college essays and chat gpt

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.

Student and Parent Forum

Our new student and parent forum, at ExpertHub.PrepScholar.com , allow you to interact with your peers and the PrepScholar staff. See how other students and parents are navigating high school, college, and the college admissions process. Ask questions; get answers.

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.

Search form

Chatgpt on campus: assessing its effects on college writing — and teaching.

Image generated by AI from a text prompt (Michael S. Helfenbein)

Since its public launch in November, the platform ChatGPT has generated a tsunami of news analyses and online discussions about how it and similar artificial intelligence (AI) technologies might upend the world as we know it.

Given the app’s ability to quickly produce cogent summaries of knowledge and comparisons of different viewpoints — the kinds of tasks commonly assigned in introductory college courses — many university professors and scholars have wondered what its evolution might mean for college writing.

At Yale, instructors looking for advice about this and other AI-related topics have been coming to the Poorvu Center for Teaching and Learning, where Alfred Guy has taken a lead role in developing faculty guidance in response to ChatGPT . Guy has directed writing programs at major universities for 30 years, including two decades at Yale. At Yale College, he is assistant dean of academic affairs and the R.W.B. Lewis Director of Writing, overseeing courses across 40 academic departments and programs.

Guy, whose own research explores the link between writing and intellectual development for undergraduate students, is also director of undergraduate writing and tutoring at the Poorvu Center. In that role he manages more than 100 undergraduate, graduate, and professional tutors who consult with students by appointment or during drop-in hours. Last year, these tutors worked with more than one-third of the students in Yale College in nearly 10,000 tutoring sessions.

In an interview, Guy discusses the potential dangers and opportunities presented by ChatGPT and how educators can utilize the platform and other AI technologies to improve student writing.

It sounds like many educators have reached out to you about ChatGPT. What kinds of questions are they asking? And how do they expect it will affect their work?

Alfred Guy: It is very exciting to see a technological development that is, so far, generating talk about teaching and not just talk about preventing the use of this tool. When Wikipedia first came out, many college teachers banned it, and as it became easier for students to find sources on the internet, many teachers clamored for better plagiarism detectors. With time, it became a common assignment to write or revise a Wikipedia entry about a topic from the course.

So far, the conversation at Yale around AI writing has focused not on demands that the software be banned or that we find a foolproof detector but rather on the opportunities for new assignments and new ways to engage our students more deeply in their work.

In a recent panel discussion about ChatGPT , some Yale faculty members pointed out that AI could help a student for whom English is not their primary language. It might help them communicate with their professors more effectively while preserving their time and energy for academic work. Do you see this technology as an equalizer?

Guy: Ever since the pandemic pushed us into remote teaching, we’ve been understanding more and more deeply how equity issues impact learning. Access to a quiet workspace, or the chance to take a walk, or decent Wi-Fi, or a large enough monitor to read lecture slides — all of these differences in students’ at-home learning environments helped us see something we should have seen before — that accommodations, some of them quite minor, can have a huge impact on making learning more equitable.

So yes, I’m sure AI writing can equalize some otherwise fairly minor differences in student language use and so eliminate bias and reduce the impact of privilege. There are many occasions for writing that are essentially bureaucratic — rather than designed to facilitate learning — and I see mostly upside for students being able to use tools to make these writing occasions easier and fairer.

Media literacy — the ability to assess the credibility of information — is an ever-growing concern. Many observers have pointed out ChatGPT’s frequent factual errors, and others have worried that its answers may be prone to bias. Is there anything we can do?

Guy: We already know that people publish things with mistakes on the internet, that many websites suffer from ideological bias, and that the need to make money through “click baiting” means that thousands of websites deliberately distort the facts to make topics more sensational. Because it summarizes what’s already been written about, ChatGPT often reproduces these same problems, releasing error-laden or biased answers.

But these very limitations can provide an opportunity for teaching critical literacy. Some of the best assignments I’ve seen using the tool so far have asked students to review ChatGPT’s answers to questions that the students are researching, separating out things that sound likely from things that are actually true . Practicing this skill was valuable before ChatGPT — we all could use more practice and expertise critiquing information from the internet. But ChatGPT can produce even shorter and, in some cases, more cogent forms of what is nonetheless baloney, providing a rich opportunity to practice critical analysis.

Your expertise is in helping students strengthen their writing skills at a particular moment in their intellectual development. What is the connection between writing and learning?

Guy: People can learn in many different ways, but there’s a kind of learning that happens best through writing. When you review notes or re-read course texts, you have some new ideas about the material, but those ideas can get crowded out by your goal to commit the facts to memory. When you talk aloud about what you’re learning, you develop even more of your own ideas — and, as you phrase things in your own words, that synthesis helps you remember both the facts and the connections you’re making.

In writing, because you can see and easily review the past few things you’ve written down, you can make even stronger and more personal connections. You can synthesize five or six ideas that you’ve recalled, versus the two or three you can hold in your mind when speaking aloud. So it’s well established that people who write about what they’re learning develop more new ideas about the material and remember those ideas for longer.

That said, students at any age have enormous demands on their time, and they might be tempted to take a shortcut, like asking an AI app to write their first draft. How can teachers keep learners motivated and engaged?

Guy: Based on research about when students plagiarize (whether from published sources, commercial services, or each other), we know that students are less likely to cheat when they are pursuing questions they feel connected to; understand how the assignment will support their longer-term learning goals; have produced preliminary work before the deadline; and have discussed their preliminary work with others. Getting a head start on the paper and feeling connected to it through conversation are two ways that students can stay motivated for the hard work of writing.

In the long run, this tool will keep getting better and will get harder to detect. I don’t mean technologically — right now I can spot an AI text about almost anything I know something about — but those limitations will become less glaring.

When ChatGPT can write something good enough, the only reason students will have for not using it will be their own motivation to learn. So we better focus on and explain how that learning works, and how our specific assignments will help students learn to solve problems they really care about.

You were a contestant on “Jeopardy!” last year, an honor once shared by the Watson computer [a form of AI] in 2011. In the battle of AI vs. Human Cognition, who’s ahead?

Guy: Ha! I don’t know if Watson cognizes, but it can come up with most “Jeopardy!” answers faster than anyone — that’s why it could beat the GOAT, Ken Jennings. Besides, Watson is way faster at buzzing in.

Campus & Community

Science & Technology

Rebecca Kramer-Bottiglio wins NSF Alan T. Waterman Award

Yale institute observes 50 years studying, celebrating the sacred arts

Sharing more than a border

Ethiopian church forests, a beacon of hope for environmental conservation

• Show More Articles

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.

• 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.

• Skip to main content
• Keyboard shortcuts for audio player

A college student created an app that can tell whether AI wrote an essay

Emma Bowman

GPTZero in action: The bot correctly detected AI-written text. The writing sample that was submitted? ChatGPT's attempt at "an essay on the ethics of AI plagiarism that could pass a ChatGPT detector tool." GPTZero.me/Screenshot by NPR hide caption

GPTZero in action: The bot correctly detected AI-written text. The writing sample that was submitted? ChatGPT's attempt at "an essay on the ethics of AI plagiarism that could pass a ChatGPT detector tool."

Teachers worried about students turning in essays written by a popular artificial intelligence chatbot now have a new tool of their own.

Edward Tian, a 22-year-old senior at Princeton University, has built an app to detect whether text is written by ChatGPT, the viral chatbot that's sparked fears over its potential for unethical uses in academia.

Edward Tian, a 22-year-old computer science student at Princeton, created an app that detects essays written by the impressive AI-powered language model known as ChatGPT. Edward Tian hide caption

Edward Tian, a 22-year-old computer science student at Princeton, created an app that detects essays written by the impressive AI-powered language model known as ChatGPT.

Tian, a computer science major who is minoring in journalism, spent part of his winter break creating GPTZero, which he said can "quickly and efficiently" decipher whether a human or ChatGPT authored an essay.

His motivation to create the bot was to fight what he sees as an increase in AI plagiarism. Since the release of ChatGPT in late November, there have been reports of students using the breakthrough language model to pass off AI-written assignments as their own.

"there's so much chatgpt hype going around. is this and that written by AI? we as humans deserve to know!" Tian wrote in a tweet introducing GPTZero.

Tian said many teachers have reached out to him after he released his bot online on Jan. 2, telling him about the positive results they've seen from testing it.

More than 30,000 people had tried out GPTZero within a week of its launch. It was so popular that the app crashed. Streamlit, the free platform that hosts GPTZero, has since stepped in to support Tian with more memory and resources to handle the web traffic.

How GPTZero works

To determine whether an excerpt is written by a bot, GPTZero uses two indicators: "perplexity" and "burstiness." Perplexity measures the complexity of text; if GPTZero is perplexed by the text, then it has a high complexity and it's more likely to be human-written. However, if the text is more familiar to the bot — because it's been trained on such data — then it will have low complexity and therefore is more likely to be AI-generated.

Separately, burstiness compares the variations of sentences. Humans tend to write with greater burstiness, for example, with some longer or complex sentences alongside shorter ones. AI sentences tend to be more uniform.

In a demonstration video, Tian compared the app's analysis of a story in The New Yorker and a LinkedIn post written by ChatGPT. It successfully distinguished writing by a human versus AI.

A new AI chatbot might do your homework for you. But it's still not an A+ student

Tian acknowledged that his bot isn't foolproof, as some users have reported when putting it to the test. He said he's still working to improve the model's accuracy.

But by designing an app that sheds some light on what separates human from AI, the tool helps work toward a core mission for Tian: bringing transparency to AI.

"For so long, AI has been a black box where we really don't know what's going on inside," he said. "And with GPTZero, I wanted to start pushing back and fighting against that."

The quest to curb AI plagiarism

Untangling Disinformation

Ai-generated fake faces have become a hallmark of online influence operations.

The college senior isn't alone in the race to rein in AI plagiarism and forgery. OpenAI, the developer of ChatGPT, has signaled a commitment to preventing AI plagiarism and other nefarious applications. Last month, Scott Aaronson, a researcher currently focusing on AI safety at OpenAI, revealed that the company has been working on a way to "watermark" GPT-generated text with an "unnoticeable secret signal" to identify its source.

The open-source AI community Hugging Face has put out a tool to detect whether text was created by GPT-2, an earlier version of the AI model used to make ChatGPT. A philosophy professor in South Carolina who happened to know about the tool said he used it to catch a student submitting AI-written work.

The New York City education department said on Thursday that it's blocking access to ChatGPT on school networks and devices over concerns about its "negative impacts on student learning, and concerns regarding the safety and accuracy of content."

Tian is not opposed to the use of AI tools like ChatGPT.

GPTZero is "not meant to be a tool to stop these technologies from being used," he said. "But with any new technologies, we need to be able to adopt it responsibly and we need to have safeguards."

• SAT BootCamp
• SAT MasterClass
• SAT Private Tutoring
• SAT Proctored Practice Test
• ACT Private Tutoring
• Academic Subjects
• College Essay Workshop
• Academic Writing Workshop
• AP English FRQ BootCamp
• 1:1 College Essay Help
• Online Instruction
• Free Resources

Can Chat GPT Write your College Essay?

Can chatgpt write your college essay.

Bonus Material: PrepMaven’s 30 College Essays that Worked

If you’re getting ready to start the college application process, you might already be dreading all the admissions essays you’ll have to write. Between the Common App essay and additional supplementals, college essay writing ends up being a lot of work. 

Naturally, some students wonder whether ChatGPT can help them write their college admissions essay. But there are a lot of questions: is it plagiarism? Can admissions committees tell if you use ChatGPT? Is ChatGPT actually helpful?

At PrepMaven, we’ve coached students in test prep, academics, and college applications for over two decades, and we know what works to get students into selective universities. In fact, our co-founder Kevin Wong was actually interviewed by Business Insider about ChatGPT-generated application essays!

In this guide, we’ll use those decades of experience to break down the benefits and risks of using ChatGPT to help with your college application essays. Plus, we had ChatGPT draft a sample college essay that we then break down. 

Below, you can download our collection of 30 College Essays That Worked, getting students into top schools like Princeton. In the meantime, read on to learn about what ChatGPT can do in the college application process. 

Download 30 College Essays that Worked

Jump to section: Is Having ChatGPT Write Your College Essays Plagiarism? Can Colleges Detect If You Used ChatGPT? Sample ChatGPT Common App Essay and Analysis 4 Good Uses of Chat GPT Next steps

Is Having ChatGPT Write Your College Essays Plagiarism?

First thing’s first: if you submit a finished product that you didn’t write yourself, then that would typically be considered plagiarism. 

So, if you simply go into ChatGPT and have it write you an essay that you then submit, you’d be passing off something you didn’t write as your original work. 

The lines can get a bit blurry (more on that below), but generally here’s a good rule of thumb: if entire sentences in your college application essay weren’t written by you, you’ve probably crossed the line into plagiarism. 

Can Colleges Detect If You Used ChatGPT?

Admissions departments can indeed tell when AI is used in writing assignments–to some extent. If you want to read more about the science of AI-detection, you can check out a detailed analysis from PC-Guide here , but we’ll give you the key information you need to know below. 

Different tools exist to analyze text and suggest the likelihood that it was generated by AI. Even though ChatGPT is fairly new technology, universities already have the technology to detect ChatGPT-generated text. The most prominent of these is probably GPTZero , a tool specifically created to detect ChatGPT. 

For the most part, these tools can’t give a 100% certain determination that your essay was written by AI, especially if you’ve made your own edits and changes to it. But it is certainly the case that if you have large AI-generated sections of text in your college application essays, university admissions committees will be able to tell . 

Ultimately, this is as good a reason as any to avoid having ChatGPT write your entire college application essay for you. It might save you some work, but it also risks immediately flagging your application as plagiarized, sinking your chances of admission. 

For examples of real–non-ChatGPT–college essays, click the button below. These are the kinds of essays that helped get students into top colleges like Ivies. Take a look, and then compare them with the AI-generated essay we analyze in the next section. 

Sample ChatGPT Common App Essay and Analysis

I asked ChatGPT to write a 600-word essay in response to the first Common App Prompt. To make it more specific, I gave GPT directions about style and content. Below, you can read the essay in its entirety–lower down, we’ll briefly analyze whether this essay would work and what the drawbacks of ChatGPT are. 

In the vast tapestry of my life, one thread stands out prominently – the intricate game of chess. From the moment I first laid eyes on the checkered board, I was captivated by its allure. Little did I know that this simple board game would evolve into a profound journey, shaping my identity and character in profound ways. Chess is more than just a game; it is a reflection of life itself. Each piece represents a facet of human existence – the king, a symbol of power and vulnerability; the queen, embodying strength and versatility; the pawns, the foot soldiers of our ambitions; the knights, rooks, and bishops, the allies and adversaries we encounter on our path. Every move carries consequences, every decision a ripple effect that reverberates throughout the game. My journey with chess began at a young age, in the quiet corners of my childhood home. I remember the first time my father introduced me to the game, his eyes alight with anticipation as he laid out the pieces on the board. With each match, he imparted not only the rules of the game but also valuable lessons about strategy, foresight, and perseverance. As I delved deeper into the world of chess, I discovered that it was not just about outmaneuvering my opponent on the board but also about understanding the subtle nuances of human psychology. The game taught me to anticipate my opponent’s moves, to think several steps ahead, and to remain calm under pressure – skills that have proven invaluable both on and off the chessboard. Playing chess became my sanctuary, a place where I could escape the chaos of the world and immerse myself in a realm of logic and order. It taught me the importance of discipline and dedication, as mastering the game required countless hours of practice and study. But more than that, it instilled in me a sense of humility, as I learned to accept defeat graciously and to glean wisdom from my mistakes. One of the most profound lessons I learned from chess is the concept of sacrifice. In order to gain an advantage on the board, one must sometimes be willing to sacrifice a piece – a pawn, a knight, even the queen – for the greater good. This principle extends beyond the confines of the game, teaching me to prioritize long-term goals over short-term gains and to make difficult decisions with courage and conviction. But perhaps the most meaningful aspect of my journey with chess has been the sense of community it has provided. Through local tournaments and online forums, I have connected with fellow enthusiasts from all walks of life, forging friendships that transcend language and cultural barriers. In the company of fellow chess players, I have found a sense of belonging and camaraderie that has enriched my life in countless ways. In the end, chess is not just a game; it is a metaphor for life itself – a complex tapestry of choices, challenges, and triumphs. It has taught me to approach every situation with a strategic mind and a resilient spirit, to embrace adversity as an opportunity for growth, and to always strive for excellence in all that I do. As I embark on the next chapter of my journey, I carry with me the lessons of the chessboard – a timeless reminder of the beauty and complexity of the human experience.

We’ve already talked about why using ChatGPT to write your college application essays is so risky, but here we’d like to briefly break down why it’s just not going to get you very good writing. Let’s take a look at the problems with this AI-generated essay. 

We can give ChatGPT points for grammar and spelling, but certainly not for style! While AI, naturally, does well with the mechanics of the English language, it struggles to sound like a real, believable person–especially a high schooler! 

One key aspect of the college admissions essay is that it needs to be written in your own voice. This gives the admissions committee a sense of your personality, which is a major factor in admissions! But the language here is stiff, formal, and–well–robotic!

Real high schoolers don’t use phrases like “the vast tapestry of my life” or “the foot soldiers of our ambitions.” At best, this essay makes you sound like you’re pretending to be older than you are. At worst, like you’ve gotten someone else to write your essay for you. 

Another main aspect of your Common App essay should be that it conveys your emotions and feelings. That’s what makes a personal statement personal! 

In this sample AI essay, we get a lot of discussion of the chessboard and its lessons, but we never see what the writer actually feels. This will always be a major failing of AI-generated essays: at best, they can mimic some of the emotional language used by real people, but they can’t get at the raw feelings the way a person can. 

• Generic Takeaways

Although this essay isn’t bad and uses some specific language, its lessons are generic. A great college essay combines personal experiences with unique insights that show how you’ve learned and grown as a person.

This essay mimics that: it talks about “the lessons of the chessboard” and “shaping my identity in profound ways.” But these lessons remain generic, the kind of things that anyone could say: “striving for excellence” and “embracing adversity” are the exact kinds of phrases a good college essay tutor would tell you to avoid.

Why? Because university admissions committees have read these phrases again and again and again! They’re cliche, they’re boring, and they’ll make it seem like you’re both of those things as well.

It’s the last thing you want, especially if your college application is getting sent to competitive schools!

Take a look at this collection of real sample essays written by successful college applicants and notice the differences: they have a distinct voice, passion, and unique lessons!

4 Good Uses of ChatGPT for College Essays

Although you absolutely shouldn’t use ChatGPT to write the actual substance of your essay, there are ways you can use ChatGPt to aid in the writing process. 

Below, we’ll list some good ways to use ChatGPT–ones that won’t run the risk of being flagged as plagiarism. 

• Of course, a Common App personal statement should be personal: it should draw on the things from your life that matter to you. Still, using ChatGPT to generate a large list of possible college essay topics isn’t a terrible idea, so long as you make sure to pick a topic that actually connects with your life. (You can read more about good college essay topics here !)
• Starting is often the hardest part of writing a college essay–that’s why we have a whole guide on it here. In addition to the advice we offer in that guide, you can use ChatGPT to draft up some free writing exercises to get you started. 
• While most college application essays are all about you, some– like the “Why us?” essay –require you to do research. ChatGPT can be quite helpful when it comes to finding specific information on a university you’re applying to. Just be sure to always double check what you find–ChatGPT can make mistakes.
• ChatGPT might not be able to understand the emotional stakes of your essay, but it’s excellent at catching grammar, spelling, and other mistakes. You can also ask ChatGPT to analyze your essay for any unclear or confusing sentences. 

Of course, while ChatGPT can help you with all of the above when it comes to your college application essays, it’ll never really be personal. If you think you need help writing your college essays–and our experience has shown us that most students do –then there’s nothing better than personalized essay help from a real human being. 

We’ve done the research (ourselves, without AI) to rank the 14 best college essay services for students applying to college, depending on exactly what kind of support you need. 

Our own tutors–most of whom come from Ivy League colleges–bring an unmatched dedication and expertise. They’ll get to know you, help you brainstorm, and walk you through every step of the college essay writing process. All you have to do is contact us to get started. 

Writing your college application essays can be tough, and it can be hard to know where to start. Sadly, ChatGPT isn’t going to be the solution if you want compelling college essays. 

But, fortunately, we’ve put together all the information you could need to get started. Below, check out our related college essay posts, covering everything from college essay formats to winning application essay conclusions to real sample essays. 

In the meantime, if you’re looking for inspiration, there’s no better resource than PrepMaven’s 30 College Essays that Worked: a real collection of 30 Common App essays that got students admitted to schools like Princeton. 

When you’re ready to start writing, contact us to get paired with a college essay coach and see why we have a perfect track record of 5-star reviews!

Top College Essay Posts

• 14 Best College Essay Services for 2023 (40 Services Reviewed)
• Qualities of a Successful College Essay
• 11 College Essays That Worked
• How to Answer the UC Personal Insight Questions
• How Colleges Read your College Applications (A 4-Step Process)
• How to Write the Princeton Supplemental Essays
• The Diamond Strategy: How We Help Students Write College Essays that Get Them Into Princeton (And Other Ivy League Schools)
• What is the College Essay? Your Complete Guide for 202 4
• College Essay Brainstorming: Where to Start
• How to Write the Harvard Supplemental Essays
• How to Format Your College Essay

Mike is a PhD candidate studying English literature at Duke University. Mike is an expert test prep tutor (SAT/ACT/LSAT) and college essay consultant. Nearly all of Mike’s SAT/ACT students score in the top 5% of test takers; many even score above 1500 on the SAT. His college essay students routinely earn admission into their top-choice schools, including Harvard, Brown, and Dartmouth. And his LSAT students have been accepted In into the top law schools in the country, including Harvard, Yale, and Columbia Law.

Privacy Preference Center

Privacy preferences.

Advertisement

Supported by

Alarmed by A.I. Chatbots, Universities Start Revamping How They Teach

With the rise of the popular new chatbot ChatGPT, colleges are restructuring some courses and taking preventive measures.

• Share full article

By Kalley Huang

Kalley Huang, who covers youth and technology from San Francisco, interviewed more than 30 professors, students and university administrators for this article.

While grading essays for his world religions course last month, Antony Aumann, a professor of philosophy at Northern Michigan University, read what he said was easily “the best paper in the class.” It explored the morality of burqa bans with clean paragraphs, fitting examples and rigorous arguments.

A red flag instantly went up.

Mr. Aumann confronted his student over whether he had written the essay himself. The student confessed to using ChatGPT , a chatbot that delivers information, explains concepts and generates ideas in simple sentences — and, in this case, had written the paper.

Alarmed by his discovery, Mr. Aumann decided to transform essay writing for his courses this semester. He plans to require students to write first drafts in the classroom, using browsers that monitor and restrict computer activity. In later drafts, students have to explain each revision. Mr. Aumann, who may forgo essays in subsequent semesters, also plans to weave ChatGPT into lessons by asking students to evaluate the chatbot’s responses.

“What’s happening in class is no longer going to be, ‘Here are some questions — let’s talk about it between us human beings,’” he said, but instead “it’s like, ‘What also does this alien robot think?’”

Across the country, university professors like Mr. Aumann, department chairs and administrators are starting to overhaul classrooms in response to ChatGPT , prompting a potentially huge shift in teaching and learning. Some professors are redesigning their courses entirely, making changes that include more oral exams, group work and handwritten assessments in lieu of typed ones.

The moves are part of a real-time grappling with a new technological wave known as generative artificial intelligence . ChatGPT, which was released in November by the artificial intelligence lab OpenAI, is at the forefront of the shift. The chatbot generates eerily articulate and nuanced text in response to short prompts, with people using it to write love letters, poetry, fan fiction — and their schoolwork.

That has upended some middle and high schools, with teachers and administrators trying to discern whether students are using the chatbot to do their schoolwork. Some public school systems, including in New York City and Seattle, have since banned the tool on school Wi-Fi networks and devices to prevent cheating, though students can easily find workarounds to access ChatGPT.

In higher education, colleges and universities have been reluctant to ban the A.I. tool because administrators doubt the move would be effective and they don’t want to infringe on academic freedom. That means the way people teach is changing instead.

“We try to institute general policies that certainly back up the faculty member’s authority to run a class,” instead of targeting specific methods of cheating, said Joe Glover, provost of the University of Florida. “This isn’t going to be the last innovation we have to deal with.”

That’s especially true as generative A.I. is in its early days. OpenAI is expected to soon release another tool, GPT-4, which is better at generating text than previous versions. Google has built LaMDA , a rival chatbot, and Microsoft is discussing a $10 billion investment in OpenAI. Silicon Valley start-ups , including Stability AI and Character.AI , are also working on generative A.I. tools.

An OpenAI spokeswoman said the lab recognized its programs could be used to mislead people and was developing technology to help people identify text generated by ChatGPT.

At many universities, ChatGPT has now vaulted to the top of the agenda. Administrators are establishing task forces and hosting universitywide discussions to respond to the tool, with much of the guidance being to adapt to the technology.

At schools including George Washington University in Washington, D.C., Rutgers University in New Brunswick, N.J., and Appalachian State University in Boone, N.C., professors are phasing out take-home, open-book assignments — which became a dominant method of assessment in the pandemic but now seem vulnerable to chatbots. They are instead opting for in-class assignments, handwritten papers, group work and oral exams.

Gone are prompts like “write five pages about this or that.” Some professors are instead crafting questions that they hope will be too clever for chatbots and asking students to write about their own lives and current events.

Students are “plagiarizing this because the assignments can be plagiarized,” said Sid Dobrin, chair of the English department at the University of Florida.

Frederick Luis Aldama, the humanities chair at the University of Texas at Austin, said he planned to teach newer or more niche texts that ChatGPT might have less information about, such as William Shakespeare’s early sonnets instead of “A Midsummer Night’s Dream.”

The chatbot may motivate “people who lean into canonical, primary texts to actually reach beyond their comfort zones for things that are not online,” he said.

In case the changes fall short of preventing plagiarism, Mr. Aldama and other professors said they planned to institute stricter standards for what they expect from students and how they grade. It is now not enough for an essay to have just a thesis, introduction, supporting paragraphs and a conclusion.

“We need to up our game,” Mr. Aldama said. “The imagination, creativity and innovation of analysis that we usually deem an A paper needs to be trickling down into the B-range papers.”

Universities are also aiming to educate students about the new A.I. tools. The University at Buffalo in New York and Furman University in Greenville, S.C., said they planned to embed a discussion of A.I. tools into required courses that teach entering or freshman students about concepts such as academic integrity.

“We have to add a scenario about this, so students can see a concrete example,” said Kelly Ahuna, who directs the academic integrity office at the University at Buffalo. “We want to prevent things from happening instead of catch them when they happen.”

Other universities are trying to draw boundaries for A.I. Washington University in St. Louis and the University of Vermont in Burlington are drafting revisions to their academic integrity policies so their plagiarism definitions include generative A.I.

John Dyer, vice president for enrollment services and educational technologies at Dallas Theological Seminary, said the language in his seminary’s honor code felt “a little archaic anyway.” He plans to update its plagiarism definition to include: “using text written by a generation system as one’s own (e.g., entering a prompt into an artificial intelligence tool and using the output in a paper).”

The misuse of A.I. tools will most likely not end, so some professors and universities said they planned to use detectors to root out that activity. The plagiarism detection service Turnitin said it would incorporate more features for identifying A.I., including ChatGPT, this year.

More than 6,000 teachers from Harvard University, Yale University, the University of Rhode Island and others have also signed up to use GPTZero, a program that promises to quickly detect A.I.-generated text, said Edward Tian, its creator and a senior at Princeton University.

Some students see value in embracing A.I. tools to learn. Lizzie Shackney, 27, a student at the University of Pennsylvania’s law school and design school, has started using ChatGPT to brainstorm for papers and debug coding problem sets.

“There are disciplines that want you to share and don’t want you to spin your wheels,” she said, describing her computer science and statistics classes. “The place where my brain is useful is understanding what the code means.”

But she has qualms. ChatGPT, Ms. Shackney said, sometimes incorrectly explains ideas and misquotes sources. The University of Pennsylvania also hasn’t instituted any regulations about the tool, so she doesn’t want to rely on it in case the school bans it or considers it to be cheating, she said.

Other students have no such scruples, sharing on forums like Reddit that they have submitted assignments written and solved by ChatGPT — and sometimes done so for fellow students too. On TikTok, the hashtag #chatgpt has more than 578 million views, with people sharing videos of the tool writing papers and solving coding problems .

One video shows a student copying a multiple choice exam and pasting it into the tool with the caption saying: “I don’t know about y’all but ima just have Chat GPT take my finals. Have fun studying.”

Kalley Huang is a technology reporting fellow based in San Francisco. She graduated from the University of North Carolina at Chapel Hill. More about Kalley Huang

Explore Our Coverage of Artificial Intelligence

News  and Analysis

Saudi Arabia is plowing money into glitzy events, computing power and artificial intelligence research, putting it in the middle of an escalating  U.S.-China struggle for technological influence.

Microsoft gave more signs that its hefty investments in A.I.  were beginning to bear fruit, as it reported a 17 percent jump in revenue and a 20 percent increase in profit for the first three months of the year.

Meta projected that revenue for the current quarter  would be lower than what Wall Street anticipated and said it would spend billions of dollars more on its artificial intelligence efforts, even as it reported robust revenue and profits for the first three months of the year.

The Age of A.I.

A new category of apps promises to relieve parents of drudgery, with an assist from A.I . But a family’s grunt work is more human, and valuable, than it seems.

Despite Mark Zuckerberg’s hope for Meta’s A.I. assistant to be the smartest , it struggles with facts, numbers and web search.

Much as ChatGPT generates poetry, a new A.I. system devises blueprints for microscopic mechanisms  that can edit your DNA.

Could A.I. change India’s elections? Avatars are addressing voters by name, in whichever of India’s many languages they speak. Experts see potential for misuse  in a country already rife with disinformation.

Which A.I. system writes the best computer code or generates the most realistic image? Right now, there’s no easy way to answer those questions, our technology columnist writes .

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

How to use Chat GPT to Write an Essay

Florencia basavilbaso.

• Best Apps And Tools , Writing Tips

Content Writer At Gradehacker

• February, 2023

If you want to speed up the essay-writing process with AI, here you’ll learn which are the basic tips you need to know to write an essay with Chat GPT.

How to Write an Essay With Chat GPT

To write an essay with Chat GPT, these are the four basic tips you need to know:

• Edit and refine the generated text
• Write a clear and concise prompt
• Take time to learn about Chat GPT
• Add your own thoughts to make it personal

Having problems to write your essay?

If Chat GPT isn’t enough and you need help with a last-minute paper, we are here to help you!

Having problems writing?

By now, you’ve probably heard about Chat GPT; an amazing AI that can (almost) write original content as if it was a real human being. So, now you are wondering how to use Chat GPT to write an essay. 

For that, we created this blog to guide you through each step so you can take all the benefits this platform has for you and use it in your favor.

Here at Gradehacker , we’ve been years dedicated to helping and improving non-traditional student’s life in multiple ways! Besides assisting them with their classes and essays , we are the most trusted resource for valuable information and tips that can change the way you work!

And today, we introduce you to Chat GPT !

This AI can help you write a college essay quickly and efficiently. If you want to know how to use chat GPT to write an essay, learn what are its pros and cons, and incorporate the best tips to change how you approach your essays, you are in the right place! 

Let’s start!

What is Chat GPT?

First, we’ll address some basics here. Let’s talk about what this platform is and what it can do for you!

ChatGPT (Chat Generative Pre-trained Transformer) is a natural language processing technology that uses artificial intelligence to generate text based on a prompt. It can be used to generate ideas, structure sentences, and even create entire essays.

This computer program was created by the artificial intelligence research laboratory OpenAI and launched on November 30, 2022. It is still a pretty new platform and has a lot to improve, but it also has several advantages that can do more good than bad for you!

It is free to the public, but we recommend taking advantage of their free service as long as you can because it was created with the intention of monetizing the service in the future.

Meaning, Chat GPT won’t continue being free for too long.

Another interesting fact is that the service works best in English but is also able to function in some other languages.

What Can You Use Chat GPT For?

So, after reading what Chat GPT is, you are probably wondering what you can use it for.

Programs like this one which can generate text based on a prompt, are good for:

• When you want to save time and don't feel inspired to write
• Don't know how to continue what you started
• Getting ideas
• Start a project

We always recommend checking and editing the text because it’s not always accurate , and the information is often wrong, especially when it comes to dates, rates, or anything very specific.

But of course, there are other ways you can use Chat GPT. 

It can help you create a title for your essay topics, text for an announcement or copywriting, an article, or what you came for: an essay!

And that leads us to the main question: how do we use it?

How to Use Chat GPT to Write an Essay

If this AI is appropriately used, it can become the saver you’ve been yearning for. 

In short, to write an essay with Chat GPT, you need to follow this process:

2) Put a command 

3) Change the command until you get the desired outcome

Now let’s see how it works.

To start, let’s go to Chat GPT website and press where it says “ Try Chat GPT “

Once we log in, at the bottom of the page you’ll find a text box where you will need to write a command. This could be the title of the essay, a topic sentence, or even a few keywords. 

After providing the prompt, Chat GPT will generate text based on it.

The text will come out as a number of items containing specific ideas about the topic we asked for.  

Then, as a new command, you can ask Chat GPT to expand on the previous information.

Because Chat GPT remembers the previous information generated, you can also ask it to write more information from a specific item. In order to do that, you can go where you wrote your first command and, this time, put something like: “write essay line (or paragraph) about (item number).” 

You can also command multiple things at once , for example: “write an essay introduction with heading about item 7,”  or you can even command to do it for every item.

You can then edit and refine the generated text to make your essay unique and give it a personal touch as it would be with human writing.

Do you need a step-by-step tutorial on how to write an essay with Chat GPT?

If you want to use Chat GPT to write an entire essay from scratch , you can read our entire experience or check out our videos!

Pros and Cons of Using Chat GPT

As with any technology, there are both advantages and disadvantages to using Chat GPT.

Pros of Chat GPT

On the plus side, we can say that:

• It is much faster than traditional writing methods, and it can save you time and effort when writing an essay
• It can help you come up with ideas to get started on a project and structure your essay in a more organized way
• Reduces the need for research , as it can generate text based on the prompt without any additional input.
• It can provide you with information that is relevant to your topic
• It can help you refine and edit your text to make it unique

Cons of Chat GPT

But we know that Chat GPT is not perfect, so on the downside, it is essential to note that:

• Sometimes it can generate text that is not accurate , has incorrect premises, and is irrelevant to the prompt
• It can be challenging to use if you are not familiar with natural language processing technology
• You may have difficulty editing and refining the generated text to make it unique and personal
• It could end up being time-consuming if you don't know how to use the platform correctly
• Because it is trained on data, it may contain inherent biases, and this can be reflected in the outputted text

It is important to be aware of the potential for bias when using Chat GPT to generate essays , as this could lead to inaccurate or offensive results.

Also, be aware of the possibility of plagiarism when using it, as this could lead to serious consequences. Taking the time to check for plagiarism before submitting a written essay is essential to ensure its originality and accuracy.

And to save yourself from falling into those situations, be sure to read our blog post on how to avoid unintentional plagiarism.

How to Avoid Plagiarism When Using Chat GPT

To avoid plagiarism when using Chat GPT to write an essay, it is critical to double-check any generated content before submitting it. Using a reliable plagiarism checker is also helpful to ensure the content is entirely original.

These are some plagiarism software you can use:

If you want to know how these platforms work, check our video, where we’ll show you what they do, why they’re useful, and why they’re better than the rest.

Chat GPT Plus

One of the biggest problems with Chat GPT is that it might not always be available to use.

Many times, when we go to the website, what can happen is that there are a lot of people using it, which will create high traffic. When that happens, it will appear on the screen a text that says:

“ChatGPT is at capacity right now. Get notified when we’re back .” 

There, you can click on get notified, put your email address, and wait until the traffic slows down.

But if you don’t want to deal with waiting to be notified, there is an alternative choice: subscribe to  Chat GPT Plus.

By subscribing, you’ll gain:

• Access to ChatGPT at all times, even during the busiest periods
• Faster response times
• Priority access to new features and improvements

The subscription has a price of $20 per month and is only available for customers in the United States.

Having doubts on how we can help you?

Get in touch with us!

Tips for Using Chat GPT

If you decide to use Chat GPT to write your essay, there are a few tips that can help you get the most out of it.

• Provide a clear and concise prompt: This will help Chat GPT generate the most accurate and relevant text.
• Edit, add your own thoughts, and refine the generated text to make it unique and personal
• If you are not familiar with natural language processing technology, take some time to learn about it before using Chat GPT

These tips will make a difference in your work, especially for those long essays where you need to do a lot of research. 

Knowing how to write a research paper or an argumentative essay is highly necessary and essential for a college student, even if you have Chat GPT helping you throughout the process, so in case you are unsure or need to refresh that, check out our video about it! 

Make Your Writing Stand Out When Using Chat GPT to Write an Essay

With our tips and guidance on how to make your essays stand out when using Chat GPT and the potential pitfalls to avoid, you’ll be in a great position to produce high-quality essays.

On the other side, you may like to know that here at Gradehacker, we offer college essays , classes and degree help services to help students like you reach their highest potential.

To check more helpful information, check our blogs:

What You Need For Your College Research Paper Outline

5 Common Essay Mistakes and How to Avoid Them

Best AI to Write Essays

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

How Much Does it Cost to Write My Essay?

Best Apps For Writing 2024 | Boost Your Writing Skills

Florencia Basavilbaso is a content creator passioned for writing, music, films, and the arts. At Gradehacker, she helps to improve non-traditional students life’s by finding and providing the most useful information, so they can always progress. You can find her 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.

Numbers, Facts and Trends Shaping Your World

Read our research on:

Full Topic List

Regions & Countries

• Publications
• Our Methods
• Short Reads
• Tools & Resources

Read Our Research On:

About 1 in 5 U.S. teens who’ve heard of ChatGPT have used it for schoolwork

Roughly one-in-five teenagers who have heard of ChatGPT say they have used it to help them do their schoolwork, according to a new Pew Research Center survey of U.S. teens ages 13 to 17. With a majority of teens having heard of ChatGPT, that amounts to 13% of all U.S. teens who have used the generative artificial intelligence (AI) chatbot in their schoolwork.

Teens in higher grade levels are particularly likely to have used the chatbot to help them with schoolwork. About one-quarter of 11th and 12th graders who have heard of ChatGPT say they have done this. This share drops to 17% among 9th and 10th graders and 12% among 7th and 8th graders.

There is no significant difference between teen boys and girls who have used ChatGPT in this way.

The introduction of ChatGPT last year has led to much discussion about its role in schools , especially whether schools should integrate the new technology into the classroom or ban it .

Pew Research Center conducted this analysis to understand American teens’ use and understanding of ChatGPT in the school setting.

The Center conducted an online survey of 1,453 U.S. teens from Sept. 26 to Oct. 23, 2023, via Ipsos. Ipsos recruited the teens via their parents, who were part of its KnowledgePanel . The KnowledgePanel is a probability-based web panel recruited primarily through national, random sampling of residential addresses. The survey was weighted to be representative of U.S. teens ages 13 to 17 who live with their parents by age, gender, race and ethnicity, household income, and other categories.

This research was reviewed and approved by an external institutional review board (IRB), Advarra, an independent committee of experts specializing in helping to protect the rights of research participants.

Here are the  questions used for this analysis , along with responses, and its  methodology .

Teens’ awareness of ChatGPT

Overall, two-thirds of U.S. teens say they have heard of ChatGPT, including 23% who have heard a lot about it. But awareness varies by race and ethnicity, as well as by household income:

• 72% of White teens say they’ve heard at least a little about ChatGPT, compared with 63% of Hispanic teens and 56% of Black teens.
• 75% of teens living in households that make $75,000 or more annually have heard of ChatGPT. Much smaller shares in households with incomes between $30,000 and $74,999 (58%) and less than $30,000 (41%) say the same.

Teens who are more aware of ChatGPT are more likely to use it for schoolwork. Roughly a third of teens who have heard a lot about ChatGPT (36%) have used it for schoolwork, far higher than the 10% among those who have heard a little about it.

When do teens think it’s OK for students to use ChatGPT?

For teens, whether it is – or is not – acceptable for students to use ChatGPT depends on what it is being used for.

There is a fair amount of support for using the chatbot to explore a topic. Roughly seven-in-ten teens who have heard of ChatGPT say it’s acceptable to use when they are researching something new, while 13% say it is not acceptable.

However, there is much less support for using ChatGPT to do the work itself. Just one-in-five teens who have heard of ChatGPT say it’s acceptable to use it to write essays, while 57% say it is not acceptable. And 39% say it’s acceptable to use ChatGPT to solve math problems, while a similar share of teens (36%) say it’s not acceptable.

Some teens are uncertain about whether it’s acceptable to use ChatGPT for these tasks. Between 18% and 24% say they aren’t sure whether these are acceptable use cases for ChatGPT.

Those who have heard a lot about ChatGPT are more likely than those who have only heard a little about it to say it’s acceptable to use the chatbot to research topics, solve math problems and write essays. For instance, 54% of teens who have heard a lot about ChatGPT say it’s acceptable to use it to solve math problems, compared with 32% among those who have heard a little about it.

Note: Here are the  questions used for this analysis , along with responses, and its  methodology .

• Artificial Intelligence
• Technology Adoption
• Teens & Tech

Olivia Sidoti is a research assistant focusing on internet and technology research at Pew Research Center

Jeffrey Gottfried is an associate director focusing on internet and technology research at Pew Research Center

Many Americans think generative AI programs should credit the sources they rely on

Americans’ use of chatgpt is ticking up, but few trust its election information, q&a: how we used large language models to identify guests on popular podcasts, striking findings from 2023, what the data says about americans’ views of artificial intelligence, most popular.

1615 L St. NW, Suite 800 Washington, DC 20036 USA (+1) 202-419-4300 | Main (+1) 202-857-8562 | Fax (+1) 202-419-4372 |  Media Inquiries

Research Topics

• Age & Generations
• Coronavirus (COVID-19)
• Economy & Work
• Family & Relationships
• Gender & LGBTQ
• Immigration & Migration
• International Affairs
• Internet & Technology
• Methodological Research
• News Habits & Media
• Non-U.S. Governments
• Other Topics
• Politics & Policy
• Race & Ethnicity
• Email Newsletters

ABOUT PEW RESEARCH CENTER  Pew Research Center is a nonpartisan fact tank that informs the public about the issues, attitudes and trends shaping the world. It conducts public opinion polling, demographic research, media content analysis and other empirical social science research. Pew Research Center does not take policy positions. It is a subsidiary of  The Pew Charitable Trusts .

Copyright 2024 Pew Research Center

Terms & Conditions

Privacy Policy

Cookie Settings

Reprints, Permissions & Use Policy

A tutor shares 3 rules for writing college application essays, including how to use ChatGPT the right way

• Carter Osborne started a side hustle tutoring students on their college admissions essays in 2017.
• The Stanford graduate shared his recommendations for students looking to ace their personal essays.
• He said students could use ChatGPT to brainstorm ideas by inputting their experiences and prompting it to ask questions.

Stanford graduate Carter Osborne started a side hustle tutoring high school students on their college application essays in 2017. He had 50 clients last year and made $114,000 from tutoring in 2023.

He quit his day job earlier this month, which he said he could only do because of his tutoring income.

Osborne shared three tips for students writing their college application essays with Business Insider — including how to use and not use AI chatbots.

1. Students should stick to their personal stories

Osborne told BI the key to writing college essays is making it personal. "What I always encourage my students to do is go off script. Find something personal about your life that nobody else could talk about, or at least an angle on something you've done that feels different," he said.

He added he viewed his job as helping high schoolers "tell compelling, interesting stories that are personal and expressive."

2. An AI chatbot like ChatGPT can help brainstorm — but it can't write it for you

Osborne would never write his students' essays for them, he said. Instead, he suggests revisions or edits based on topics they've discussed in meetings.

"The thought has to have come from my student," he said. "My job is to help them weave those thoughts together in the most compelling way."

Related stories

If stuck, students could use an AI chatbot to help them develop an idea, Osborne said. "Tell it to pretend that it's a college admissions counselor, and ask it questions about what you should write about for your college essay," he suggested.

He said students could talk to it about their experiences and use it to help them brainstorm ideas for essay topics based on their achievements or experiences. He said they could input some personal information, values, and activities they do and prompt ChatGPT to ask them questions about themselves.

Some colleges have issued guidelines against using AI in the application process, while others have encouraged its use in brainstorming and editing their essays. Many colleges, however, have warned students against copying and pasting content from ChatGPT or other AI models.

Osborne said students should never use ChatGPT or other AI chatbots to write an essay , though, he said.

"It comes out feeling stock and flat. There's no life to it," he said. But AI can provide an outline to help students structure the first draft of their essays, he added.

After figuring out their idea, Osborne suggested students could ask ChatGPT to: "Provide an outline for a 650-word personal statement that's four or five paragraphs, and tell me what each section should be about."

3. A chatbot could also give you ideas for improving the first draft

Once students have written their first draft, if they don't have access to a tutor or an English teacher, they could ask ChatGPT what it thinks about it, he said.

They could prompt it to, "Imagine you're a college admissions counselor and react to this essay. What do you think about it? And provide several specific suggestions about how to improve it," he said.

Osborne said some of its suggestions might be bad, but some could be useful. The important thing is never to take what the AI says as a "firm recommendation" that you should follow but as ideas that you might consider, he added.

"Always bring that critical thinking to the process," he said.

Watch: Former Princeton admissions director reveals the biggest mistakes applicants make

• Main content

More From Forbes

5 chatgpt prompts to make everything you write more compelling.

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

5 ChatGPT prompts to make everything you write more compelling

Bad copy kills businesses. It finds its way into emails, Slack messages, memos and more. Copywriting is not a skill reserved for marketers. It’s everyone’s problem. Every member of your team should learn how to write compelling words and edit them until they sing. And who knows? If the HR manager wrote updates like a Buzzfeed journalist, you might even read until the end.

Use these prompts to upgrade the copy for everything you write, no matter how many people will actually see. Copy, paste and edit the square brackets in ChatGPT, and keep the same chat window open so the context carries through.

Improve your writing with 5 powerful ChatGPT prompts

Improve the hook.

Grab attention with the first line or face an uphill battle from the start. Just because you have a fancy job title, doesn’t mean anyone will read your messages. Make them want to. Use this prompt to find a more compelling way of opening. Strike a chord, create an information gap. Make someone stand up and pay attention so they keep on reading. On Twitter you have a second to get someone’s attention. Keep that in mind when writing for anywhere else.

“I’m pasting a message I wrote, a [describe the nature of the message] designed for [describe the audience]. Your task is to help the first line grab the attention of the reader so they keep reading. Understand the copy and create a hook. The hook should be between 6-12 words long and aim to strike a chord, create an information gap or draw someone in. This should not be a question. Give me 5 options for new hooks for this copy so I can choose the best: [Paste copy here]”

‘Challengers’ Reviews: Does Zendaya Tennis Movie Score With Critics?

‘baby reindeer’ star says real martha searches need to stop, patriots select north carolina quarterback drake maye with no 3 pick in nfl draft, make it shorter.

“I haven’t got time to read all that. Just tell me what it means.” If given that response, you’d tell them in a few sentences. Those are the sentences that matter. If in doubt, cut the fluff. The context can be a footnote for those interested in knowing more. Online or within your company, someone doesn’t need to be taken on a convoluted journey to find the single line that’s relevant to them. Make everything you write shorter. Pack a punch with your words, don’t make someone want to punch you.

“I’m pasting a message I wrote, a [describe the nature of the message] designed for [describe the recipients]. Your task is to make it shorter so my audience will read and understand it without needing to skim read. Look to remove waffle and additional words, and change any instances of passive voice to active. Remove repetition. Keep my tone of voice and keep the meaning of the text the same. Remove any information not essential to the main message and add as numbered footnotes at the end: [Paste copy here]”

Everyone’s favourite radio station

WII FM. What’s in it for me? It’s everyone’s favourite radio station and you need to take note. No one wants to read your diary. They want to know what information means for them. So make it easy. Re-read your copy with this in mind. Ask, why should they care? Ask, so what? Ask questions of your words and flip the script to gain longer reads.

“I’m pasting a message I wrote, a [describe the nature of the message] designed for [describe the audience]. Your task is to make sure it’s clear what’s in it for them. Make sure it’s clear why they should care about this message. Suggest edits, including additional lines or reordering of information, that will have this effect: [Paste copy here]”

Remove ambiguity

Confused customers don’t buy. Confused team members don’t read. Your task is to deliver information and not raise objections. So remove ambiguity from every line. Phrases you would say out loud often don’t translate written down. Being self-deprecating in prose will make you sound weak. Flippant or sarcastic, like a bit of a jerk. So edit. Use ChatGPT to find ambiguous terms and make them more simple. Say what you mean and mean what you say.

“I’m pasting a message I wrote, a [describe the nature of the message] designed for [describe the audience]. Your task is to remove ambiguity. Without changing the meaning, style, tone or anything that is not ambiguous, produce a new version that simplifies anything potentially confusing and avoids raising objections. Explain what you changed so I can understand: [Paste copy here]”

What’s the point?

There’s a reason you typed something, so make sure it’s known. Upon reading your words, make it abundantly clear what you want someone to do. Click a link, respond to an email, make a decision. Or maybe it’s just an FYI. Whatever is next, let them know. Make the call to action obvious, clear and compelling to stand the best chance of success. This applies to internal company memos and everything you share in public. We’re here to do business.

“I’m pasting a message I wrote, a [describe the nature of the message] designed for [describe the audience]. Your task is to ensure there’s a compelling call to action. When someone has read this, I want them to [describe the desired action]. Ensure this is clear in my copy. Provide 3 options for new wording and explain where this new wording should go for best chance of the call to action being followed. [Paste copy here]”

Re-work your writing to make more impact: ChatGPT prompts

You need to be a better writer, and this starts today. Make a pledge to send no more waffly, unclear or underwhelming messages under your name. Grab someone’s attention and keep them hooked until the end. Shape your request to their needs, make it as short as possible, remove all ambiguity, then tell them what to do. Get known for your directness, and don’t waste anyone’s time. Create better results with compelling copy.

• Editorial Standards
• Reprints & Permissions

Teacher's 'Clever' Hack For Catching Students Using ChatGPT On Essay

A leading educator has shared a simple hack for catching out students using ChatGPT to write their essays for them.

Though ChatGPT's terms of use say those aged 13 to 18 should only use it with parental permission, research suggests a worrying number of students are already misusing AI in the classroom.

Earlier this month, a survey conducted by the Center for Democracy and Technology revealed a significant increase in U.S. student discipline issues related to the use of generative AI chatbots.

The nationally representative surveys of K-12 public school teachers found 64 percent said students at their school had got into trouble for using or being accused of using AI on a school assignment . That represented a 16 percent increase on the previous year.

Daina Petronis is a full-time curriculum designer and former high school English teacher who runs the online teaching resources community mondaysmadeeasy.com. She believes that while there may come a day when the likes of ChapGPT have a place in the classroom, right now the biggest challenge facing teachers when it comes to language learning models (LLMs) is their potential misuse.

"In theory, LLMs can benefit learning, but there needs to be plenty of support in place to ensure that they are not being misused ," Petronis told Newsweek .

Much of Petronis's work involves researching trends in education, not least when it comes to the use of ChatGPT, the methods available to help teachers catch those using LLMs illicitly, and the limitations around them.

"I am often approached by companies developing AI-detection tools who are looking to promote their software to my audience," she said. "Before sharing these tools with my community, I always ask their representatives about their accuracy. The consistent response from these companies is that there is no surefire method to detect AI."

Another method endorsed by some involves asking the LLM if it produced the work in question. "I've actually tested this with several samples of original writing alongside text generated by an LLM," Petronis said. "I used my own writing that was published years ago and it falsely claimed to have generated it. I also used the writing that it had generated, and it didn't recognize it."

Thankfully, Petronis has hit upon a much simpler approach at weeding out the cheats using what she calls a "trojan horse" hack. In a video posted to her TikTok account mondaysmadeeasy, she explained "this hack is pretty clever and can show you exactly what to look out for without the use of any software of special programs."

She begins by splitting her essay prompt—the title of the essay given to her students—into two paragraphs before adding a sentence in-between in white using the smallest size possible. The idea is that if the essay prompt is copied and pasted into ChatGPT, the teacher can then search for the sentence hidden in the small white font when the assignment is submitted.

Though the video has been watched over one million times, garnering plenty of praise in the process, Petronis acknowledges there are "limitations" to the method.

"If a student happens to notice that there is hidden text in their assignment prompt, then there are some possible outcomes: they can either remove the text or mistake it as a part of the instructions," she said.

However, she feels the positives far outweigh the negatives. "What makes the trojan horse arguably more effective than other methods is that it offers a point of reference that is easy to identify and discuss with a student," she said. "I would not feel comfortable talking to a student about their writing process just because an AI detection tool or an LLM indicates that it's been plagiarized. But if I saw that their work had my trojan horse terms in it, I could simply ask them about it in an open-ended way."

Though the clip has been praised for highlighting a simple way to tackle plagiarism, Petronis said some watching the clip "misunderstood" the message of the video as being "anti-AI." Petronis refutes this suggestion.

"Even though this video sparked a lot of controversy, I think many of us have the same goal—we want what is best for students," she said. "While some people believe this involves training children on AI so that they can use it in the workforce, educators also understand literacy to be a more valuable skill and a prerequisite for using AI appropriately."

Start your unlimited Newsweek trial

OpenAI makes ChatGPT ‘more direct, less verbose’

ChatGPT , OpenAI’s viral AI-powered chatbot, just got a big upgrade.

OpenAI announced today that premium ChatGPT users — customers paying for ChatGPT Plus, Team or Enterprise — can now leverage an updated and enhanced version of GPT-4 Turbo, one of the models that powers the conversational ChatGPT experience.

This new model (“gpt-4-turbo-2024-04-09”) brings with it improvements in writing, math, logical reasoning and coding, OpenAI claims, as well as a more up-to-date knowledge base. It was trained on publicly available data up to December 2023, in contrast to the previous edition of GPT-4 Turbo available in ChatGPT, which had an April 2023 cut-off.

“When writing with ChatGPT [with the new GPT-4 Turbo], responses will be more direct, less verbose and use more conversational language,” OpenAI writes in a post on X.

Our new GPT-4 Turbo is now available to paid ChatGPT users. We’ve improved capabilities in writing, math, logical reasoning, and coding. Source: https://t.co/fjoXDCOnPr pic.twitter.com/I4fg4aDq1T — OpenAI (@OpenAI) April 12, 2024

The ChatGPT update — which follows the GA launch on Tuesday of new models in OpenAI’s API, notably GPT-4 Turbo with Vision, which adds image understanding capabilities to the normally-text-only GPT-4 Turbo — arrives after an unflattering week for OpenAI.

Reporting from The Intercept revealed that Microsoft pitched OpenAI’s DALL-E text-to-image model as a battlefield tool for the U.S. military. And, according to a piece in The Information, OpenAI recently fired two researchers — including an ally of chief scientist Ilya Sutskever, who was among those who pushed for the ouster of CEO Sam Altman late last year — for allegedly leaking information.

• Do Not Sell My Personal Info

•  ⋅ 

How To Write ChatGPT Prompts To Get The Best Results

Learn how to craft powerful ChatGPT prompts to generate high-quality SEO content. Follow expert tips, examples, and strategies for layering prompts to get the best results.

ChatGPT is a game changer in the field of SEO . This powerful language model can generate human-like content, making it an invaluable tool for SEO professionals.

However, the prompts you provide largely determine the quality of the output.

To unlock the full potential of ChatGPT and create content that resonates with your audience and search engines, writing effective prompts is crucial.

In this comprehensive guide, we’ll explore the art of writing prompts for ChatGPT, covering everything from basic techniques to advanced strategies for layering prompts and generating high-quality, SEO-friendly content.

Writing Prompts For ChatGPT

What is a chatgpt prompt.

A ChatGPT prompt is an instruction or discussion topic a user provides for the ChatGPT AI model to respond to.

The prompt can be a question, statement, or any other stimulus to spark creativity, reflection, or engagement.

Users can use the prompt to generate ideas, share their thoughts, or start a conversation.

ChatGPT prompts are designed to be open-ended and can be customized based on the user’s preferences and interests.

How To Write Prompts For ChatGPT

Start by giving ChatGPT a writing prompt, such as, “Write a short story about a person who discovers they have a superpower.”

ChatGPT will then generate a response based on your prompt. Depending on the prompt’s complexity and the level of detail you requested, the answer may be a few sentences or several paragraphs long.

Use the ChatGPT-generated response as a starting point for your writing . You can take the ideas and concepts presented in the answer and expand upon them, adding your own unique spin to the story.

If you want to generate additional ideas, try asking ChatGPT follow-up questions related to your original prompt.

For example, you could ask, “What challenges might the person face in exploring their newfound superpower?” Or, “How might the person’s relationships with others be affected by their superpower?”

Remember that ChatGPT’s answers are generated by artificial intelligence and may not always be perfect or exactly what you want.

However, they can still be a great source of inspiration and help you start writing.

Must-Have GPTs Assistant

I recommend installing the WebBrowser Assistant created by the OpenAI Team. This tool allows you to add relevant Bing results to your ChatGPT prompts.

This assistant adds the first web results to your ChatGPT prompts for more accurate and up-to-date conversations.

It is very easy to install in only two clicks. (Click on Start Chat. )

For example, if I ask, “Who is Vincent Terrasi?,” ChatGPT has no answer.

With WebBrower Assistant, the assistant creates a new prompt with the first Bing results, and now ChatGPT knows who Vincent Terrasi is.

You can test other GPT assistants available in the GPTs search engine if you want to use Google results.

Master Reverse Prompt Engineering

ChatGPT can be an excellent tool for reverse engineering prompts because it generates natural and engaging responses to any given input.

By analyzing the prompts generated by ChatGPT, it is possible to gain insight into the model’s underlying thought processes and decision-making strategies.

One key benefit of using ChatGPT to reverse engineer prompts is that the model is highly transparent in its decision-making.

This means that the reasoning and logic behind each response can be traced, making it easier to understand how the model arrives at its conclusions.

Once you’ve done this a few times for different types of content , you’ll gain insight into crafting more effective prompts.

Prepare Your ChatGPT For Generating Prompts

First, activate the reverse prompt engineering.

• Type the following prompt: “Enable Reverse Prompt Engineering? By Reverse Prompt Engineering I mean creating a prompt from a given text.”

ChatGPT is now ready to generate your prompt. You can test the product description in a new chatbot session and evaluate the generated prompt.

• Type: “Create a very technical reverse prompt engineering template for a product description about iPhone 11.”

The result is amazing. You can test with a full text that you want to reproduce. Here is an example of a prompt for selling a Kindle on Amazon.

• Type: “Reverse Prompt engineer the following {product), capture the writing style and the length of the text : product =”

I tested it on an SEJ blog post. Enjoy the analysis – it is excellent.

• Type: “Reverse Prompt engineer the following {text}, capture the tone and writing style of the {text} to include in the prompt : text = all text coming from https://www.searchenginejournal.com/google-bard-training-data/478941/”

But be careful not to use ChatGPT to generate your texts. It is just a personal assistant.

Prompts and examples for SEO:

• Keyword research and content ideas p rompt : “Provide a list of 20 long-tail keyword ideas related to ‘local SEO strategies’ along with brief content topic descriptions for each keyword.”
• Optimizing content for featured snippets p rompt : “Write a 40-50 word paragraph optimized for the query ‘what is the featured snippet in Google search’ that could potentially earn the featured snippet.”
• Creating meta descriptions p rompt: “Draft a compelling meta description for the following blog post title: ’10 Technical SEO Factors You Can’t Ignore in 2024′.”

Important Considerations:

• Always Fact-Check: While ChatGPT can be a helpful tool, it’s crucial to remember that it may generate inaccurate or fabricated information. Always verify any facts, statistics, or quotes generated by ChatGPT before incorporating them into your content.
• Maintain Control and Creativity: Use ChatGPT as a tool to assist your writing, not replace it. Don’t rely on it to do your thinking or create content from scratch. Your unique perspective and creativity are essential for producing high-quality, engaging content.
• Iteration is Key: Refine and revise the outputs generated by ChatGPT to ensure they align with your voice, style, and intended message.

Additional Prompts for Rewording and SEO: – Rewrite this sentence to be more concise and impactful. – Suggest alternative phrasing for this section to improve clarity. – Identify opportunities to incorporate relevant internal and external links. – Analyze the keyword density and suggest improvements for better SEO.

Remember, while ChatGPT can be a valuable tool, it’s essential to use it responsibly and maintain control over your content creation process.

Experiment And Refine Your Prompting Techniques

Writing effective prompts for ChatGPT is an essential skill for any SEO professional who wants to harness the power of AI-generated content .

Hopefully, the insights and examples shared in this article can inspire you and help guide you to crafting stronger prompts that yield high-quality content.

Remember to experiment with layering prompts, iterating on the output, and continually refining your prompting techniques.

This will help you stay ahead of the curve in the ever-changing world of SEO.

More resources: 

• 25 ChatGPT Examples For Digital Marketers & SEOs 
• From Zero To ChatGPT Hero: How To Harness The Power Of AI In Marketing
• Leveraging Generative AI Tools For SEO

Featured Image: Tapati Rinchumrus/Shutterstock

Vincent Terrasi is the Co-founder and CTO at Draft&Goal. With more than 15 year’s experience, Vincent has become an expert ...

Subscribe To Our Newsletter.

Conquer your day with daily search marketing news.