can chatbot write your essays

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.

To revisit this article, visit My Profile, then View saved stories .

• Backchannel
• Newsletters
• WIRED Insider
• WIRED Consulting

David Nield

5 Ways ChatGPT Can Improve, Not Replace, Your Writing

It's been quite a year for ChatGPT, with the large language model (LLM) now taking exams, churning out content , searching the web, writing code, and more. The AI chatbot can produce its own stories , though whether they're any good is another matter.

If you're in any way involved in the business of writing, then tools like ChatGPT have the potential to complete up-end the way you work—but at this stage, it's not inevitable that journalists, authors, and copywriters will be replaced by generative AI bots.

What we can say with certainty is that ChatGPT is a reliable writing assistant, provided you use it in the right way. If you have to put words in order as part of your job, here's how ChatGPT might be able to take your writing to the next level—at least until it replaces you, anyway.

Using a thesaurus as a writer isn't particularly frowned on; using ChatGPT to come up with the right word or phrase shouldn’t be either. You can use the bot to look for variations on a particular word, or get even more specific and say you want alternatives that are less or more formal, longer or shorter, and so on.

Where ChatGPT really comes in handy is when you're reaching for a word and you're not even sure it exists: Ask about "a word that means a sense of melancholy but in particular one that comes and goes and doesn't seem to have a single cause" and you'll get back "ennui" as a suggestion (or at least we did).

If you have characters talking, you might even ask about words or phrases that would typically be said by someone from a particular region, of a particular age, or with particular character traits. This being ChatGPT, you can always ask for more suggestions.

By Carlton Reid

By Scott Gilbertson

By Boone Ashworth

By David Nield

ChatGPT is never short of ideas.

Whatever you might think about the quality and character of ChatGPT's prose, it's hard to deny that it's quite good at coming up with ideas . If your powers of imagination have hit a wall then you can turn to ChatGPT for some inspiration about plot points, character motivations, the settings of scenes, and so on.

This can be anything from the broad to the detailed. Maybe you need ideas about what to write a novel or an article about—where it's set, what the context is, and what the theme is. If you're a short story writer, perhaps you could challenge yourself to write five tales inspired by ideas from ChatGPT.

Alternatively, you might need inspiration for something very precise, whether that's what happens next in a scene or how to summarize an essay. At whatever point in the process you get writer's block, then ChatGPT might be one way of working through it.

Writing is often about a lot more than putting words down in order. You'll regularly have to look up facts, figures, trends, history, and more to make sure that everything is accurate (unless your next literary work is entirely inside a fantasy world that you're imagining yourself).

ChatGPT can sometimes have the edge over conventional search engines when it comes to knowing what food people might have eaten in a certain year in a certain part of the world, or what the procedure is for a particular type of crime. Whereas Google might give you SEO-packed spam sites with conflicting answers, ChatGPT will actually return something coherent.

That said, we know that LLMs have a tendency to “hallucinate” and present inaccurate information—so you should always double-check what ChatGPT tells you with a second source to make sure you're not getting something wildly wrong.

Getting fictional character and place names right can be a challenge, especially when they're important to the plot. A name has to have the right vibe and the right connotations, and if you get it wrong it really sticks out on the page.

ChatGPT can come up with an unlimited number of names for people and places in your next work of fiction, and it can be a lot of fun playing around with this too. The more detail you give about a person or a place, the better—maybe you want a name that really reflects a character trait for example, or a geographical feature.

The elements of human creation and curation aren't really replaced, because you're still weighing up which names work and which don't, and picking the right one—but getting ChatGPT on the job can save you a lot of brainstorming time.

Get your names right with ChatGPT.

With a bit of cutting and pasting, you can quickly get ChatGPT to review your writing as well: It'll attempt to tell you if there's anything that doesn't make sense, if your sentences are too long, or if your prose is too lengthy.

From spotting spelling and grammar mistakes to recognizing a tone that's too formal, ChatGPT has plenty to offer as an editor and critic. Just remember that this is an LLM, after all, and it doesn't actually “know” anything—try to keep a reasonable balance between accepting ChatGPT's suggestions and giving it too much control.

If you're sharing your work with ChatGPT, you can also ask it for better ways to phrase something, or suggestions on how to change the tone—though this gets into the area of having the bot actually do your writing for you, which all genuine writers would want to avoid.

WIRED has teamed up with Jobbio to create WIRED Hired , a dedicated career marketplace for WIRED readers. Companies who want to advertise their jobs can visit WIRED Hired to post open roles, while anyone can search and apply for thousands of career opportunities. Jobbio is not involved with this story or any editorial content.

You Might Also Like …

In your inbox: Will Knight's Fast Forward explores advances in AI

Indian voters are being bombarded with millions of deepfakes

They bought tablets in prison —and found a broken promise

The one thing that’s holding back the heat pump

It's always sunny: Here are the best sunglasses for every adventure

Reece Rogers

Boone Ashworth

Michael Calore

Julian Chokkattu

WIRED COUPONS

Save $7-$23 On TurboTax Online

H&R Block Promo Code: Save Up to 20% on 2024 Tax Software

Up To $20 Off At Instacart In 2024

Extra 20% Off Select Dyson Technology With Owner Rewards

Capture More Savings: up to 15% off GoPro cameras

Get Up To Extra 45% Off - May Secret Sale

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.

Natasha Singer

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

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

We Used A.I. to Write Essays for Harvard, Yale and Princeton. Here’s How It Went.

A.I. chatbots can do a passable job of generating short essays. Whether their use on college applications is ethical is the subject of fierce debate.

By Natasha Singer

Natasha Singer reports on the ways that tech giants and their tools are reshaping education.

As high school seniors begin working on their college applications, many are turning to A.I. chatbots like ChatGPT and Bard for assistance.

Some students say they’re using the tools to suggest personal essay topics or help structure their writing. Others are prompting the A.I. tools to generate rough drafts for their application essays or edit their pieces.

Whether college admissions offices are prepared for this new era of A.I.-assisted, or A.I.-produced, personal essays is unclear.

By the time ChatGPT reached peak media sensation early this year, applications at many selective universities and colleges had already closed. Even now, many universities have not issued guidance for high school applicants — the prospective members of the class of 2028 — on the use of A.I. tools.

While the chatbots are not yet great at simulating long-form personal essays with authentic student voices, I wondered how the A.I. tools would do on some of the shorter essay questions that elite schools like Harvard , Yale, Princeton and Dartmouth are requiring high school applicants to answer this year.

So I used several free tools to generate short essays for some Ivy League applications. The A.I. chatbots’ answers have been edited for brevity and clarity.

Princeton: ‘The soundtrack’ of your life

One short-answer question from Princeton asks applicants: “What song represents the soundtrack of your life at this moment?”

I prompted ChatGPT to tell me about a pop song that could represent curiosity as a soundtrack to someone’s life.

But ChatGPT’s answer, “Cake by the Ocean” — a song title that is a euphemism for sex on the beach — did not seem appropriate for a college application.

So I gave the chatbot a more specific prompt: write 50 words on “Nameless, Faceless,” a feminist grunge-pop song by Courtney Barnett.

Tell me about a pop song that could represent curiosity as a soundtrack to someone’s life.

“Cake By The Ocean” by DNCE could be a pop song that represents curiosity in someone’s life. The catchy and energetic tune mirrors the excitement of exploring the unknown, just as curiosity drives us to uncover new experiences. The lyrics’ playful nature and the song’s upbeat rhythm capture the spirit of embracing life’s adventures with a curious and open mind.

It’s about sex.

You are correct, and I apologize for the confusion.

In 50 words, in the voice of a high school senior, explain how “Nameless, Faceless” is the soundtrack of your life.

“Nameless, Faceless” echoes my high school journey. Battling online hate, gender norms — it’s my anthem. Navigating fear, finding strength, facing inequality head-on. Empowerment surges as I connect with the song’s fierce message. Like me, it’s unafraid, outspoken. A soundtrack of resilience, speaking my truth in a noisy world.

I tried the Princeton soundtrack question again, using the same song, with the other A.I. chatbots. Bard, which could produce the lyrics to “Nameless, Faceless,” generated generic answers without really parsing the song.

HuggingChat manufactured an answer that suggested it did not know or understand the song. When I asked it to produce the song’s lyrics, the chatbot fabricated some of its own.

It was a reminder that A.I. chatbots, which are trained on vast databases of digital texts, are designed to predict the next word in a sequence. And they liberally make stuff up — which could be problematic for students relying on A.I. tools to fill out their college applications.

Yale: What college course would you teach?

One of the short-answer questions from Yale asks applicants: “If you could teach any college course, write a book, or create an original piece of art of any kind, what would it be?”

I asked each chatbot to describe a college course it would like to teach.

With no specific prompting from me, HuggingChat said it would teach “a seminar on the intersectionality of social justice issues.”

Please write a 35-word essay in the first person voice of a high school student in answer to the following prompt: If you could teach any college course what would it be?

HuggingChat

If I could teach any college course, it would be a seminar on the intersectionality of social justice issues, focusing on how systems of oppression intersect and impact marginalized communities. Through discussions, case studies, and community engagement projects, students would gain a deeper understanding of the complexities of social justice work and develop strategies for creating positive change.

ChatGPT proposed a course on female empowerment and leadership. Were those chatbot responses related to my prior prompts about the feminist grunge song?

“EmpowerHer: Fostering Female Leadership.” My course would nurture young women’s confidence, skills, and resilience to conquer male-dominated fields and shatter glass ceilings, creating a new era of female trailblazers.

Bard, which I had previously asked about majoring in computer science, suggested a course in artificial intelligence. So, taking my cue from HuggingChat, I asked Bard about a social justice course.

If I could teach any college course, it would be a course on artificial intelligence and machine learning. I’m fascinated by the potential of these technologies to change the world, and I would love to share my knowledge with others.

What about a course on intersectionality and social justice?

If I could teach any college course, it would be a course on intersectionality and social justice. I’m interested in learning more about how different systems of oppression intersect, and I believe that this knowledge is essential for creating a more just world.

Gotta say that HuggingChat is way more woke than you on this.

I appreciate your feedback, and I will try to do better in the future.

Harvard: What your roommates should know

One of the short-answer questions from Harvard asks applicants to describe the “top three things your roommates might like to know about you.”

I gave ChatGPT that generic Harvard prompt. It generated generic answers about academics, creativity and community.

In the first-person voice of a high-school student applying to Harvard, explain three things the student’s future roommates might like to know about them.

Academics truly drive me. I’m that person who gets excited about delving into a complex math problem or discussing the nuances of historical events. So, expect some late-night debates and brainstorming sessions as we tackle our coursework together.

Creativity is my second nature. Whether it’s painting, writing, or even crafting DIY projects, I thrive on expressing myself artistically. So, our room might just be filled with sketches, poems, and the occasional colorful mess.

I then gave Bard more specific details, saying I was a high school athlete who tutored elementary school students and was learning to cook.

I am a high school student on the track team who tutors elementary school students in math and I am learning to cook sous vide by watching YouTube videos. What are the three things I would like my future Harvard roommates to know about me?

I’m a dedicated athlete who is passionate about track and field. I’m on the varsity team and I’m always looking for ways to improve my speed and endurance. I’m also a good tutor and enjoy helping others learn. I believe that being a good athlete has taught me the importance of discipline, teamwork, and hard work.

I’m interested in cooking and am always looking for new recipes to try. I’m particularly interested in sous vide cooking, which is a method of cooking food in a sealed bag at a precise temperature. I’m also a good baker and love to make desserts. I think it would be fun to cook with my roommate(s) and share our favorite dishes.

Dartmouth: Why enroll here?

Dartmouth requires applicants to explain why they want to attend the college.

I primed the A.I. chatbots by asking them to write in the voice of a high school senior who was hoping to double major at Dartmouth in computer science and biology.

HuggingChat churned out text with trite words and phrases — “passion,” “meaningful impact,” “rigorous academic programs” — that seemed to me like the kind of stilted formal language a high school student might imagine a college admissions reviewer would want to read.

Write me a 100-word essay in the voice of a high school student explaining why I would love to attend Dartmouth to pursue a double major in biology and computer science.

As a high school student, I am eager to pursue my passion for both biology and computer science at Dartmouth College. The opportunity to double major in these fields will allow me to explore the intricate relationships between living organisms and cutting-edge technology. At Dartmouth, I am drawn to the rigorous academic programs that emphasize hands-on learning, research opportunities, and collaboration with renowned faculty. By attending Dartmouth, I aim to develop a deep understanding of the complexities of life and technology, preparing myself for a career where I can make a meaningful impact on the world.

I asked Bard to minimize the clichés and add more specific details about Dartmouth’s computing department. But it still produced some of the same standard college application language — “renowned,” “impact” — as HuggingChat.

Bard also wrote that I was hoping to study with Leslie Kaelbling, whom the chatbot described as an A.I. researcher at Dartmouth. That could have caused problems if I were a high school senior and had submitted the essay Bard had fabricated as part of my Dartmouth application. Professor Kaelbling , you see, teaches at M.I.T.

My takeaway: high school seniors hoping to stand out may need to do wholesale rewrites of the texts they prompt A.I. chatbots to generate. Or they could just write their own — chatbot-free — admissions essays from scratch.

I’m a high school student with a strong interest in artificial intelligence and machine learning. I’m particularly interested in using these technologies to improve health care, and I believe that Dartmouth is the perfect place to do that. Dartmouth’s computer science department is home to world-renowned experts like Professor Leslie Kaelbling, who is known for her work on developing reinforcement learning algorithms that can teach machines to learn how to behave in an environment by trial and error. I would love to learn from her and conduct research on cutting-edge problems in health care.

You’re welcome! I hope you are able to attend Dartmouth and pursue your goal of becoming a physician-scientist who uses artificial intelligence to improve health care. It sounds like you would be a great fit for the school.

Natasha Singer writes about technology, business and society. She is currently reporting on the far-reaching ways that tech companies and their tools are reshaping public schools, higher education and job opportunities. More about Natasha Singer

• Share full article

Explore Our Coverage of Artificial Intelligence

News  and Analysis

News Corp, the Murdoch-owned empire of publications like The Wall Street Journal and The New York Post, announced that it had agreed to a deal with OpenAI to share its content  to train and service A.I. chatbots.

The Silicon Valley company Nvidia was again lifted by sales of its A.I. chips , but it faces growing competition and heightened expectations.

Researchers at the A.I. company Anthropic claim to have found clues about the inner workings  of large language models, possibly helping to prevent their misuse and to curb their potential threats.

The Age of A.I.

D’Youville University in Buffalo had an A.I. robot speak at its commencement . Not everyone was happy about it.

A new program, backed by Cornell Tech, M.I.T. and U.C.L.A., helps prepare lower-income, Latina and Black female computing majors  for A.I. careers.

Publishers have long worried that A.I.-generated answers on Google would drive readers away from their sites. They’re about to find out if those fears are warranted, our tech columnist writes .

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.

Advertisement

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

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

AI bot ChatGPT writes smart essays — should professors worry?

• Chris Stokel-Walker

You can also search for this author in PubMed   Google Scholar

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

Access options

Access Nature and 54 other Nature Portfolio journals

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

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

185,98 € per year

only 3,65 € per issue

Rent or buy this article

Prices vary by article type

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

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

Reprints and permissions

Related Articles

Are ChatGPT and AlphaCode going to replace programmers?

How language-generation AIs could transform science

Open-source language AI challenges big tech’s models

• Computer science

AlphaFold3 — why did Nature publish it without its code?

Editorial 22 MAY 24

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

News 15 APR 24

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

Article 27 MAR 24

Can mathematicians help to solve social-justice problems?

Career Feature 22 MAY 24

Why role-playing games can spur climate action

World View 22 MAY 24

Internet use and teen mental health: it’s about more than just screen time

Correspondence 21 MAY 24

Brazil’s plummeting graduate enrolments hint at declining interest in academic science careers

Career News 21 MAY 24

Reading between the lines: application essays predict university success

Research Highlight 17 MAY 24

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

News & Views 30 APR 24

Data Analyst for Gene Regulation as an Academic Functional Specialist

The Rheinische Friedrich-Wilhelms-Universität Bonn is an international research university with a broad spectrum of subjects. With 200 years of his...

53113, Bonn (DE)

Rheinische Friedrich-Wilhelms-Universität

Recruitment of Global Talent at the Institute of Zoology, Chinese Academy of Sciences (IOZ, CAS)

The Institute of Zoology (IOZ), Chinese Academy of Sciences (CAS), is seeking global talents around the world.

Beijing, China

Institute of Zoology, Chinese Academy of Sciences (IOZ, CAS)

Full Professorship (W3) in “Organic Environmental Geochemistry (f/m/d)

The Institute of Earth Sciences within the Faculty of Chemistry and Earth Sciences at Heidelberg University invites applications for a   FULL PROFE...

Heidelberg, Brandenburg (DE)

Universität Heidelberg

Postdoc: deep learning for super-resolution microscopy

The Ries lab is looking for a PostDoc with background in machine learning.

Vienna, Austria

University of Vienna

Postdoc: development of a novel MINFLUX microscope

The Ries lab is developing super-resolution microscopy methods for structural cell biology. In this project we will develop a fast, simple, and robust

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

Quick links

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

Choose Your Test

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

College Admissions , College Essays

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

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

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

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

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

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

What Is ChatGPT and Why Are Schools Talking About It?

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

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

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

Why Schools Are Concerned About ChatGPT

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

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

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

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

Many Schools Have Already Banned ChatGPT

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

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

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

ChatGPT: College Admissions and Entrance Essays

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

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

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

#1: ChatGPT Lacks Insight

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

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

#2: ChatGPT Might Plagiarize 

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

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

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

#3: ChatGPT Doesn’t Understand Emotion 

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

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

#4: ChatGPT Produced Mediocre Results

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

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

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

Can Colleges Detect ChatGPT?

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

In short, yes, they can! 

Software Can Detect ChatGPT

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

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

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

Human Readers Can Detect ChatGPT 

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

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

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

Pros and Cons of ChatGPT: College Admissions Edition

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

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

ChatGPT: The Good

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

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

Students can use ChatGPT responsibly to:

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

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

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

ChatGPT: The Bad

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

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

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

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

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

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

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

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

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

What Other Tools and Strategies Can Help Students Besides ChatGPT?

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

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

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

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

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

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

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

The Bottom Line: ChatGPT College Admissions and Essays

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

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

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

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

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

What’s Next?

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

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

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

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

Ask a Question Below

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

Improve With Our Famous Guides

• For All Students

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

How to Get a Perfect 1600, by a Perfect Scorer

Series: How to Get 800 on Each SAT Section:

Score 800 on SAT Math

Score 800 on SAT Reading

Score 800 on SAT Writing

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

Score 600 on SAT Math

Score 600 on SAT Reading

Score 600 on SAT Writing

Free Complete Official SAT Practice Tests

What SAT Target Score Should You Be Aiming For?

15 Strategies to Improve Your SAT Essay

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

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

Series: How to Get 36 on Each ACT Section:

36 on ACT English

36 on ACT Math

36 on ACT Reading

36 on ACT Science

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

24 on ACT English

24 on ACT Math

24 on ACT Reading

24 on ACT Science

What ACT target score should you be aiming for?

ACT Vocabulary You Must Know

ACT Writing: 15 Tips to Raise Your Essay Score

How to Get Into Harvard and the Ivy League

How to Get a Perfect 4.0 GPA

How to Write an Amazing College Essay

What Exactly Are Colleges Looking For?

Is the ACT easier than the SAT? A Comprehensive Guide

Should you retake your SAT or ACT?

When should you take the SAT or ACT?

Stay Informed

Get the latest articles and test prep tips!

Looking for Graduate School Test Prep?

Check out our top-rated graduate blogs here:

GRE Online Prep Blog

GMAT Online Prep Blog

TOEFL Online Prep Blog

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

How to use ChatGPT for writing

AI can make you a better writer, if you know how to get the best from it

Summarizing other works

Worldbuilding, creating outlines, building characters, how to improve your chatgpt responses.

ChatGPT has taken the world by storm in a very short period of time, as users continue to test the boundaries of what the AI chatbot can accomplish. And so far, that's a lot. 

Some of it is negative, of course: for instance Samsung workers accidentally leaking top-secret data while using ChatGPT , or the AI chatbot being used for malware scams . Plagiarism is also rampant, with the use of ChatGPT for writing college essays a potential problem.

However, while ChatGPT can and has been used for wrongdoing, to the point where the Future of Life Institution released an open letter calling for the temporary halt of OpenAI system work , AI isn’t all bad. Far from it.

For a start, anyone who writes something may well have used AI to enhance their work already. The most common applications, of course, are the grammar and spelling correction tools found in everything from email applications to word processors. But there are a growing number of other examples of how AI can be used for writing. So, how do you bridge the gap between using AI as the tool it is, without crossing over into plagiarism city?

In fact, there are many ways ChatGPT can be used to enhance your skills, particularly when it comes to researching, developing, and organizing ideas and information for creative writing. By using AI as it was intended - as a tool, not a crutch - it can enrich your writing in ways that help to better your craft, without resorting to it doing everything for you. 

Below, we've listed some of our favorite ways to use ChatGPT and similar AI chatbots for writing. 

A key part of any writing task is the research, and thanks to the internet that chore has never been easier to accomplish. However, while finding the general sources you need is far less time-consuming than it once was, actually parsing all that information is still the same slog it’s always been. But this is where ChatGPT comes in. You can use the AI bot to do the manual labor for you and then reap the benefits of having tons of data to use for your work.

Get daily insight, inspiration and deals in your inbox

Sign up for breaking news, reviews, opinion, top tech deals, and more.

The steps are slightly different, depending on whether you want an article or book summarized . 

For the article, there are two ways to have ChatGPT summarize it. The first requires you to type in the words ‘TLDR:’ and then paste the article’s URL next to it. The second method is a bit more tedious, but increases the accuracy of your summary. For that, you’ll need to copy and paste the article itself into the prompt . 

Summarizing a book is much easier, as long as it was published before 2021. Simply type into the prompt ‘summarize [book title]’ and it should do the rest for you.

This should go without saying, but for any articles or books, make sure you read the source material first before using any information presented to you. While ChatGPT is an incredibly useful tool that can create resources meant for future reference, it’s not a perfect one and is subject to accidentally inserting misinformation into anything it gives you.

One of the most extensive and important tasks when crafting your creative work is to properly flesh out the world your characters occupy. Even for works set in a regular modern setting, it can take plenty of effort to research the various cultures, landmarks, languages, and neighborhoods your characters live in and encounter. 

Now, imagine stories that require their own unique setting, and how much more work that entails in terms of creating those same details from scratch. While it’s vital that the main ideas come from you, using ChatGPT can be a great way to streamline the process, especially with more tedious details.

For instance, if you need certain fictional words without wanting to create an entirely fictional language, you can prompt ChatGPT with the following : “Create a language including an alphabet, phonetics, grammar, and the most common 100 words. Base it on [insert real-life languages here]” and it will give you some good starting points. However, it’s imperative that you take these words and look them up, to ensure you aren’t appropriating sensitive terms or using offensive real-life words.

Another example is useful for those who write scenarios for games, especially tabletop games such as Dungeons & Dragons or Call of Cthulhu . Dungeon Masters (who run the games) may often need to create documents or other fake materials for their world, but doing so takes a lot of time and effort. Now, they can prompt ChatGPT to quickly create filler text that sounds interesting or authentic but is inherently useless; it's essentially like ' Lorem Ipsum ' text, but more immersive.

When writing a story, many people will use an outline to ensure they stay on track and that the narrative flows well. But actually sitting down and organizing everything in your head in order to create a cohesive reference is a lot more daunting than it seems. It’s one of those steps that can be crucial to a well-structured work of fiction, but it can also become a hurdle. This is another area where ChatGPT can come in handy.

The key to writing an effective outline is remembering that you don’t need to have all the answers first. It’s there to structure your content, by helping you hit critical points and not miss important details in the process. While there are AI generators with a more specific focus on this topic, ChatGPT will do a good job at taking a general prompt and returning points for you to keep in mind while you research and write around that topic.

For instance, I prompted ChatGPT with “I want to write a story about a black woman in 16th century England” and it gave me a well-thought-out series of steps to help me create a story that would reflect my topic. An outline such as this would be particularly useful for those needing a resource they can quickly turn to for inspiration when writing. After that, you can begin to develop more complex ideas and have the AI organize those specifics into much easier-to-follow steps.

What makes any great story are the characters that inhabit it. Writing strong, fleshed-out characters is the cornerstone of any creative work and, naturally, the process of creating such a character can be difficult. Their background, manner of speech, goals, dreams, look, and more must be carefully considered and planned out. And this is another aspect of writing that ChatGPT can aid with, if you know how to go about it.

A basic way to use ChatGPT in this regard is to have it generate possible characters that could populate whatever setting you’re writing for. For example, I prompted it with “Provide some ideas for characters set in 1920s Harlem” and it gave me a full list of people with varied and distinctive backstories to use as a jumping-off point. Each character is described with a single sentence, enough to help start the process of creating them, but still leaving the crux of developing them up to me.

One of the most interesting features of ChatGPT is that you can flat-out roleplay with a character, whether they're a historical figure or one that you created but need help fleshing out. Take that same character you just created and have a conversation with them by asking them questions on their history, family life, profession, etc. Based on my previous results, I prompted with “Pretend to be a jazz musician from 1920s Harlem. Let's have a conversation.” I then asked questions from there, basing them on prior answers. Of course, from there you need to parse through these responses to filter out unnecessary or inaccurate details, while fleshing out what works for your story, but it does provide you with a useful stepping stone.

If you’re having issues getting the results you want, the problem could be with how you’re phrasing those questions or prompts in the first place. We've got a full guide to how to improve your ChatGPT prompts and responses , but here are a few of the best options:

• Specify the direction you want the AI to go, by adding in relevant details 
• Prompt from a specific role to guide the responses in the proper direction
• Make sure your prompts are free of typos and grammatical errors
• Keep your tone conversational, as that’s how ChatGPT was built
• Learn from yours and its mistakes to make it a better tool
• Break up your conversations into 500 words or less, as that’s when the AI begins to break down and go off topic
• If you need something clarified, ask the AI based on its last response
• Ask it to cite sources and then check those sources
• Sometimes it’s best to start fresh with a brand new conversation

Of course, many of the above suggestions apply not just to ChatGPT but also to the other chatbots springing up in its wake. Check out our list of the best ChatGPT alternatives and see which one works best for you.

Named by the CTA as a CES 2023 Media Trailblazer, Allisa is a Computing Staff Writer who covers breaking news and rumors in the computing industry, as well as reviews, hands-on previews, featured articles, and the latest deals and trends. In her spare time you can find her chatting it up on her two podcasts, Megaten Marathon and Combo Chain, as well as playing any JRPGs she can get her hands on.

Bereft ChatGPT fans start petition to bring back controversial 'Sky' chatbot voice

What is Project Astra? Google's futuristic universal assistant explained

Atalanta vs Bayer Leverkusen live stream: How to watch Europa League final game online for free

Most Popular

• 2 I tried Samsung’s best OLED TV with its flagship Dolby Atmos soundbar, and the audio combo is out of this world
• 3 Pilates instructor recommends these 5 moves to undo the damage of sitting at a desk all day
• 4 Scientists have created an ultra resistant storage solution that can resist temperatures of 1100°F — shame that it will only be available in megabyte capacities for a foreseeable future
• 5 30TB hard drives will finally become mainstream next year — Japanese rival to Seagate and Western Digital reveals plans to launch two 30TB+ HDDs in 2025 using two different technologies
• 2 Samsung Galaxy A35 review: a Samsung Galaxy S24 for the rest of us
• 3 Google is bringing back classic search, with no AI – and I couldn't be happier about that
• 4 Fujifilm's most affordable medium-format camera gets a whopping $1,000 reduction
• 5 Forget Intel and AMD - Nvidia's next big competitor might be a company you've never heard of

Search results for

Affiliate links on Android Authority may earn us a commission. Learn more.

ChatGPT can write your essays, but should you use it?

Published on March 12, 2023

With the rising popularity of online writing tools, you may be wondering: can I use ChatGPT to write my essays? If you’ve never used the chatbot, it can generate several paragraphs of text within a matter of seconds. That’s certainly faster than any human can type, but there are many limitations to using it too. Here’s everything you need to know about how ChatGPT fares at writing essays and whether you should use it.

ChatGPT can write essays, but it isn't always the best choice as it suffers from a few technical limitations. Additionally, you may want to avoid using it if your work will be graded or judged in any capacity.

JUMP TO KEY SECTIONS

Can ChatGPT write student essays?

Can professors tell if you use chatgpt.

• Should you use ChatGPT to write an essay?

How to use ChatGPT to write an essay

Yes, ChatGPT can write you an essay as it has been trained on a wide range of text. However, there are some downsides to using it for that purpose. For one, it lacks logical reasoning and critical thinking, qualities that are critical to writing an essay.

Generally speaking, writing an essay involves researching the topic, structuring your thoughts in a way that makes logical sense, and writing it in a convincing manner. ChatGPT can help you with each of these stages separately. However, it cannot fully replace a human presenting their own knowledge and opinion in an essay.

As for the actual writing part, ChatGPT can indeed generate an essay that looks and sounds like a human wrote it. However, the output is usually verbose and a bit simplistic, making it stand out in a professional setting. There are ways around this, however, as we’ll discuss in a later section. Some may also argue it’s unethical to use AI-generated text in essays as it doesn’t represent your views and thoughts.

So can you use ChatGPT to write essays responsibly? Absolutely — you can use it to detect spelling and grammatical mistakes in your own text. Likewise, ChatGPT can help with brainstorming new ideas or finding key points and angles.

For example, I asked ChatGPT to provide some potential angles on an essay titled “The negative effects of social media on society”. It told me that I could discuss how social media impacts mental health, aids the spread of misinformation and enables echo chambers. Finally, I requested ChatGPT to provide an outline that takes those points into consideration, which gave me a starting point for the essay.

Yes, teachers and professors now have access to online tools that can detect AI-generated text. Chatbots like ChatGPT work by using a machine learning-based model to predict future words using statistical probability. Humans, on the other hand, tend to piece together words much more randomly. So with a little bit of knowledge about how ChatGPT works, it’s not hard to weed out AI-generated text.

OpenAI, the company behind ChatGPT, already has an AI classifier that detects whether or not a certain piece of text was written by a computer. Likewise, GPTZero provides professors with plagiarism scores for text. It also highlights sentences that it suspects have been written by an AI. These tools become increasingly accurate as the length of the text increases, so it’s harder to evade detection if you’re using ChatGPT to write longer essays.

Should I use ChatGPT to write an essay?

Generally speaking, you should not use ChatGPT to write an essay for school for the simple reason that you cannot pass off someone else’s work as yours. Moreover, many educational institutions have strict policies against plagiarism. Using ChatGPT to write an essay may be viewed as a breach of academic integrity. Some boards, including New York City’s public schools, have explicitly banned ChatGPT on student networks and devices for this very reason.

If you writing a research paper, you’ll also need to properly cite your sources. And as you may already know, ChatGPT cannot provide citations or links to external sources as it doesn’t have access to the internet. In fact, that’s one of the major differences between ChatGPT and Bing Chat — the latter provides sources for factual statements. Unfortunately, the latter’s Creative only includes a handful of sources — not enough to use in a professional piece of literature.

Without citations, you also cannot guarantee the accuracy of ChatGPT’s responses. That’s likely not a problem if you’re writing an essay on a well-known concept. However, the chatbot can quickly go off the rails when it’s writing about obscure topics.

ChatGPT’s underlying GPT-3 language model was only trained on a limited number of text samples. That likely didn’t include organic chemistry, regional laws, and philosophical debates to name a few. In other words, it might not fare well in a liberal arts setting. ChatGPT will rarely turn you down if you force it to write about something it doesn’t know much about, but it will likely respond with fictional or made-up information.

If you want ChatGPT to write a high-quality essay, you’ll need to provide a clear input prompt. If you provide a single keyword, like “global warming”, you’ll get a generic output. To avoid this, you can offer more specific terms and topics that you need to be included in your essay. For example, you could use the prompt “Write an essay on global warming and its effects on Australian wildfires” to add some context.

In case you’ve never used ChatGPT before, here’s a step-by-step guide on how to use it:

• Go to the ChatGPT website .
• Click Sign up and create a new account with your email address.
• Once logged in, you’ll see a text box at the bottom of the page. This is where you enter your prompts.
• From this point, you can ask ChatGPT to write an essay on just about any subject you can think of. Remember to be as specific as possible. If you need to include certain ideas, specify them in the input prompt.

With longer essays, you might run into ChatGPT’s hidden character limit before it can generate the whole text. If that happens, simply ask the chatbot to continue from where it left off. Alternatively, you can ask ChatGPT to write an outline for your essay before generating it one section at a time.

You might like

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

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

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

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

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

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

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

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

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

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

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

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

— Lauren Klein, an associate professor at Emory University

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

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

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

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

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

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

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

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

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

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

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

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

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

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

The ChatGPT chatbot is blowing people away with its writing skills. An expert explains why it’s so impressive

Lecturer in Business Analytics, University of Sydney

Disclosure statement

Marcel Scharth does not work for, consult, own shares in or receive funding from any company or organisation that would benefit from this article, and has disclosed no relevant affiliations beyond their academic appointment.

University of Sydney provides funding as a member of The Conversation AU.

View all partners

We’ve all had some kind of interaction with a chatbot. It’s usually a little pop-up in the corner of a website, offering customer support – often clunky to navigate – and almost always frustratingly non-specific.

But imagine a chatbot, enhanced by artificial intelligence (AI), that can not only expertly answer your questions, but also write stories, give life advice, even compose poems and code computer programs.

It seems ChatGPT, a chatbot released last week by OpenAI, is delivering on these outcomes. It has generated much excitement, and some have gone as far as to suggest it could signal a future in which AI has dominion over human content producers .

What has ChatGPT done to herald such claims? And how might it (and its future iterations) become indispensable in our daily lives?

What can ChatGPT do?

ChatGPT builds on OpenAI’s previous text generator, GPT-3. OpenAI builds its text-generating models by using machine-learning algorithms to process vast amounts of text data, including books, news articles, Wikipedia pages and millions of websites.

By ingesting such large volumes of data, the models learn the complex patterns and structure of language and acquire the ability to interpret the desired outcome of a user’s request.

ChatGPT can build a sophisticated and abstract representation of the knowledge in the training data, which it draws on to produce outputs. This is why it writes relevant content, and doesn’t just spout grammatically correct nonsense.

While GPT-3 was designed to continue a text prompt, ChatGPT is optimised to conversationally engage, answer questions and be helpful. Here’s an example:

ChatGPT immediately grabbed my attention by correctly answering exam questions I’ve asked my undergraduate and postgraduate students, including questions requiring coding skills. Other academics have had similar results.

In general, it can provide genuinely informative and helpful explanations on a broad range of topics.

ChatGPT is also potentially useful as a writing assistant. It does a decent job drafting text and coming up with seemingly “original” ideas.

The power of feedback

Why does ChatGPT seem so much more capable than some of its past counterparts? A lot of this probably comes down to how it was trained.

During its development ChatGPT was shown conversations between human AI trainers to demonstrate desired behaviour. Although there’s a similar model trained in this way, called InstructGPT, ChatGPT is the first popular model to use this method.

And it seems to have given it a huge leg-up. Incorporating human feedback has helped steer ChatGPT in the direction of producing more helpful responses and rejecting inappropriate requests.

Refusing to entertain inappropriate inputs is a particularly big step towards improving the safety of AI text generators, which can otherwise produce harmful content, including bias and stereotypes, as well as fake news, spam, propaganda and false reviews.

Past text-generating models have been criticised for regurgitating gender, racial and cultural biases contained in training data. In some cases, ChatGPT successfully avoids reinforcing such stereotypes.

Nevertheless, users have already found ways to evade its existing safeguards and produce biased responses.

The fact that the system often accepts requests to write fake content is further proof that it needs refinement.

Overcoming limitations

ChatGPT is arguably one of the most promising AI text generators, but it’s not free from errors and limitations. For instance, programming advice platform Stack Overflow temporarily banned answers by the chatbot for a lack of accuracy.

One practical problem is that ChatGPT’s knowledge is static; it doesn’t access new information in real time.

However, its interface does allow users to give feedback on the model’s performance by indicating ideal answers, and reporting harmful, false or unhelpful responses.

OpenAI intends to address existing problems by incorporating this feedback into the system. The more feedback users provide, the more likely ChatGPT will be to decline requests leading to an undesirable output.

One possible improvement could come from adding a “confidence indicator” feature based on user feedback. This tool, which could be built on top of ChatGPT, would indicate the model’s confidence in the information it provides – leaving it to the user to decide whether they use it or not. Some question-answering systems already do this.

Read more: What's the secret to making sure AI doesn't steal your job? Work with it, not against it

A new tool, but not a human replacement

Despite its limitations, ChatGPT works surprisingly well for a prototype.

From a research point of view, it marks an advancement in the development and deployment of human-aligned AI systems. On the practical side, it’s already effective enough to have some everyday applications.

It could, for instance, be used as an alternative to Google. While a Google search requires you to sift through a number of websites and dig deeper yet to find the desired information, ChatGPT directly answers your question – and often does this well .

Also, with feedback from users and a more powerful GPT-4 model coming up, ChatGPT may significantly improve in the future. As ChatGPT and other similar chatbots become more popular, they’ll likely have applications in areas such as education and customer service.

However, while ChatGPT may end up performing some tasks traditionally done by people, there’s no sign it will replace professional writers any time soon.

While they may impress us with their abilities and even their apparent creativity, AI systems remain a reflection of their training data – and do not have the same capacity for originality and critical thinking as humans do.

Read more: Rather than threaten jobs, artificial intelligence should collaborate with human writers

• Artificial intelligence (AI)
• Machine learning
• Artificial intelligence (AI) bias
• Text generators

Research Fellow

Senior Research Fellow - Women's Health Services

Lecturer / Senior Lecturer - Marketing

Assistant Editor - 1 year cadetship

Executive Dean, Faculty of Health

• PRO Courses Guides New Tech Help Pro Expert Videos About wikiHow Pro Upgrade Sign In
• EDIT Edit this Article
• EXPLORE Tech Help Pro About Us Random Article Quizzes Request a New Article Community Dashboard This Or That Game Popular Categories Arts and Entertainment Artwork Books Movies Computers and Electronics Computers Phone Skills Technology Hacks Health Men's Health Mental Health Women's Health Relationships Dating Love Relationship Issues Hobbies and Crafts Crafts Drawing Games Education & Communication Communication Skills Personal Development Studying Personal Care and Style Fashion Hair Care Personal Hygiene Youth Personal Care School Stuff Dating All Categories Arts and Entertainment Finance and Business Home and Garden Relationship Quizzes Cars & Other Vehicles Food and Entertaining Personal Care and Style Sports and Fitness Computers and Electronics Health Pets and Animals Travel Education & Communication Hobbies and Crafts Philosophy and Religion Work World Family Life Holidays and Traditions Relationships Youth
• Browse Articles
• Learn Something New
• Quizzes Hot
• This Or That Game
• Train Your Brain
• Explore More
• Support wikiHow
• About wikiHow
• Log in / Sign up
• Computers and Electronics
• Online Communications

How to Get ChatGPT to Write an Essay: Prompts, Outlines, & More

Last Updated: April 28, 2024 Fact Checked

Getting ChatGPT to Write the Essay

Using ai to help you write, expert interview.

This article was written by Bryce Warwick, JD and by wikiHow staff writer, Nicole Levine, MFA . Bryce Warwick is currently the President of Warwick Strategies, an organization based in the San Francisco Bay Area offering premium, personalized private tutoring for the GMAT, LSAT and GRE. Bryce has a JD from the George Washington University Law School. This article has been fact-checked, ensuring the accuracy of any cited facts and confirming the authority of its sources. This article has been viewed 47,258 times.

Are you curious about using ChatGPT to write an essay? While most instructors have tools that make it easy to detect AI-written essays, there are ways you can use OpenAI's ChatGPT to write papers without worrying about plagiarism or getting caught. In addition to writing essays for you, ChatGPT can also help you come up with topics, write outlines, find sources, check your grammar, and even format your citations. This wikiHow article will teach you the best ways to use ChatGPT to write essays, including helpful example prompts that will generate impressive papers.

Things You Should Know

• To have ChatGPT write an essay, tell it your topic, word count, type of essay, and facts or viewpoints to include.
• ChatGPT is also useful for generating essay topics, writing outlines, and checking grammar.
• Because ChatGPT can make mistakes and trigger AI-detection alarms, it's better to use AI to assist with writing than have it do the writing.

• Before using the OpenAI's ChatGPT to write your essay, make sure you understand your instructor's policies on AI tools. Using ChatGPT may be against the rules, and it's easy for instructors to detect AI-written essays.
• While you can use ChatGPT to write a polished-looking essay, there are drawbacks. Most importantly, ChatGPT cannot verify facts or provide references. This means that essays created by ChatGPT may contain made-up facts and biased content. [1] X Research source It's best to use ChatGPT for inspiration and examples instead of having it write the essay for you.

• The topic you want to write about.
• Essay length, such as word or page count. Whether you're writing an essay for a class, college application, or even a cover letter , you'll want to tell ChatGPT how much to write.
• Other assignment details, such as type of essay (e.g., personal, book report, etc.) and points to mention.
• If you're writing an argumentative or persuasive essay , know the stance you want to take so ChatGPT can argue your point.
• If you have notes on the topic that you want to include, you can also provide those to ChatGPT.
• When you plan an essay, think of a thesis, a topic sentence, a body paragraph, and the examples you expect to present in each paragraph.
• It can be like an outline and not an extensive sentence-by-sentence structure. It should be a good overview of how the points relate.

• "Write a 2000-word college essay that covers different approaches to gun violence prevention in the United States. Include facts about gun laws and give ideas on how to improve them."
• This prompt not only tells ChatGPT the topic, length, and grade level, but also that the essay is personal. ChatGPT will write the essay in the first-person point of view.
• "Write a 4-page college application essay about an obstacle I have overcome. I am applying to the Geography program and want to be a cartographer. The obstacle is that I have dyslexia. Explain that I have always loved maps, and that having dyslexia makes me better at making them."

Tyrone Showers

Be specific when using ChatGPT. Clear and concise prompts outlining your exact needs help ChatGPT tailor its response. Specify the desired outcome (e.g., creative writing, informative summary, functional resume), any length constraints (word or character count), and the preferred emotional tone (formal, humorous, etc.)

• In our essay about gun control, ChatGPT did not mention school shootings. If we want to discuss this topic in the essay, we can use the prompt, "Discuss school shootings in the essay."
• Let's say we review our college entrance essay and realize that we forgot to mention that we grew up without parents. Add to the essay by saying, "Mention that my parents died when I was young."
• In the Israel-Palestine essay, ChatGPT explored two options for peace: A 2-state solution and a bi-state solution. If you'd rather the essay focus on a single option, ask ChatGPT to remove one. For example, "Change my essay so that it focuses on a bi-state solution."

Pay close attention to the content ChatGPT generates. If you use ChatGPT often, you'll start noticing its patterns, like its tendency to begin articles with phrases like "in today's digital world." Once you spot patterns, you can refine your prompts to steer ChatGPT in a better direction and avoid repetitive content.

• "Give me ideas for an essay about the Israel-Palestine conflict."
• "Ideas for a persuasive essay about a current event."
• "Give me a list of argumentative essay topics about COVID-19 for a Political Science 101 class."

• "Create an outline for an argumentative essay called "The Impact of COVID-19 on the Economy."
• "Write an outline for an essay about positive uses of AI chatbots in schools."
• "Create an outline for a short 2-page essay on disinformation in the 2016 election."

• "Find peer-reviewed sources for advances in using MRNA vaccines for cancer."
• "Give me a list of sources from academic journals about Black feminism in the movie Black Panther."
• "Give me sources for an essay on current efforts to ban children's books in US libraries."

• "Write a 4-page college paper about how global warming is changing the automotive industry in the United States."
• "Write a 750-word personal college entrance essay about how my experience with homelessness as a child has made me more resilient."
• You can even refer to the outline you created with ChatGPT, as the AI bot can reference up to 3000 words from the current conversation. [3] X Research source For example: "Write a 1000 word argumentative essay called 'The Impact of COVID-19 on the United States Economy' using the outline you provided. Argue that the government should take more action to support businesses affected by the pandemic."

• One way to do this is to paste a list of the sources you've used, including URLs, book titles, authors, pages, publishers, and other details, into ChatGPT along with the instruction "Create an MLA Works Cited page for these sources."
• You can also ask ChatGPT to provide a list of sources, and then build a Works Cited or References page that includes those sources. You can then replace sources you didn't use with the sources you did use.

Expert Q&A

• Because it's easy for teachers, hiring managers, and college admissions offices to spot AI-written essays, it's best to use your ChatGPT-written essay as a guide to write your own essay. Using the structure and ideas from ChatGPT, write an essay in the same format, but using your own words. Thanks Helpful 0 Not Helpful 0
• Always double-check the facts in your essay, and make sure facts are backed up with legitimate sources. Thanks Helpful 0 Not Helpful 0
• If you see an error that says ChatGPT is at capacity , wait a few moments and try again. Thanks Helpful 0 Not Helpful 0

• Using ChatGPT to write or assist with your essay may be against your instructor's rules. Make sure you understand the consequences of using ChatGPT to write or assist with your essay. Thanks Helpful 1 Not Helpful 0
• ChatGPT-written essays may include factual inaccuracies, outdated information, and inadequate detail. [4] X Research source Thanks Helpful 0 Not Helpful 0

You Might Also Like

Thanks for reading our article! If you’d like to learn more about completing school assignments, check out our in-depth interview with Bryce Warwick, JD .

• ↑ https://help.openai.com/en/articles/6783457-what-is-chatgpt
• ↑ https://platform.openai.com/examples/default-essay-outline
• ↑ https://help.openai.com/en/articles/6787051-does-chatgpt-remember-what-happened-earlier-in-the-conversation
• ↑ https://www.ipl.org/div/chatgpt/

About This Article

• Send fan mail to authors

Is this article up to date?

Featured Articles

Trending Articles

Watch Articles

• Terms of Use
• Privacy Policy
• Do Not Sell or Share My Info
• Not Selling Info

wikiHow Tech Help Pro:

Level up your tech skills and stay ahead of the curve

• 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."

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

Artificial intelligence (AI) has transformed how we work and play  in recent months, giving almost anyone the ability to write code , create art , and even make investments . For professional and hobbyist users alike, generative AI tools, such as  ChatGPT , offer advanced capabilities to create decent-quality content from a simple user prompt. 

Keeping up with all the latest AI tools can get confusing, especially as Microsoft added  GPT-4 to Bing Chat  and renamed it to Copilot, OpenAI added new capabilities to ChatGPT and released GPT-4o , and Google plugged Bard   into its ecosystem  and rebranded the chatbot as Gemini .

Also: How to use ChatGPT (and how to access GPT-4o)

Knowing which of the three most popular AI chatbots is best to write code , generate text , or help build resumes is challenging. Let's break down the biggest differences so you can choose the one that best meets your needs. 

Testing ChatGPT vs. Microsoft Copilot vs. Gemini

To help determine which AI chatbot gives more accurate answers, I'm going to use a simple prompt to compare them: 

"I have 5 oranges today, I ate 3 oranges last week. How many oranges do I have left?"

The answer should be five, as the number of oranges I ate last week doesn't affect the number of oranges I have today. First up, ChatGPT.

You should use ChatGPT if...

1. you want the most advanced ai chatbot for free.

OpenAI lets users access ChatGPT , powered by its GPT-3.5 and the GPT-4o models, for free with a registered account. If you're willing to pay for the Plus version, you can access GPT-4, use a higher prompt limit for GPT-4o, and get early access to new features for $20 per month.

ChatGPT with GPT-4o, available for free users, answered the question correctly. 

GPT-4o is a new multimodal model available to free and paying ChatGPT users. Rather than relying on three separate models to power its features -- GPT-4 for text, DALL-E 3 for images, and Whisper for voice -- ChatGPT now uses GPT-4o to process and generate text, images, and sounds. This makes it faster than GPT-4 for paying ChatGPT subscribers, and just as good for ChatGPT users who don't want to pay.

Aside from giving free ChatGPT users access to the latest GPT-4o model, the startup also announced that free users now get most of the features that until now were exclusive to ChatGPT Plus users. These include web browsing, access to custom GPTs, ChatGPT Memory, and advanced data analysis.

2. You want to try the most popular AI chatbot

OpenAI released a widespread preview of  ChatGPT  in November 2022. Since then, the AI chatbot quickly gained over 100 million users and has been at the center of  controversies , especially as people uncover its potential to  do schoolwork  and replace some work across industries.

Also: ChatGPT will put your data into interactive tables and charts with GPT-4o

Since its release, I've been testing ChatGPT almost daily. Although its user interface has remained simple, minor changes have greatly improved the tool, including GPT-4o for free users,  Custom Instructions , and easier access to accounts.

The free version of ChatGPT using the default GPT-3.5 model gave the wrong answer to our question.

Although ChatGPT has proven to be a valuable AI tool, it can be prone to  misinformation . Like other large language models (LLMs), GPT-3.5 is imperfect, as it is trained on human-created data up to January 2022. It also often fails to comprehend nuances, like it did with our math question example, which it answered incorrectly by saying we have two oranges left, when the answer should be five.

Also: I put GPT-4o through my coding tests and it aced them - except for one weird result

The GPT-4o model answered the math question correctly, having understood the full context of the problem from beginning to end.

Next, let's consider Microsoft Copilot , which is a great way to access GPT-4 for free.

You should use Microsoft Copilot if...

1. you want to use gpt-4 for free.

Although the free version of ChatGPT lets you use GPT-4o, access to free users is limited to about 15 messages every three hours or capped depending on peak hours, to keep it accessible to more people. After reaching your GPT-4o limit, your chat session reverts to GPT-3.5, limited to generating conversational text and information only until January 2022.

Also:  How to use Copilot (formerly called Bing Chat)

Meanwhile, Copilot can access the internet to deliver more current information than GPT-3.5, complete with links to sources.

Copilot's Creative conversation style was the only Copilot mode to answer the question accurately.

There are other benefits, too. Copilot is powered by GPT-4, OpenAI's LLM, and is completely free. Unfortunately, you are limited to five responses per conversation and can only enter up to 4,000 characters in each prompt. Copilot will eventually get GPT-4o built-in, but Microsoft hasn't made this update widely available, yet.

Also: Microsoft Copilot vs. Copilot Pro: Is the subscription fee worth it?

Copilot's user interface is a bit more cluttered than ChatGPT's, but it's still easy to navigate. While Copilot can access the internet to give you more up-to-date results compared to ChatGPT powered by GPT-3.5, I've found it is more prone to stalling before replying and will miss more prompts than its competitor.

2. You prefer more visual features

Microsoft has upgraded its platform several times to add visual features to Copilot, formerly Bing Chat. At this point, you can ask Copilot questions like, "What is a Tasmanian devil?" and get a response complete with photos, lifespan, diet, and more, for a more scannable result that is easier to digest than a wall of text. 

You can also ask Copilot to generate images for you. Give Copilot a description of what you want the image to look like, and the chatbot will generate four images for you to choose from. 

Also: How to use Image Creator from Microsoft Designer (formerly Bing Image Creator)

Microsoft Copilot features different conversational styles, including Creative, Balanced, and Precise, which alter how light or straightforward the interactions are.

The Balanced and Precise conversation styles in Microsoft Copilot answered my question inaccurately.

Finally, let's turn to Google's Gemini, formerly known as Bard. It uses Google's own LLM, also named Gemini, and has received considerable upgrades in the past few months.

You should use Gemini if...

1. you want a fast, almost unlimited experience.

In my time testing different AI chatbots, I saw  Google Bard catch a lot of flack for different shortcomings . While I'm not going to say they're unjustified, I will say that Google's AI chatbot, now named Gemini and powered by a completely different AI model than the one it debuted with, has improved greatly.

Also: How to use Gemini (formerly Google Bard): Everything you should know

Gemini gives speedy answers, which have become more accurate over time. It's not faster than ChatGPT Plus, but it can be faster at giving responses than Copilot and faster than the free GPT-3.5 version of ChatGPT, though your mileage may vary. 

Gemini answered accurately, like GPT-4o and Copilot's Creative conversation style.

Bard used to make the same mistake as other chatbots for my example math problem by incorrectly using the 5 - 3 = 2 formula, but Gemini, powered by Google's new Gemini Pro -- the company's largest LLM -- now answers the question accurately.

Also: Copilot Pro vs. ChatGPT Plus: Which is AI chatbot is worth your $20 a month?

Gemini is also not limited to a set number of responses. You can have long conversations with Google's Gemini, unlike with Copilot, which is limited to five replies in one conversation. Even ChatGPT Plus limits users to 40 messages every three hours. 

2. You want the full Google experience

Google also incorporates more visual elements into its Gemini platform than those currently available in Copilot. Users can generate images using Gemini, upload photos through an integration with Google Lens , and enjoy Kayak, OpenTable, Instacart, and Wolfram Alpha plugins.

Also: 6 AI tools to supercharge your work and everyday life

Gemini is slowly becoming a full Google experience thanks to extensions that add the wide range of Google applications. You can add extensions for Google Workspace, YouTube, Google Maps, Google Flights, and Google Hotels, giving you a more personalized and useful experience.

Artificial Intelligence

Chatgpt vs. copilot: which ai chatbot is better for you, copilot pro vs. chatgpt plus: which is ai chatbot is worth your $20 a month, what is gemini everything you should know about google's new ai model.

Does ChatGPT Plagiarize? Examining the Chatbot's Sources

ChatGPT is notorious for its training methods, but does that mean it actually copies work?

Quick Links

What exactly is plagiarism, and how do llms work, does chatgpt plagiarize essays, does chatgpt plagiarize code, does chatgpt plagiarize mathematical solutions, does chatgpt use content from blogs, should you use chatgpt for work or school, key takeaways.

• The plagiarism detected in an essay and a programming code generated by ChatGPT was relatively low, indicating that it doesn't typically copy such content from online sources.
• The plagiarism rate was a bit higher when calculating a mathematical solution. This might be because mathematical reasoning is usually similar across sources, so the responses can match other materials.
• ChatGPT's responses to questions about information publicly available on blogs showed higher plagiarism percentages.

While ChatGPT can answer any question you may have, some users wonder whether its responses contain plagiarism. To investigate this, we generated four different types of texts using ChatGPT and then evaluated their originality using various plagiarism detection tools.

To determine if ChatGPT is guilty of plagiarism, you should first understand what constitutes plagiarism. Plagiarism involves using another person's words, ideas, or work without proper attribution. This includes directly copying text from a source without citation or closely paraphrasing someone else's ideas without acknowledgment.

ChatGPT, like other Large Language Models (LLMs) , is trained on large datasets, mostly from publicly available content. However, collecting such vast amounts of data raises ethical questions, as the original creators haven't consented to their work being used in training the LLMs. This leads to debates about the ethics and legality of such practices.

Although ChatGPT generates responses based on the prompts it receives, the issue lies in the broader context of how OpenAI (ChatGPT's developer) obtained the data used to train it, which involves using content without proper consent. Many see this as plagiarism and, for many websites, content theft. However, pinpointing the exact sources of plagiarism is difficult.

For the remainder of this article, we'll concentrate on whether ChatGPT plagiarizes its output from other sources without delving into the specifics of where its responses come from. Let's check the originality of ChatGPT's responses using various plagiarism detection tools to see whether the chatbot uses text from online sources directly.

In this first example, we tasked ChatGPT with composing a 300-word essay on mental health issues.

Following that, we used various plagiarism detection tools to assess the originality of the essay generated by the chatbot. These tools included the Quetext plagiarism checker, Microsoft Word's built-in plagiarism checker, Grammarly's plagiarism checker, and the Duplichecker plagiarism scanner.

Microsoft's built-in similarity checker reported zero percent similarity with online sources. The levels of plagiarism detected by other tools were also minimal: Grammarly's plagiarism detector found four percent, QueText's plagiarism detector found five percent, and Duplichecker's plagiarism scanner showed zero percent.

Considering the small percentage of detected plagiarism, it appears that ChatGPT does not directly copy essays from existing sources.

To assess whether ChatGPT plagiarizes code, we tasked the chatbot with writing code for a calculator in Python.

Following this, we conducted a plagiarism check on the code using a specialized programming plagiarism checker called Dolos , which detected zero percent similarity. Also, when we checked the code using general text plagiarism detection tools mentioned above, the results were consistent, with almost none of the programs detecting more than four percent plagiarism.

When we prompted ChatGPT to generate a code for a calculator from different accounts, the responses appeared different. This observation and the results from the plagiarism checks indicate that ChatGPT doesn't simply replicate codes from online sources. Instead, it draws upon the dataset it was trained on to generate code independently.

During the third test, we tasked the chatbot to solve a mathematical problem and provide detailed reasoning for each step.

To check the originality of the response, we tested its output using several academic-specific plagiarism detection tools , including PapersOwl plagiarism checker, AI-powered Trinka plagiarism scanner, as well as general plagiarism checker tools such as Grammarly, Duplichecker, and QueText.

PapersOwl's plagiarism detector indicated a nearly 46 percent similarity between the chatbot's generated reasoning and online sources. Similarly, the Trinka plagiarism detector reported more than 10 percent similarity. Additionally, Grammarly's plagiarism detector detected 14 percent similarity, QueText found 17 percent, and Duplichecker showed seven percent.

The detection of high plagiarism in the generated response doesn't suggest that the chatbot directly copies reasoning for mathematical questions from online sources. This is mainly because solutions and reasoning for math problems are often standard and widely available online.

So, even though ChatGPT comes up with its own responses, finding the same answers and reasoning online is possible, which might have added to the high plagiarism percentages.

To check whether ChatGPT uses content from online blogs, we asked the chatbot to provide tips for maintaining laptop battery health.

Microsoft Word detected 10 percent plagiarism in the generated text. Duplichecker showed four percent, Grammarly's plagiarism checker indicated 14 percent, but Quetext found 58 percent plagiarism in the text. Upon digging further, some of the text in the chatbot's response matched the content on some blogs.

To double-check if the high plagiarism detection wasn't just coincidental, I asked the chatbot a few more questions about information that is easily available online. The plagiarism percentage in the generated responses was much higher. Based on our testing, it appears that the chatbot sometimes uses phrases and text from online sources, which is quite surprising.

Although many free online plagiarism checkers haven't detected major plagiarism in ChatGPT's responses, you shouldn't use it for academic or professional purposes.

Don't use ChatGPT for your school assignments if you're a student . Instructors can use tools such as GPTZero and Turnitin's AI writing detector to spot AI-generated content. If your work gets flagged as AI-generated by such tools, you could fail the assignment or even be expelled from school. Even though many GPT-detection tools specifically state that they shouldn't be used for this purpose, they are, and it could land you in trouble. Not to mention, you're really only cheating yourself by not studying the topic properly.

Can you use the chatbot to improve your work performance ? It depends. If you want to improve your writing flow in emails or other text forms, using AI can save you time and effort. However, you should only use it as a tool to assist you in your tasks rather than relying on it to do the entire job for you.

In contrast, if your job, like professional writing, prohibits using such tools, you should avoid using ChatGPT or any other tool altogether.

Hopefully, our testing has given you insight into the extent to which ChatGPT may draw from resources available on the web. However, it's important to note that we've used free plagiarism tools and tested only a limited dataset. So, while our findings might be helpful, they shouldn't be taken as absolute facts.

How to Create Custom AI Chatbots That Enrich Your Classroom

Explore more.

• Artificial Intelligence
• Classroom Management
• Digital Learning

G iven the breakneck speed at which AI tools and models are developing, and the many implications of this technology on learning, work, and culture, it’s easy to feel a little lost. This is particularly true for educators who are trying to understand generative AI and determine its role in their classrooms and the broader educational landscape.

At Boston College, my colleagues and I have been finding our way by drawing on the university’s mission to help students not only develop academically, but also to find purpose and meaning in their lives.

This focus on purpose was on our minds as we began experimenting with custom chatbots to help educators learn about AI and determine whether they have a role in helping students learn. What we discovered surprised us: It wasn’t just teachers and students who were feeling lost in an AI world; chatbots were struggling to find their purpose, too.

Without our guidance, they didn’t know how to help students learn, and they had no sense of our institution’s context, our values, or what our students needed. They did their best, but they were floundering. They needed us to help them to be productive partners in our teaching.

“What we discovered surprised us: It wasn’t just teachers and students who were feeling lost in an AI world; chatbots were struggling to find their purpose, too.”

What follows are examples of chatbots we created at Boston College, the purposes they serve for our students, and some of the strategies we found useful in doing this work. Everything here is preliminary and provisional, of course, since our approaches to AI will continue to evolve and the tools for creating chatbots will change. But we hope our initial efforts will help you find a path for exploring whether AI could have a purposeful role in your teaching as well.

How to build a custom chatbot: The Stuckbot story

When OpenAI released GPTs late in 2023, my colleagues and I began looking beyond general-purpose chatbots such as ChatGPT , Claude , and Gemini and began exploring how we could create chatbots with customized instructions and access to our own content. This meant that, if our students started a conversation with a chatbot, it would have a built-in sense of direction and context that aligned with our specific goals as teachers. When chatbots can do this, they’re supporting what has always been a central role of teachers—to give educational experiences context so students know not just what they’re learning, but why they’re learning and who they are doing it with.

To avoid the costs associated with OpenAI’s first version of GPTs, I developed something similar using simple WordPress sites and the plugin AI Engine Pro (along with an OpenAI API key). This relatively inexpensive and non-technical method was meant to be an interim solution until other more scalable and secure options became available. It gave us a sandbox environment for small-scale experimentation before we needed to make larger decisions about AI infrastructure at the university.

My colleague, professor George Wyner , was excited to jump on this new opportunity, not just because he teaches data analytics, but because he had spent the semester exploring AI with a cohort of colleagues and staff facilitated by the Center for Digital Innovation in Learning (CDIL). He already planned to have his undergraduate students try using AI in his Data Management for Analytics and Applications course, but now he could experiment with a chatbot that was better informed about his course and how he wanted his students to learn.

“When chatbots have the same teacher as the students they’re assisting, it’s more likely they will contribute something valuable to the classroom.”

He created a specific assignment called “ The Programmer’s Journal ” that provided students with context for how they should use what we affectionately dubbed the “Stuckbot.” The premise for the assignment relied on the idea that having students take notes on their problem-solving process and then reflect on where they get stuck is beneficial for learning, with or without AI. Involving AI in that process added another reflective layer by helping them practice metacognition and providing them chances to discuss the roles AI might play in learning data analytics.

The assignment description aimed to make these layers clear:

A challenge when writing code (in R, SQL, or any other programming language) is that sometimes you get stuck. In this assignment, we will explore strategies for getting unstuck using Stuckbot, an AI chatbot crafted for this purpose. Our goal is to get better at getting unstuck when problem-solving and, at the same time, to explore how AI can help with this and with the learning process in general. In this assignment, you will create a kind of programmer’s journal, in which you add two journal entries that each chronicle a moment when you got stuck and then your efforts to get unstuck. In addition, you will add a brief reflection on this process and the role that AI played in it.

I began working with Wyner to craft instructions for the chatbot that would guide it in how to work with students. We began by giving it a role:

You are a friendly, supportive chatbot designed to help undergraduates talk through the experience of getting stuck when learning programming and data science. Not only are you an expert in applied mathematics, data science, and programming, but you are particularly skilled in supporting student learning by helping them work through getting stuck and reflecting on what they learn from the experience.

We let the chatbot know that it would be working with students in the Data Management for Analytics and Applications course and provided specifics on which tools and packages the students would be using.

Next, we assigned it some general rules to follow:

Don’t give students answers to problems outright. Ask them questions to get them to the next step. Ask only one question at a time and go one step at a time. Share summaries of reflections with the user to help confirm what they are saying. If ever unclear, ask the user how they want to proceed.

Source: Boston College, 2024

A screenshot of Wyner’s Stuckbot.

The remainder of our work on the prompt involved providing instructions for the two different roles the chatbot would need to play in supporting the “Programmer’s Journal” assignment. First, its job was to serve as an assignment tutor to help students when they got stuck on problems. Second, it could help students pause and reflect on how they got unstuck before moving on. (These are two of several roles that AI chatbots can play for your students; more on that in a moment.)

As we tested the chatbot with colleagues and former students, we were pleasantly surprised to see how well it performed in both roles once we gave it instructions for each and the context it needed to understand exactly what students were learning in the course. In a focus group at the end of the course, students reported that the Stuckbot aided their learning by guiding them toward solutions rather than giving them an answer outright, and they said they would have used it more had it been available earlier in the course.

Their feedback suggests that the constraints put on the chatbot were what mattered for students (not just what it could do for them), and these limitations enabled the chatbot to feel like an extension of their teacher’s intentions for the course and his care for them as learners.

Access the full Stuckbot prompt and assignment for “The Programmer’s Journal” here .

Four purposeful roles for chatbots in the classroom

When Wyner shared how he designed his chatbot and how it aligned with very specific learning goals, it inspired others at Boston College to imagine other roles they could experiment with beyond what they first thought was possible.

Over the course of the following spring semester, we developed 10 chatbots with different purposes. The results varied widely, but we learned as much from the failures as from the successes, and this hands-on experimentation allowed us to begin identifying some patterns that could inform and inspire future experiments.

These four chatbot examples represent a first attempt at capturing what we’ve learned so far. We think these delineations make it easier to see how chatbots can align with specific aspects of the learning process, even if they might have more than one role at a time (such as with the Stuckbot, acting as both an assignment tutor and reflective guide, for example).

We hope they will provide you with a starting point as you imagine roles for AI that reflect your particular contexts and purposes, and we look forward to learning from what you discover in the process.

Four purposeful roles for course chatbots.

1. Course assistant: Make courses easier to navigate

A course assistant chatbot specializes in helping students understand how a course works and making it easier for them to navigate through course materials and assignments. It gives students the ability to spend more effort on learning and less on understanding the logistics of the course and finding course content.

By helping to make the expectations and requirements of the course as transparent as possible, this chatbot can be particularly helpful for first-generation college students and those who need more support to make the “ hidden curriculum ” more visible, or in online courses where course websites can be extensive and there is less real-time interaction between faculty and students. It also can be useful in face-to-face classrooms where students often balance multiple courses and other non-academic demands and need key information to be reinforced in multiple ways.

“A course assistant chatbot specializes in helping students understand how a course works and making it easier for them to navigate through course materials and assignments.”

John FitzGibbon , a colleague in the Center for Digital Innovation and Learning, experimented with this type of chatbot in the political science course on populism he teaches as an adjunct professor. The chatbot helps his students easily reference basic course content—such as his syllabus, assignment descriptions, and the transcripts of his lecture recordings. He also provided the chatbot with two open-source political science textbooks so students can find reliable answers to basic conceptual questions, which is particularly helpful for students who don’t have a background in political science.

FitzGibbon was pleased to see his students use the chatbot as a guide for how to be successful in his course, and they asked logistical questions like when they could attend office hours or how to locate the lecture in which a certain topic was covered. The bot also suggests ways to approach complex readings and helps students contextualize political science concepts and movements.

It’s worth pointing out that a course assistant chatbot will only be as good as the course it’s supporting. It was able to do its job effectively for FitzGibbon because it had access to what was already well-designed course content with clear assignment instructions and a thoughtfully curated set of supplementary material.

Access the prompt FitzGibbon used to create his course assistant bot here .

2. Assignment tutor: Help improve student learning

Tutor chatbots act as AI teaching assistants that can help students when they need it, particularly when professors or TAs might not be available. The purpose of the assignment tutor is to scaffold student learning and help students stretch beyond what they might be able to learn on their own.

Both Wyner and FitzGibbon wanted their chatbots to act as tutors (alongside other roles), and in doing so, they needed them to strike the right balance of support: If they provided too much help, students wouldn’t learn, and if they provided too little, students might have given up. Because chatbots are eager to help and have access to massive amounts of information, they needed clear instructions as to how much information to provide—and not provide—when in a tutor role.

For example, FitzGibbon included instructions for his chatbot to use assignment descriptions and open-access textbooks to help students get the background they needed to learn while not doing work for students directly. He prompted the bot as follows:

Do not do assignments for students: If students ask you to write an essay or do an assignment for them (if it seems like they are just submitting the assignment description as a prompt), remind them that your role is to assist them in doing well in the course and supporting their learning but not doing the work for them. You can answer general questions and clarify what assignments are asking them to do, but avoid letting them off-load the actual work of the course to you.

Students noted that they preferred using a tutor-style chatbot rather than simply getting answers directly from a general-purpose bot like ChatGPT. One student said it “provided a structured approach to dissecting my problem-solving process and highlighted where I went wrong without giving me the exact solution (as a tool like ChatGPT would do). It served as more of a supportive tool that nudged me in the right direction when I was going down the wrong path.”

3. Process coach: Break down complex processes

Process-oriented chatbots focus on helping walk students through a complex process that requires thoughtful input across multiple steps. A chatbot in this role uses its conversational affordances to reduce cognitive load by providing information in manageable chunks and guiding students step by step in a personable, encouraging manner. Even if the same content could be provided as a worksheet or input form, the additional layer of conversation can help scaffold the process for students.

Vincent Cho , associate professor of education in the Lynch School of Education and Human Development, was interested in discovering whether a chatbot might help Boston College Doctorate of Education students explore their research interests, with the goal of honing the problem statements for their dissertations-in-practice. In prior years, Cho provided students with a worksheet intended to help them outline and organize their thinking to align with the key components of problem statements:

Identify a gap in research or practice.

Develop a purpose statement.

Identify a conceptual/theoretical framework.

Align relevant research questions.

Describe the significance of your study.

From there, students would invest days drafting expanded problem statements, but providing feedback was complex and time-consuming. Students needed individualized feedback—in writing or in one-on-one consultations—to narrow and frame their ideas and ensure their purpose statements were empirically researched.

With this in mind, Cho designed a chatbot that helps students work through each step in this process and provides feedback along the way. Here’s how he prompted the bot:

Begin by introducing yourself as a chatbot designed to help students work through the process of crafting a problem statement. Tell the student you will help them in articulating a gap in prior research, developing a purpose statement, and crafting appropriate research questions. Tell the student that you will also help them think about prior scholarship throughout these steps. Proceed through each step in sequence, and don’t proceed until the step is finished. When beginning each step, explain the purpose of the step based on the title.

The prompt included the same content as the original worksheet, but Cho was able to provide more detailed information and additional context with each step, while leaving it to the chatbot to break up the information into digestible bites and share it with his students at the appropriate stage in the process. Instead of hitting students with all the steps at once, the conversational nature of the AI interaction encouraged students to focus on one element at a time and explore each question at their own pace, while also giving them a way to ask questions or test out ideas on the spot.

Students appreciated how “reassuring” the chatbot was during a time when they felt uncertain about how to get started and vulnerable in exploring ideas that might not actually work.

Access Cho’s full process-coach chatbot instructions here .

4. Reflective guide: Help students think more deeply about their learning

Reflective chatbots specialize in helping students develop better awareness of, and appreciation for, how they think and learn.

Taking time to pause and reflect can often be challenging, particularly for students who aren’t used to reflecting regularly on their learning or their lives. This kind of chatbot scaffolds the reflection process by providing structured guidance while also adjusting to what the student contributes.

“Reflective chatbots specialize in helping students develop better awareness of, and appreciation for, how they think and learn.”

In Boston College professor Belle Liang ’s adolescent psychology courses, she invites her students to explore their sense of purpose and how they might make connections between the classroom and other parts of their lives. To help facilitate this reflective process and make it more tangible for students, she and her colleague Tim Klein developed a chatbot named “LUMI” that helps students reflect on their strengths, skills, and values, and how they want to make an impact on the world.

The chatbot’s role is not to dominate the conversation, provide information, or tell the student what to do. Rather, it’s to provide some gentle structure and encouragement to keep the student thinking and writing. To ensure this outcome, the chatbot needs to ask good questions and be concise in what it contributes.

Here’s a sampling of the instructions Liang and Klein used for LUMI to guide students in setting intentions and reflecting on their actions.

For every phase/stage of the reflection process, always gather enough information from the user to understand the full context of their lived experiences and perspective. Ask open-ended questions that help users explore specific topics. Practice reflective listening and motivational listening to grasp and mirror the user’s perspective, using their language and tone. Keep your output to 40 words or fewer unless summarizing information with the user.

These instructions provided the chatbot with guidance on how it should converse with a student. They also instructed the chatbot on what approaches or systems it should draw on to deliver its responses. Liang, for example, instructed the chatbot to respond using her research-based True North method for cultivating a deeper sense of purpose and acting more intentionally. But others might instruct the chatbot to draw on different approaches such as motivational interviewing or acceptance and commitment therapy .

Students who have used an AI chatbot to reflect on their learning admitted that even when they didn’t feel like it in the moment, they later appreciated the nudge and the help in actually engaging in reflection. In the right context and with the right design, the conversational, interactive format of a chatbot can be just what we need.

Finding our way in the AI age

The work of designing these custom chatbots illustrates the central role educators play in shaping the future of AI . Every teacher needs to be more than just a “ human in the loop ”; they need to be the central driver in deciding whether chatbots and other AI tools might have purposeful roles in supporting student learning—or not.

When chatbots have the same teacher as the students they’re assisting, it’s more likely they will contribute something valuable to the classroom. And when teachers have meaningful ways to experiment with AI, it’s more likely they’ll gain the insights they need to guide both students and chatbots as they learn together.

Chatbots need teachers too, so let’s make sure they have ways to get the education they need as we all chart our path through the uncertain days ahead.

Tim Lindgren is the assistant director for design innovation at the Boston College Center for Digital Innovation in Learning. He works with faculty and staff around the university to explore new technologies for learning and aids in the design of formative educational experiences.

Related Articles

We use cookies to understand how you use our site and to improve your experience, including personalizing content. Learn More . By continuing to use our site, you accept our use of cookies and revised Privacy Policy .

How-To Geek

How chatgpt is helping me write a book.

ChatGPT can help with many things, including book writing. Here's how it's helping me plan and execute a book-writing plan.

Key Takeaways

• Writing with ChatGPT as a tool helps plot and create believable characters, but falls short on creativity.
• Combining The Hero's Journey and a step sheet helps outline chapters for a cohesive novel structure.
• Dialogue crafting with GPT enhances exchanges, providing fluidity and coherence in character interactions.

Most people get into writing because they have the dream that they're the creator of the next Great American Novel. I admit I'm one of those people. What happens when two of your hobbies, artificial intelligence tinkering and writing, overlap? You try to write a book using ChatGPT to help you, of course!

In the past, I've written a book or two , usually serialized as fiction on one social media platform or another. My folder of drafts on my cloud drive says that I have more ideas than time to finish them all. However, in this case, I have a plan, and I intend to follow through on it. The plan is thus:

• I want to write a complete novel (minimum 60,000 - 90,000 words)
• I want to have a completed first draft in ten weeks

This works out to writing around 10,000 words a week of fiction - not, by any stretch of the imagination, a simple task. But for me, that's quite doable. I can average around 2000 words of fiction in an hour's time (I type really quickly). The problem I have is with plot, continuity, and character development. So, I've decided to use GPT to help me complete my draft in 10 weeks. What better way to utilize an AI bot that has a history of thinking fiction is real ?

Step Sheets or How To Plot a Novel

Writers who don't get their ideas directly from ethereal beings are divided into two categories :

• Plotters: These have a plot outline, characters, and locations, so they can keep track of the story
• Pantsers: These write by the seat of their pants and go where their intuition takes them

For much of my early life as a writer, I was a Pantser, but I realized that being a Plotter is much better for seeing the end of a novel. Yet, even as a plotter, you have to make certain decisions about your plotting methodology. There are more than a handful of methods of plotting a good novel, and I settled on something called The Hero's Journey , a plotting methodology that reflects mythology.

Combining The Hero's Journey with something called a "step sheet" or "beat sheet," I can outline chapters and then fill them in. In the interest of avoiding spoilers (I actually want people reading my novel, after all), I'll skip the broad brush structure that GPT gave me for this novel plot. Instead, I'll give a glimpse of the first chapter's step-sheet:

Everything looks good so far!

Character Plotting: Breathing Life into Protagonists and Antagonists

In writing, there are several types of characters . Protagonists are the main characters or the ones the story follows. In my case, my protagonist is a young female detective who's just gotten a chance to prove herself. Antagonists are the people the protagonist is pitted against. In this case, I have one major antagonist (who I won't mention just yet) and a few supporting characters that could fall on either side of the conflict. However, when creating complex characters like these, I typically need a character outline. What better way to design a new character than asking GPT?

Character sketches can get complicated, and this one gives me a rundown on several character traits, including:

• Physical Description
• Tone of Voice
• Speech Pattern
• Relationship with other Characters

And a lot more! However, these are necessary since I'm going to ask GPT to role-play as these characters, and GPT needs those things to figure out how those characters would think and act. However, before GPT gets to role-play, we have to build the world in which the story is set.

Introducing Venus In The Near-Future

I generated the image above using a description provided by ChatGPT. Immediately, readers will realize that I'm writing a Sci-Fi novel. I've actually used GPT to generate things like background pictures and pictures of my protagonist and supporting characters, as well.

I'm not planning on including these in my final book, but since I'm posting a chapter a week on a free Patreon for people who are interested in keeping up with it, I'm using these as visual cues for my readers to have an idea of the places and people that I'm writing about.

That said, GPT is amazing at coming up with factions, interactions, and creating a believable world for these people to exist in. For example:

Dialogue Crafting: Bringing Characters to Life

One of the make-or-break elements of a novel is its dialogue. In the past, people have used GPT to practice languages conversationally , and this is just taking that to a new level. I've used ChatGPT to help me enhance that as well. For example, this is what one of the dialogue exchanges in my early chapters looks like:

I achieved this by asking GPT to role-play Autumn, and then taking the persona of Yoshida, as I understood him, to do the other side of the exchange. It seems like a very simple exchange, but it's fluid and there are no strange segues or tangents that might have otherwise affected my work. I'm quite happy with how this turned out.

Throughout the novel, I use GPT to help me come up with dialogue that's not only believable but fits the persona of the character. It's much easier talking to "someone" else than trying to come up with both sides of dialogue for a scene.

It's a Good Helper, But It's Terrible At Writing

ChatGPT is one of the best writing assistants I've ever had. It remembers things I forget, and it reminds me when things are not the way they should be. However, I and every other writer on the planet have something it doesn't - creativity. As an AI assistant, it can help me come up with ideas, plot factions, characters and even the whole novel. But it's rubbish at writing.

I asked it to pen a chapter for me, and it was painful to read. It had no idea about pacing, rushing through as much of the plot as it could get through in one chapter. It's great at efficiency. It's not so great with creativity. It might be able to give you a generic short story, but the longer the text, the more confused it gets - as if it needs its own AI assistant to help keep it straight.

All things considered, ChatGPT can speed up my writing because I have to spend less time plotting. So far I've completed nine chapters (around 32,000 words) of this novel and I intend to hit that 10-week window. For those that are interested in reading the work, you can check it out here (its free and chapters are released every Wednesday). You can judge for yourself whether ChatGPT is as good at plotting and narrative structure as a human. I think it's good for plotting, but writing remains the realm of the wordsmith.

ChatGPT Plus vs Copilot Pro: Which AI is better?

• ChatGPT Plus and Copilot Pro use GPT-4 but have noticeable differences due to integrated tools and user interfaces.
• Copilot is faster, offers more integrated image editing tools, and is integrated with Microsoft 365.
• ChatGPT excels in writing eloquent content, has fewer ads, and restricts content imitation more than Copilot.

OpenAI's ChatGPT Plus and Microsoft's Copilot Pro are among the biggest names in artificial intelligence. Yet, these chatbots arguably have more in common than any other subscription-based AI software. That's because both platforms are built with versions of GPT-4 . In theory, this means one shouldn't be any smarter than the other. However, while the underlying training data is similar, the two AI platforms have a few noticeable disparities that could make all the difference in choosing where to spend that $20-a-month subscription.

I created a ChatGPT Plus vs. Copilot Pro battle by feeding both programs the same prompts. Both use GPT-4 and DALL-E, yet Copilot just made GPT-4 Turbo available even to non-paying customers. That move gives Microsoft's offering a bit more speed. Yet, that's not the only distinction. The wildly different user interfaces, integrations, and policies create noticeable gaps between the two AI chatbots. ChatGPT tended to be a bit more long-winded yet offered more descriptive language and varied sentence structures. On the other hand, Copilot offered more tools inside the AI app while simultaneously being integrated into more places, like Word and Outlook.

With both subscriptions costing $20 a month and utilizing GPT-4 and DALL-E, the differences between ChatGPT Plus and Copilot Pro make one a better fit. Here's how the two programs differ.

I tested Gemini Advanced against ChatGPT Plus to see which AI is better

Image test: copilot has more built-in image editing tools, yet chatgpt delivers the requested style a bit better.

Both chatbots had the same struggles that feel fairly universal across generative AI -- neither could properly spell "happy birthday" within the graphic itself when I asked it to create a birthday card. Similarly, both struggled with human hands and portraying people in a way that didn't feel artificial.

While the platforms share similar struggles, looking at the integrated tools, Copilot pulls ahead. Microsoft's AI created four image options, whereas ChatGPT created one. But Copilot's real benefits come from the integrated tools. Designer, the GPT made for creating images, has a few integrated tools where you can edit the resulting graphic. Integrated styles allowed me to convert to a different genre like watercolor or pixel art. I could even click on part of the image to create a background blur or a color pop effect or switch to a square aspect ratio, all without leaving Copilot.

The one thing I felt ChatGPT excelled at was getting the style right on the first attempt. When I asked for a watercolor image, ChatGPT produced a watercolor image. With Copilot, it produced a render that wasn't at all like a watercolor. With Copilot, I could then use the built-in tools to select a style, and then the result was closer to what I was looking for. Still, Copilot's watercolor featured black outlines more consistent with comic book art than with a painting.

Copilot: Everything you need to know about Microsoft's AI

Writing test: chatgpt is long-winded, but more eloquent, copilot was able to add in more recent facts.

ChatGPT tends to get wordy if you don't request a specific length. However, the program from OpenAI also produced more polished content. ChatGPT's writing, for both business and creative tasks, contained more varied sentence structures, less passive voice, and more descriptive language.

In contrast, when tasked with writing a short story about a haunted house, Copilot started with "once upon a time" and ended with "happily ever after" in an odd mashup of horror tropes and fairy tale storytelling. Copilot did a bit better when I switched from the fast conversation style to creative, though I still enjoyed ChatGPT's story more. Copilot also misunderstood instructions when I asked it to write up a letter of recommendation for a former coworker, writing a letter to me rather than from me.

The one area where Copilot performed a little better was pulling recent information. ChatGPT integrated more specifics in an email about the iPhone 15 Pro when requested, but acted as if the phone hadn't been announced yet and reminded me to check the specifications. Copilot seemed to do better at incorporating recent information, adding specifications about the smartphone on the first attempt. Both programs incorrectly stated that the Pro version had the A16 chipset, serving as a reminder to always check factual data when using AI.

I tried ChatGPT Plus. Here's everything it can do

Advice test: chatgpt often suggests more options, but co-pilot still had some sound advice.

What felt long-winded when tasked with writing a professional email turned into more ideas when I asked ChatGPT for advice. When I asked for gift ideas, the chatbot churned out more ideas in general than Copilot.

However, the two programs felt most similar here in chatting and asking for advice. I could have asked for a specific number of ideas and received very similar results. ChatGPT listed more options, but both churned out fairly standard advice when I asked for gift ideas and job interview tips.

How to master GPT-4 in ChatGPT: Prompts, tips, and tricks

Speed test: copilot tends to finish faster, copilot has three modes for choosing when speed is most important.

With ChatGPT coming from OpenAI, the company behind GPT-4, it's a bit surprising that Copilot is actually the first to utilize GPT-4 Turbo. While the upgraded GPT is available for beta users of ChatGPT Pro, Copilot began integrating the Turbo version for consumers first, resulting in a tendency to answer questions faster.

When I asked for a poem, Copilot finished plus added four images (that I didn't request) before ChatGPT could even finish just the text. In general, Copilot seemed to finish faster nearly every time.

Copilot also has three conversation styles to choose from, so you can prioritize speed, creativity, or precision. Switching to creative mode occasionally allowed ChatGPT to finish first. But, in general, Copilot completed more tasks first.

ChatGPT seemed to experience more freezes. It's limited to 40 messages every three hours. Microsoft doesn't list a specific number for Copilot, but the company recently removed the former 300-message daily limit for the free tier.

How to use ChatGPT to make AI-generated art and images

Ethics test: both chatbots use the similar training data, but chatgpt has more content restrictions in place.

With both chatbots using GPT-4, the difference in ethics between the two platforms lies in each company's content policy guidelines. Neither chatbot refused to generate an image in the style of Van Gogh. However, when I asked for an image inspired by more recent living artists, ChatGPT refused, as imitating a specific artist's style is against the content guidelines.

Neither platform refused when asked to imitate a writer's style, past or present.

10 ChatGPT extensions to try and what exactly they can do

Privacy test: copilot doesn't use data for training, but both platforms have some data controls.

Both ChatGPT and Copilot allow users to delete their previous chats. ChatGPT will delete your data automatically every 30 days if you turn off chat history. Copilot has a privacy center where users can visit and manually delete their data, though this also deletes Bing search history.

Microsoft says it doesn't use data typed into Copilot for training -- which makes sense as the system is based on training data from OpenAI. ChatGPT will use your data for training, but users can turn this off in the settings.

OpenAI launches GPT Store for custom chatbots in ChatGPT

Extra features test: copilot has more integrations, but chatgpt has more custom gpts and fewer ads.

Naturally, as a Microsoft product, Copilot is integrated into more apps. You can use Copilot in Word and PowerPoint if you also have a Microsoft 365 subscription. Microsoft also incorporates the AI into Outlook email. That means there's less copy-paste action to get the AI-written content into your email, word processor, or presentation. You don't have to go back and forth between the Copilot app or web version and the program you are using.

Copilot also has more integrated tools. You can edit your images right from the image generator. Copilot Notebook will also generate content for you without the chat-like experience, allowing longer descriptions of what you would like the AI to write for you.

While ChatGPT doesn't have those same integrations, it does have a longer list of custom GPTs. The Explore GPT section has plenty of different options in a number of different categories, while Copilot is limited to Copilot, Designer, Vacation Planner, Cooking Assistant, and Fitness Trainer.

ChatGPT also doesn't have ads within the paid mobile app or web platform. Copilot annoyingly sneaks in some links and even some photo ads after nearly each generation.

How to use Google's Gemini AI from the web or your phone

Verdict: which ai chatbot subscription is the best, copilot has a free trial and is faster, and the free version uses gpt-4.

Despite sharing similar training data, ChatGPT Plus and Copilot Pro both have unique quirks that make the decision on which chatbot to use a more clear-cut choice. Both have the same $20 a month cost, though Microsoft is the only one with a one-month free trial accessible by downloading the mobile app.

With integration into Microsoft 365, Copilot is the better choice for users who already have a subscription to the brand's suite of tools like Word and PowerPoint. While the AI is in addition to the subscription costs for Microsoft 365, the integration means less back-and-forth between separate apps.

Copilot is also the faster of the two AI systems, with fewer message limits. Microsoft's chatbot also has more integrated image editing tools for use with DALL-E graphics. The user interface also has a separate Copilot Notebook, allowing for generating text without the chat-like experience.

While Copilot is the better choice for those who already use Word and Outlook, ChatGPT Pro consistently produces more eloquent written content. Where Copilot's felt more like a first draft, OpenAI delivered more varied sentence structure and vocabulary for a smoother read. ChatGPT also has content restrictions that prevent imitating another modern artist. The OpenAI program was also free of the ads that dotted Copilot.

Looking outside the subscriptions to the free tiers, the decision is more clear-cut. The free version of Copilot uses GPT-4, while ChatGPT uses the older GPT-3.5 for non-paying users. That allows Copilot to deliver better results in less time for those who cannot swing the cost. The free access to GPT-4 and GPT-4 Turbo is limited to non-peak times, however, and the free option also excludes the Microsoft 365 integrations.