it on.

But young people do need some opportunities for growth. Rebecca Raby, a professor of child and youth studies at Brock University, in Canada, told me that first jobs can be extremely formative, even empowering experiences. She’s found that many young babysitters have a sense of pride in their craft and their earning ability. In the liminal space of early teenhood—a time of feeling awkward, misunderstood, and largely powerless—having a job can grant you dignity. And to be a role model for a younger kid might be nothing short of profound.

Ideally, society could acknowledge the gravity of caregiving but also support the teens who want to do it—and some people are working toward just that. Margaret House, a coordinator for Oregon State University’s community-partnership program, runs a babysitting-training program through the youth-leadership organization 4-H. She teaches teens about child development but also how to impress wary parents: the dos and don’ts of being in someone else’s home, different parenting styles, how to talk about yourself in interviews. They discuss how this work can lead to a real career—working in a day-care center, teaching preschool, researching early childhood—and how they might include babysitting on a résumé. Still, she doesn’t forget that this work is about creating trust in communities. Sure, it takes a village to raise a child, she told me, but “there is no village.” So grown-ups have to build it themselves.

House does sometimes have trouble connecting her sitters to parents. Recently, she tried to do a meet and greet at the local library, and she remembers that only a couple of adults showed up. But she doesn’t doubt that there’s an audience out there. She reminds the teens to tell parents about any extra talents they have, yes, but she boosts them up regardless: “Parents might want someone who’s older and going to be able to teach them multiple languages or whatever.” But just by being present and attentive, they’re offering a valuable service. “So don’t shortchange yourself,” she tells them.

Families still need help caring for their kids. Teens still need money, and chances to practice responsibility. And neighbors could stand to trust one another more—to start building their village. That won’t look just like it did in 1950, but that’s for the best. Perhaps we’ll find a way to finally treat adolescents as just what they are: not children and not adults, not scary and not superhuman. Just young people who, with a bit of support, can be capable of a great deal.

the essay is dead

​When you buy a book using a link on this page, we receive a commission. Thank you for supporting The Atlantic.

  • Share full article

Advertisement

Supported by

Guest Essay

It’s Not You: Dating Apps Are Getting Worse

the essay is dead

By Magdalene J. Taylor

Ms. Taylor is a writer covering sex and culture.

“The golden age of dating apps is over,” a friend told me at a bar on Super Bowl Sunday. As we waited for our drinks, she and another friend swiped through Bumble and Hinge, hunting for new faces and likes. Across the bar were two young men: phones out, apps open, clearly doing the exact same thing. Never did the duos meet.

What’s lamentable here isn’t only that dating apps have become the de facto medium through which single people meet. Since 2019, three in 10 U.S. adults have reported using them, with that figure rising to roughly six in 10 for Americans under 50 who have never been married. Not only are people not meeting partners in bars or any of the once normal in-person venues — they’re barely meeting them on the apps, either.

Maybe most of us just aren’t as hot as we used to be. Maybe it’s time our inflated egos got knocked down a notch. Maybe the market of people still willing to put themselves out there in an attempt to date has gotten smaller. Or maybe the apps have functionally, intentionally gotten worse, as have our romantic prospects. The more they fail to help us form relationships, the more we’re forced to keep swiping — and paying.

The internet, where so many of us spend so much of our time, has not been spared from the decline in quality that seems to plague so much of consumer life. This phenomenon was described by the writer Cory Doctorow in a November 2022 blog post and is sometimes called “platform decay”: Tech platforms like Amazon, Reddit and X have declined in quality as they’ve expanded. These sites initially hooked consumers by being almost too good to be true, attempting to become essential one-stop shops within their respective spaces while often charging nothing, thanks to low interest rates and free-flowing venture capital funding . Now that we’re all locked in and that capital has dried up, those initial hooks have been walked back — and there’s nowhere else to go.

This is precisely what is happening with dating apps now, too, with much more urgent consequences. What’s worsening isn’t just the technological experience of online dating but also our ability to form meaningful, lasting connections offline.

The collapse of dating apps’ usability can be blamed on the paid subscription model and the near-monopoly these apps have over the dating world. While dozens of sites exist, most 20-something daters use the big three: Tinder, Hinge and Bumble. (Older people often gravitate toward Match.com or eHarmony.) All three sites offer a “premium” version users must pay for — according to a study conducted by Morgan Stanley , around a quarter of people on dating apps use these services, averaging out at under $20 a month. The purpose, many believe, is to keep them as paid users for as long as possible. Even if we hate it, even if it’s a cycle of diminishing returns, there is no real alternative.

In the early heyday of Tinder, the only limits on whom you could potentially match with were location, gender and age preferences. You might not have gotten a like back from someone you perceived to be out of your league, but at least you had the chance to swipe right. Today, however, many apps have pooled the people you’d most like to match with into a separate category (such as Hinge’s “Standouts” section), often only accessible to those who pay for premium features. And even if you do decide to sign up for them, many people find the idea of someone paying to match with them to be off-putting anyway.

“If I don’t pay, I don’t date,” a friend in his 30s told me. He spends around $50 a month on premium dating app subscriptions and digital “roses” to grab the attention of potential matches. He’s gone on 65 dates over the last year, he said. None have stuck, so he keeps paying. “Back in the day, I never would have imagined paying for OKCupid,” he said.

Yet shares (Bumble’s stock price has fallen from about $75 to about $11 since its I.P.O.) and user growth have fallen , so the apps have more aggressively rolled out new premium models. In September 2023, Tinder released a $500 per month plan. But the economics of dating apps may not add up .

On Valentine’s Day this year, Match Group — which owns Tinder, Hinge, Match.com, OKCupid and many other dating apps — was sued in a proposed class action lawsuit asserting that the company gamifies its platforms “to transform users into gamblers locked in a search for psychological rewards that Match makes elusive on purpose.” This is in contrast to one of the group’s ad slogans that promotes Hinge as “designed to be deleted.”

People are reporting similar complaints across the apps — even when they aren’t taking the companies to court. Pew Research shows that over the last several years, the percentage of dating app users across demographics who feel dissatisfied with the apps has risen . Just under half of all users report feeling somewhat to very negative about online dating, with the highest rates coming from women and those who don’t pay for premium features. Notably, there is a gender divide: Women feel overwhelmed by messages, while men are underwhelmed by the lack thereof.

With seemingly increasing frequency, people are going to sites like TikTok , Reddit and X to complain about what they perceive to be a dwindling group of eligible people to meet on apps. Commonly, complaints are targeted toward these monthly premium fees, in contrast to the original free experience. Dating has always cost money, but there’s something uniquely galling about the way apps now function. Not only does it feel like the apps are the only way to meet someone, just getting in the door can also comes with a surcharge.

Perhaps dating apps once seemed too good to be true because they were. We never should have been exposed to what the apps originally provided: the sense that the dating pool is some unlimited, ever-increasing-in-quality well of people. Even if the apps are not systematically getting worse but rather you’ve just spent the last few years as a five thinking you should be paired with eights, the apps have nonetheless fundamentally skewed the dating world and our perception of it. We’ve distorted our understanding of how we’d organically pair up — and forgotten how to actually meet people in the process.

Our romantic lives are not products. They should not be subjected to monthly subscription fees, whether we’re the ones paying or we’re the ones people are paying for. Algorithmic torture may be happening everywhere, but the consequences of feeling like we are technologically restricted from finding the right partner are much heavier than, say, being duped into buying the wrong direct-to-consumer mattress. Dating apps treat people like commodities, and encourage us to treat others the same. We are not online shopping. We are looking for people we may potentially spend our lives with.

There is, however, some push toward a return to the real that could save us from this pattern. New in-person dating meet-up opportunities and the return of speed dating events suggests app fatigue is spreading. Maybe we’ll start meeting at bars again — rather than simply swiping through the apps while holding a drink.

Have you ditched dating apps for a new way to meet people, or are you still swiping left?

Opinion wants to hear your story.

Magdalene J. Taylor (@ magdajtaylor ) is a writer covering sex and culture. She writes the newsletter “ Many Such Cases .”

The Times is committed to publishing a diversity of letters to the editor. We’d like to hear what you think about this or any of our articles. Here are some tips . And here’s our email: [email protected] .

Follow the New York Times Opinion section on Facebook , Instagram , TikTok , X and Threads .

IMAGES

  1. ⇉Is the Author Really Dead? Essay Example

    the essay is dead

  2. The Personal Essay Isn’t Dead. It’s Just No Longer White · The Walrus

    the essay is dead

  3. Essay about Death

    the essay is dead

  4. Essay about Death

    the essay is dead

  5. The College Essay Is Dead

    the essay is dead

  6. Of Death Essay, Of Death Essay Line by Line Explanation, Of Death Essay

    the essay is dead

VIDEO

  1. The Walking Dead is Unironically Great

  2. How Kevin Feige KILLED the MCU

  3. Video Essay of the Dead

  4. The Brutality Of DEAD SNOW

  5. Why "Conquer" Is the Most Underrated Finale in the Series

  6. Why The MCU needs to STOP

COMMENTS

  1. Will ChatGPT Kill the Student Essay?

    The College Essay Is Dead. Nobody is prepared for how AI will transform academia. By Stephen Marche. Paul Spella / The Atlantic; Getty. December 6, 2022. Suppose you are a professor of pedagogy ...

  2. ChatGPT won't kill the college essay.

    But the college essay isn't doomed, and A.I. like ChatGPT won't replace flesh and blood writers. ... (On Tuesday, Marche wrote an article for the Atlantic titled "The College Essay Is Dead ...

  3. The College Essay Is Still Very Much Alive

    Stephen Marche's December 6th article for The Atlantic is a prominent example of the sensationalized response to ChatGPT, in which Marche boldly argues that with the innovations in AI, "the ...

  4. ChatGPT Will End High-School English

    Read: The college essay is dead. I've also long held, for those who are interested in writing, ... Whether someone is writing a five-paragraph essay or a 500-page book, these are the building ...

  5. Is the college essay dead? AI apps write scripts, speeches ...

    Is the college essay dead? AI apps write scripts, speeches and so much more ... an essay in The Atlantic suggested that artificial intelligence technology makes it easy for a program to produce a ...

  6. Opinion: The college essay is not dead

    Let me dispel any notion that the college essay is dead or that this new technology will end my career as a writing teacher. Contrary to popular belief, we writing teachers believe more in the ...

  7. AI and the Death of the College Essay

    The Atlantic's December issue has an essay "The College Essay Is Dead: Nobody is prepared for how AI will transform academia" by Stephen Marche that says that AI is going to make the college essay irrelevant. I say good riddance. I write this as a former English and Adult Basic Education Community College teacher.

  8. 'The college essay is dead': Academics react to ChatGPT

    ChatGPT has made quite a stir in academic circles. "The college essay is dead," Stephen Marche states in an article for The Atlantic. "Nobody is prepared for how AI will transform academia ...

  9. Here's how teachers can foil ChatGPT: Handwritten essays

    "The College Essay Is Dead," the Atlantic declared. That's unlikely. There are some obvious workarounds. For example, even laptop-equipped students wouldn't benefit from ChatGPT if they ...

  10. Is the Essay Dead?

    Is the Essay Dead? By Heather Horn. March 30, 2010. Share. Save. This article is from the archive of our partner . "The word essay has been hijacked, blasphemed, forced into service for the enemy."

  11. AI Can Save Writing by Killing "The College Essay"

    In their essays, some students reflected on the usefulness of GPT-3 as a brainstorming tool. ... Marche does eventually move on from "the college essay is dead" argument by the end of his commentary, and he discusses how GPT-3 and similar natural language processing technologies will have a lot of value to humanities scholars. Academics ...

  12. No, AI chatbots haven't killed the college essay. Here's why. (Opinion)

    Opinion: No, AI chatbots haven't killed the college essay. Here's why. By Burke Nixon Jan 1, 2023. Viviana Zavala works on a lesson during Maritza Grajeda's fifth-grade bilingual language arts ...

  13. The American Scholar: Words, Words, Words

    The subtitle to Marche's essay is: "The College Essay is Dead." Perhaps because Marche no longer teaches, he does not realize that the obit is a bit late: the college essay died years ago. During my three decades of teaching at a public university, I have encountered a dwindling number of students who can write a declarative sentence ...

  14. The College Essay Is Dead

    The College Essay Is Dead Nobody is prepared for how AI will transform academia. Summary: The impact of the recent and sudden improvements in AI text-generation systems, driven by large language models, will challenge and transform the humanities, interactions between disciplines, and higher education more generally.

  15. The College Essay Is Dead

    The College Essay Is Dead. Nobody is prepared for how AI will transform academia. Suppose you are a professor of pedagogy, and you assign an essay on learning styles. A student hands in an essay with the following opening paragraph: The construct of "learning styles" is problematic because it fails to account for the processes ….

  16. The College Essay Is Dead

    The College Essay Is Dead - The Atlantic. Interesting article on the ways in which science and the humanities continue to diverge while also offering an interesting take on the possibilities of AI being able to fill in some literary "gaps" that may or may not have potential uses to the future of the field. Thanks for sharing this, here's the ...

  17. Do you guys think the personal essay is dead? : r/writing

    I'd argue, for example, that the boom in personal essay blogs was also parallel to a huge boom in vlog-style videos, which could be about women's stories, but also about everything else. And I mean everything, really. She's placed in that particular niche and positions those essays as ubiquitous, which is a bit naive. Still the points stands.

  18. The College Essay Is Dead. Nobody is prepared for how AI will ...

    My problem with essay exams is, depending on the class, time pressures turn me into a shitty writer. I love doing a well researched paper, when I can sit down, take my time, and enjoy the process. I can reword sections as many times as I want, hell even completely pivot the structure/argument of my paper halfway through when I make new connection/discoveries.Testing a student's skill at ...

  19. Is the Five-Paragraph Essay Dead?

    Dennis Allen doesn't think the five-paragraph essay is dead. In the years before his retirement in May from West Virginia University, the Professor Emeritus did not assign "strict" five-paragraph essays. He contends that the five-paragraph essay may be dead in the literal sense because instructors of college composition classes don't ...

  20. With ChatGPT, is the college essay dead?

    15,906. 5,562. This article reminded me of the current Fun with ChatGPT thread in General Discussion: The College Essay Is Dead ( The Atlantic) Suppose you are a professor of pedagogy, and you assign an essay on learning styles. A student hands in an essay with the following opening paragraph: The construct of "learning styles" is ...

  21. The Essay is Dead, Long Live the Essay!

    The Essay is Dead, Long Live the Essay! The hottest topic of conversation in teachers' staff rooms around the world this past week has probably been how Chat GPT s hocked teachers! The computer programme writes essays and is able to answer advanced, high-level questions.

  22. After a writer expressed sympathy for Israelis in an essay, all hell

    A Jewish writer described her attempts after Oct. 7 to find empathy across the Israeli-Palestinian divide. Her essay triggered mass resignations and a retraction.

  23. The College Essay Is Dead : r/atlanticdiscussions

    Sharples's intent was to urge educators to "rethink teaching and assessment" in light of the technology, which he said "could become a gift for student cheats, or a powerful teaching assistant, or a tool for creativity.". Essay generation is neither theoretical nor futuristic at this point.

  24. Prompt Engineering Embraces New Essay-Compression Technique ...

    A new prompting technique in generative AI to compress essays and other text is handy and a good addition to prompt engineering skillsets. ... The brave men, living and dead, who struggled here ...

  25. From the Rubble of 'Be'eri': A Kibbutz Mourns Its Dead ...

    From the Rubble of 'Be'eri': a Kibbutz Mourns Its Dead and Vows to Rebuild | Photo Essay TheWrap gets a rare glimpse inside a devastated community five months after a murderous rampage by ...

  26. Kibbutz Be'eri Mourns Its Dead, Rebuilds

    From the Rubble of 'Be'eri': A Kibbutz Mourns Its Dead and Vows to Rebuild | Photo Essay. Sharon Shani stands amid the ruins of the elementary school in Kibbutz Be'eri, taken over by Hamas ...

  27. The College Essay Is Dead. Nobody is prepared for how AI will ...

    The College Essay Is Dead. Nobody is prepared for how AI will transform academia. : r/Futurology. The College Essay Is Dead. Nobody is prepared for how AI will transform academia. The following submission statement was provided by u/mossadnik : The world of generative AI is progressing furiously.

  28. Neil Perry Dead Poets Society: [Essay Example], 709 words

    This essay examines Neil Perry's character arc in Dead Poets Society, focusing on his struggle for authenticity and self-expression, and the broader implications of his story for understanding the complexities of adolescent development and the importance of supportive educational environments.

  29. Whatever Happened to Teen Babysitters?

    Babysitting used to be both a job and a rite of passage. For countless American teens, and especially teen girls, it was a tentative step toward adulthood—responsibility, but with guardrails.

  30. Opinion

    Ms. Taylor is a writer covering sex and culture. "The golden age of dating apps is over," a friend told me at a bar on Super Bowl Sunday. As we waited for our drinks, she and another friend ...