chat gpt write college essay

Choose Your Test

Sat / act prep online guides and tips, can you use chatgpt for your college essay.

College Admissions , College Essays

ChatGPT has become a popular topic of conversation since its official launch in November 2022. The artificial intelligence (AI) chatbot can be used for all sorts of things, like having conversations, answering questions, and even crafting complete pieces of writing.

If you’re applying for college, you might be wondering about ChatGPT college admissions’ potential.  Should you use a ChatGPT college essay in your application ? 

By the time you finish reading this article, you’ll know much more about ChatGPT, including how students can use it responsibly and if it’s a good idea to use ChatGPT on college essays . We’ll answer all your questions, like:

• What is ChatGPT and why are schools talking about it?
• What are the good and bad aspects of ChatGPT?
• Should you use ChatGPT for college essays and applications?
• Can colleges detect ChatGPT?
• Are there other tools and strategies that students can use, instead?

We’ve got a lot to cover, so let’s get started!

Schools and colleges are worried about how new AI technology affects how students learn. (Don't worry. Robots aren't replacing your teachers...yet.)

What Is ChatGPT and Why Are Schools Talking About It?

ChatGPT (short for “Chat Generative Pre-trained Transformer”) is a chatbot created by OpenAI , an artificial intelligence research company. ChatGPT can be used for various tasks, like having human-like conversations, answering questions, giving recommendations, translating words and phrases—and writing things like essays. 

In order to do this, ChatGPT uses a neural network that’s been trained on thousands of resources to predict relationships between words. When you give ChatGPT a task, it uses that knowledge base to interpret your input or query. It then analyzes its data banks to predict the combinations of words that will best answer your question. 

So while ChatGPT might seem like it’s thinking, it’s actually pulling information from hundreds of thousands of resources , then answering your questions by looking for patterns in that data and predicting which words come next.  

Why Schools Are Concerned About ChatGPT

Unsurprisingly, schools are worried about ChatGPT and its misuse, especially in terms of academic dishonesty and plagiarism . Most schools, including colleges, require students’ work to be 100% their own. That’s because taking someone else’s ideas and passing them off as your own is stealing someone else’s intellectual property and misrepresenting your skills. 

The problem with ChatGPT from schools’ perspective is that it does the writing and research for you, then gives you the final product. In other words, you’re not doing the work it takes to complete an assignment when you’re using ChatGPT , which falls under schools’ plagiarism and dishonesty policies.  

Colleges are also concerned with how ChatGPT will negatively affect students’ critical thinking, research, and writing skills . Essays and other writing assignments are used to measure students’ mastery of the material, and if students submit ChatGPT college essays, teachers will just be giving feedback on an AI’s writing…which doesn’t help the student learn and grow. 

Beyond that, knowing how to write well is an important skill people need to be successful throughout life. Schools believe that if students rely on ChatGPT to write their essays, they’re doing more than just plagiarizing—they’re impacting their ability to succeed in their future careers. 

Many Schools Have Already Banned ChatGPT

Schools have responded surprisingly quickly to AI use, including ChatGPT. Worries about academic dishonesty, plagiarism, and mis/disinformation have led many high schools and colleges to ban the use of ChatGPT . Some schools have begun using AI-detection software for assignment submissions, and some have gone so far as to block students from using ChatGPT on their internet networks. 

It’s likely that schools will begin revising their academic honesty and plagiarism policies to address the use of AI tools like ChatGPT. You’ll want to stay up-to-date with your schools’ policies. 

ChatGPT is pretty amazing...but it's not a great tool for writing college essays. Here's why.

ChatGPT: College Admissions and Entrance Essays

College admissions essays—also called personal statements—ask students to explore important events, experiences, and ideas from their lives. A great entrance essay will explain what makes you you !  

ChatGPT is a machine that doesn’t know and can’t understand your experiences. That means using ChatGPT to write your admissions essays isn’t just unethical. It actually puts you at a disadvantage because ChatGPT can’t adequately showcase what it means to be you. 

Let’s take a look at four ways ChatGPT negatively impacts college admissions essays.

#1: ChatGPT Lacks Insight

We recommend students use u nexpected or slightly unusual topics because they help admissions committees learn more about you and what makes you unique. The chat bot doesn’t know any of that, so nothing ChatGPT writes can’t accurately reflect your experience, passions, or goals for the future. 

Because ChatGPT will make guesses about who you are, it won’t be able to share what makes you unique in a way that resonates with readers. And since that’s what admissions counselors care about, a ChatGPT college essay could negatively impact an otherwise strong application.  

#2: ChatGPT Might Plagiarize 

Writing about experiences that many other people have had isn’t a very strong approach to take for entrance essays . After all, you don’t want to blend in—you want to stand out! 

If you write your essay yourself and include key details about your past experiences and future goals, there’s little risk that you’ll write the same essay as someone else. But if you use ChatGPT—who’s to say someone else won’t, too? Since ChatGPT uses predictive guesses to write essays, there’s a good chance the text it uses in your essay already appeared in someone else’s.  

Additionally, ChatGPT learns from every single interaction it has. So even if your essay isn’t plagiarized, it’s now in the system. That means the next person who uses ChatGPT to write their essay may end up with yours. You’ll still be on the hook for submitting a ChatGPT college essay, and someone else will be in trouble, too.

#3: ChatGPT Doesn’t Understand Emotion 

Keep in mind that ChatGPT can’t experience or imitate emotions, and so its writing samples lack, well, a human touch ! 

A great entrance essay will explore experiences or topics you’re genuinely excited about or proud of . This is your chance to show your chosen schools what you’ve accomplished and how you’ll continue growing and learning, and an essay without emotion would be odd considering that these should be real, lived experiences and passions you have!

#4: ChatGPT Produced Mediocre Results

If you’re still curious what would happen if you submitted a ChatGPT college essay with your application, you’re in luck. Both Business Insider and Forbes asked ChatGPT to write a couple of college entrance essays, and then they sent them to college admissions readers to get their thoughts. 

The readers agreed that the essays would probably pass as being written by real students—assuming admissions committees didn’t use AI detection software—but that they both were about what a “very mediocre, perhaps even a middle school, student would produce.” The admissions professionals agreed that the essays probably wouldn’t perform very well with entrance committees, especially at more selective schools.  

That’s not exactly the reaction you want when an admission committee reads your application materials! So, when it comes to ChatGPT college admissions, it’s best to steer clear and write your admission materials by yourself. 

Can Colleges Detect ChatGPT?

We’ve already explained why it’s not a great idea to use ChatGPT to write your college essays and applications , but you may still be wondering: can colleges detect ChatGPT? 

In short, yes, they can! 

Software Can Detect ChatGPT

As technology improves and increases the risk of academic dishonesty, plagiarism, and mis/disinformation, software that can detect such technology is improving, too. For instance, OpenAI, the same company that built ChatGPT, is working on a text classifier that can tell the difference between AI-written text and human-written text .  

Turnitin, one of the most popular plagiarism detectors used by high schools and universities, also recently developed the AI Innovation Lab —a detection software designed to flag submissions that have used AI tools like ChatGPT. Turnitin says that this tool works with 98% confidence in detecting AI writing. 

Plagiarism and AI companies aren’t the only ones interested in AI-detection software. A 22-year old computer science student at Princeton created an app to detect ChatGPT writing, called Zero GPT. This software works by measuring the complexity of ideas and variety of sentence structures.  

Human Readers Can Detect ChatGPT 

It’s also worth keeping in mind that teachers can spot the use of ChatGPT themselves , even if it isn’t confirmed by a software detector. For example, if you’ve turned in one or two essays to your teacher already, they’re probably familiar with your unique writing style. If you submit a college essay draft essay that uses totally different vocabulary, sentence structures, and figures of speech, your teacher will likely take note.

Additionally , admissions committees and readers may be able to spot ChatGPT writing, too. ChatGPT (and AI writing, in general) uses more simplistic sentence structures with less variation, so that could make it easier to tell if you’ve submitted a ChatGPT college essay. These professionals also read thousands of essays every year, which means they know what a typical essay reads like. You want your college essay to catch their attention…but not because you used AI software! 

If you use ChatGPT responsibly, you can be as happy as these kids.

Pros and Cons of ChatGPT: College Admissions Edition

ChatGPT is a brand new technology, which means we’re still learning about the ways it can benefit us. It’s important to think about the pros and the cons to any new tool …and that includes artificial intelligence!

Let’s look at some of the good—and not-so-good—aspects of ChatGPT below. 

ChatGPT: The Good

It may seem like we’re focused on just the negatives of using ChatGPT in this article, but we’re willing to admit that the chatbot isn’t all bad. In fact, it can be a very useful tool for learning if used responsibly !

Like we already mentioned, students shouldn’t use ChatGPT to write entire essays or assignments. They can use it, though, as a learning tool alongside their own critical thinking and writing skills.

Students can use ChatGPT responsibly to:

• Learn more about a topic . It’s a great place to get started for general knowledge and ideas about most subjects.
• Find reputable and relevant sources on a topic. Students can ask ChatGPT for names and information about leading scholars, relevant websites and databases, and more. 
• Brainstorm ideas for assignments. Students can share the ideas they already have with ChatGPT, and in return, the chatbot can suggest ideas for further exploration and even organization of their points.
• Check work (that they’ve written themselves!) for errors or cla rity. This is similar to how spell- and grammar-checking software is used. ChatGPT may be even better than some competitors for this, because students can actually ask ChatGPT to explain the errors and their solutions—not just to fix them. 

Before you use ChatGPT—even for the tasks mentioned above—you should talk to your teacher or school about their AI and academic dishonesty policies. It’s also a good idea to include an acknowledgement that you used ChatGPT with an explanation of its use. 

This guy made some bad decisions using ChatGPT. Don't be this guy.

ChatGPT: The Bad

The first model of ChatGPT (GPT-3.5) was formally introduced to the public in November 2022, and the newer model (GPT-4) in March 2023. So, it’s still very new and there’s a lot of room for improvement .  

There are many misconceptions about ChatGPT. One of the most extreme is that the AI is all-knowing and can make its own decisions. Another is that ChatGPT is a search engine that, when asked a question, can just surf the web for timely, relevant resources and give you all of that information. Both of these beliefs are incorrect because ChatGPT is limited to the information it’s been given by OpenAI . 

Remember how the ‘PT’ in ChatGPT stands for “Pre-trained”? That means that every time OpenAI gives ChatGPT an update, it’s given more information to work with (and so it has more information to share with you). In other words, it’s “trained” on information so it can give you the most accurate and relevant responses possible—but that information can be limited and biased . Ultimately, humans at OpenAI decide what pieces of information to share with ChatGPT, so it’s only as accurate and reliable as the sources it has access to.

For example, if you were to ask ChatGPT-3.5 what notable headlines made the news last week, it would respond that it doesn’t have access to that information because its most recent update was in September 2021!

You’re probably already familiar with how easy it can be to come across misinformation, misleading and untrue information on the internet. Since ChatGPT can’t tell the difference between what is true and what isn’t, it’s up to the humans at OpenAI to make sure only accurate and true information is given to the chatbot . This leaves room for human error , and users of ChatGPT have to keep that in mind when using and learning from the chatbot.

These are just the most obvious problems with ChatGPT. Some other problems with the chatbot include:

• A lack of common sense. ChatGPT can create seemingly sensical responses to many questions and topics, but it doesn’t have common sense or complete background knowledge.
• A lack of empathy. ChatGPT doesn’t have emotions, so it can’t understand them, either. 
• An inability to make decisions or problem solve . While the chatbot can complete basic tasks like answering questions or giving recommendations, it can’t solve complex tasks. 

While there are some great uses for ChatGPT, it’s certainly not without its flaws.

Our bootcamp can help you put together amazing college essays that help you get into your dream schools—no AI necessary.

What Other Tools and Strategies Can Help Students Besides ChatGPT?

While it’s not a good idea to use ChatGPT for college admissions materials, it’s not the only tool available to help students with college essays and assignments. 

One of the best strategies students can use to write good essays is to make sure they give themselves plenty of time for the assignment. The writing process includes much more than just drafting! Having time to brainstorm ideas, write out a draft, revise it for clarity and completeness, and polish it makes for a much stronger essay. 

Teachers are another great resource students can use, especially for college application essays. Asking a teacher (or two!) for feedback can really help students improve the focus, clarity, and correctness of an essay. It’s also a more interactive way to learn—being able to sit down with a teacher to talk about their feedback can be much more engaging than using other tools. 

Using expert resources during the essay writing process can make a big difference, too. Our article outlines a complete list of strategies for students writing college admission essays. It breaks down what the Common Application essay is, gives tips for choosing the best essay topic, offers strategies for staying focused and being specific, and more.  

You can also get help from people who know the college admissions process best, like former admissions counselors. PrepScholar’s Admissions Bootcamp guides you through the entire application process , and you’ll get insider tips and tricks from real-life admissions counselors that’ll make your applications stand out. Even better, our bootcamp includes step-by-step essay writing guidance , so you can get the help you need to make sure your essay is perfect.  

If you’re hoping for more technological help, Grammarly is another AI tool that can check writing for correctness. It can correct things like misused and misspelled words and grammar mistakes, and it can improve your tone and style. 

It’s also widely available across multiple platforms through a Windows desktop app, an Android and iOS app, and a Google Chrome extension. And since Grammarly just checks your writing without doing any of the work for you, it’s totally safe to use on your college essays. 

The Bottom Line: ChatGPT College Admissions and Essays

ChatGPT will continue to be a popular discussion topic as it continues evolving. You can expect your chosen schools to address ChatGPT and other AI tools in their academic honesty and plagiarism policies in the near future—and maybe even to restrict or ban the use of the chatbot for school admissions and assignments.

As AI continues transforming, so will AI-detection. The goal is to make sure that AI is used responsibly by students so that they’re avoiding plagiarism and building their research, writing, and critical thinking skills. There are some great uses for ChatGPT when used responsibly, but you should always check with your teachers and schools beforehand.

ChatGPT’s “bad” aspects still need improving, and that’s going to take some time.Be aware that the chatbot isn’t even close to perfect, and it needs to be fact-checked just like other sources of information.

Similarly to other school assignments, don’t submit a ChatGPT college essay for college applications, either. College entrance essays should outline unique and interesting personal experiences and ideas, and those can only come from you.  

Just because ChatGPT isn’t a good idea doesn’t mean there aren’t resources to help you put together a great college essay. There are many other tools and strategies you can use instead of ChatGPT , many of which have been around for longer and offer better feedback. 

What’s Next?

Ready to write your college essays the old-fashioned way? Start here with our comprehensive guide to the admissions essays. 

Most students have to submit essays as part of their Common Application . Here's a complete breakdown of the Common App prompts —and how to answer them. 

The most common type of essay answers the "why this college?" prompt. We've got an expert breakdown that shows you how to write a killer response , step by step. 

Ashley Sufflé Robinson has a Ph.D. in 19th Century English Literature. As a content writer for PrepScholar, Ashley is passionate about giving college-bound students the in-depth information they need to get into the school of their dreams.

Ask a Question Below

Have any questions about this article or other topics? Ask below and we'll reply!

Improve With Our Famous Guides

• For All Students

The 5 Strategies You Must Be Using to Improve 160+ SAT Points

How to Get a Perfect 1600, by a Perfect Scorer

Series: How to Get 800 on Each SAT Section:

Score 800 on SAT Math

Score 800 on SAT Reading

Score 800 on SAT Writing

Series: How to Get to 600 on Each SAT Section:

Score 600 on SAT Math

Score 600 on SAT Reading

Score 600 on SAT Writing

Free Complete Official SAT Practice Tests

What SAT Target Score Should You Be Aiming For?

15 Strategies to Improve Your SAT Essay

The 5 Strategies You Must Be Using to Improve 4+ ACT Points

How to Get a Perfect 36 ACT, by a Perfect Scorer

Series: How to Get 36 on Each ACT Section:

36 on ACT English

36 on ACT Math

36 on ACT Reading

36 on ACT Science

Series: How to Get to 24 on Each ACT Section:

24 on ACT English

24 on ACT Math

24 on ACT Reading

24 on ACT Science

What ACT target score should you be aiming for?

ACT Vocabulary You Must Know

ACT Writing: 15 Tips to Raise Your Essay Score

How to Get Into Harvard and the Ivy League

How to Get a Perfect 4.0 GPA

How to Write an Amazing College Essay

What Exactly Are Colleges Looking For?

Is the ACT easier than the SAT? A Comprehensive Guide

Should you retake your SAT or ACT?

When should you take the SAT or ACT?

Stay Informed

Get the latest articles and test prep tips!

Looking for Graduate School Test Prep?

Check out our top-rated graduate blogs here:

GRE Online Prep Blog

GMAT Online Prep Blog

TOEFL Online Prep Blog

Holly R. "I am absolutely overjoyed and cannot thank you enough for helping me!”

Celebrating 150 years of Harvard Summer School. Learn about our history.

Should I Use ChatGPT to Write My Essays?

Everything high school and college students need to know about using — and not using — ChatGPT for writing essays.

Jessica A. Kent

ChatGPT is one of the most buzzworthy technologies today.

In addition to other generative artificial intelligence (AI) models, it is expected to change the world. In academia, students and professors are preparing for the ways that ChatGPT will shape education, and especially how it will impact a fundamental element of any course: the academic essay.

Students can use ChatGPT to generate full essays based on a few simple prompts. But can AI actually produce high quality work, or is the technology just not there yet to deliver on its promise? Students may also be asking themselves if they should use AI to write their essays for them and what they might be losing out on if they did.

AI is here to stay, and it can either be a help or a hindrance depending on how you use it. Read on to become better informed about what ChatGPT can and can’t do, how to use it responsibly to support your academic assignments, and the benefits of writing your own essays.

What is Generative AI?

Artificial intelligence isn’t a twenty-first century invention. Beginning in the 1950s, data scientists started programming computers to solve problems and understand spoken language. AI’s capabilities grew as computer speeds increased and today we use AI for data analysis, finding patterns, and providing insights on the data it collects.

But why the sudden popularity in recent applications like ChatGPT? This new generation of AI goes further than just data analysis. Instead, generative AI creates new content. It does this by analyzing large amounts of data — GPT-3 was trained on 45 terabytes of data, or a quarter of the Library of Congress — and then generating new content based on the patterns it sees in the original data.

It’s like the predictive text feature on your phone; as you start typing a new message, predictive text makes suggestions of what should come next based on data from past conversations. Similarly, ChatGPT creates new text based on past data. With the right prompts, ChatGPT can write marketing content, code, business forecasts, and even entire academic essays on any subject within seconds.

But is generative AI as revolutionary as people think it is, or is it lacking in real intelligence?

The Drawbacks of Generative AI

It seems simple. You’ve been assigned an essay to write for class. You go to ChatGPT and ask it to write a five-paragraph academic essay on the topic you’ve been assigned. You wait a few seconds and it generates the essay for you!

But ChatGPT is still in its early stages of development, and that essay is likely not as accurate or well-written as you’d expect it to be. Be aware of the drawbacks of having ChatGPT complete your assignments.

It’s not intelligence, it’s statistics

One of the misconceptions about AI is that it has a degree of human intelligence. However, its intelligence is actually statistical analysis, as it can only generate “original” content based on the patterns it sees in already existing data and work.

It “hallucinates”

Generative AI models often provide false information — so much so that there’s a term for it: “AI hallucination.” OpenAI even has a warning on its home screen , saying that “ChatGPT may produce inaccurate information about people, places, or facts.” This may be due to gaps in its data, or because it lacks the ability to verify what it’s generating. 

It doesn’t do research  

If you ask ChatGPT to find and cite sources for you, it will do so, but they could be inaccurate or even made up.

This is because AI doesn’t know how to look for relevant research that can be applied to your thesis. Instead, it generates content based on past content, so if a number of papers cite certain sources, it will generate new content that sounds like it’s a credible source — except it likely may not be.

There are data privacy concerns

When you input your data into a public generative AI model like ChatGPT, where does that data go and who has access to it? 

Prompting ChatGPT with original research should be a cause for concern — especially if you’re inputting study participants’ personal information into the third-party, public application. 

JPMorgan has restricted use of ChatGPT due to privacy concerns, Italy temporarily blocked ChatGPT in March 2023 after a data breach, and Security Intelligence advises that “if [a user’s] notes include sensitive data … it enters the chatbot library. The user no longer has control over the information.”

It is important to be aware of these issues and take steps to ensure that you’re using the technology responsibly and ethically. 

It skirts the plagiarism issue

AI creates content by drawing on a large library of information that’s already been created, but is it plagiarizing? Could there be instances where ChatGPT “borrows” from previous work and places it into your work without citing it? Schools and universities today are wrestling with this question of what’s plagiarism and what’s not when it comes to AI-generated work.

To demonstrate this, one Elon University professor gave his class an assignment: Ask ChatGPT to write an essay for you, and then grade it yourself. 

“Many students expressed shock and dismay upon learning the AI could fabricate bogus information,” he writes, adding that he expected some essays to contain errors, but all of them did. 

His students were disappointed that “major tech companies had pushed out AI technology without ensuring that the general population understands its drawbacks” and were concerned about how many embraced such a flawed tool.

Explore Our High School Programs

How to Use AI as a Tool to Support Your Work

As more students are discovering, generative AI models like ChatGPT just aren’t as advanced or intelligent as they may believe. While AI may be a poor option for writing your essay, it can be a great tool to support your work.

Generate ideas for essays

Have ChatGPT help you come up with ideas for essays. For example, input specific prompts, such as, “Please give me five ideas for essays I can write on topics related to WWII,” or “Please give me five ideas for essays I can write comparing characters in twentieth century novels.” Then, use what it provides as a starting point for your original research.

Generate outlines

You can also use ChatGPT to help you create an outline for an essay. Ask it, “Can you create an outline for a five paragraph essay based on the following topic” and it will create an outline with an introduction, body paragraphs, conclusion, and a suggested thesis statement. Then, you can expand upon the outline with your own research and original thought.

Generate titles for your essays

Titles should draw a reader into your essay, yet they’re often hard to get right. Have ChatGPT help you by prompting it with, “Can you suggest five titles that would be good for a college essay about [topic]?”

The Benefits of Writing Your Essays Yourself

Asking a robot to write your essays for you may seem like an easy way to get ahead in your studies or save some time on assignments. But, outsourcing your work to ChatGPT can negatively impact not just your grades, but your ability to communicate and think critically as well. It’s always the best approach to write your essays yourself.

Create your own ideas

Writing an essay yourself means that you’re developing your own thoughts, opinions, and questions about the subject matter, then testing, proving, and defending those thoughts. 

When you complete school and start your career, projects aren’t simply about getting a good grade or checking a box, but can instead affect the company you’re working for — or even impact society. Being able to think for yourself is necessary to create change and not just cross work off your to-do list.

Building a foundation of original thinking and ideas now will help you carve your unique career path in the future.

Develop your critical thinking and analysis skills

In order to test or examine your opinions or questions about a subject matter, you need to analyze a problem or text, and then use your critical thinking skills to determine the argument you want to make to support your thesis. Critical thinking and analysis skills aren’t just necessary in school — they’re skills you’ll apply throughout your career and your life.

Improve your research skills

Writing your own essays will train you in how to conduct research, including where to find sources, how to determine if they’re credible, and their relevance in supporting or refuting your argument. Knowing how to do research is another key skill required throughout a wide variety of professional fields.

Learn to be a great communicator

Writing an essay involves communicating an idea clearly to your audience, structuring an argument that a reader can follow, and making a conclusion that challenges them to think differently about a subject. Effective and clear communication is necessary in every industry.

Be impacted by what you’re learning about : 

Engaging with the topic, conducting your own research, and developing original arguments allows you to really learn about a subject you may not have encountered before. Maybe a simple essay assignment around a work of literature, historical time period, or scientific study will spark a passion that can lead you to a new major or career.

Resources to Improve Your Essay Writing Skills

While there are many rewards to writing your essays yourself, the act of writing an essay can still be challenging, and the process may come easier for some students than others. But essay writing is a skill that you can hone, and students at Harvard Summer School have access to a number of on-campus and online resources to assist them.

Students can start with the Harvard Summer School Writing Center , where writing tutors can offer you help and guidance on any writing assignment in one-on-one meetings. Tutors can help you strengthen your argument, clarify your ideas, improve the essay’s structure, and lead you through revisions. 

The Harvard libraries are a great place to conduct your research, and its librarians can help you define your essay topic, plan and execute a research strategy, and locate sources. 

Finally, review the “ The Harvard Guide to Using Sources ,” which can guide you on what to cite in your essay and how to do it. Be sure to review the “Tips For Avoiding Plagiarism” on the “ Resources to Support Academic Integrity ” webpage as well to help ensure your success.

Sign up to our mailing list to learn more about Harvard Summer School

The Future of AI in the Classroom

ChatGPT and other generative AI models are here to stay, so it’s worthwhile to learn how you can leverage the technology responsibly and wisely so that it can be a tool to support your academic pursuits. However, nothing can replace the experience and achievement gained from communicating your own ideas and research in your own academic essays.

About the Author

Jessica A. Kent is a freelance writer based in Boston, Mass. and a Harvard Extension School alum. Her digital marketing content has been featured on Fast Company, Forbes, Nasdaq, and other industry websites; her essays and short stories have been featured in North American Review, Emerson Review, Writer’s Bone, and others.

5 Key Qualities of Students Who Succeed at Harvard Summer School (and in College!)

This guide outlines the kinds of students who thrive at Harvard Summer School and what the programs offer in return.

Harvard Division of Continuing Education

The Division of Continuing Education (DCE) at Harvard University is dedicated to bringing rigorous academics and innovative teaching capabilities to those seeking to improve their lives through education. We make Harvard education accessible to lifelong learners from high school to retirement.

Can ChatGPT get into Harvard? We tested its admissions essay.

ChatGPT’s release a year ago triggered a wave of panic among educators. Now, universities are in the midst of college application season, concerned that students might use the artificial intelligence tool to forge admissions essays.

But is a chatbot-created essay good enough to fool college admissions counselors?

To find out, The Washington Post asked a prompt engineer — an expert at directing AI chatbots — to create college essays using ChatGPT. The chatbot produced two essays: one responding to a question from the Common Application, which thousands of colleges use for admissions, and one answering a prompt used solely for applicants to Harvard University.

We presented these essays to a former Ivy League college admissions counselor, Adam Nguyen, who previously advised students at Harvard University and read admissions essays at Columbia University. We presented Nguyen with a control: a set of real college admissions essays penned by Jasmine Green, a Post intern who used them to get into Harvard University, where she is currently a senior.

We asked Nguyen to read the essays and spot which ones were produced by AI. The results were illuminating.

Can you figure out which one was written by a human?

Who wrote this?

Since kindergarten, I have evaluated myself from the reflection of my teachers. I was the clever, gifted child. I was a pleasure to have in class. I was driven and tenacious - but lazy? Unmotivated? No instructor had ever directed those harsh words at me. My identity as a stellar student had been stripped of its luster; I was destroyed.

Computer science and college admissions experts say that AI-created essays have some easy tells — helpful for admissions officers who are prepping for an uptick in ChatGPT-written essays.

Responses written by ChatGPT often lack specific details, leading to essays that lack supporting evidence for their points. The writing is trite and uses platitudes to explain situations, rather than delving into the emotional experience of the author. The essays are often repetitive and predictable, leaving readers without surprise or a sense of the writer’s journey. If chatbots produce content on issues of race, sex or socioeconomic status, they often employ stereotypes.

At first, Nguyen was impressed by the AI-generated essays: They were readable and mostly free of grammatical errors. But if he was reviewing the essay as part of an application package, he would’ve stopped reading.

“The essay is such a mediocre essay that it would not help the candidate’s application or chances,” he said in an interview. “In fact, it would probably diminish it.”

Here is how Nguyen evaluated ChatGPT’s essay.

Nguyen said that while AI may be sufficient to use for everyday writing, it is particularly unhelpful in creating college admissions essays. To start, he said, admissions offices are using AI screening tools to filter out computer-generated essays. (This technology can be inaccurate and falsely implicate students, a Post analysis found .)

But more importantly, admissions essays are a unique type of writing, he said. They require students to reflect on their life and craft their experiences into a compelling narrative that quickly provides college admissions counselors with a sense of why that person is unique.

“ChatGPT is not there,” he said.

Nguyen understands why AI might be appealing. College application deadlines often fall around the busiest time of the year, near winter holidays and end-of-semester exams. “Students are overwhelmed,” Nguyen said.

But Nguyen isn’t entirely opposed to using AI in the application process. In his current business, Ivy Link, he helps students craft college applications. For those who are weak in writing, he sometimes suggests they use AI chatbots to start the brainstorming process, he said.

For those who can’t resist the urge to use AI for more than just inspiration, there may be consequences.

“Their essays will be terrible,” he said, “and might not even reflect who they are.”

About this story

Jasmine Green contributed to this report.

The Washington Post worked with Benjamin Breen, an associate professor of history at the University of California in Santa Cruz who studies the impact of technological change, to create the AI-generated essays.

Editing by Karly Domb Sadof, Betty Chavarria and Alexis Sobel Fitts.

• Share full article

Advertisement

Supported by

Student Opinion

Should Students Let ChatGPT Help Them Write Their College Essays?

If so, how? Tell us what you are thinking, and what practical and ethical questions these new A.I. tools raise for you.

Natasha Singer

Hey, ChatGPT, can you help me write my college admissions essays?

Absolutely! Please provide me with the essay prompts and any relevant information about yourself, your experiences, and your goals.

By Katherine Schulten

Teachers: We also have a lesson plan that accompanies this Student Opinion forum.

Are you working on a college application essay? Have you sought help from an adult? How about from an A.I. chatbot like ChatGPT or Bard? Were either useful? If so, how?

The New York Times recently published two articles about the questions these new tools are raising for the college process. One explores how A.I. chatbots are upending essay-writing. The other details what happened when a reporter fed application questions from Harvard, Yale, Princeton and Dartmouth to different bots.

Here’s how the first article, “ Ban or Embrace? Colleges Wrestle With A.I.-Generated Admissions Essays ,” explains what’s going on:

The personal essay has long been a staple of the application process at elite colleges, not to mention a bane for generations of high school students. Admissions officers have often employed applicants’ essays as a lens into their unique character, pluck, potential and ability to handle adversity. As a result, some former students say they felt tremendous pressure to develop, or at least concoct, a singular personal writing voice. But new A.I. tools threaten to recast the college application essay as a kind of generic cake mix, which high school students may simply lard or spice up to reflect their own tastes, interests and experiences — casting doubt on the legitimacy of applicants’ writing samples as authentic, individualized admissions yardsticks.

The piece continues:

Some teachers said they were troubled by the idea of students using A.I. tools to produce college essay themes and texts for deeper reasons: Outsourcing writing to bots could hinder students from developing important critical thinking and storytelling skills. “Part of the process of the college essay is finding your writing voice through all of that drafting and revising,” said Susan Barber, an Advanced Placement English literature teacher at Midtown High School, a public school in Atlanta. “And I think that’s something that ChatGPT would be robbing them of.” In August, Ms. Barber assigned her 12th-grade students to write college essays. This week, she held class discussions about ChatGPT, cautioning students that using A.I. chatbots to generate ideas or writing could make their college essays sound too generic. She advised them to focus more on their personal views and voices. Other educators said they hoped the A.I. tools might have a democratizing effect. Wealthier high school students, these experts noted, often have access to resources — alumni parents, family friends, paid writing coaches — to help them brainstorm, draft and edit their college admissions essays. ChatGPT could play a similar role for students who lack such resources, they said, especially those at large high schools where overworked college counselors have little time for individualized essay coaching.

The second article, “ We Used A.I. to Write Essays for Harvard, Yale and Princeton. Here’s How It Went ,” includes this example:

Dartmouth requires applicants to explain why they want to attend the college. I primed the A.I. chatbots by asking them to write in the voice of a high school senior who was hoping to double major at Dartmouth in computer science and biology. HuggingChat churned out text with trite words and phrases — “passion,” “meaningful impact,” “rigorous academic programs” — that seemed to me like the kind of stilted formal language a high school student might imagine a college admissions reviewer would want to read.

I asked Bard to minimize the clichés and add more specific details about Dartmouth’s computing department. But it still produced some of the same standard college application language — “renowned,” “impact” — as HuggingChat. Bard also wrote that I was hoping to study with Leslie Kaelbling, whom the chatbot described as an A.I. researcher at Dartmouth. That could have caused problems if I were a high school senior and had submitted the essay Bard had fabricated as part of my Dartmouth application. Professor Kaelbling , you see, teaches at M.I.T. My takeaway: high school seniors hoping to stand out may need to do wholesale rewrites of the texts they prompt A.I. chatbots to generate. Or they could just write their own — chatbot-free — admissions essays from scratch.

Students, read both articles, and then tell us:

Do you think you would use a chatbot to help you write your personal essay for college? If so, how? For example, would you ask it to suggest topics? Help structure your writing? Generate a rough draft? Edit?

If you have already used A.I. to write or edit a personal essay, what did you think of the result? Was the experience useful to you? To what extent did you, like the Times reporter, find the output generic and clichéd? Did the bot make any errors? How, if at all, did you use the results?

Some, like the teacher quoted in the first article, worry that letting A.I. help with your essays robs you of the chance to develop your personal voice. Do you agree? Why or why not?

Do you think there is value in drafting and revising writing without help? What has that process been like for you in the past? What have you learned from it?

Some people believe that these tools will help students who don’t have easy access to college counselors or writing coaches. Do you agree? Do these chatbots make the application process more fair for students with fewer resources?

Do any of the colleges you are applying to have a policy on the use of these tools? If so, what do you think of those guidelines?

What do you think is, or should be, the purpose of a college essay? Can it really show colleges who you are? If so, is it ethical to let a bot — or even another human — help?

Now, return to the questions we started with: Should students let ChatGPT help them write their college essays? If so, how? Did your answers change as you read the related articles or looked at other students’ responses? Are you left with any questions — whether practical or ethical — about the role of this new technology?

Students 13 and older in the United States and Britain, and 16 and older elsewhere, are invited to comment. All comments are moderated by the Learning Network staff, but please keep in mind that once your comment is accepted, it will be made public and may appear in print.

Find more Student Opinion questions here. Teachers, check out this guide to learn how you can incorporate these prompts into your classroom.

Katherine Schulten has been a Learning Network editor since 2006. Before that, she spent 19 years in New York City public schools as an English teacher, school-newspaper adviser and literacy coach. More about Katherine Schulten

'ZDNET Recommends': What exactly does it mean?

ZDNET's recommendations are based on many hours of testing, research, and comparison shopping. We gather data from the best available sources, including vendor and retailer listings as well as other relevant and independent reviews sites. And we pore over customer reviews to find out what matters to real people who already own and use the products and services we’re assessing.

When you click through from our site to a retailer and buy a product or service, we may earn affiliate commissions. This helps support our work, but does not affect what we cover or how, and it does not affect the price you pay. Neither ZDNET nor the author are compensated for these independent reviews. Indeed, we follow strict guidelines that ensure our editorial content is never influenced by advertisers.

ZDNET's editorial team writes on behalf of you, our reader. Our goal is to deliver the most accurate information and the most knowledgeable advice possible in order to help you make smarter buying decisions on tech gear and a wide array of products and services. Our editors thoroughly review and fact-check every article to ensure that our content meets the highest standards. If we have made an error or published misleading information, we will correct or clarify the article. If you see inaccuracies in our content, please report the mistake via this form .

How ChatGPT (and other AI chatbots) can help you write an essay

ChatGPT  is capable of doing many different things very well, with one of the biggest standout features being its ability to compose all sorts of text within seconds, including songs, poems, bedtime stories, and essays . 

The chatbot's writing abilities are not only fun to experiment with, but can help provide assistance with everyday tasks. Whether you are a student, a working professional, or just getting stuff done, we constantly take time out of our day to compose emails, texts, posts, and more. ChatGPT can help you claim some of that time back by helping you brainstorm and then compose any text you need. 

How to use ChatGPT to write: Code | Excel formulas | Resumes  | Cover letters  

Contrary to popular belief, ChatGPT can do much more than just write an essay for you from scratch (which would be considered plagiarism). A more useful way to use the chatbot is to have it guide your writing process. 

Below, we show you how to use ChatGPT to do both the writing and assisting, as well as some other helpful writing tips. 

How ChatGPT can help you write an essay

If you are looking to use ChatGPT to support or replace your writing, here are five different techniques to explore. 

It is also worth noting before you get started that other AI chatbots can output the same results as ChatGPT or are even better, depending on your needs.

Also: The best AI chatbots of 2024: ChatGPT and alternatives

For example,  Copilot  has access to the internet, and as a result, it can source its answers from recent information and current events. Copilot also includes footnotes linking back to the original source for all of its responses, making the chatbot a more valuable tool if you're writing a paper on a more recent event, or if you want to verify your sources.

Regardless of which AI chatbot you pick, you can use the tips below to get the most out of your prompts and from AI assistance.

1. Use ChatGPT to generate essay ideas

Before you can even get started writing an essay, you need to flesh out the idea. When professors assign essays, they generally give students a prompt that gives them leeway for their own self-expression and analysis. 

As a result, students have the task of finding the angle to approach the essay on their own. If you have written an essay recently, you know that finding the angle is often the trickiest part -- and this is where ChatGPT can help. 

Also: ChatGPT vs. Copilot: Which AI chatbot is better for you?

All you need to do is input the assignment topic, include as much detail as you'd like -- such as what you're thinking about covering -- and let ChatGPT do the rest. For example, based on a paper prompt I had in college, I asked:

Can you help me come up with a topic idea for this assignment, "You will write a research paper or case study on a leadership topic of your choice." I would like it to include Blake and Mouton's Managerial Leadership Grid, and possibly a historical figure. 

Also: I'm a ChatGPT pro but this quick course taught me new tricks, and you can take it for free

Within seconds, the chatbot produced a response that provided me with the title of the essay, options of historical figures I could focus my article on, and insight on what information I could include in my paper, with specific examples of a case study I could use. 

2. Use the chatbot to create an outline

Once you have a solid topic, it's time to start brainstorming what you actually want to include in the essay. To facilitate the writing process, I always create an outline, including all the different points I want to touch upon in my essay. However, the outline-writing process is usually tedious. 

With ChatGPT, all you have to do is ask it to write the outline for you. 

Also: Thanks to my 5 favorite AI tools, I'm working smarter now

Using the topic that ChatGPT helped me generate in step one, I asked the chatbot to write me an outline by saying: 

Can you create an outline for a paper, "Examining the Leadership Style of Winston Churchill through Blake and Mouton's Managerial Leadership Grid."

After a couple of seconds, the chatbot produced a holistic outline divided into seven different sections, with three different points under each section. 

This outline is thorough and can be condensed for a shorter essay or elaborated on for a longer paper. If you don't like something or want to tweak the outline further, you can do so either manually or with more instructions to ChatGPT. 

As mentioned before, since Copilot is connected to the internet, if you use Copilot to produce the outline, it will even include links and sources throughout, further expediting your essay-writing process. 

3. Use ChatGPT to find sources

Now that you know exactly what you want to write, it's time to find reputable sources to get your information. If you don't know where to start, you can just ask ChatGPT. 

Also: How to make ChatGPT provide sources and citations

All you need to do is ask the AI to find sources for your essay topic. For example, I asked the following: 

Can you help me find sources for a paper, "Examining the Leadership Style of Winston Churchill through Blake and Mouton's Managerial Leadership Grid."

The chatbot output seven sources, with a bullet point for each that explained what the source was and why it could be useful. 

Also:   How to use ChatGPT to make charts and tables

The one caveat you will want to be aware of when using ChatGPT for sources is that it does not have access to information after 2021, so it will not be able to suggest the freshest sources. If you want up-to-date information, you can always use Copilot. 

Another perk of using Copilot is that it automatically links to sources in its answers. 

4. Use ChatGPT to write an essay

It is worth noting that if you take the text directly from the chatbot and submit it, your work could be considered a form of plagiarism since it is not your original work. As with any information taken from another source, text generated by an AI should be clearly identified and credited in your work.

Also: ChatGPT will now remember its past conversations with you (if you want it to)

In most educational institutions, the penalties for plagiarism are severe, ranging from a failing grade to expulsion from the school. A better use of ChatGPT's writing features would be to use it to create a sample essay to guide your writing. 

If you still want ChatGPT to create an essay from scratch, enter the topic and the desired length, and then watch what it generates. For example, I input the following text: 

Can you write a five-paragraph essay on the topic, "Examining the Leadership Style of Winston Churchill through Blake and Mouton's Managerial Leadership Grid."

Within seconds, the chatbot gave the exact output I required: a coherent, five-paragraph essay on the topic. You could then use that text to guide your own writing. 

Also: ChatGPT vs. Microsoft Copilot vs. Gemini: Which is the best AI chatbot?

At this point, it's worth remembering how tools like ChatGPT work : they put words together in a form that they think is statistically valid, but they don't know if what they are saying is true or accurate. 

As a result, the output you receive might include invented facts, details, or other oddities. The output might be a useful starting point for your own work, but don't expect it to be entirely accurate, and always double-check the content. 

5. Use ChatGPT to co-edit your essay

Once you've written your own essay, you can use ChatGPT's advanced writing capabilities to edit the piece for you. 

You can simply tell the chatbot what you want it to edit. For example, I asked ChatGPT to edit our five-paragraph essay for structure and grammar, but other options could have included flow, tone, and more. 

Also: AI meets AR as ChatGPT is now available on the Apple Vision Pro

Once you ask the tool to edit your essay, it will prompt you to paste your text into the chatbot. ChatGPT will then output your essay with corrections made. This feature is particularly useful because ChatGPT edits your essay more thoroughly than a basic proofreading tool, as it goes beyond simply checking spelling. 

You can also co-edit with the chatbot, asking it to take a look at a specific paragraph or sentence, and asking it to rewrite or fix the text for clarity. Personally, I find this feature very helpful. 

How I test an AI chatbot's coding ability - and you can too

5 ways ai can help you study for finals - for free, the best ai chatbots: chatgpt isn't the only one worth trying.

Things you buy through our links may earn Vox Media a commission.

Can ChatGPT Write a Good College-Admissions Essay?

In January, I raised my hourly rate to $300 before wondering if I could get away with charging anything at all.

I teach high-schoolers how to write college essays, helping students claw their way out of hackneyed bildungsroman and into deftly tuned narratives . The clients (and their parents) can be a lot to handle, but my results ensure that I have a new cluster of rising seniors every summer. And the service I provide is in perpetually high demand among the moneyed and desperate private-school crowd.

Recently, though, the rise of ChatGPT had me questioning how much longer this comfortable arrangement could last. I started to fear obsolescence when I heard about uncannily passable AI-generated  letters of recommendation and wedding toasts — forms of writing not a million miles away from my specialty.  So, in an attempt to get to know my new enemy —  and gauge whether I was still employable —  I paid $20 for access to the “more creative” GPT4.

Nervously, I prompted ChatGPT with a series of bullet points and fed it what anyone who has applied to college in the past 15 years knows is the formula for the Common Application personal essay: “Write 600 words including a catchy hook to draw the reader in, a conflict, and a thoughtful self-reflection.”

ChatGPT didn’t even take a beat to process my outline; it spat out an essay as fast as I could read it. Its first draft (about a freak accident washing dishes leading to a lesson in the power of fear) was unsettlingly well-composed, but stiff in a way that kept it from resonating emotionally (often a problem with student-generated drafts, too). ChatGPT wrote, “ I was horrified, not just at the sight of my own blood but also at the thought of needing stitches. In that moment, I was transported back to the time when I was a child and I got my first stitches. ” Not bad, but not exactly transcendent, either.

The next big test: Could this thing incorporate feedback? I replied that the essay was “a little formal, can you make it more conversational?” Done. ChatGPT added a few “ you see ”s and began several sentences with “ So .” The essay was suddenly more casual: “ The experience taught me that fear, no matter how powerful it may seem, can be overcome with perseverance and determination ” became “ But eventually, I realized that this fear was holding me back and preventing me from enjoying something that brought me so much joy. ”

With these small tweaks, ChatGPT’s effort was already significantly better than most first drafts I come across. I tried to throw it off with something random, adding, “My favorite comedian is Jon Stewart. Can you incorporate that into the essay?” ChatGPT wrote three new sentences that explained how Stewart “helped me see the lighter side of things and lifted my spirits.”

I told it to be funny. It tried. I corrected it, “No, that’s too corny, make it more sarcastic.” It revised, “ And let’s face it, what’s a little scar compared to the joy of a rack of clean dishes? ” Then I wrote, “Add in my high-achieving older brother who I always compare myself to a classic Common App essay character as a foil.” I specified that the brother breaks his collarbone around the same time the main character has to get stitches. ChatGPT came up with this: “ And here I was, feeling guilty for even complaining about my measly scratch when his pain was so much worse. It was like a twisted game of ‘whose injury is more severe?’ ” I watched ChatGPT revise (in seconds) the amount of material it typically takes students (with my help) hours to get through.  Intrusive thought: Even if I lower my rates, there won’t be any demand.

And then I slowed down, stopped panicking, and really read the essay.

I began noticing all the cracks in it. For one thing, ChatGPT was heavy on banal reflections (“ Looking back on my experience… ”) and empty-sounding conclusions (“ I am grateful for the lessons it taught me ”) that I would never let slide. I always advise students to get into specifics about how they’ve changed as people, but ChatGPT relied on anodyne generalities. Most importantly, it couldn’t go beyond a generic narrative into the realm of the highly specific. (A good student essay might have, say, detailed how Stewart’s Mark Twain Prize acceptance speech helped them overcome a fear of public speaking.)

AI is also just lazy. There’s nothing wrong with an occasional transitional phrase, but using “ Slowly but surely, ” “ Over time, ” “ Looking back on my experience, ” and “ In conclusion ” to lead off consecutive paragraphs is only okay if it’s your first time writing an essay. Leading off a conclusion with “ In conclusion ” means you’re either in sixth grade or satisfied with getting a C.

While the essay technically met every criterion I set (hook, conflict, self-reflection), it also failed the main test I pose to students: Have you ever read a version of this story? The answer here was most definitely “yes.” It’s uncanny how well ChatGPT mimicked the contrived essay that I’m paid to steer kids away from — the one you’d be shown as an example of what not to do in a college-essay seminar. It reads like a satire of one of those “the ability was inside me all along” or “all I needed to do was believe in myself/be true to myself/listen to my inner voice” narratives rife with clichés and half-baked epiphanies. ChatGPT’s basic competence led me to overlook the middling quality of its execution. It’s the same disbelief-to-disillusionment arc ChatGPT has inspired elsewhere — take the viral AI travel itinerary that seemed perfect until people pointed out some pretty glaring (and possibly dangerous) errors.

Credit where it’s due. I expend a lot of effort translating overwritten, clunky, and generally unclear student prose. ChatGPT excels in writing cleanly — if flatly. It’s great at producing simple, informational text from a set of data. Creating a rule book for Airbnb guests, writing a “help wanted” ad, drafting an email with details for a surprise party: These are perfect cases for ChatGPT right now. From this mess, ChatGPT would translate the raw information into a block of concise text that wouldn’t need style, voice, or flair to be successful. If you want to share facts in a digestible and clear way, ChatGPT is your guy.

But ChatGPT failed hardest at the most important part of the college essay: self-reflection. Literary agent Jamie Carr of the Book Group describes great storytelling as something that makes “connections between things and ideas that are totally nonsensical — which is something only humans can do.” Can ChatGPT bring together disparate parts of your life and use a summer job to illuminate a fraught friendship? Can it link a favorite song to an identity crisis? So far, nope. Crucially, ChatGPT can’t do one major thing that all my clients can: have a random thought. “I’m not sure why I’m telling you this” is something I love to hear from students, because it means I’m about to go on a wild ride that only the teenage brain can offer. It’s frequently in these tangents about collecting cologne or not paying it forward at the Starbucks drive-thru that we discover the key to the essay. I often describe my main task as helping students turn over stones they didn’t know existed, or stones they assumed were off-limits. ChatGPT can’t tap into the unpredictable because it can only turn over the precise stones you tell it to — and if you’re issuing these orders, chances are you already know what’s under the stone.

In the South Park episode “Deep Learning,” Clyde and Stan use AI to compose thoughtful, emotionally mature text messages to their girlfriends. When Bebe asks if she should cut her hair, Clyde (via ChatGPT) replies, “You would look great with any length of hair. Trying a new look could be fun.” Only a fourth-grader (no offense, Bebe) would buy that the message is authentic. When Stan’s girlfriend Wendy wants to repair their relationship, Stan responds, “We can work things out if you’re willing. I still believe we can make this work. Let’s not give up on each other.” ChatGPT is credited as a writer in this episode, though I wouldn’t be surprised if the messages were punched up to reach this level of dullness. But the style speaks to something I noticed when I asked ChatGPT to write a short story: It makes everything sound like an unfunny parody. A parody of an attentive boyfriend. A parody of a short story. A parody of a college essay.

AI may supplant me one day, but for now, ChatGPT isn’t an admissions-essay quick fix. It’s not even a moderate threat to the service I offer. And while there are plenty of problems with a system in which the ultra-elite pay someone like me to help package insight into a few hundred words, ChatGPT doesn’t solve any of them. Perhaps one day, we’ll figure out a fairer way forward. For now, I’m quite relieved to report that my expertise is still definitely worth something — maybe even more than $300 an hour.

• artificial intelligence
• college admissions

Most Viewed Stories

• The Northern Lights May Be Visible Again on Sunday Night
• The Kristi Noem Dog-Killing Story Is Actually Worse in Context
• The Package King of Miami  
• The Man Who Brought Theoretical Physics to Wall Street
• In Defense of Punching Left
• Who’s the Trump VP Pick? Latest Odds for Every Shortlist Candidate.

Editor’s Picks

Most Popular

• The Northern Lights May Be Visible Again on Sunday Night By Chas Danner
• The Kristi Noem Dog-Killing Story Is Actually Worse in Context By Margaret Hartmann
• The Package King of Miami   By Ezra Marcus
• The Man Who Brought Theoretical Physics to Wall Street By Kevin T. Dugan
• In Defense of Punching Left By Jonathan Chait
• Who’s the Trump VP Pick? Latest Odds for Every Shortlist Candidate. By Margaret Hartmann

What is your email?

This email will be used to sign into all New York sites. By submitting your email, you agree to our Terms and Privacy Policy and to receive email correspondence from us.

Sign In To Continue Reading

Create your free account.

Password must be at least 8 characters and contain:

• Lower case letters (a-z)
• Upper case letters (A-Z)
• Numbers (0-9)
• Special Characters (!@#$%^&*)

As part of your account, you’ll receive occasional updates and offers from New York , which you can opt out of anytime.

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• NEWS EXPLAINER
• 09 December 2022

AI bot ChatGPT writes smart essays — should professors worry?

• Chris Stokel-Walker

You can also search for this author in PubMed   Google Scholar

Between overwork, underpayment and the pressure to publish, academics have plenty to worry about. Now there’s a fresh concern: ChatGPT , an artificial intelligence (AI) powered chatbot that creates surprisingly intelligent-sounding text in response to user prompts, including homework assignments and exam-style questions. The replies are so lucid, well-researched and decently referenced that some academics are calling the bot the death knell for conventional forms of educational assessment. How worried should professors and lecturers be?

Access options

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

185,98 € per year

only 3,65 € per issue

Rent or buy this article

Prices vary by article type

Prices may be subject to local taxes which are calculated during checkout

doi: https://doi.org/10.1038/d41586-022-04397-7

Reprints and permissions

Related Articles

Are ChatGPT and AlphaCode going to replace programmers?

How language-generation AIs could transform science

Open-source language AI challenges big tech’s models

• Computer science

AI now beats humans at basic tasks — new benchmarks are needed, says major report

News 15 APR 24

High-threshold and low-overhead fault-tolerant quantum memory

Article 27 MAR 24

Three reasons why AI doesn’t model human language

Correspondence 19 MAR 24

Is the Internet bad for you? Huge study reveals surprise effect on well-being

News 12 MAY 24

Hunger on campus: why US PhD students are fighting over food

Career Feature 03 MAY 24

US National Academies report outlines barriers and solutions for scientist carers

Career News 02 MAY 24

How to stop students cramming for exams? Send them to sea

News & Views 30 APR 24

How young people benefit from Swiss apprenticeships

Spotlight 17 APR 24

Ready or not, AI is coming to science education — and students have opinions

Career Feature 08 APR 24

Clinician Researcher/Group Leader in Cancer Cell Therapies

An excellent opportunity is available for a Group Leader with expertise in cellular therapies to join the Cancer Research program at QIMR Berghofer.

Herston, Brisbane (AU)

QIMR Berghofer

Faculty Positions at the Center for Machine Learning Research (CMLR), Peking University

CMLR's goal is to advance machine learning-related research across a wide range of disciplines.

Beijing, China

Center for Machine Learning Research (CMLR), Peking University

Faculty Positions at SUSTech Department of Biomedical Engineering

We seek outstanding applicants for full-time tenure-track/tenured faculty positions. Positions are available for both junior and senior-level.

Shenzhen, Guangdong, China

Southern University of Science and Technology (Biomedical Engineering)

Southeast University Future Technology Institute Recruitment Notice

Professor openings in mechanical engineering, control science and engineering, and integrating emerging interdisciplinary majors

Nanjing, Jiangsu (CN)

Southeast University

Staff Scientist

A Staff Scientist position is available in the laboratory of Drs. Elliot and Glassberg to study translational aspects of lung injury, repair and fibro

Maywood, Illinois

Loyola University Chicago - Department of Medicine

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

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 through which learning styles are shaped. Some students might develop a particular learning style because they have had particular experiences. Others might develop a particular learning style by trying to accommodate to a learning environment that was not well suited to their learning needs. Ultimately, we need to understand the interactions among learning styles and environmental and personal factors, and how these shape how we learn and the kinds of learning we experience.

Pass or fail? A- or B+? And how would your grade change if you knew a human student hadn’t written it at all? Because Mike Sharples, a professor in the U.K., used GPT-3, a large language model from OpenAI that automatically generates text from a prompt, to write it. (The whole essay, which Sharples considered graduate-level, is available, complete with references, here .) Personally, I lean toward a B+. The passage reads like filler, but so do most student essays.

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. In May, a student in New Zealand confessed to using AI to write their papers, justifying it as a tool like Grammarly or spell-check: ​​“I have the knowledge, I have the lived experience, I’m a good student, I go to all the tutorials and I go to all the lectures and I read everything we have to read but I kind of felt I was being penalised because I don’t write eloquently and I didn’t feel that was right,” they told a student paper in Christchurch. 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.

The essay, in particular the undergraduate essay, has been the center of humanistic pedagogy for generations. It is the way we teach children how to research, think, and write. That entire tradition is about to be disrupted from the ground up. 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.

A chasm has existed between humanists and technologists for a long time. In the 1950s, C. P. Snow gave his famous lecture, later the essay “The Two Cultures,” describing the humanistic and scientific communities as tribes losing contact with each other. “Literary intellectuals at one pole—at the other scientists,” Snow wrote. “Between the two a gulf of mutual incomprehension—sometimes (particularly among the young) hostility and dislike, but most of all lack of understanding. They have a curious distorted image of each other.” Snow’s argument was a plea for a kind of intellectual cosmopolitanism: Literary people were missing the essential insights of the laws of thermodynamics, and scientific people were ignoring the glories of Shakespeare and Dickens.

The rupture that Snow identified has only deepened. In the modern tech world, the value of a humanistic education shows up in evidence of its absence. Sam Bankman-Fried, the disgraced founder of the crypto exchange FTX who recently lost his $16 billion fortune in a few days , is a famously proud illiterate. “I would never read a book,” he once told an interviewer . “I don’t want to say no book is ever worth reading, but I actually do believe something pretty close to that.” Elon Musk and Twitter are another excellent case in point. It’s painful and extraordinary to watch the ham-fisted way a brilliant engineering mind like Musk deals with even relatively simple literary concepts such as parody and satire. He obviously has never thought about them before. He probably didn’t imagine there was much to think about.

The extraordinary ignorance on questions of society and history displayed by the men and women reshaping society and history has been the defining feature of the social-media era. Apparently, Mark Zuckerberg has read a great deal about Caesar Augustus , but I wish he’d read about the regulation of the pamphlet press in 17th-century Europe. It might have spared America the annihilation of social trust .

These failures don’t derive from mean-spiritedness or even greed, but from a willful obliviousness. The engineers do not recognize that humanistic questions—like, say, hermeneutics or the historical contingency of freedom of speech or the genealogy of morality—are real questions with real consequences. Everybody is entitled to their opinion about politics and culture, it’s true, but an opinion is different from a grounded understanding. The most direct path to catastrophe is to treat complex problems as if they’re obvious to everyone. You can lose billions of dollars pretty quickly that way.

As the technologists have ignored humanistic questions to their peril, the humanists have greeted the technological revolutions of the past 50 years by committing soft suicide. As of 2017, the number of English majors had nearly halved since the 1990s. History enrollments have declined by 45 percent since 2007 alone. Needless to say, humanists’ understanding of technology is partial at best. The state of digital humanities is always several categories of obsolescence behind, which is inevitable. (Nobody expects them to teach via Instagram Stories.) But more crucially, the humanities have not fundamentally changed their approach in decades, despite technology altering the entire world around them. They are still exploding meta-narratives like it’s 1979, an exercise in self-defeat.

Read: The humanities are in crisis

Contemporary academia engages, more or less permanently, in self-critique on any and every front it can imagine. In a tech-centered world, language matters, voice and style matter, the study of eloquence matters, history matters, ethical systems matter. But the situation requires humanists to explain why they matter, not constantly undermine their own intellectual foundations. The humanities promise students a journey to an irrelevant, self-consuming future; then they wonder why their enrollments are collapsing. Is it any surprise that nearly half of humanities graduates regret their choice of major ?

The case for the value of humanities in a technologically determined world has been made before. Steve Jobs always credited a significant part of Apple’s success to his time as a dropout hanger-on at Reed College, where he fooled around with Shakespeare and modern dance, along with the famous calligraphy class that provided the aesthetic basis for the Mac’s design. “A lot of people in our industry haven’t had very diverse experiences. So they don’t have enough dots to connect, and they end up with very linear solutions without a broad perspective on the problem,” Jobs said . “The broader one’s understanding of the human experience, the better design we will have.” Apple is a humanistic tech company. It’s also the largest company in the world.

Despite the clear value of a humanistic education, its decline continues. Over the past 10 years, STEM has triumphed, and the humanities have collapsed . The number of students enrolled in computer science is now nearly the same as the number of students enrolled in all of the humanities combined.

And now there’s GPT-3. Natural-language processing presents the academic humanities with a whole series of unprecedented problems. 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. Teachers are already some of the most overworked, underpaid people in the world. They are already dealing with a humanities in crisis. And now this. I feel for them.

And yet, despite the drastic divide of the moment, natural-language processing is going to force engineers and humanists together. They are going to need each other despite everything. Computer scientists will require basic, systematic education in general humanism: The philosophy of language, sociology, history, and ethics are not amusing questions of theoretical speculation anymore. They will be essential in determining the ethical and creative use of chatbots, to take only an obvious example.

The humanists will need to understand natural-language processing because it’s the future of language, but also because there is more than just the possibility of disruption here. Natural-language processing can throw light on a huge number of scholarly problems. It is going to clarify matters of attribution and literary dating that no system ever devised will approach; the parameters in large language models are much more sophisticated than the current systems used to determine which plays Shakespeare wrote, for example . It may even allow for certain types of restorations, filling the gaps in damaged texts by means of text-prediction models. It will reformulate questions of literary style and philology; if you can teach a machine to write like Samuel Taylor Coleridge, that machine must be able to inform you, in some way, about how Samuel Taylor Coleridge wrote.

The connection between humanism and technology will require people and institutions with a breadth of vision and a commitment to interests that transcend their field. 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. But that’s always been the beginning of wisdom, no matter what technological era we happen to inhabit.

ChatGPT and Your College Essays

Understanding chatgpt essays.

Earlier this year, ChatGPT became the fastest-growing web platform in internet history. If you’re not familiar with ChatGPT essays and the ChatGPT essay writer, this article is for you. 

With AI technology on the rise, the benefits of AI chatbot technology across industries are being weighed against potential concerns regarding misinformation, bias, and security/privacy. 

In academia , some institutions are embracing the technology, offering courses on utilizing ChatGPT . However, academic dishonesty is a big point of concern, with some students relying on the platform to generate ChatGPT essays for their courses. Moreover, some students have even started generating ChatGPT college essays for their college applications.

At CollegeAdvisor, our experts agree that ChatGPT and other AI sources are no substitute for authentic, personal, and human-generated college essays. In this article, we’ll break down how ChatGPT relates to the college admissions process with tips from former admissions officers. We’ll also discuss concerns related to the ChatGPT essay writer and ChatGPT essays so you understand how to responsibly engage with AI tools. 

ChatGPT and College Admissions

So, what is the impact of ChatGPT on the college admissions process ? And can ChatGPT write essays? 

Later, we’ll look at examples from a ChatGPT essay writer with feedback from former admissions officers. These Chatbot examples will include AI-generated supplemental essays from Harvard , Yale , and UChicago . Finally, we’ll go over how colleges are screening for ChatGPT college essays and review how to use ChatGPT for essays responsibly. We’ll also discuss where to find helpful resources for writing supplemental essays on your own.

Before we dive in, please understand that CollegeAdvisor does not condone the use of a ChatGPT essay writer or any other AI when it comes to writing your college essays. Beyond concerns related to academic honesty, authenticity is key when it comes to writing strong essays. After all, colleges want to admit individuals—not robots.

That being said, let’s begin by answering the question: can ChatGPT write essays?

Can ChatGPT write essays?

Yes, ChatGPT and other AI tools can create essays if given a prompt. However, the quality and overall impact of an AI generated essay is up for debate. There are limitations to what ChatGPT can produce versus what a person can. 

When using an AI chatbot for essays, concerns might include:

Authenticity

While this is not an extensive list of limitations, these features definitely play an important role in characterizing ChatGPT essays. Later on, we’ll see how these limitations play out in actual ChatGPT college essays.

First of all, ChatGPT’s work is not your work. In many academic contexts , the use of ChatGPT can amount to plagiarism. Although ChatGPT writing claims to be original, it won’t necessarily be unique or vastly different from other responses to the same or similar prompt.

ChatGPT is not a fact-checking tool. As such, information that ChatGPT/AI generates may include factual errors. It is also possible for ChatGPT to create sources that don’t actually exist. A ChatGPT essay may also string together details that are unrelated to one another. So, even if the details end up being correct, the essay as a whole won’t make sense or deliver a cohesive argument.

ChatGPT tends to have a strong hold on grammar and syntax. However, it may also use words inappropriately and tends to write in a tone that isn’t as authentic or clear as a human’s. The phrases used are often generic or repetitive , which will end up making the writing sound empty of true passion and meaning.

Overall, your college essays should be about you—your life, values, and experiences. ChatGPT can’t replicate that. By the time you’ve fed ChatGPT enough specific details, anecdotes, characteristics, or interests to incorporate in an essay, you’ll have already brainstormed plenty to include in your own! And, you’ll likely do a better job weaving them together than ChatGPT ever could.

So, can ChatGPT write essays? Absolutely. However, there are many limitations to the quality and depth of ChatGPT essays. To further understand these limitations, let’s learn a little more about Chatbot technology and how it’s used to produce ChatGPT essays.

What is Chatbot technology?

How can ChatGPT write essays with only a prompt ? Well, let’s talk about how the technology works . Essentially, ChatGPT is an AI system that is trained to recognize and respond to information. GPT stands for:

• Pre-trained
• Transformers

Generative means AI that has been trained to evaluate an input and produce a new, original output according to its training. Pre-trained means the AI has been developed using a training model. Basically, the AI is fed a data set from which it learns parameters to apply to future tasks.

There are two types of training: supervised and non-supervised. Supervised training is based on direct matching, teaching the AI to connect specific inputs to corresponding outputs. Non-supervised training is based on pattern recognition, teaching the AI to learn underlying patterns and structures.

Supervised and non-supervised pre-training is then combined with transformer architecture. Transformers are able to understand words in context, taking note of the relationships between words and weighing their importance. Essentially, the ChatGPT essay writer has learned English syntax by training on a large dataset, making predictions, and then fine-tuning those predictions.

AI and College Admissions

The recent rise of AI has led to many debates across colleges and universities. In one case, Michigan Law School banned the use of AI chatbot for essays. On the other hand, Arizona State University Law School has approved its use, in particular for writing personal statements (the equivalent of the Common App essay).

These two schools show the range in how institutions are reacting to AI’s role in the college admissions process . However, many schools do not have a specific stance regarding ChatGPT essay writers. Unless a school you are applying to has a clear policy on ChatGPT essays, the decision of if and how you use ChatGPT essays will ultimately be yours. However, keep in mind that AI is included in many anti-plagiarism restrictions within the college admissions process. 

Understanding ChatGPT’s writing process is important to understanding its end product. So, just how does the ChatGPT essay writer write essays?

How to write essays with ChatGPT

All you need to get your ChatGPT essay writer started is a prompt, a word limit, and some ideas of what you want to include in your essay. If you’ve never asked ChatGPT to write an essay , you might be surprised by how fast your ChatGPT essay writer will spit out a complete draft. 

Not only can a ChatGPT essay writer produce a draft from a limited outline in just a few seconds; but it will also do its best to incorporate specific feedback . This means that the ChatGPT essay writer can redraft essays based on particular suggestions. Because the ChatGPT essay writer is responsive, it will continue to make changes to align with each piece of feedback you give it.

From that alone, using ChatGPT for essays may seem like an easy way to save yourself time. However, that doesn’t mean relying on ChatGPT college essays is a good idea.

ChatGPT College Essays

Can ChatGPT write essays? Yes. But, can ChatGPT write essays that will impress admissions officers? Not likely. 

While you can input prompts into ChatGPT and receive a response, there’s a good chance that the response will not be suitable as a college essay.

Remember, there’s a reason why CollegeAdvisor doesn’t condone nor recommend the use of ChatGPT to write college essays . While ChatGPT essays may look polished (and they do have the benefit of being free of any spelling or grammar errors), they also tend to be generic. This isn’t altogether surprising when you consider how ChatGPT produces essays.

How does ChatGPT write essays?

ChatGPT works off of language modeling—that is, it recognizes and repeats patterns in language. As such, it’s trained to produce words—not information. Based on the data it has available (namely, much of what already exists on the internet), ChatGPT recognizes and replicates how writers string words together.

A ChatGPT essay writer reproduces human language using natural language processing , or NLP. It then incorporates real-time feedback using dialogue management , which allows AI to take in new information and contextualize it within the conversation history.

So, when we answer “yes” to the question of “can ChatGPT write essays,” what we mean is that it can predict what words might go together in the context of a specific topic. While your ChatGPT essays might address the general concepts of a prompt, we’ll see why this isn’t enough when it comes to writing a compelling college essay.

An admissions officer reviews ChatGPT essays

Now, it’s time to put a ChatGPT essay writer to the test. Below we have Chatbot examples of Harvard, Yale, and UChicago chatGPT essays reviewed by former admissions officers. For each of our Chatbot examples, we’ll provide the prompts, ChatGPT college essays, and notes from our readers. Take note of how similar the feedback is across the three examples, regardless of the essay prompt or length.

We asked our former admissions officers to review these ChatGPT college essays as if a student had submitted them for review. After each essay, you’ll see our team’s responses to these ChatGPT essays. 

Please note the prompts are simply those provided by each university. They do not capture what prompt was provided to the ChatGPT essay writer in order to produce each of the ChatGPT essays below.

Harvard supplemental essays from ChatGPT

First, we gave our ChatGPT essay writer a prompt from Harvard.

Harvard Supplemental Essay Prompt

Please briefly elaborate on one of your extracurricular activities or work experiences. (150 words), chatgpt harvard supplemental essay response.

As the founder and president of my high school’s first Robotics Club, I experienced the incredible power of shared compassion converging with interdisciplinary learning. When I first established the club, it was not simply out of a fascination for robots; it was a desire to foster an environment where innovation and collaboration were paramount, where my peers could witness the convergence of theoretical science, math, and tangible technology.

Every meeting was a melting pot of ideas. We worked collectively on programming, design, assembly, and testing of our robots, each member’s input crucial in crafting innovative solutions. This hands-on experience honed my problem-solving skills, allowing me to see the direct applications of the STEM knowledge we gained in classrooms.

Through the Robotics Club, I learned more than just how to build a robot. Leadership, teamwork, and the value of perseverance when faced with setbacks have been invaluable lessons. This experience has deepened my commitment to leadership and sharing my passion for technology with others and I look forward to bringing this dedication and innovation to Harvard’s campus.

Like other successful Harvard supplemental essays, the topic expressed in this draft addresses the prompt and the writing is free of any mistakes. However, the essay lacks specificity and a personal focus.

So, what did our former admissions officer have to say about ChatGPT’s work? Here are some of their comments about this essay’s lack of detail:

CollegeAdvisor Admissions Officer Feedback

Text from essay:.

“interdisciplinary learning “

Former Admissions Officer Comment:

“This needs to be defined, what do you mean by this?”

“ it was a desire to foster an environment where innovation and collaboration were paramount “

“You need to support this with specific examples of what you did and what the outcome of your efforts were.”

“ convergence of theoretical science, math, and tangible technology “

“These are really big concepts that need to be better defined and explained through practical examples.”

Overall, the reader was supportive of the topic and agreed that the writing was solid. However, the essay as a whole failed to highlight what the student contributed to the organization and what they learned from the experience. The lack of specificity ultimately made the writing feel generic and left the reader with more questions than answers.

In their final feedback to the student, the reader provided a perfect critique of what ChatGPT essays lack:

“Right now it is just a collection of lofty ideas and words without any specific details and personalization…The essay lacks any key thesis and structure and needs more development and representation of the statements made and most importantly needs to represent YOU as a person and founder of this club.”

Let’s look at another example of what you might be missing out on if using ChatGPT for essays.

Yale supplemental essays from ChatGPT

Next, we had our ChatGPT essay writer take a shot at one of the Yale supplemental essays.

Yale Supplemental Essay Prompt

What is it about yale that has led you to apply (125 words or fewer), chatgpt yale supplemental essay response.

Yale’s commitment to a comprehensive, interdisciplinary education, solid cutting edge research and engaging residential college deeply resonates with my academic aspirations. I am particularly drawn to the unique combination of intellectual rigor and flexibility found within Yale’s Directed Studies program, which I believe will allow me to explore the breadth and depth of Western thought in an intensely thoughtful academic community. Moreover, the rich culture and innovation and intellectual curiosity at Yale, coupled with its focus on undergraduate research, particularly intrigues me. The opportunity to engage in cutting-edge research in the fields of artificial intelligence and machine learning at Yale’s Computer Science department would align perfectly with my career aspirations. Lastly, the vibrant residential college system promises a tight-knit community, enriching both my personal growth and academic journey.

This essay included great specifics about Yale’s offerings, including:

• Yale’s Directed Studies program
• Artificial intelligence and machine learning research at Yale’s CS department
• Yale’s residential college system

While these can all be compelling details to include in a why Yale essay, ChatGPT failed to make a personal connection to them. In their feedback, our former admissions officer wrote:

“You’ve introduced three different aspects…with very little description or understanding of why they are important to you.”

The essay also has some contradictions in terms of focus. Our former admissions officer called out these competing statements:

“I don’t understand how your desire to study AI and CS relates to your prior statement about exploring the breadth and depth of Western thought – these don’t make sense and seem like you are confused about what you want to study – need to tie them together or perhaps delete and focus on what is your primary academic interest.”

Especially with shorter essays, you don’t have any extra space for broad statements or unconnected thoughts. Every idea, detail, and sentence matters and needs to carry its own weight and impact.

As you can see, using ChatGPT for essays generates similar feedback across the board. Let’s look at one more ChatGPT essay example.

UChicago essays from ChatGPT

The last of our chatbot college essays is a UChicago essay.

UChicago Supplemental Essay Prompt

How does the university of chicago, as you know it now, satisfy your desire for a particular kind of learning, community, and future please address with some specificity your own wishes and how they relate to uchicago (less than 300 words)., chatgpt uchicago supplemental essay response.

The University of Chicago has always represented the epitome of intellectual vitality and critical thinking for me. Its ethos, encapsulated in its motto “Crescat scientia; vita excolatur” (Let knowledge grow from more to more; and so be human life enriched), resonates deeply with my own approach to learning.

UChicago’s commitment to interdisciplinary study aligns perfectly with my educational philosophy. I am attracted to the ability to navigate freely between different academic disciplines. Particularly, the Core Curriculum, with its focus on broad intellectual exposure, will allow me to explore beyond my primary interest in Astrophysics and tap into diverse fields such as philosophy, sociology, and literature. This will satisfy my desire for a holistic education that pushes the boundaries of my understanding.

The engaging intellectual culture at UChicago is something I am eager to participate in. I have always been captivated by the university’s tradition of vibrant discourse and the intellectual challenges offered by its student body and faculty. From attending stimulating events hosted by the Ryerson Astronomical Society to engaging in enlightening discussions in the House system, I look forward to exchanging ideas with individuals as passionate about learning as I am.

Looking towards the future, UChicago’s strong emphasis on research is compelling. As someone who seeks a career in Astrophysics, the opportunity to work with renowned faculty and access to world-class facilities, like the Kavli Institute for Cosmological Physics, will enable me to participate in cutting-edge research, paving the way for my future pursuits in the field.

In essence, UChicago, with its unparalleled academic environment, dynamic student community, and dedication to research, is the perfect place for me to grow intellectually, connect with like-minded peers, and shape a promising future.

Again, the main thing this essay is lacking is personal specificity. Our former admissions officer wrote:

“Make sure you are more specific about you and your desired experience…You really need to insert yourself in some of these programs you mention.”

For example, the reader suggests adding specific examples of research the student has completed and drawing a parallel to specific research being done at UChicago.

In one instance, the reader comments that the essay does not justly capture the goals of UChicago’s Core Curriculum:

“Broad intellectual exposure sounds very open and undefined, but it appears the key focus on the core is development of specific skills, critical thinking, problem solving.”

The reader even provides a link to UChicago’s academic page describing their curriculum , suggesting the student go back and review it. This is a perfect example of why you always want to do a deeper research dive into each school’s website vs. trusting ChatGPT to accurately pull information.

Additionally, the reader provided suggestions regarding wording and organization to help improve the overall flow and clarity. You’re likely to have similar weaknesses in your structure if you use ChatGPT for essays with longer word counts.

Reading these chatbot examples – were you able to tell they were written by AI? Maybe you’re wondering if admissions officers are able to spot if students used an AI chatbot for essays. Next, let’s discuss some key characteristics of ChatGPT essays.

How to tell if an essay was written by a Chatbot

ChatGPT and other AI tools identify and replicate linguistic patterns to predict which word a person would use next. Since they are programmed to adhere to grammar and syntax rules, ChatGPT writing will be entirely free of errors. However, just because the writing is “correct” doesn’t mean it will come off as natural.

In general, ChatGPT essays will be largely impersonal. AI tools like ChatGPT can’t generate the kind of personal stories that form the heart of a strong college essay. 

Additionally, various AI checking tools exist, and some institutions may employ these tools to protect against the use of AI. While these tools are imperfect, they are still relatively effective in identifying AI-produced writing. 

Will colleges know if you use ChatGPT to write your essays?

As AI technology improves, so does AI detection. So, always assume that admissions officers will know if you used ChatGPT to write your college essays.

Even without the use of specific tools, ChatGPT essays have various giveaways. The combination of general, formulaic writing along with zero writing errors in ChatGPT essays may lead admissions officers to suspect students have used an AI chatbot for their essays.

Overall, college admissions officers are very savvy when it comes to technology hacks and are definitely on the lookout for AI-generated essays. Especially if the institution has a policy against applicants submitting ChatGPT college essays, you can bet their admissions officers will be on the lookout for any red flags.

AI checking tools may be integrated into the application submission process in the future. Similar to systems like Turnitin, which checks for plagiarism in academic essays, AI detection tools may perform linguistic or contextual analysis to determine if an essay was produced by a ChatGPT essay writer.

After learning more about ChatGPT, you may be wondering, can ChatGPT write essays that will help me get into college? Ultimately, using AI chatbots alone to write the kind of personal essays required to stand out in college admissions probably won’t work. 

How can I use ChatGPT to help write my essays?

Instead of viewing this platform as a ChatGPT essay writer, try looking at it as a ChatGPT collaborator. While it may be tempting to use an AI chatbot for essays, you can see from our chatbot examples that ChatGPT college essays lack a certain substance and nuance that is crucial to a strong application essay.

After reading the ChatGPT essays written by our ChatGPT essay writer, you likely understand why these essays won’t help you succeed in the application process. Moreover, many colleges will automatically disqualify essays written by ChatGPT and similar tools. 

Additionally, we encourage you not to use ChatGPT to write a draft of your essays—even if you plan to edit them afterward. While this may seem faster than writing your college essays yourself, you might find yourself boxed in trying to edit the writing of a ChatGPT essay writer. Making someone else’s words sound like your own isn’t as easy as you might think.

However, there are some ways to use tools like ChatGPT for essays without having the ChatGPT essay writer do all the work for you. 

Tools like ChatGPT can sometimes help expedite your research. If you’re writing a “why school” essay, you can use ChatGPT to learn more about a specific program. Suppose you’re interested in eventually attending medical school. In that case, you can ask ChatGPT to provide information about a school’s pre-med program.

When asked about UChicago’s pre-med program, ChatGPT provided a list that includes flexible majors, clinical experience, MCAT preparation, and pre-medical societies. To gain further insight into their pre-medical societies, you can ask ChatGPT for more details. In response to this prompt, ChatGPT listed organizations such as Health Leads UChicago, the Women in Science Committee, and the Minority Association of Pre-Medical Students. This can be a great way to learn about programs you might not know about. However, in your essays, you’ll want to detail what specifically about the program aligns with your goals.

Overall, while you shouldn’t use ChatGPT for essays, you can use it to gain quick insights into the offerings available at some schools. However, you’ll want to confirm the details of your research. When providing the above information about UChicago, our ChatGPT essay writer provided the following caveat:

”Please note that the availability and names of these organizations may have changed since then [September 2021], so I recommend checking the university’s official website or contacting the Office of Career Advancement for the most up-to-date information. “

Even the ChatGPT essay writer agrees that you should double-check facts provided by AI. 

Interview Preparation

We’ve described the limitations of using an AI chatbot for essays. As you saw in the feedback on our ChatGPT essays, ChatGPT essays have strong syntax and command of the language, but they tend to lack substance. 

Instead of looking for a ChatGPT essay writer, you might use ChatGPT to prepare for interviews. ChatGPT has enough knowledge in its database to provide you with sample interview questions that you can practice answering in real time. 

Application Review

Instead of using ChatGPT to write essays, you might look for other tools—namely, AdmitYogi, which is a market-leading tool that provides users with examples of successful applications to various schools and programs. This resource can help inspire you as you craft your own applications. 

Helpful College Essay Resources from CollegeAdvisor

Now, let’s say you’ve decided using an AI chatbot for essays isn’t for you. Where should you go for help writing your college essays? Here at CollegeAdvisor, we have countless free resources to help you feel confident writing your college essays on your own.

Essay Specific Guides

While there are commonalities between certain prompts, each ultimately has its own specific questions, context, and word count you’ll need to address. Consider each prompt as a unique opportunity to share something about yourself. This will help you craft a more nuanced, personal piece of writing than the ChatGPT essays.

CollegeAdvisor has resources for both the Common App and Coalition essays (you can find more essay examples here ). We also have up-to-date 2023-24 supplemental essay guides for top schools across the country, like, Columbia , USC , UMich , and UChicago (as well as corresponding examples ). Additionally, you can find essay examples that fit into more general categories, like Ivy League Universities or “ Why this college ” prompts.

Common App Essays 2023‒2024

Essay Workshops

Webinars let you hear advice from our essay experts directly. These advisors have unique backgrounds reading and reviewing college applications, so they know the ins and outs of what makes a strong college application essay. They also offer unique perspectives you won’t get anywhere else. In the Yale workshop , you’ll hear from a past admissions reader. However, in our Harvard workshop , you’ll hear from a first-generation student who specializes in education research. 

Yale Supplemental Essays Workshop

Harvard University Supplemental Essays Workshop

In these school-specific workshops, you’ll learn a bit more about how supplemental essays factor into the admissions process. You’ll also learn tips and tricks for how long to spend on your essays and what you can do to make them great.

General Writing Resources

Can’t find resources specific to your school? Don’t worry. We have resources with writing tips you can use for all of your college application essays. You can read up on common college essay topics and how to approach them. In How to Write Better Essays , we’ll give you tips for approaching the Common App vs. supplemental essays and tips for making all of your essays stand out (something a ChatGPT essay writer can’t do!).

ChatGPT and Your College Essays – Final Thoughts

Can ChatGPT write essays? While students can use ChatGPT to produce college essays, a ChatGPT essay writer has significant limitations. Using ChatGPT for essays often results in writing that lacks honesty, accuracy, style, and authenticity. Some schools may start implementing AI detection tools as part of their admissions process, so you’re better off writing your essays on your own (and your application will be stronger for it!).

CollegeAdvisor is here to help students craft the strongest college applications possible — without using AI chatbot for essays. We have countless resources to help you, no matter which schools top your college list . Although writing your essays on your own is more time-consuming, it is definitely worth it in the end. So, be sure to give yourself plenty of time to brainstorm, draft, and edit your essays – good luck!

This article was written by Stefanie Tedards. Looking for more admissions support? Click here to schedule a free meeting with one of our Admissions Specialists. During your meeting, our team will discuss your profile and help you find targeted ways to increase your admissions odds at top schools. We’ll also answer any questions and discuss how CollegeAdvisor.com can support you in the college application process.

Personalized and effective college advising for high school students.

• Advisor Application
• Popular Colleges
• Privacy Policy and Cookie Notice
• Student Login
• California Privacy Notice
• Terms and Conditions
• Your Privacy Choices

By using the College Advisor site and/or working with College Advisor, you agree to our updated Terms and Conditions and Privacy Policy , including an arbitration clause that covers any disputes relating to our policies and your use of our products and services.

• Gradehacker
• Meet the Team
• Essay Writing
• Degree Accelerator
• Entire Class Bundle
• Learning Center
• Gradehacker TV

Write an Essay From Scratch With Chat GPT: Step-by-Step Tutorial

Santiago mallea.

• Best Apps And Tools , Writing Tips

Chief of Content At Gradehacker

Chat GPT Essay Writer: Step-by-Step Tutorial

To write an essay with Chat GPT, you need to:

• Understand your prompt
• Choose a topic
• Write the entire prompt in Chat GPT
• Break down the arguments you got
• Write one prompt at a time
• Check the sources
• Create your first draft
• Edit your draft

Want an Actual Human Help You Write?

If you are looking for a more personalized approach, get in touch with our team and get a top-quality essay!

Want an Actual Human Help You?

How amazing would it be if there was a robot willing to help you write a college essay from scratch?

A few years ago, that may have sounded like something so futuristic that could only be seen in movies. But actually, we are closer than you might think so.

Artificial Intelligence tools are everywhere , and college students have noticed it. Among all, there is one revolutionary AI that learns over time and writes all types of content, from typical conversations to academic texts.

But can Chat GPT write essays from scratch?

We tried it, and the answer is kind so (for now at least.)

Here at Gradehacker, we have years of being the non-traditional adult students’ #1 resource.

We have lots of experience helping people like you write their essays on time or get their college degree sooner , and we know how important it is to be updated with the latest tools.

AIs and Chat GPT are going to stay for a while , so you better learn how to use them properly. If you ever wondered whether it was possible to write an essay from scratch with Chat GPT, you are about to find out!

Now, in case you aren’t familiarized with Chat GPT or don’t know the basics of how it works, we recommend watching our video first!

How we Used Chat GPT to Write Essays

So, to try our experiment with Chat GPT, we created two different college assignments that any student could find:

• An argumentative essay about America's healthcare system
• A book review of George Orwell's 1984

Our main goal is to test Chat GPT’s essay-writing skills and see how much students can use it to write their academic assignments.

Now, we are pretty aware that this (or any) artificial intelligence can carry a wide range of problems such as:

• Giving you incorrect premises and information
• Delivering a piece of writing that is plagiarised from somewhere else
• Does not include citations or list the sources it used
• Is not always available to use

That’s why after receiving our first rough draft, we’ll edit the parts of the text that are necessary and run what we get through our plagiarism checker. After our revision, we’ll ask the AI to expand on the information or make the changes we need.

We’ll consider that final version after our revision as the best possible work that Chat GPT could have done to write an essay from scratch.

And to cover the lack of citations, we’ll see what academic sources the chatbot considers worthy for us to use when writing our paper.

Now, we don’t think that AIs are ready to deliver fully edited and well-written academic writing assignments that you can simply submit to your professor without reading them first.

But is it possible to speed up the writing process and save time by asking Chat GPT to write essays?

Let’s see!

Can Chat GPT Write an Argumentative Paper?

First, we’ll see how it can handle one of the most common academic essays: an argumentative paper.

We chose the American healthcare system as our topic, but as we know that we to find a specific subject with a wide range of sources to write a strong and persuasive essay, we are focusing on structural racism in our healthcare system and how African Americans accessed it during covid.

It’s a clear and specific topic that we included in our list of best topics for your research paper. If you want similar alternatives for college papers, be sure to watch our video !

Instructions and Essay Prompt

Take a position on an issue and compose a 5-page paper that supports it.

In the introduction, establish why your topic is important and present a specific, argumentative thesis statement that previews your argument.

The body of your essay should be logical, coherent, and purposeful. It should synthesize your research and your own informed opinions in order to support your thesis.

Address other positions on the topic along with arguments and evidence that support those positions. 

Write a conclusion that restates your thesis and reminds your reader of your main points.

First Results

After giving Chat GPT this prompt, this is what we received:

To begin with, after copying and pasting these paragraphs into a word document, it only covered two and a half pages.

While the introduction directly tackles the main topic, it fails to provide a clear thesis statement. And even if it’s included in a separate section, the thesis is broad and lacks factual evidence or statistics to support it.

Throughout the body of the text, the AI lists many real-life issues that contribute to the topic of the paper. Still, these are never fully explained nor supported with evidence.

For example, in the first paragraph, it says that “African Americans have long experienced poorer health outcomes compared to other racial groups.” Here it would be interesting to add statistics that prove this information is correct.

Something that really stood up for us, was that Chat GPT credited a source to back up important data, even though it didn’t cite it properly. It talks about a study conducted by the Kaiser Family Foundation that supports that in 2019, 11% of African Americans and 6% of non-Hispanic Whites were uninsured. 

We checked the original article and found that the information was almost 100% accurate . The correct rates were 8% for White Americans and 10.9% for African Americans, but the biggest issue was that the study included more updated statistics from 2021.

Then, when addressing other issues like transportation and discrimination, the problem is presented without any problems, but once again, there are no sources that support them .

Once the essay starts developing the thesis statement on how these issues could be fixed, we can see the same problem.

But even if they lack supporting evidence , the arguments listed are cohesive and make sense . These were:

• Expanding Medicaid coverage
• Provide incentives for healthcare providers to practice in underserved areas
• Invest in telehealth services
• Improve transportation infrastructure, particularly in rural areas
• Train healthcare providers on cultural competence and anti-racism
• Increase diversity in the healthcare workforce
• Implement patient-centered care models

These are all strong ideas that could be stronger and more persuasive with specific information and statistics.

Still, the main problem is that there is no counter-argument that is against the essay’s main arguments.

Overall, Chat GPT delivered a cohesive first draft that tackled the topic by explaining its multiple issues and listing possible solutions. However, there is a clear lack of evidence, no counter-arguments were included, and the essay we got was half the length we needed.

Changes and Final Results

In our second attempt, we asked the AI to expand on each section and subtopic of the essay . While the final result ended up repeating some parts on multiple occasions, Chat GPT wrote more extensively and even included in-text citations with their corresponding reference.

By pasting all these new texts (without editing) into a new document, we get more than seven pages, which is a great starting point for writing a better essay.

Explanation of the issues and use of sources

The new introduction stayed pretty much the same, but the difference is that now the thesis statement is stronger and even had a cited statistic to back it up . Unfortunately, while the information is correct, the source isn’t.

Clicking on the link included in the references took us to a non-existing page , and after looking for that data on Google, we found that it actually belonged to a study from the National Library of Medicine.

But then, the AI did a solid job expanding on the issues that were related to the paper’s topic. But again, while some sources were useful, sometimes the information reflected in the text didn’t correspond to it.

For example, when citing an article posted in KFF to evidence the importance of transportation as a critical factor in health disparities, when we go to the site, we don’t find any mention of that issue.

Similarly, when addressing the higher rates of infection and death compared to White Americans, the AI once again cited the wrong source. The statistics came from a study conducted by the CDC , but from a different article than the one that is credited.

And sometimes, the information displayed was incorrect.

In that same section, when listing the percentages of death in specific states, we see in the cited source that the statistics don’t match.

However, what’s interesting is that if we search for that data on Google, we find a different study that backs it up. So, even if Chat GPT didn’t include inaccurate information in the text, it failed to properly acknowledge the real source.

And so did this problem of having correct information but citing the wrong source continued throughout the paper.

Solutions and counter-arguments

When we asked the AI to write more about the solutions it mentioned in the first draft, we received more extensive arguments with supporting evidence for each case.

As we were expecting , the statistics were real, but the source credited wasn’t the original and didn’t mention anything related to what was included in the text. 

And it wasn’t any different with the counterarguments. They made sense and had a strong point, but the sources credited weren’t correct. 

For instance, regarding telehealth services, it recognized the multiple barriers it would take for low-income areas to adopt this modality. It credited an article posted in the KKF mainly written by “Gillespie,” but after searching for the information, we see that the original study was conducted by other people.

Still, the fact that Chat GPT now provided us with multiple data and information we could use to develop counter-arguments and later refute them is excellent progress. 

The good news is that none of the multiple paragraphs that Chat GPT delivered had plagiarism issues.

After running them through our plagiarism checker, it only found a few parts that had duplicated content, but these were sentences composed of commonly used phrases that other articles about different topics also had.

For example, multiple times it recognized as plagiarism phrases like “according to the CDC” or “according to a report by the Kaiser Family Foundation.” And even these “ plagiarism issues ” could be easily solved by rearranging the order or adding new words.

Checking for plagiarism is a critical part of the essay writing process. If you are not using one yet, be sure to pick one as soon as possible. We recommend checking our list of best plagiarism checkers.

Key Takeaways

So, what did we learn by asking Chat GPT to write an argumentative paper?

• It's better if the AI writes section per section
• It can give you accurate information related to issues, solutions, and counterarguments
• There is a high chance the source credited won't be the right one
• The texts, which can have duplicated content among themselves, don't appear to be plagiarized

It’s clear that we still need to do a lot of editing and writing.

However, considering that Chat GPT wrote this in less than an hour , the AI proved to be a solid tool. It gave us many strong arguments, interesting and accurate statistics, and an order that we cal follow to structure our argumentative paper.

If writing these types of assignments isn’t your strength, be sure to watch our tutorial on how to write an exceptional argumentative essay!

Want to Know Who is Helping You?

At Gradehacker, you have direct communication with your writer. We are here to help!

Can Chat GPT Write a Book Review?

For our second experiment, we want to see if Chat GPT can write an essay for a literature class.

To do so, we picked one of the novels we consider one of the 5 must-read books any college student should read: 1984 by George Orwell. There is so much written and discussed about this literary classic that we thought it would be a perfect choice for an artificial intelligence chatbot like Chat GPT to write something about.

Write a book review of the book 1984 by George Orwell. The paper needs to include an introduction with the author’s title, publication information (Publisher, year, number of pages), genre, and a brief introduction to the review.

Then, write a summary of the plot with the basic parts of the plot: situation, conflict, development, climax, and resolution.

Continue by describing the setting and the point of view and discussing the book’s literary devices.

Lastly, analyze the book, and explain the particular style of writing or literary elements used.

And then write a conclusion.

This is the first draft we got:

Starting with the introduction, all the information is correct , while including the number of pages is worthless as it depends on the edition of the book.

The summary is also accurate, but it relies too heavily on the plot instead of the context and world described in the novel , which is arguably the reason 1984 transcended time. For example, there is no mention of Big Brother, the leader of the totalitarian superstate.

Now, the setting and point of view section is the poorest section written by Chat GPT . It is very short and lacks development.

The literary devices are not necessarily wrong, but it would be better to focus more on each . For instance, talk more about the importance of symbolism or explain how the book critiques propaganda, totalitarianism, and individual freedom.

The analysis of Orwell’s writing is simple , but the conclusion is clear and straightforward, so it might be the best piece that the AI wrote.

For the second draft, instead of submitting the entire prompt, we wrote one command per section . As a result, Chat GPT focused on each part of the review and tossed more paragraphs with more detailed information in every case.

It’s clear that this way, the AI can write better and more developed texts that are easier to edit and improve . Each section analyzes more in-depth the topic it’s reviewing, which facilitates the upcoming process of structuring the most useful paragraphs into a cohesive essay.

For example, it now added more literary devices used by Orwell and gave specific examples of the symbolism of the novel.

Of course, there are many sentences and ideas that are repeated throughout the different sections. But now, because each has more specific information, we can take these parts and structure a new paragraph that comprises the most valuable sentences.

Now, even if sometimes book reviews don’t need to include citations from external sources apart from the novel we are analyzing, Chat GPT gave us five different options for us to choose from.

The only problem was that we couldn’t find any of them on Google.

The names of the authors were real people, but the titles of the articles and essays were nowhere to be found. This made us think that it’s likely that the AI picked real-life writers and created a title for a fictional essay about 1984 or George Orwell .

Finally, we need to see if the texts are original or plagiarized material.

After running it through our plagiarism detection software, we found that it was mostly original content with only a few issues on sight . But nothing too big to worry about.

One easy-to-solve example is in the literary devices section, where it directly quotes a sentence from the book. In this case, we would just need to add the in-text citation.

The biggest plagiarism problem was with one sentence (or six words, to be more specific) from the conclusion that linked to the introduction from a summary review . But by rearranging the word order or adding synonyms, this issue can be easily solved too.

So, what are the most important tips we can take from Chat GPT writing a book review?

• It will review each section more in-depth if you ask it one prompt at a time
• The analysis and summary of the book were accurate
• If you ask it to list scholarly sources, the AI will create unexisting sources based on real authors
• Very few plagiarism issues

Once again, there is still a lot of work to do.

The writing sample chat GPT gave us is a solid start, but we need to rearrange all the paragraphs into one cohesive essay that perfectly summarizes the different aspects of the novel. Plus, we would also have to find scholarly sources on our own.

Still, the AI can do the heavy lifting and give you a great starting point.

If writing book reviews isn’t your strong suit, you have our tutorial and tips!

Having Doubts on How we Can Help You?

Get in touch with us!

Save Time And Use Chat GPT to Write Your Essay

We know that writing essays can be a tedious task.

Sometimes, kicking off the process can be harder than what it looks. That’s why understanding how to use a powerful tool like Chat GPT can truly make the difference.

It may not have the critical thinking skills you have or write a high-quality essay from scratch, but by using our tips, it can deliver you a solid first draft to start writing your entire essay.

But if you want to have an expert team of writers giving you personalized support or aren’t sure about editing an AI-written essay, you can trust Gradehacker to help you with your assignments.

You can also check out our related blog posts if you want to learn how to take your writing skills to the next level!

7 Best Websites to Find Free College Textbooks in 2023

Best iPads For College Students

How To Be More Productive | Tips For Non-Traditional Students

Studying with Mnemonic Techniques 

How To Nail Every Discussion Board | Tips To Improve Your Discussion Posts

Study Habits That Keep College Students Focused

Santiago Mallea is a curious and creative journalist who first helped many college students as a Gradehacker consultant in subjects like literature, communications, ethics, and business. Now, as a Content Creator in our blog, YouTube channel, and TikTok, he assists non-traditional students improve their college experience by sharing the best tips. You can find him on LinkedIn .

• Best Apps and Tools
• Writing Tips
• Financial Tips and Scholarships
• Career Planning
• Non-Traditional Students
• Student Wellness
• Cost & Pricing

• 2525 Ponce de Leon Blvd Suite 300 Coral Gables, FL 33134 USA
• Phone: (786) 991-9293
• Gradehacker 2525 Ponce de Leon Blvd Suite 300 Coral Gables, FL 33134 USA

About Gradehacker

Business hours.

Mon - Fri: 10:00 am - 7 pm ET ​​Sat - Sun: 10 am - 3 pm ET ​

© 2024 Gradehacker LLC All Rights Reserved.

New bot ChatGPT will force colleges to get creative to prevent cheating, experts say

After its viral launch last week, the chatbot ChatGPT was lauded online by some as a dramatic step forward for artificial intelligence and the potential future of web search.

But with such praise also came concern regarding its potential usage in academic settings. Could the chatbot, which provides coherent, quirky and conversational responses to simple language inquiries, inspire more students to cheat?

Students have been able to cheat on assignments using the internet for decades, giving rise to tools meant to check if their work was original. But the fear now is that ChatGPT could render those resources obsolete.

Already, some people online have tested out whether it's possible to have the bot complete an assignment. "holyyyy, solved my computer networks assignment using chatGPT," one person, who later clarified the assignment was old, tweeted . Others suggested that its existence could result in the death of the college essay. One technologist went as far as saying that with ChatGPT, "College as we know it will cease to exist."

Artificial intelligence company OpenAI, which developed ChatGPT , did not immediately respond to a request for comment regarding cheating concerns.

However, several experts who teach in the field of AI and humanities said the chatbot, while impressive, is not something they’re ready to sound the alarm about when it comes to possible widespread student cheating.

"We’re not there, but we’re also not that far away," said Andrew Piper, a professor of language, literatures and culture and a professor of AI and storytelling at McGill University. "We’re definitely not at the stage of like, out-of-the-box, it’ll write a bunch of student essays and no one will be able to tell the difference."

Piper and other experts who spoke with NBC News likened the fear around cheating and ChatGPT to concerns that arose when the calculator was invented, when people thought it would be the death of humans learning math.

Lauren Klein, an associate professor in the Departments of English and Quantitative Theory and Methods at Emory University, even compared the panic to the philosopher Plato’s fears that writing would dissolve human memory.

“There’s always been this concern that technologies will do away with what people do best, and the reality is that people have had to learn how to use these technologies to enhance what they do best,” Klein said.

There’s always been this concern that technologies will do away with what people do best, and the reality is that people have had to learn how to use these technologies to enhance what they do best.

— Lauren Klein, an associate professor at Emory University

Academic institutions will need to get creative and find ways to integrate new technologies like ChatGPT into their curriculum just like they did during the rise of the calculator, Piper noted.

In reality, AI tools like ChatGPT could actually be used to enhance education, according to Paul Fyfe, an associate professor of English at North Carolina State University.

He said there’s plenty of room for collaboration between AI and educators.

“It’s important to be talking about this right now and to bring students into the conversation," Fyfe said. "Rather than try to legislate from the get-go that this is strange and scary, therefore we need to shut it down."

And some teachers are already embracing AI programs in the classroom.

Piper, who runs .txtlab, a research laboratory for artificial intelligence and storytelling, said he’s had students analyze AI writing and found they can often tell which papers were written by a machine and which were written by a human.

As for educators who are concerned about the rise of AI, Fyfe and Piper said the technology is already used in many facets of education.

Computer-assisted writing tools, such as Grammarly or Google Doc’s Smart Compose, already exist — and have long been utilized by many students. Platforms like Grammarly and Chegg also offer plagiarism checker tools, so both students and teachers can assess if an essay has been, in part or in total, lifted from somewhere else. A spokesperson for Grammarly did not return a request for comment. A spokesperson for Chegg declined to comment.

Those who spoke with NBC News said they're not aware of any technology that detects if an AI wrote an essay, but they predict that someone will soon capitalize on building that technology.

As of right now, Piper said the best defense against AI essays is teachers getting to know their students and how they write in order to catch a discrepancy in the work they're turning in.

When an AI does reach the level of meeting all the requirements of academic assignments and if students use that technology to coast through college, Piper warned that could be a major detriment to students' education.

For now, he suggested an older technology to combat fears of students using ChatGPT to cheat.

"It will reinvigorate the love of pen and paper," he said.

Kalhan Rosenblatt is a reporter covering youth and internet culture for NBC News, based in New York.

• 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.

ChatGPT in Higher Education: Facts and Ideas to Consider

Introduction

It is safe to say that by now, you have seen many articles/posts, opinions, and stories about ChatGPT—and the larger AI-Language Learning Models (LLMs)—in relation to higher education and teaching/learning in particular. These writings included several perspectives ranging from raising concerns to celebrating new opportunities and a mix of the former and the latter. Also, these writings continue to evolve and grow rapidly in number as new AI-powered LLMs continue to emerge and evolve (e.g., Google’s new AI LLMs: Bard ).

The intent of this piece is not to add another article sharing tips or concerns about ChatGPT. That being said, this article (1) summarizes the major concerns about ChatGPT and (2) the ideas about its positive implications based on what it is published to date.

Concerns about ChatGPT

Faculty, scholars, and higher education leaders have raised several concerns about ChatGPT. These concerns stem from possible ways it can be used.

• Using ChatGPT to cheat by asking it to write essays/answer open-ended questions in exams/discussion forums and homework assignments (December 19th, 2022 NPR Story ) (December 6th, 2022 Atlantic Story ) (January 16 New York Times Story ).
• Using ChatGPT to author scholarly works which conflict with the ethical standards of scientific inquiry. Several high-impact/profile journals have already formulated principles to guide authors on how to use LLMs AI tools and why it is not allowed to credit such tool as an author—any attribution of authorship carries with it accountability for the scholarly work, and no AI tool can take such responsibility (January 24th, 2023 Nature Editorial ).
• ChatGPT can threaten the privacy of students/faculty (and any other user). Its privacy policy states that data can be shared with third-party vendors, law enforcement, affiliates, and other users. Also, while one can delete their ChatGPT account, the prompts they entered into ChatGPT cannot be deleted. This setup threatens sensitive or controversial topics as this data cannot be removed (January 2023 Publication by Dr. Torrey Trust ).
• ChatGPT is not always trustworthy, as it can fabricate quotes and references. In an experiment conducted by Dr. Daniel Hickey at Indiana University Bloomington, Instructional Systems Technology department, “ ChatGPT was able to write a marginally acceptable literature review paper, but fabricated some quotes and references. With more work such as including paper abstracts in the prompts, GPT is scarily good at referencing research literature, perhaps as well as a first-year graduate student.” (January 6th, 2023, Article by Dr. Daniel Hickey )

Excitement about ChatGPT

At the other end of the spectrum, there have been several ideas that express interest and excitement about ChatGPT in higher education. These ideas stem from how they can be used ethically and in a controlled manner.

• Using ChatGPT to speed up the writing of drafts for several outlets (reports, abstracts, emails, conference proposals, press releases, recommendation letters, etc.) ChatGPT can produce elaborated writing that must be edited to remove any possible inconsistencies or inaccuracies (December 7th, 2022 Social Science Space story )
• Using ChatGPT in the process of brainstorming ideas for curriculum design, lesson planning, and learning activities. The tool can provide some novel ideas or remind educators of some instructional techniques and strategies that they had heard about in the past (January 23rd, 2023, Article by Dr. David Wiley ).
• Using ChatGPT to provide students tutoring/scaffolds. The tool can act like a virtual tutor who does not simply give the answer to the student but rather scaffold them to reach the correct answers by themselves. (Sal Khan, founder/CEO of Khan Academy, Spring 2023 TED Talk )
• Teaching with ChatGPT to train students on using AI tools and models, provide opportunities to exercise critical thinking skills, and improve their technological literacy (January 12th New York Times story ).

Concluding Thoughts

There are major concerns about ChatGPT and the larger AI-powered Language Learning Models (LLMs) phenomenon. These concerns are legitimate and are opposed by notable ideas about the positive implications of AI-powered LLMs in higher education classrooms. As we aspire to make evidence-based educational and learning design decisions, one should carefully review the research that has been done on AI in relation to higher education up to this point and engage with the gaps as opportunities to expand knowledge and find new opportunities and risks.

Our University’s newly formed advisory committee on the applications of generative AI is a good example of how higher education institutions ought to recommend the use, evaluation, and development of emergent AI tools and services. Additionally, discussions about generative AI and its implications on education happening in public venues are necessary to strengthen the public-facing mission of the University, where input from educators, students, and members of the community is welcome.

Related Articles

Generative AI for Course Design: Crafting Learning Objectives

Generative AI for Course Design: The Basics

Featured Topics

Featured series.

A series of random questions answered by Harvard experts.

Explore the Gazette

Read the latest.

Roger Ware Brockett, 84

Providing community support

A change of mind, heart, and soul

“Telling people not to use ChatGPT is not preparing people for the world of the future,” said Sam Altman, CEO of OpenAI.

Niles Singer/Harvard Staff Photographer

Did student or ChatGPT write that paper? Does it matter?

Sam Altman, CEO of firm that developed app, says ethics do matter, but they need to be rethought (and AI isn’t going away)

Harvard Correspondent

Colleges and universities have been wrestling with concerns over plagiarism and other ethical questions surrounding the use of AI since the emergence of ChatGPT in late 2022.

But Sam Altman, whose company, OpenAI, launched the chatbot app, said during a campus visit Wednesday that AI is such a powerful tool that higher education would be doing its students a disservice by turning its back on it — if that were even possible now. And some of the old rules of ethics will need to be rethought.

“Cheating on homework is obviously bad,” said Altman. “But what we mean by cheating and what the expected rules are does change over time.”

Altman discussed AI in the academy, along with the subtleties of using ChatGPT and other generative AI tools, while at the University to receive the Experiment Cup from Xfund , an early stage venture capital firm. That event was sponsored by the John A. Paulson School for Engineering and Applied Science, Harvard Business School, and the Institute for Business in Global Society ( BiGS ). It featured a conversation between Altman and Xfund co-founder Patrick Chung ’96.

Speaking to the Gazette before the Cup presentation, Altman likened the initial uproar at schools over ChatGPT to the ones that arose after the arrival of calculators and, later, search engines like Google. “People said, ‘We’ve got to ban these because people will just cheat on their homework,’” he said.

Altman, who left Stanford at 19 to start Loopt, a location-sharing social media app, said the reaction to calculators, for instance, was overblown. “If people don’t need to calculate a sine function by hand again … then mathematical education is over,” he said, with a gentle half-smile on his face.

Altman helped launch OpenAI in 2015 and its wildly influential ChatGPT — which can write papers and generate computer programs, among other things — before being removed in 2023 and then reinstated four days later as the company’s CEO.

ChatGPT, he said, has the potential to exponentially increase productivity in the same way calculators freed users from performing calculations by hand, calling the app “a calculator for words.”

He warned, “Telling people not to use ChatGPT is not preparing people for the world of the future.”

Following a bit of back-and-forth about how the ethics of using ChatGPT and other generative AI may differ in various disciplines, Altman came down hard in favor of utility, praising AI’s massive potential in every field.

“Standards are just going to have to evolve,” he said. He dismissed the notion that ChatGPT could be used for writing in the sciences, where the emphasis is on the findings, but not in the humanities, where the expression of ideas is central.

“Writing a paper the old-fashioned way is not going to be the thing,” he said. “Using the tool to best discover and express, to communicate ideas, I think that’s where things are going to go in the future.”

Altman, who last month joined the Department of Homeland Security’s Artificial Intelligence Safety and Security Board , said ethics remains a concern, and one that has yet to be resolved.

“There will be a conversation about what are the absolute limits of the tool, how do we as a society … negotiate ‘Here is what AI systems can never do.’ Where do we set the defaults? How much does an individual user get to move things around within those boundaries? How do we think about different countries’ laws?”

However, that discussion should not slow the development of AI. Instead, Altman described parallel tracks.

“Generally speaking, I do think these are tools that should do what their users want,” he said, before adding an important, if less than specific, caveat: “But there are going to have to be real limits.”

Share this article

You might like.

Memorial Minute — Faculty of Arts and Sciences

Harvard Allston Partnership Fund awards grants to 26 Allston-Brighton nonprofits

Choosing Harvard took LyLena Estabine down an uncertain path. The former student co-president has no regrets.

Epic science inside a cubic millimeter of brain

Researchers publish largest-ever dataset of neural connections

Excited about new diet drug? This procedure seems better choice.

Study finds minimally invasive treatment more cost-effective over time, brings greater weight loss

How far has COVID set back students?

An economist, a policy expert, and a teacher explain why learning losses are worse than many parents realize

Impacts of ChatGPT-assisted writing for EFL English majors: Feasibility and challenges

• Published: 11 May 2024

Cite this article

• Chung-You Tsai   ORCID: orcid.org/0000-0003-0527-1830 1 , 2 ,
• Yi-Ti Lin   ORCID: orcid.org/0000-0002-0258-595X 3 &
• Iain Kelsall Brown   ORCID: orcid.org/0009-0003-2792-7498 3  

To determine the impacts of using ChatGPT to assist English as a foreign language (EFL) English college majors in revising essays and the possibility of leading to higher scores and potentially causing unfairness.

A prospective, double-blinded, paired-comparison study was conducted in Feb. 2023. A total of 44 students provided 44 original essays and 44 ChatGPT-assisted revised essays, which were rated by two independent graders in a randomized and crossover fashion to minimize grading bias. The original and revision scores were paired for before-after comparison. Eight control essays were also rated by both graders to ensure inter-rater reliability.

This study used a rigorous experimental design to confirm that ChatGPT-assisted revised essays led to significantly higher scores for EFL college English majors. Significant improvements were observed in all four dimensions of writing quality assessment, with the largest effects observed in vocabulary, followed by grammar, organization, and content. ChatGPT-assisted revised essays shifted the score curve from a normal distribution to a skewed distribution towards higher grades, with the greatest increase in revision scores seen among students who had lower original scores. This disproportionate improvement raises concerns about fairness in evaluation.

The findings suggest that ChatGPT is effective in providing timely feedback to EFL English majors in an affordable manner, but it also highlights the potential for unfairness in writing evaluation. We should note that ChatGPT-assisted revisions do not reveal learners’ writing competence. Therefore, new forms of writing performance assessment should be implemented in EFL composition classes in this AI era.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price includes VAT (Russian Federation)

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Data availability

Data is available upon reasonable request to the corresponding author.

Carvalho, L., Martinez-Maldonado, R., Tsai, Y.-S., Markauskaite, L., & De Laat, M. (2022). How can we design for learning in an AI world? Computers and Education: Artificial Intelligence, 3 , 1–9. https://doi.org/10.1016/j.caeai.2022.100053

Article   Google Scholar  

Cotton, D. R., Cotton, P. A., & Shipway, J. R. (2024). Chatting and cheating: Ensuring academic integrity in the era of ChatGPT. Innovations in Education and Teaching International , 61 (2), 228–239.

Fang, Y. (2010). Perceptions of the Computer-Assisted Writing Program among EFL College Learners. Journal of Educational Technology & Society, 13 (3), 246–256.

Google Scholar  

Gao, C. A., Howard, F. M., Markov, N. S., Dyer, E. C., Ramesh, S., Luo, Y., & Pearson, A. T. (2023). Comparing scientific abstracts generated by ChatGPT to real abstracts with detectors and blinded human reviewers. NPJ Digital Medicine, 6 (1), 75.

Godwin-Jones, R. (2022). Partnering with AI: Intelligent writing assistance and instructed language learning. Language Learning & Technology, 26 (2), 5–24.

Henrickson, L. (2022). Cheating on your college essay with ChatGPT won’t get you good grades, say professors – but AI could make education fairer. Insider . https://www.businessinsider.com/professors-say-chatgpt-wont-kill-college-essays-make-education-fairer-2022-12 . Accessed 17 Jan 2023.

Li, J. (2021). Research on AI-assisted hybrid teaching for English writing. In 2021 International Conference on Computers, Information Processing and Advanced Education (CIPAE), (pp. 309–312). IEEE.

Lim, W. M., Gunasekara, A., Pallant, J. L., Pallant, J. I., & Pechenkina, E. (2023). Generative AI and the future of education: Ragnarök or reformation? A paradoxical perspective from management educators. The International Journal of Management Education, 21 (2), 100790.

Qi, D. S., & Lapkin, S. (2001). Exploring the role of noticing in a three-stage second language writing task. Journal of Second Language Writing, 10 (4), 277–303.

Ranalli, J., & Yamashita, T. (2022). Automated written corrective feedback: Error-correction performance and timing of delivery. Language Learning & Technology, 26 (1), 1–25.

Rudolph, J., Tan, S., & Tan, S. (2023). ChatGPT: Bullshit spewer or the end of traditional assessments in higher education? Journal of Applied Learning and Teaching, 6 (1), 342–363.

Sachs, R., & Polio, C. (2007). Learners’ uses of two types of written feedback on a L2 writing revision task. Studies in Second Language Acquisition, 29 (1), 67–100.

Saricaglu, A. (2019). The impact of automated feedback on L2 learners’ written causal explanations. ReCALL, 31 (2), 189–203. https://doi.org/10.1017/S095834401800006X

Selber, S. (2022). Cheating on your college esssay with ChatGPT won’t get you good grades, say professors – but AI could make education fairer. Insider .  https://www.businessinsider.com/professors-say-chatgpt-wont-kill-college-essays-make-education-fairer-2022-12 . Accessed 16 Jan 2023.

Stacey, S. (2022). Cheating on your college essay with ChatGPT won’t get you good grades, say professors – but AI could make education fairer. Insider . https://www.businessinsider.com/professors-say-chatgpt-wont-kill-college-essays-make-education-fairer-2022-12 . Accessed 16 Jan 2023.

Stokel-Walker, C. (2022). AI bot ChatGPT writes smart essays – should professors worry? Nature . https://doi.org/10.1038/d41586-022-04397-7

Straume, I., & Anson, C. (2022). Amazement and Trepidation: Implications of AI-Based Natural Language Production for the Teaching of Writing. Journal of Academic Writing, 12 (1), 1–9. https://doi.org/10.18552/joaw.v12i1.820

Susnjak, T. (2022). ChatGPT: The end of online exam integrity? arXiv . https://doi.org/10.48550/arXiv.2212.09292

Truscott, J., & Smith, M. S. (2011). Input, intake, and consciousness: The quest for a theoretical foundation. Studies in Second Language Acquisition, 33 (4), 497–528.

Zhai, X. (2022). ChatGPT user experience: Implications for education. SSRN Electronic Journal . https://doi.org/10.2139/ssrn.4312418

Zomer, Z., & Frankenberg-Garcia, A. (2021). Beyong Grammar Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder models. In Findings of the Association for Computational Linguistics: EMNLP 2021 (pp. 2534–2540).

Download references

Author information

Authors and affiliations.

Division of Urology, Department of Surgery, Far Eastern Memorial Hospital, New Taipei City, Taiwan

Chung-You Tsai

Department of Electrical Engineering, Yuan Ze University, Taoyuan City, Taiwan

Department of English, Tamkang University, New Taipei City, Taiwan

Yi-Ti Lin & Iain Kelsall Brown

You can also search for this author in PubMed   Google Scholar

Contributions

C.Y. Tsai contributed to study design, data analysis, and the first draft of the manuscript, while Y.T. Lin contributed to data acquisition, discussion, and critical revision as a corresponding author. I. Brown contributed to data acquisition.

Corresponding author

Correspondence to Yi-Ti Lin .

Ethics declarations

The participants were protected in accordance to the ethics guidelines and the details were described in the section on participants.

Competing Interests

We, the authors, declare that we have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 377 KB)

Rights and permissions.

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Tsai, CY., Lin, YT. & Brown, I.K. Impacts of ChatGPT-assisted writing for EFL English majors: Feasibility and challenges. Educ Inf Technol (2024). https://doi.org/10.1007/s10639-024-12722-y

Download citation

Received : 24 August 2023

Accepted : 16 April 2024

Published : 11 May 2024

DOI : https://doi.org/10.1007/s10639-024-12722-y

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Artificial intelligence
• AI-assisted writing
• EFL writing
• Find a journal
• Publish with us
• Track your research

How to use ChatGPT to write code: What it can and can't do for you

O ne of the more intriguing discoveries about ChatGPT is that it can write pretty good code. I first tested this out last year when I asked it to write a WordPress plugin my wife could use on her website. ChatGPT did a fine job, but it was a very simple project. 

How to use ChatGPT to write: Resumes  | Excel formulas | Essays | Cover letters  

So, how can you use ChatGPT to write code as part of your daily coding practice? Here's a quick summary:

• ChatGPT can produce both useful and unusable code. For best results, provide clear and detailed prompts.
• ChatGPT excels in assisting with specific coding tasks or routines, rather than building complete applications from scratch.
• Use ChatGPT to find and choose the right coding libraries for specific purposes, and engage in an interactive discussion to narrow down options.
• Be cautious about the ownership of AI-generated code and always verify the code's reliability. Don't blindly trust the generated output.
• Treat interactions with ChatGPT as a conversation. Refine your questions based on the AI's responses to get closer to the desired output.

Now, let's explore ChatGPT in considerably more depth.

What types of coding can ChatGPT do well?

There are two important facts about ChatGPT and coding. The first is that the AI can, in fact, write useful code. 

The second is that it can get completely lost, fall down a rabbit hole, chase its own tail, and produce unusable garbage.

Also: The best free AI courses

I found this out the hard way. After I finished the WordPress plugin, I decided to see how far ChatGPT could go. 

I wrote out a very careful prompt for a Mac application, including detailed descriptions of user interface elements, interactions, what would be provided in settings, how they would work, and so on. Then, I fed the prompt to ChatGPT.

ChatGPT responded with a flood of text and code. Then, it stopped mid-code. When I asked it to continue, it vomited out even more code and text. I requested continue after continue, and it dumped out more and more code. But... none of it was usable . It didn't identify where the code should go, how to construct the project, and -- when I looked carefully at the code produced -- it left out major operations I requested, leaving in simple text descriptions stating "program logic goes here".

Also: Yikes! Microsoft Copilot failed every single one of my coding tests

After a bunch of repeated tests, it became clear to me that if you ask ChatGPT to deliver a complete application, it will fail. A corollary to this observation is that if you know nothing about coding and want ChatGPT to build you something, it will fail.

Where ChatGPT succeeds -- and does so very well -- is in helping someone who already knows how to code to build specific routines and get specific tasks done. Don't ask for an app that runs on the menu bar. But if you ask ChatGPT for a routine to put a menu on the menu bar, and then paste that into your project, the tool will do quite well.

Also, keep in mind that while ChatGPT appears  to have a tremendous amount of domain-specific knowledge (and it often does), it lacks wisdom . As such, the tool may be able to write code, but it won't be able to write code containing the nuances for very specific or complex problems that require deep experience to understand.

Also:  How to use ChatGPT to create an app

Use ChatGPT to demo techniques, write small algorithms, and produce subroutines. You can even get ChatGPT to help you break down a bigger project into chunks, and then you can ask it to help you code those chunks.

So, with that in mind, let's look at some specific steps for how ChatGPT can help you write code.

• How to use ChatGPT to write code

I started with a prompt that was designed to elicit information about what libraries would provide the functionality I wanted. A library (for those of you reading along who aren't programmers) is a body of code a programmer can access that does a lot of the heavy lifting for a specific purpose. A big part of modern programming is finding and choosing the right libraries, so this is a good starting point.

In this case, I'm looking at blocks of code written by other people that will summarize text. Here's my first prompt:

Describe ten different open source AI libraries (and the languages they work with) that I can use to generate a summary of the main core contents of any web page, ignoring any ads or embedded materials.

This prompt gave me exactly what I wanted, including a mention of OpenAI's offerings. I think OpenAI would do great here, but for this hypothetical project, I don't want to budget for API fees. So. I'll narrow down the question:

Are any of these free?

ChatGPT hedged its bets with its answer. Here's what it said: "Yes, all ten of these AI libraries are open source and free to use. However, some of them may have usage limits or require payment for access to additional features or resources." So, based on that, I clarified my query:

Which of these libraries have no usage limits and don't require any additional payment or licensing?

Notice how this is very much a conversation. I don't have to re-ask the originating question. I'm just drilling down in the same way I might if I had an expert at hand and was seeking clarification. In this case, ChatGPT gave me eight library choices, but none of them mentioned the PHP language that I was planning to code in. So, here's the next prompt:

Of those 8 libraries, can I use any with PHP?

It returned three libraries, but I wasn't sure about what each did. So, another question:

What's the difference between Sumy, Gensim, and NLTK?

I still wasn't sure, so I clarified my use plan and then asked:

If I want to create summaries of web page news articles, which library would work better?

The answer I got was clear and promising: "Sumy is specifically designed for text summarization, which is the task of creating a summary that captures the most important information from a piece of text." So, now it was time to see what was involved in using Sumy with PHP. I asked my last question for this part of the project:

Can you explain how to use Sumy from PHP?

Feel free to play along on your computer and paste these prompts into your instance of ChatGPT. Notice that, in step one, I decided what program module I was going to get help on. Then, in this step, I had a conversation with ChatGPT to decide what library to use and how to integrate it into my project.

Also: The best AI chatbots

That may not seem like programming, but I assure you it is. Programming isn't just blasting lines of code onto a page. Programming is figuring out how to integrate all the various resources and systems together, and how to talk to all the various components of your solution. Here, ChatGPT helped me do that integration analysis.

By the way, I was curious whether Google's Gemini AI (formerly Bard) could help in the same way. Gemini can't actually write code, but it did give some extra insights into the planning aspect of programming over ChatGPT's responses. So, don't hesitate to use multiple tools to triangulate on answers you want. Here's that story: Gemini vs. ChatGPT: Can Gemini help you code?  Since I wrote that article, Google added some coding capabilities to Gemini, but they're not all that great. You can read about it here: I tested Google Gemini's new coding skills. It didn't go well . And even more recently, I dug into Gemini Advanced . It's still not passing many tests.

Also: How I test an AI chatbot's coding ability - and you can too

Coding is next. 

That limitation means you have to do it yourself. As we know, the first draft of a piece of code is rarely the final code. So, even if you were to expect ChatGPT to generate final code, it would really be a starting point, one where you need to take it to completion, integrate it into your bigger project, test it, refine it, debug it, and so on.

Also:   I asked ChatGPT to write a short Star Trek episode. It actually succeeded

But that doesn't mean the example code is worthless -- far from it. Let's take a look at a prompt I wrote based on the project I described earlier. Here's the first part:

Wite a PHP function called summarize_article. As input, summarize_article will be passed a URL to an article on a news-related site like ZDNET.com or Reuters.com.

I'm telling ChatGPT the programming language it should use. I'm also telling it the input but, while doing so, providing two sites as samples to help ChatGPT understand the style of article. Honestly, I'm not sure ChatGPT didn't ignore that bit of guidance. Next, I'll tell it how to do the bulk of the work:

Inside summarize_article, retrieve the contents of the web page at the URL provided. Using the library Sumy from within PHP and any other libraries necessary, extract the main body of the article, ignoring any ads or embedded materials, and summarize it to approximately 50 words. Make sure the summary consists of complete sentences. You can go above the 50 words to finish the last sentence, if necessary.

This is very similar to how I'd instruct an employee. I'd want that person to know that they weren't only restricted to Sumy. If they needed another tool, I wanted them to use it. 

Also: How to get a perfect face match using Midjourney AI

I also specified an approximate number of words to create bounds for what I wanted as a summary. A later version of the routine might take that number as a parameter. I then ended by saying what I wanted as a result:

Once processing is complete, code summarize_article so it returns the summary in plain text.

The resulting code is pretty simple. ChatGPT did call on another library (Goose) to retrieve the article contents. It then passed that summary to Sumy with a 50-word limit and then returned the result. But once the basics are written, it's a mere matter of programming to go back in and add tweaks, customize what's passed to the two libraries, and delivering the results.

One interesting point of note. When I originally tried this test in early 2023, ChatGPT created a sample call to the routine it wrote, using a URL from after 2021. At that time, in March 2023, ChatGPT's dataset only went to 2021. Now, the ChatGPT knowledge base extends to the end of December 2023. But my point is that ChatGPT made up a sample link that it couldn't possibly know about:

https://www.reuters.com/business/retail-consumer/teslas-musk-says-fremont-california-factory-may-be-sold-chip-shortage-bites-2022-03-18/

I checked that URL against both Reuters' site and the Wayback Machine, and it doesn't exist. Never assume ChatGPT is accurate. Always double-check everything it gives you.

Does ChatGPT replace programmers? 

Not now -- or, at least -- not yet. ChatGPT programs at the level of a talented first-year programming student, but it's lazy (like that first-year student). The tool might reduce the need for entry-level programmers, but at its current level, I think it will just make life easier for entry-level programmers (and even programmers with more experience) to write code and look up information. It's definitely a time-saver, but there are few programming projects it can do on its own -- at least now. In 2030? Who knows.

How do I get coding answers in ChatGPT?

Just ask it. You saw above how I used an interactive discussion dialog to narrow down the answers I wanted. When you're working with ChatGPT, don't expect one question to magically do all your work for you. But use ChatGPT as a helper and resource, and it will give you a lot of very helpful information. Of course, test that information -- because, as John Schulman, a co-founder of OpenAI, says , "Our biggest concern was around factuality, because the model likes to fabricate things."

Is the code generated by ChatGPT guaranteed to be error-free?

Hell, no! But you also can't trust the code human programmers write. I certainly don't trust any code I write. Code comes out of the code-making process incredibly flawed. There are always bugs. Before you ship, you need to test, test, and test again. Then, alpha test with a few chosen victims. Then beta test with your wider user community. Even after all that, there will be bugs. Just because an AI is playing at this coding thing doesn't mean it can do bug-free code. Do not trust. Always verify. And you still won't have it fully bug-free. Such is the nature of the universe.

How detailed should my description of a programming issue be when asking ChatGPT?

Detailed. Look at it this way: the more you leave open for interpretation, the more the AI will go its own way. When I give prompts to ChatGPT to help me while programming, I imagine I'm assigning a programming task to one of my students or someone who works for me. Did I give that person enough details to go off and create a first draft or will that person have to ask me a ton of additional questions? Worse, will that person have so little guidance that they'll go off in entirely the wrong direction? Don't be lazy here. ChatGPT can save you hours or even days programming (it has for me), but only if you give it useful instructions to begin with.

If I use ChatGPT to write my code, who owns it?

As it turns out, there's not a lot of case law yet to definitively answer this question. The US, Canada, and the UK require something that's copyrighted to have been created by human hands, so code generated by an AI tool may not be copyrightable. There are also issues of liability based on where the training code came from and how the resulting code is used. ZDNET did a deep dive on this topic, spoke to legal experts, and produced the following three articles. If you're concerned about this issue (and if you're using AI to help with code, you should be), I recommend you give them a read.

• Who owns the code? If ChatGPT's AI helps write your app, does it still belong to you?
• If you use AI-generated code, what's your liability exposure?
• A thorny question: Who owns code, images, and narratives generated by AI?

What programming languages does ChatGPT know?

Most of them.  I tested common modern languages , like PHP, Python, Java, Kotlin, Swift, C#, and more. But then I had the tool  write code in obscure dark-age languages like COBOL, Fortran, Forth, LISP, ALGOL, RPG (the report program generator, not the role-playing game), and even IBM/360 assembly language. 

As the icing on the cake, I gave it this prompt:

Write a sequence that displays 'Hello, world' in ascii blinking lights on the front panel of a PDP 8/e

The PDP 8/e was my very first computer , and ChatGPT actually gave me instructions for toggling in a program using front-panel switches. I was impressed, gleeful, and ever so slightly afraid.

Can ChatGPT help me with data analysis and visualization tasks?

Yes, and a lot of it can be done without code. Check out my entire article on this topic:  The moment I realized ChatGPT Plus was a game-changer for my business .

I also did a piece on generated charts and tables:  How to use ChatGPT to make charts and tables

But here's where it gets fun. In the article above, I asked ChatGPT Plus "Make a bar chart of the top five cities in the world by population," and it did. But do you want code? Try asking:

Make a bar chart of the top five cities in the world by population in Swift. Pull the population data from online. Be sure to include any necessary libraries.

By adding "in Swift," you're specifying the programming language. By specifying where the data comes from and forcing ChatGPT Plus to include libraries, it knows to bring in the other resources the program needs. That's why, fundamentally, programming with an AI's help requires you to know things about programming. But if you do, it's cool. Because three sentences can get you a nice chunk of annotated code. Cool, huh?  

How does ChatGPT handle the differences between dialects and implementations of a given programming language?

We don't have exact details on this issue from OpenAI, but our understanding of how ChatGPT is trained can shed some light on this question. Keep in mind that dialects and implementations of programming languages (and their little quirks) change much more rapidly than the full language itself. This reality makes it harder for ChatGPT (and many programming professionals) to keep up.

Also:  How I used ChatGPT to write a custom JavaScript bookmarklet

As such, I'd work off these two assumptions:

• The more recent the dialectic change, the less likely ChatGPT knows about it, and
• The more popular a language overall, the more training data it likely has learned from, and therefore the more accurate it will be.

What's the bottom line? ChatGPT can be a very helpful tool. Just don't ascribe superpowers to it. Yet.

You can follow my day-to-day project updates on social media. Be sure to follow me on Twitter at @DavidGewirtz , on Facebook at Facebook.com/DavidGewirtz , on Instagram at Instagram.com/DavidGewirtz , and on YouTube at YouTube.com/DavidGewirtzTV .

• How to use ChatGPT to write Excel formulas
• ChatGPT vs. Bing Chat: Which AI chatbot should you use?
• How to use ChatGPT to build your resume
• How does ChatGPT work?
• How to get started using ChatGPT