chat ai write me an essay

'ZDNET Recommends': What exactly does it mean?

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

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

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

5 ways ChatGPT can help you write an essay

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

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

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

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

Below, we show you how to use ChatGPT for both writing and assisting and include some other helpful writing tips. 

How ChatGPT can help you write an essay

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

It is also worth noting before you get started that other AI chatbots can output the same results as ChatGPT or are even better, depending on your needs. For example,  Copilot , Perplexity , and Gemini also have access to the internet and include footnotes linking back to the original source for all of their responses, making the chatbots solid alternatives if you rather skip out on ChatGPT. 

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

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

1. Use ChatGPT to generate essay ideas

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

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

Also: How do AI checkers actually work?

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

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

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

2. Use the chatbot to create an outline

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

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

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

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

Also: How my 4 favorite AI tools help me get more done at work

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

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

If you want ChatGPT to include links and sources throughout, you can ask it to and it will regenerate the answer using its web-browsing feature , further expediting your essay-writing process. 

3. Use ChatGPT to find sources

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

All you need to do is ask the AI to find sources for your essay topic. The biggest thing to remember is to include the type of source you want, whether it be web pages, books, PDFs, research, papers, etc. 

Also:   How to make ChatGPT provide sources and citations

The specifics are necessary because when you specify web pages, ChatGPT will activate the web browsing feature and include web links in its article. If you use a very general prompt, however, it will likely default to generating its answer from its database, which isn't up to date. 

For example, I asked the following: 

"Examining the Leadership Style of Abraham Lincoln through Blake and Mouton's Managerial Leadership Grid."

The chatbot outputs links, accessible right at the top of the answer under the drop-down that says "Searched # of sites." Then, within the response, it will answer your prompt conversationally, also including sources with site names and links in parathesis. 

4. Use ChatGPT to write an essay

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

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

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

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

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

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

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

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

5. Use ChatGPT to co-edit your essay

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

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

Also:  How to use ChatGPT to make charts and tables

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

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

Ready to go 'leaf peeping' this fall? ChatGPT can help

How apple, google, and microsoft can save us from ai deepfakes, adobe offers students an ai study buddy for just $2 a month - but at what cost.

• 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 Happiness Hub 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
• Happiness Hub
• 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: June 2, 2024 Fact Checked

Getting ChatGPT to Write the Essay

Using ai to help you write, expert interview.

This article was co-authored 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 52,526 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. 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. [3] 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://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

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.

• Resources Home 🏠
• Try SciSpace Copilot
• Search research papers
• Add Copilot Extension
• Try AI Detector
• Try Paraphraser
• Try Citation Generator
• April Papers
• June Papers
• July Papers

AI for Essay Writing — Exploring Top 10 Essay Writers

Table of Contents

Let’s admit it — essay writing is quite a challenging task for students. Especially with the stringent deadlines, conducting research, writing , editing, and addressing to-and-fro reviews — consumes a whole lot of time and often becomes stressful. Therefore, students are always on the lookout for tools that speed up the essay writing process.

And that’s when AI writing tools make their debut! Using the best AI for essay writing makes the lives of students much easier by automatically generating the essay for them.

The rise in the popularity of artificial intelligence technology and deep learning has paved the way for the numerous AI writer tools available today. To help you understand the different types of AI tools and their benefits, we’ve uncovered the features of the top 10 AI essay generators in this article.

Let’s explore the tools and learn how they are transforming the tedious task of essay writing!

What is essay writing?

Essay writing is a part of academic writing that emphasizes formulating an idea or argument. The main objective of academic essay writing is to present a well-reasoned argument or idea. Evidence, analysis, and interpretation are the three major components of essay writing . It should have a logical structure to support the argument or idea of the essay so that it communicates clearly and concisely.

What is an AI essay writer?

AI essay writers is a tool that is designed to help students generate essays using machine learning techniques. They can be used to generate a full essay or generate a few parts of the essay, for example, essay titles, introduction, conclusion, etc.

Why should researchers use AI essay generators?

There are infinite benefits to using AI tools for writing unique essays, especially for researchers or students. Here are a few of them —

1. Saves time

Using best AI for essay writing has its own benefits. Students can take care of the research process while these AI tools write the essays for them. Be it an essay topic or a full-length essay generation, it saves a bunch of students' time.

2. Boosts productivity

Writing is a tedious task especially when you want to write an essay about a novel topic, that writer’s block starts haunting and your productivity gets affected. But, with AI, it’s the other way around and increases productivity by quickly generating the essays for you.

3. Enhances writing skills — Vocabulary and Style

Adopting the best AI essay writing AI tool not only help with creating essays but also help us hone our writing skills by giving proper suggestions about grammar, sentence structure, tone, style, and word choice.

4. Reduces stress

Students often undergo a lot of pressure and stress because of deadlines and submissions. With the best AI essay generator, they help you write essays smarter thereby reducing stress and fear in no time.

5. Facilitates multidisciplinary research

AI essay writing tools foster interdisciplinary study through their ability to scan and combine knowledge from multiple domains. That way, it helps us quickly get a grasp of new subjects or topics without a heavy-lifting process.

6. Cost-effective

Most of the AI essay writing tools have lower pricing and also allow certain discounts for students. So, it is also a cost-effective approach to use AI writing tools.

The Top AI Essay Writing Tools and Their Features

Several AI essay writers are available based on the types of essays one would want to generate. Now, let's quickly understand the top 10 AI writing tools that generate essays within just a few minutes.

1. PerfectEssayWriter.ai

It is one of the best AI for essay writing that not only creates an essay but also comes up with advanced features including plagiarism detection, auto-referencing, and contextual analysis. As a result, it generates coherent essays that are well-researched and properly cited. It is best recommended for creating academic essays and essay outlines.

How does PerfectEssayWriter work?

• Pick the right tool for your purpose — Go with an essay writer if you want to generate a full essay or choose the essay outliner if you want to create just the outline of the essay.
• Enter your specific conditions and preferences. Add essay topic, academic level, essay type, number of pages, and special instructions, if any.
• Click on “generate” and wait for the result
• Once you have the essay generated, you can review, edit, or refine it and then download it.
• Generates a large chunk of data up to 2000 words
• Output is provided within 90 seconds
• Provides a plethora of other tools like Citation generator, grammar checker, thesis statement generator, and more
• Comes with 10+ essay writing templates
• Subscription-based and not a free tool
• Human review is a mandate

2. Essaybot - Personalized AI writing

Essaybot is the product of a reputed online essay-writing service, MyPerfectWords. It is meant to enhance academic essay writing and streamline the tasks of students. Its user friendly website makes it an instant and hassle-free essay generation saving a lot of time and effort for students.

How does Essaybot work?

• Enter the essay title or topic
• Click on “start writing” and wait for it to generate a well-reasoned essay.
• The tools come for free
• No sign-up is required
• 100% unique and High-quality output
• Very limited features that lack advanced functionalities

3. FreeEssayWriter.net

FreeEssayWriter is an organization that provides essay-writing services to students worldwide. It has an AI essay typer tool — that helps you generate essays instantly. What sets this essay typer apart is its initiative to help students with their free essay writer providing the students with a 2-page free essay.

How does FreeEssayWriter.net work?

It works similarly to Essaybot, input the title or the topic of your essay and wait for it to generate the essay. They also have an option to edit and download a free version of the generated essay instantly.

• Provides high-quality essays and is considered to be one of the reliable and trusted sources of information
• Students can improve their writing skills and learn more about essays by referring to their free essay database or sources
• Priority customer support is available 24*7
• The site is not optimized for mobile devices
• The quality of the essay output could still be improved

4. MyEssayWriter

This AI essay writing tool is no exception in terms of generating a high-quality essay. You can generate essays for various topics depending on the background of your research study. Be it academic or non-academic essay writing, this tool comes in handy.

How does MyEssay Writer work?

Add your preferences and then click on generate. It will give you a high-quality and 100% unique essay crafted based on your requirements.

• The tool comes for free — no subscription is required
• Knows for its consistency in the quality and the tone of the essay output
• Also has a paid custom writing service that provides human-written essays
• Might not provide quality output for complex and technical-based keywords or topic

5. College Essay AI

College essay AI stands unique as an ai writing tool as it not only uses an AI-based algorithm to generate essays but it also backs up the output as it is reviewed and approved by a team of professional experts. It is the best AI essay writing tool for college and graduate students where the output adheres to the graduate students' essay writing guidelines.

How does the College Essay AI generator work?

• Input the required information — essay topic, academic level, number of pages, sources, and specific instructions, if any.
• Click on “generate essay” and wait for the output
• Conduct plagiarism and grammar check
• Download the essay
• High-level output for academic essay writing
• Pocket-friendly premium plans
• Doesn’t provide multiple sets of templates
• Not quite suitable for non-academic essay writing

6. Jasper AI

Jasper AI has been the oldest player in the game of AI content writing. Fast forward to now, its features have been magnified with the inception of natural language processing algorithms and that’s how they are helping students write their essays as well. However, Jasper is the best AI tool for non-academic writing projects like content writing or creative writing.

How does Jasper AI work?

• Choose a template — if you are about to write an essay, go with the “document”
• Add your preferences
• Click “compose” and get the output
• Generates the essays instantly
• Provides well-structured output according to the tone and style of your preferences
• Not quite suitable for academic writing essays

7. Textero AI

Textero AI provides a few writing tools for students that facilitate their various academic papers and writing projects. Its essay generator helps you generate ideas for a full-length essay based on the topic and also suggests new topic ideas or thesis statement ideas for your academic assignments.

How does Textero AI work?

• Click on “Essay Generator” located on the LHS (Left-hand Side)
• Input the title and description based on which you want to generate the essay
• Pick the right citation style
• Click “generate” and wait for the output
• It also provides other tools like an outline generator, and summary generator and has an AI research assistant that answers all your questions relevant to the research
• The output is 100% unique and plagiarism and error-free
• Might fail to provide an essay focussed on complex or technical topics

8. Quillbot

Though Quillbot is essentially built for paraphrasing and summarizing tasks. It comes as a rescue when you have to revamp, improvise, or refine your already-composed essay. Its co-writer helps you transform your thoughts and ideas and make them more coherent by rephrasing them. You can easily customize your text based on the customization options available.

How does Quillbot Paraphraser work?

• Import or copy the content
• Click on “Paraphrase” “Summarize” or “Suggest text” based on your requirement
• Make the required customizations and save the document.
• Offers a plethora of tools required for students
• Both free and premium plans are available
• Enhances vocabulary and language skills
• Limited customization options with the free plan
• Only supports the English language

9. SciSpace Paraphraser

SciSpace is the best AI tool that helps you fine-tune your essay. If you feel your essay writing needs AI suggestions to improve the language, vocabulary, writing styles, and tone of your essay, SciSpace is at your rescue. It has more customized options than Quillbot and improves your essay by rephrasing it according to the required or preferred writing style, and tone. This is a very good alternative to Quillbot.

How does SciSpace Paraphrasing work?

• Simply paste the content to the screen
• Choose the length and variation properly
• Select the language
• Click “Paraphrase”
• Has 22 custom tones and all of them are available even on the free plan
• Supports 75+ languages
• Comes with an AI-detection report for English paraphrase output
• Delay in the output

10. ChatGPT

It would be unfair if we talk about AI tools and do not enlist ChatGPT. When it comes to automated essay writing tasks, ChatGPT is not trivial. With proper prompts, you can automate the essay writing process and generate a well-crafted and coherent essay. However, the quality and the accuracy cannot be trusted as the model hallucinates and doesn’t include sources.

How does ChatGPT work?

• Create a prompt based on your requirement
• Ask ChatGPT to write an essay about your topic, specify conditions and preferences
• Click enter and wait for the essay
• Comes for free
• Cannot rely on the output as the model hallucinates
• Lacks the upgraded features that other essay-writing tools have

Concluding!

Writing essays can be a real struggle. But, the inception of the best AI essay-generation tools makes the entire writing process a lot easier and smoother. However, you should be extra vigilant while relying on these tools and consciously use them only as a technological aid. Because over-reliance on these AI tools could diminish student's writing skills and the user can become more gripped by the tools. So, use it wisely without affecting your knowledge and skills.

You can explore the above tools whenever you need any help with essay writing, and reap the benefits of them without compromising on the quality of your writing.

And! If you're stuck exploring multiple research papers or want to conduct a comprehensive literature review , you know which tool to use? Yes, it's SciSpace Literature Review, our AI-powered workspace, which is meant to make your research workflow easier. Plus, it also comes with SciSpace Copilot , our AI research assistant that answers any question that you may have about the research paper.

If you haven't used it yet, you can use it here !

Choosing the best AI for writing long-form essays depends on your requirements. Here are the top 5 tools that help you create long-form and college essays —

1. Free Essay Writer AI

2. College Essay AI

3. My Essay Writer

4. Textero AI

5. Perfect Essay Writer

The Perfect Essay Writer AI and Textero AI are the two best AI essay generators that help you write the best essays.

ChatGPT is not specifically built to assist you with essay writing, however, you can use the tool to create college essays and long-form essays. It’s important to review, fact-check the essay, and refer to the sources properly.

Essaybot is a free AI essay generator tool that helps you create a well-reasoned essay with just a click.

Unless your university permits it, using AI essay generators or writing tools to write your essay can be considered as plagiarism.

You might also like

5 Tools zur Literaturrecherche für die optimale Recherche (+2 Bonustools)

5 outils de revue de littérature pour réussir vos recherches (+2 outils bonus)

人工智能在系统文献综述中的作用

• 🔓 Unlock this to increase your essay length Go Pro
• 🔓 Unlock this to write your essay with Super AI Go Pro
• 🔓 Unlock this to Humanize essay from AI Go Pro

0 Characters

0 Sentences

The generated essay falls into the following category:

Editpad AI Essay Writer only generates essays to help you educate the way of writing. We strictly do not allow users to generate sexual, self-harm, violence, and other NSFW (not safe for work) content.

Are you sure you want to continue?

terms & conditions

AI Essay Writer

AI Essay Writer by Editpad is a free essay generator that helps you write narrative, persuasive, argumentative and descriptive essays online in seconds.

How to use AI Essay Writer by Editpad?

To use Editpad's AI Essay Writer, you need to follow these simple steps below:

• Type or paste your essay topic or requirements in the input box provided.
• Select the required essay length and writing tone.
• You can also select the " Add References " option if required.
• Click on " Write My Essay " button.
• After that, our essay generator will automatically generate your essay and provide results in the output box.

Other Tools

• Plagiarism Checker
• Paraphrasing Tool
• Reverse Text - Backwards Text Generator
• Small Text Generator - Small Caps / Tiny Text
• Upside Down Text Generator
• Words to Pages
• Case Converter
• Online rich-text editor
• Grammar Checker
• Article Rewriter
• Invisible Character
• Readability Checker
• Diff Checker
• Text Similarity Checker
• Extract Text From Image
• Text Summarizer
• Emoji Translator
• Weird Text Generator
• Stylish Text Generator
• Glitch Text Generator
• Cursive Font Generator
• Gothic Text Generator
• Discord Font Generator
• Aesthetic Text Generator
• Cool Text Generator
• Wingdings Translator
• Old English Translator
• Online HTML Editor
• Cursed Text Generator
• Bubble Text Generator
• Strikethrough Text Generator
• Zalgo Text Generator
• Big Text Generator - Generate Large Text
• Old Norse Translator
• Fancy Font Generator
• Cool Font Generator
• Fortnite Font Generator
• Fancy Text Generator
• Word Counter
• Character Counter
• Punctuation checker
• Text Repeater
• Vaporwave Text Generator
• Citation Generator
• Title Generator
• Text To Handwriting
• Alphabetizer
• Conclusion Generator
• Abstract Generator
• List Randomizer
• Sentence Counter
• Speech to text
• Check Mark Symbol
• Bionic Reading Tool
• Fake Address Generator
• JPG To Word
• Random Choice Generator
• Thesis Statement Generator
• AI Content Detector
• Podcast Script Generator
• Poem Generator
• Story Generator
• Slogan Generator
• Business Idea Generator
• Cover Letter Generator
• Blurb Generator
• Blog Outline Generator
• Blog Idea Generator
• Essay Writer
• AI Email Writer
• Binary Translator
• Paragraph Generator
• Book Title generator
• Research Title Generator
• Business Name Generator
• AI Answer Generator
• FAQ Generator
• Active Passive Voice Converter
• Sentence Expander
• White Space Remover
• Remove Line Breaks
• Product Description Generator
• Meta Description Generator
• Acronym Generator
• AI Sentence Generator
• Review Generator
• Humanize AI Text
• AI Translator
• Excel Formula Generator
• AI Prompt Generator
• Sentence Rewriter
• QR Code Generator
• QR Code Scanner
• Paragraph Rewriter

Supported Languages

EN ES BR DE

Terms and Conditions

Introduction

Welcome to our AI Writing Generator. By using our AI writing assistants such as AI Essay Writer, AI Story Generator, AI Poem Generator, AI Paragraph Generator, AI Sentence Generator or AI Email Writer, etc., you agree to comply with and be bound by the following terms and conditions. If you do not agree to these terms, please do not use our service.

Prohibited Content

Our AI Writing Generator does not allow users to generate content that contain Sexual, Self-Harm, Violence, and other NSFW (Not Safe For Work) content. We are committed to maintaining a safe and respectful environment for all users and will take necessary steps to prevent the generation of such content.

Efforts to Control Prohibited Content

We are continuously working to improve our AI Writing Generator to ensure that it does not generate prohibited content. Despite our efforts, there may be instances where such content is generated due to the nature of AI and its learning processes.

Use of Third-Party APIs

Our AI Writing Generator utilizes third-party APIs, including but not limited to OpenAI ChatGPT , Gemini , and Claude , to generate AI content. As a result, the content generated by the tool is not entirely within our control. We rely on these third-party services to provide the best possible experience, but we cannot guarantee that prohibited content will never be generated.

User Responsibilities

As a user of our AI Writing Generator, you are responsible for ensuring that the content you generate complies with these terms and conditions. You agree not to use the tool to generate any content that is Sexual, Self-Harm, Violent, or otherwise NSFW.

Disclaimer of Warranties

Our AI Writing Generator is provided on an "as is" and "as available" basis. We make no warranties, express or implied, regarding the performance or reliability of the tool. We do not guarantee that the tool will meet your requirements or that it will be uninterrupted or error-free.

Limitation of Liability

To the fullest extent permitted by law, we disclaim all liability for any damages arising out of or in connection with your use of our AI Writing Generator. This includes, but is not limited to, any direct, indirect, incidental, consequential, or punitive damages, regardless of the basis of the claim.

Changes to Terms and Conditions

We reserve the right to modify these terms and conditions at any time. Any changes will be effective immediately upon posting on our website. Your continued use of the AI Writing Generator following the posting of changes constitutes your acceptance of those changes.

If you have any questions about these terms and conditions, please contact us at [email protected] .

Converted to HTML with WordToHTML.net

100k AI Words

$159 $127.20

2 Million AI Words

Get exclusive Pro Benefits and time-saving tools by becoming a Pro Member.

Already have an account? Sign in

New User? Sign up

• Refund Policy

Adblock Detected!

Editpad offers free tools by showing ads to visitors. Support us by disabling your ad blocker and refreshing the page or you can purchase our Premium Plan to enjoy an ad-free experience.

What do you think about this tool?

Your submission has been received. We will be in touch and contact you soon!

Get answers. Find inspiration. Be more productive.

Free to use. Easy to try. Just ask and ChatGPT can help with writing, learning, brainstorming, and more.

Writes, brainstorms, edits, and explores ideas with you

Summarize meetings. Find new insights. Increase productivity.

Generate and debug code. Automate repetitive tasks. Learn new APIs.

Learn something new. Dive into a hobby. Answer complex questions.

Explore more features in ChatGPT

Type, talk, and use it your way.

With ChatGPT, you can type or start a real-time voice conversation by tapping the soundwave icon in the mobile app.

Browse the web

ChatGPT can answer your questions using its vast knowledge and with information from the web.

Analyze data and create charts

Upload a file and ask ChatGPT to help analyze data, summarize information or create a chart. 

Talk about an image

Take or upload an image and ask ChatGPT about it.

Customize ChatGPT for work, daily tasks or inspiration with GPTs

​​ Explore the GPT store and see what others have made. ChatGPT Plus users can also create their own custom GPTs. 

Create images

A sk ChatGPT to create images using a simple sentence or detailed paragraph.

Apple & ChatGPT

At WWDC in June 2024, we announced a partnership with Apple to integrate ChatGPT into experiences within iOS, iPadOS, and macOS.

Get started with ChatGPT today

Assistance with writing, problem solving and more

Access to GPT-4o mini

Limited access to GPT-4o

Limited access to advanced data analysis, file uploads, vision, web browsing, and image generation

Use custom GPTs

Early access to new features

Access to GPT-4, GPT-4o, GPT-4o mini

Up to 5x more messages for GPT-4o

Access to advanced data analysis, file uploads, vision, and web browsing

Access to Advanced Voice Mode

DALL·E image generation

Create and use custom GPTs

• $20 / month

Join hundreds of millions of users and try ChatGPT today.

Here’s how to use ChatGPT to write an essay

Reviewed By: Steve Hook

Table of Contents

What is the easiest way to write an essay using chatgpt, using chatgpt to outline your essay’s framework, what’s the best ai to write an essay, can you use chatgpt to write essays, how to use ai to write an essay, how to use chatgpt to write an essay, launch chatgpt, customize your custom instructions, give chatgpt a prompt, limitations when using chatgpt to write an essay, what is the bot that writes essays, is there an ai that can write essays, final thoughts.

ChatGPT is a great tool for helping write an essay – whether that’s framing an essay, outlining key points, or giving insight on a subject matter you aren’t super confident with. Here are our quickest tips on how to use it in a meaningful, moral way for your next assignment.

Whether you need an essay writer or a speed boost for that last-minute assignment, you may be wondering how to use ChatGPT to write an essay. Since its public release in November 2022, OpenAI’s AI Chatbot has seen several updates to the quality of natural language processing (NLP) that guides it toward a high-quality, human writing style suitable for essays.

The AI bot, created by OpenAI, has been making headlines for its ability to communicate in a way that mimics human dialogue. But that’s not all! In fact, the AI model can also do some pretty wicked stuff such as essay writing, language translations, and quite recently passing university-level exams . However, it is also worth noting that colleges and universities can detect ChatGPT , and services like Turnitin will flag ChatGPT-generated content.

So while you can use ChatGPT to write an essay, we’d advise only doing so as a starting point for your own work – AI inspiration if you will. It’s fair and undetectable to use artificial intelligence for guidance, to help move past writing blocks and create your own essays.

To exemplify this, the following are excerpts from an essay that ChatGPT wrote based on the prompt “Write an essay about natural language processing”. NLP is the technology that allows the AI Chatbot to write in such a way, based on such a command.

“The genesis of NLP traces back to the 1950s, with the advent of machine translation. The Georgetown experiment in 1954 was a seminal moment, showcasing the potential of machines in translating languages. However, early optimism was curtailed by the enormity of linguistic nuances. The 1966 ALPAC report marked a period of reduced funding and interest in NLP, citing the high error rates and the lack of understanding of contextual meanings.” An excerpt from the essay generated by ChatGPT

Sometimes, framing your article so that it reads well and flows into each next segment can be a tricky thing to produce. Thankfully, ChatGPT is a great tool when it comes to outlining essays and can be used for all types of article frameworks.

To do this, simply take the subject that you’re writing your essay on and ask ChatGPT to create an outline for it. In just a few seconds, the chatbot will create a thorough, well-rounded page outline that segments some of the subject’s main focus points.

Remember, if you aren’t happy with the outline ChatGPT has provided, simply ask it to redo it (maybe adding some prompts on how to tweak the existing outline).

At this stage, you can also ask ChatGPT to add source links or relevant quotes that may help you inform your essay.

The use of ChatGPT is frowned upon by academia, and likely won’t reflect your writing style anyway. As a result, you’ll still need to rewrite it. The best AI chatbots can take an example of your writing, and use it to customize the tone of the generated text with greater understanding. Older models like GPT-2 were not reliable in this respect, although current models like GPT-3 (especially GPT-3.5 with fine-tuning ) are both serviceable and free to use for essay writing.

The most advanced models, such as GPT-4 accessible via the ChatGPT Plus or ChatGPT Enterprise plan from OpenAI, are the best options for writing your essays. While GPT-4 is not open-source , it is better than essentially all of the immediate competition.

This is true even of Microsoft’s Copilot (formerly Bing Chat), with which ChatGPT shares an LLM — namely GPT-4; Despite the shared language model, ChatGPT offers superior functionality, especially considering the “ All Tools ” update which enables Browse with Bing, Advanced Data Analysis, Plugins, and DALL·E 3 at the same time.

Many users have been putting ChatGPT to the test, by asking the large language model to write essays. Surprisingly, these essays came out well-written and completely coherent, although they lacked the originality you get from human writers. A Twitter user even asked it to write their (slightly tongue-in-cheek) Havard application essay.

Without a doubt, ChatGPT essay writing is starting to be all the more common, but as above we would advise caution when using it. It also has various limitations which we outline below. So, thanks to the increase in ChatGPT detectors, and teachers and professors starting to ‘get wise’ to essays written by artificial intelligence, there is a real risk you could get caught if you, say, actually submit a college essay written by ChatGPT. Our recommendation is don’t; use the powerful tool as a guide for your own writing process and work.

Chat GPT is not the only AI that can write essays. Google Bard and Microsoft Copilot (formerly Bing Chat) can also write a high-quality essay. This tech, when paired with an AI checker like GPTZero allows students to circumvent AI detection tools used by their professors. Typically, these major language models will have no issues with grammar . However, a grammar checker like Grammarly would not go amiss.

The process of using these AI-text generation tools is pretty much identical, no matter which you choose. So, let’s take a look at that process!

To start things off, head to the ChatGPT website and sign in with your login details. Alternatively, you can access ChatGPT via the mobile app for Android or iOS.

At this point, it is pretty common to be faced with a capacity error from OpenAI. In most cases, if you wait a couple of minutes you will be let in. If this is not the case, you can read our article here which shows you how to fix it.

Custom instructions are a new feature that improves the user experience by giving you greater control over ChatGPT responses. Instead of controlling how the AI chatbot responds by including instructions within the prompt itself, custom instructions stay how you set them for each new chat interaction unless changed.

To use them via web browser, click on the ‘Settings’ option to open up ChatGPT settings. You will see an option called ‘Custom instructions’.

If you’re using the iOS or Android app, you can turn on custom instructions by going to ‘Settings’, clicking on ‘New features’, and turning on ‘Custom instructions’.

ChatGPT custom instructions are now available for all users (Except EU & UK which is coming soon). Announced via OpenAI blog post on August 9th, 2023, the release notes show that neither ChatGPT Plus nor ChatGPT Enterprise are required to access the feature.

Now that you are logged in, you should be presented with the ChatGPT opening page and search bar. To get ChatGPT to generate an essay you will need to type a prompt into the search bar and click the send button.

Note, that the more detail you give ChatGPT the more specific your essay will be. For example, you can tell ChatGPT the length of the essay, to include references and the number of paragraphs.

Here are a couple examples:

• Write a 400-word essay about the impact of climate change including references
• Write a 4-paragraph essay about the causes of World War One

After ChatGPT has generated your essay you can ask the model to edit its response by typing and submitting “make it longer” or “write it again”.

To ensure your essay is the best it could be, we recommend making some edits. You can copy and paste ChatGPT’s response into a word processor such as Word or Google Docs to make some changes.

Ideally, rewriting the essay in your own words would be best, although tweaking ChatGPT’s response also works. At this stage, it is definitely important to proofread the essay and double check any facts with other sources to mitigate against ChatGPT’s accuracy limitation.

It may also be useful to run the essay through a plagiarism checker, such as Turnitin, to ensure your essay is safe from plagiarism .

In odd cases that require a specific voice, or character, you could try a ChatGPT alternative like Beta Character AI . It’s helpful to have more than one option to choose from when ChatGPT is down, or you can’t connect to Character.ai. Here’s how to make your own AI chatbot Character, and why you might prefer it compared to ChatGPT .

Essential AI Tools

Content Guardian – AI Content Checker – One-click, Eight Checks

• FREE 7 DAY TRIAL

Originality AI detector

• Find out more

There are a few things you should be wary of when using ChatGPT to write an essay. The first issue surrounds ChatGPT’s accuracy. OpenAI warns its users that the model may produce some inaccuracies that could have an obvious negative impact on their essays. The company also states that the application has the potential to produce biased responses too. This is definitely something you should be aware of, as there is a possibility that your essay could be incorrect and will need revising.

These issues are not unique to ChatGPT and can be observed in other popular LLMs (Large Language Models) like Google Bard and Microsoft Copilot (formerly Bing Chat). Ultimately, it’s functionally impossible to remove bias from an LLM at the source because the training data was produced by humans who themselves are inherently biased. Instead, the company running the LLM and its public-facing interface (ChatGPT) can add censorship filters at the end of the generation process – an imperfect solution, but more practical (and philosophically possible) than the alternative.

Another major concern is plagiarism. Plagiarism is definitely something to be concerned about when using AI to write your assignments. According to OpenAI, ChatGPT does not necessarily copy specific pieces of text that can be found somewhere else. But, it does have the capability to word its response in a way that is closely similar. The best way to check this is by putting the essay through a high-quality plagiarism checker, such as Turnitin.

OpenAI’s ChatGPT isn’t the only AI software that could help you write an essay. Here are some other AI essay writers you could try out:

• Microsoft Copilot (formerly Bing Chat) – Since the free version of ChatGPT isn’t connected to the internet, you may want a tool that can provide an up-to-date outline based on relevant and recent data. Copilot can be that tool, as it is powered by ChatGPT but is also web-connected. It also uses GPT-4, OpenAI’s current most advanced machine learning model, for free – a privilege you must pay for when using ChatGPT.
• Jasper AI – Can produce long-form AI content automatically and can continue building content based on past paragraphs you have written. The starting price is $29 per month.
• ContentBot – Can create short-form ideas to long-form text such as blog posts and essays. An interactive tool that allows you to contribute to some of the essay writing. The starting price is free.

NOW READ The best  free AI essay writer  tools.

How to use ChatGPT to write an essay on mobile

OpenAI released the official ChatGPT iOS app on Thursday, May 18th, 2023. This was then followed by the ChatGPT Android app on Wednesday, July 26th, 2023.

These apps offer all of the same functionality (most of the time, as development cycles rarely sync up perfectly). You can download the ChatGPT mobile app to help write an essay on the go!

So that’s all you need to know about writing essays using ChatGPT. With the help of ChatGPT, you, and the right inputs and prompts, you can get a great start on essays around a wide range of topics. It also has the added bonus of being able to check for grammar, punctuation, and clarity.

There are some limitations, however, where the AI chatbot falls down, namely, its inaccuracies. We’d recommend that if you are going to use ChatGPT to help you write essays, you use it to assist with a rough draft or to give you essay ideas, rather than getting it to do the whole thing.

• NOW READ Can universities detect ChatGPT?

Funmi Somoye

Funmi joined PC Guide in November 2022, and was a driving force for the site's ChatGPT coverage. She has a wide knowledge of AI apps, gaming and consumer technology.

What is ChatGPT? Everything you need to know about…

Does chatgpt plagiarize here’s what you need to know, 18 chatgpt alternatives in 2024 – our best free…, how to use chatgpt – our step-by-step guide and…, how to use snapchat dreams – step-by-step guide to…, how to slow down a video on snapchat –…, how to get a yellow heart on snapchat –…, how to hide and unhide chats on snapchat.

• Helldivers 2
• Dragon’s Dogma 2
• Wuthering Waves
• Genshin Impact
• Counter Strike 2
• Honkai Star Rail
• Lego Fortnite
• Stardew Valley
• NYT Strands
• NYT Connections
• Apple Watch
• Crunchyroll
• Prime Video
• Jujutsu Kaisen
• Demon Slayer
• Chainsaw Man
• Solo Leveling
• Beebom Gadgets

How to Use ChatGPT to Write Essays That Impress

Step 1: Use ChatGPT to Find and Refine Essay Topics

• Log into the service and type the following prompt into ChatGPT:

• As you can see, ChatGPT gave several good ideas for our essay. If you want to refine the idea further, you can ask the chatbot to cut out some parts of the idea and replace them. Or, you can ask for more context in certain parts. Example – “Expand more on topic number 5 and what it means.”

Step 2: Ask ChatGPT to Construct an Outline

• With the same chat open, type out “ Give me an essay outline for <selected topic>. Make sure to keep it structured as I’ll use it to write my essay .” In this case, I will use topic number 2 since it aligns with what I had in mind.

• As you can see above, we now have a structured outline for our essay. We can use this to write our essay or have ChatGPT do that job. Nonetheless, it’s a good starting point. As always, you can have the AI chatbot cut out parts of the outline or specifically add new ones depending on your requirement.

Step 3: Get ChatGPT to Cite Sources for Your Essay

Even though we have the idea and the outline, we will need to do our research for proof supporting our essay. Thankfully, ChatGPT can be of some help here. Since the chatbot is adept at moderate research, users can get a general idea of where to look for gathering information. Let’s begin doing that.

• Let’s begin asking ChatGPT for sources. With the same chat open, type in the following prompt:

• Now we have a list of 10 sources we can reference from. However, you can also see that ChatGPT mentions the year 2021 in some of them. Therefore, it’s best to use these websites but navigate to the latest pages pertaining to your essay for research. This applies to every topic, so always do it. Also, chatbots like ChatGPT have a habit of hallucinating and making up information, so do be careful.

Step 4: Have ChatGPT Write the Essay

• In the same chat, type the following prompt – “With the topic and outline available to you, generate a 700-word essay. Make sure to keep it structured and concise yet informational. Also, keep in mind my target audience is <Insert target audience> so cater to that accordingly.”
• In the middle of the essay, ChatGPT might stop and not answer. Simply type “ Continue ,” and it will finish the rest of the essay.

Step 5: Edit the Essay with ChatGPT

No matter if you have used ChatGPT to draft a complete essay or have written one yourself, you can use this step to make ChatGPT your co-editor and grammar checker. While your essay might need an initial look from a human, you can definitely use the bot to hash out the tone and add little details.

• Either open up the same chat or have your essay already in the clipboard. With that done, type out the following prompt:

Step 6: Export the Essay for Submission

However, for those who want to export the essay into a more aesthetic format, we have just the thing for you. There is no shortage of best ChatGPT Chrome extensions on the internet right now. We have one such selection linked in our list that can export selective chats onto beautiful image formats if you want to show off your essay. Check it out and let us know how you liked it.

Bonus: ChatGPT and AI Apps to Write Essays

1. writesonic.

Ryter is another helpful AI writing assistant that not only helps with essays but all types of articles. The service is powered by a language model that gives it intelligence. Rytr comes with 40+ different use cases and 20+ writing tones for all types of written material. For those who don’t want to stick to English, it even comes with support for 30+ languages.

Upanishad Sharma

Combining his love for Literature and Tech, Upanishad dived into the world of technology journalism with fire. Now he writes about anything and everything while keeping a keen eye on his first love of gaming. Often found chronically walking around the office.

Add new comment

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
• Open access
• Published: 30 October 2023

A large-scale comparison of human-written versus ChatGPT-generated essays

• Steffen Herbold 1 ,
• Annette Hautli-Janisz 1 ,
• Ute Heuer 1 ,
• Zlata Kikteva 1 &
• Alexander Trautsch 1  

Scientific Reports volume  13 , Article number:  18617 ( 2023 ) Cite this article

27k Accesses

48 Citations

98 Altmetric

Metrics details

• Computer science
• Information technology

ChatGPT and similar generative AI models have attracted hundreds of millions of users and have become part of the public discourse. Many believe that such models will disrupt society and lead to significant changes in the education system and information generation. So far, this belief is based on either colloquial evidence or benchmarks from the owners of the models—both lack scientific rigor. We systematically assess the quality of AI-generated content through a large-scale study comparing human-written versus ChatGPT-generated argumentative student essays. We use essays that were rated by a large number of human experts (teachers). We augment the analysis by considering a set of linguistic characteristics of the generated essays. Our results demonstrate that ChatGPT generates essays that are rated higher regarding quality than human-written essays. The writing style of the AI models exhibits linguistic characteristics that are different from those of the human-written essays. Since the technology is readily available, we believe that educators must act immediately. We must re-invent homework and develop teaching concepts that utilize these AI models in the same way as math utilizes the calculator: teach the general concepts first and then use AI tools to free up time for other learning objectives.

Similar content being viewed by others

ChatGPT-3.5 as writing assistance in students’ essays

Evaluating the role of ChatGPT in enhancing EFL writing assessments in classroom settings: A preliminary investigation

Perception, performance, and detectability of conversational artificial intelligence across 32 university courses

Introduction.

The massive uptake in the development and deployment of large-scale Natural Language Generation (NLG) systems in recent months has yielded an almost unprecedented worldwide discussion of the future of society. The ChatGPT service which serves as Web front-end to GPT-3.5 1 and GPT-4 was the fastest-growing service in history to break the 100 million user milestone in January and had 1 billion visits by February 2023 2 .

Driven by the upheaval that is particularly anticipated for education 3 and knowledge transfer for future generations, we conduct the first independent, systematic study of AI-generated language content that is typically dealt with in high-school education: argumentative essays, i.e. essays in which students discuss a position on a controversial topic by collecting and reflecting on evidence (e.g. ‘Should students be taught to cooperate or compete?’). Learning to write such essays is a crucial aspect of education, as students learn to systematically assess and reflect on a problem from different perspectives. Understanding the capability of generative AI to perform this task increases our understanding of the skills of the models, as well as of the challenges educators face when it comes to teaching this crucial skill. While there is a multitude of individual examples and anecdotal evidence for the quality of AI-generated content in this genre (e.g. 4 ) this paper is the first to systematically assess the quality of human-written and AI-generated argumentative texts across different versions of ChatGPT 5 . We use a fine-grained essay quality scoring rubric based on content and language mastery and employ a significant pool of domain experts, i.e. high school teachers across disciplines, to perform the evaluation. Using computational linguistic methods and rigorous statistical analysis, we arrive at several key findings:

AI models generate significantly higher-quality argumentative essays than the users of an essay-writing online forum frequented by German high-school students across all criteria in our scoring rubric.

ChatGPT-4 (ChatGPT web interface with the GPT-4 model) significantly outperforms ChatGPT-3 (ChatGPT web interface with the GPT-3.5 default model) with respect to logical structure, language complexity, vocabulary richness and text linking.

Writing styles between humans and generative AI models differ significantly: for instance, the GPT models use more nominalizations and have higher sentence complexity (signaling more complex, ‘scientific’, language), whereas the students make more use of modal and epistemic constructions (which tend to convey speaker attitude).

The linguistic diversity of the NLG models seems to be improving over time: while ChatGPT-3 still has a significantly lower linguistic diversity than humans, ChatGPT-4 has a significantly higher diversity than the students.

Our work goes significantly beyond existing benchmarks. While OpenAI’s technical report on GPT-4 6 presents some benchmarks, their evaluation lacks scientific rigor: it fails to provide vital information like the agreement between raters, does not report on details regarding the criteria for assessment or to what extent and how a statistical analysis was conducted for a larger sample of essays. In contrast, our benchmark provides the first (statistically) rigorous and systematic study of essay quality, paired with a computational linguistic analysis of the language employed by humans and two different versions of ChatGPT, offering a glance at how these NLG models develop over time. While our work is focused on argumentative essays in education, the genre is also relevant beyond education. In general, studying argumentative essays is one important aspect to understand how good generative AI models are at conveying arguments and, consequently, persuasive writing in general.

Related work

Natural language generation.

The recent interest in generative AI models can be largely attributed to the public release of ChatGPT, a public interface in the form of an interactive chat based on the InstructGPT 1 model, more commonly referred to as GPT-3.5. In comparison to the original GPT-3 7 and other similar generative large language models based on the transformer architecture like GPT-J 8 , this model was not trained in a purely self-supervised manner (e.g. through masked language modeling). Instead, a pipeline that involved human-written content was used to fine-tune the model and improve the quality of the outputs to both mitigate biases and safety issues, as well as make the generated text more similar to text written by humans. Such models are referred to as Fine-tuned LAnguage Nets (FLANs). For details on their training, we refer to the literature 9 . Notably, this process was recently reproduced with publicly available models such as Alpaca 10 and Dolly (i.e. the complete models can be downloaded and not just accessed through an API). However, we can only assume that a similar process was used for the training of GPT-4 since the paper by OpenAI does not include any details on model training.

Testing of the language competency of large-scale NLG systems has only recently started. Cai et al. 11 show that ChatGPT reuses sentence structure, accesses the intended meaning of an ambiguous word, and identifies the thematic structure of a verb and its arguments, replicating human language use. Mahowald 12 compares ChatGPT’s acceptability judgments to human judgments on the Article + Adjective + Numeral + Noun construction in English. Dentella et al. 13 show that ChatGPT-3 fails to understand low-frequent grammatical constructions like complex nested hierarchies and self-embeddings. In another recent line of research, the structure of automatically generated language is evaluated. Guo et al. 14 show that in question-answer scenarios, ChatGPT-3 uses different linguistic devices than humans. Zhao et al. 15 show that ChatGPT generates longer and more diverse responses when the user is in an apparently negative emotional state.

Given that we aim to identify certain linguistic characteristics of human-written versus AI-generated content, we also draw on related work in the field of linguistic fingerprinting, which assumes that each human has a unique way of using language to express themselves, i.e. the linguistic means that are employed to communicate thoughts, opinions and ideas differ between humans. That these properties can be identified with computational linguistic means has been showcased across different tasks: the computation of a linguistic fingerprint allows to distinguish authors of literary works 16 , the identification of speaker profiles in large public debates 17 , 18 , 19 , 20 and the provision of data for forensic voice comparison in broadcast debates 21 , 22 . For educational purposes, linguistic features are used to measure essay readability 23 , essay cohesion 24 and language performance scores for essay grading 25 . Integrating linguistic fingerprints also yields performance advantages for classification tasks, for instance in predicting user opinion 26 , 27 and identifying individual users 28 .

Limitations of OpenAIs ChatGPT evaluations

OpenAI published a discussion of the model’s performance of several tasks, including Advanced Placement (AP) classes within the US educational system 6 . The subjects used in performance evaluation are diverse and include arts, history, English literature, calculus, statistics, physics, chemistry, economics, and US politics. While the models achieved good or very good marks in most subjects, they did not perform well in English literature. GPT-3.5 also experienced problems with chemistry, macroeconomics, physics, and statistics. While the overall results are impressive, there are several significant issues: firstly, the conflict of interest of the model’s owners poses a problem for the performance interpretation. Secondly, there are issues with the soundness of the assessment beyond the conflict of interest, which make the generalizability of the results hard to assess with respect to the models’ capability to write essays. Notably, the AP exams combine multiple-choice questions with free-text answers. Only the aggregated scores are publicly available. To the best of our knowledge, neither the generated free-text answers, their overall assessment, nor their assessment given specific criteria from the used judgment rubric are published. Thirdly, while the paper states that 1–2 qualified third-party contractors participated in the rating of the free-text answers, it is unclear how often multiple ratings were generated for the same answer and what was the agreement between them. This lack of information hinders a scientifically sound judgement regarding the capabilities of these models in general, but also specifically for essays. Lastly, the owners of the model conducted their study in a few-shot prompt setting, where they gave the models a very structured template as well as an example of a human-written high-quality essay to guide the generation of the answers. This further fine-tuning of what the models generate could have also influenced the output. The results published by the owners go beyond the AP courses which are directly comparable to our work and also consider other student assessments like Graduate Record Examinations (GREs). However, these evaluations suffer from the same problems with the scientific rigor as the AP classes.

Scientific assessment of ChatGPT

Researchers across the globe are currently assessing the individual capabilities of these models with greater scientific rigor. We note that due to the recency and speed of these developments, the hereafter discussed literature has mostly only been published as pre-prints and has not yet been peer-reviewed. In addition to the above issues concretely related to the assessment of the capabilities to generate student essays, it is also worth noting that there are likely large problems with the trustworthiness of evaluations, because of data contamination, i.e. because the benchmark tasks are part of the training of the model, which enables memorization. For example, Aiyappa et al. 29 find evidence that this is likely the case for benchmark results regarding NLP tasks. This complicates the effort by researchers to assess the capabilities of the models beyond memorization.

Nevertheless, the first assessment results are already available – though mostly focused on ChatGPT-3 and not yet ChatGPT-4. Closest to our work is a study by Yeadon et al. 30 , who also investigate ChatGPT-3 performance when writing essays. They grade essays generated by ChatGPT-3 for five physics questions based on criteria that cover academic content, appreciation of the underlying physics, grasp of subject material, addressing the topic, and writing style. For each question, ten essays were generated and rated independently by five researchers. While the sample size precludes a statistical assessment, the results demonstrate that the AI model is capable of writing high-quality physics essays, but that the quality varies in a manner similar to human-written essays.

Guo et al. 14 create a set of free-text question answering tasks based on data they collected from the internet, e.g. question answering from Reddit. The authors then sample thirty triplets of a question, a human answer, and a ChatGPT-3 generated answer and ask human raters to assess if they can detect which was written by a human, and which was written by an AI. While this approach does not directly assess the quality of the output, it serves as a Turing test 31 designed to evaluate whether humans can distinguish between human- and AI-produced output. The results indicate that humans are in fact able to distinguish between the outputs when presented with a pair of answers. Humans familiar with ChatGPT are also able to identify over 80% of AI-generated answers without seeing a human answer in comparison. However, humans who are not yet familiar with ChatGPT-3 are not capable of identifying AI-written answers about 50% of the time. Moreover, the authors also find that the AI-generated outputs are deemed to be more helpful than the human answers in slightly more than half of the cases. This suggests that the strong results from OpenAI’s own benchmarks regarding the capabilities to generate free-text answers generalize beyond the benchmarks.

There are, however, some indicators that the benchmarks may be overly optimistic in their assessment of the model’s capabilities. For example, Kortemeyer 32 conducts a case study to assess how well ChatGPT-3 would perform in a physics class, simulating the tasks that students need to complete as part of the course: answer multiple-choice questions, do homework assignments, ask questions during a lesson, complete programming exercises, and write exams with free-text questions. Notably, ChatGPT-3 was allowed to interact with the instructor for many of the tasks, allowing for multiple attempts as well as feedback on preliminary solutions. The experiment shows that ChatGPT-3’s performance is in many aspects similar to that of the beginning learners and that the model makes similar mistakes, such as omitting units or simply plugging in results from equations. Overall, the AI would have passed the course with a low score of 1.5 out of 4.0. Similarly, Kung et al. 33 study the performance of ChatGPT-3 in the United States Medical Licensing Exam (USMLE) and find that the model performs at or near the passing threshold. Their assessment is a bit more optimistic than Kortemeyer’s as they state that this level of performance, comprehensible reasoning and valid clinical insights suggest that models such as ChatGPT may potentially assist human learning in clinical decision making.

Frieder et al. 34 evaluate the capabilities of ChatGPT-3 in solving graduate-level mathematical tasks. They find that while ChatGPT-3 seems to have some mathematical understanding, its level is well below that of an average student and in most cases is not sufficient to pass exams. Yuan et al. 35 consider the arithmetic abilities of language models, including ChatGPT-3 and ChatGPT-4. They find that they exhibit the best performance among other currently available language models (incl. Llama 36 , FLAN-T5 37 , and Bloom 38 ). However, the accuracy of basic arithmetic tasks is still only at 83% when considering correctness to the degree of \(10^{-3}\) , i.e. such models are still not capable of functioning reliably as calculators. In a slightly satiric, yet insightful take, Spencer et al. 39 assess how a scientific paper on gamma-ray astrophysics would look like, if it were written largely with the assistance of ChatGPT-3. They find that while the language capabilities are good and the model is capable of generating equations, the arguments are often flawed and the references to scientific literature are full of hallucinations.

The general reasoning skills of the models may also not be at the level expected from the benchmarks. For example, Cherian et al. 40 evaluate how well ChatGPT-3 performs on eleven puzzles that second graders should be able to solve and find that ChatGPT is only able to solve them on average in 36.4% of attempts, whereas the second graders achieve a mean of 60.4%. However, their sample size is very small and the problem was posed as a multiple-choice question answering problem, which cannot be directly compared to the NLG we consider.

Research gap

Within this article, we address an important part of the current research gap regarding the capabilities of ChatGPT (and similar technologies), guided by the following research questions:

RQ1: How good is ChatGPT based on GPT-3 and GPT-4 at writing argumentative student essays?

RQ2: How do AI-generated essays compare to essays written by students?

RQ3: What are linguistic devices that are characteristic of student versus AI-generated content?

We study these aspects with the help of a large group of teaching professionals who systematically assess a large corpus of student essays. To the best of our knowledge, this is the first large-scale, independent scientific assessment of ChatGPT (or similar models) of this kind. Answering these questions is crucial to understanding the impact of ChatGPT on the future of education.

Materials and methods

The essay topics originate from a corpus of argumentative essays in the field of argument mining 41 . Argumentative essays require students to think critically about a topic and use evidence to establish a position on the topic in a concise manner. The corpus features essays for 90 topics from Essay Forum 42 , an active community for providing writing feedback on different kinds of text and is frequented by high-school students to get feedback from native speakers on their essay-writing capabilities. Information about the age of the writers is not available, but the topics indicate that the essays were written in grades 11–13, indicating that the authors were likely at least 16. Topics range from ‘Should students be taught to cooperate or to compete?’ to ‘Will newspapers become a thing of the past?’. In the corpus, each topic features one human-written essay uploaded and discussed in the forum. The students who wrote the essays are not native speakers. The average length of these essays is 19 sentences with 388 tokens (an average of 2.089 characters) and will be termed ‘student essays’ in the remainder of the paper.

For the present study, we use the topics from Stab and Gurevych 41 and prompt ChatGPT with ‘Write an essay with about 200 words on “[ topic ]”’ to receive automatically-generated essays from the ChatGPT-3 and ChatGPT-4 versions from 22 March 2023 (‘ChatGPT-3 essays’, ‘ChatGPT-4 essays’). No additional prompts for getting the responses were used, i.e. the data was created with a basic prompt in a zero-shot scenario. This is in contrast to the benchmarks by OpenAI, who used an engineered prompt in a few-shot scenario to guide the generation of essays. We note that we decided to ask for 200 words because we noticed a tendency to generate essays that are longer than the desired length by ChatGPT. A prompt asking for 300 words typically yielded essays with more than 400 words. Thus, using the shorter length of 200, we prevent a potential advantage for ChatGPT through longer essays, and instead err on the side of brevity. Similar to the evaluations of free-text answers by OpenAI, we did not consider multiple configurations of the model due to the effort required to obtain human judgments. For the same reason, our data is restricted to ChatGPT and does not include other models available at that time, e.g. Alpaca. We use the browser versions of the tools because we consider this to be a more realistic scenario than using the API. Table 1 below shows the core statistics of the resulting dataset. Supplemental material S1 shows examples for essays from the data set.

Annotation study

Study participants.

The participants had registered for a two-hour online training entitled ‘ChatGPT – Challenges and Opportunities’ conducted by the authors of this paper as a means to provide teachers with some of the technological background of NLG systems in general and ChatGPT in particular. Only teachers permanently employed at secondary schools were allowed to register for this training. Focusing on these experts alone allows us to receive meaningful results as those participants have a wide range of experience in assessing students’ writing. A total of 139 teachers registered for the training, 129 of them teach at grammar schools, and only 10 teachers hold a position at other secondary schools. About half of the registered teachers (68 teachers) have been in service for many years and have successfully applied for promotion. For data protection reasons, we do not know the subject combinations of the registered teachers. We only know that a variety of subjects are represented, including languages (English, French and German), religion/ethics, and science. Supplemental material S5 provides some general information regarding German teacher qualifications.

The training began with an online lecture followed by a discussion phase. Teachers were given an overview of language models and basic information on how ChatGPT was developed. After about 45 minutes, the teachers received a both written and oral explanation of the questionnaire at the core of our study (see Supplementary material S3 ) and were informed that they had 30 minutes to finish the study tasks. The explanation included information on how the data was obtained, why we collect the self-assessment, and how we chose the criteria for the rating of the essays, the overall goal of our research, and a walk-through of the questionnaire. Participation in the questionnaire was voluntary and did not affect the awarding of a training certificate. We further informed participants that all data was collected anonymously and that we would have no way of identifying who participated in the questionnaire. We orally informed participants that they consent to the use of the provided ratings for our research by participating in the survey.

Once these instructions were provided orally and in writing, the link to the online form was given to the participants. The online form was running on a local server that did not log any information that could identify the participants (e.g. IP address) to ensure anonymity. As per instructions, consent for participation was given by using the online form. Due to the full anonymity, we could by definition not document who exactly provided the consent. This was implemented as further insurance that non-participation could not possibly affect being awarded the training certificate.

About 20% of the training participants did not take part in the questionnaire study, the remaining participants consented based on the information provided and participated in the rating of essays. After the questionnaire, we continued with an online lecture on the opportunities of using ChatGPT for teaching as well as AI beyond chatbots. The study protocol was reviewed and approved by the Research Ethics Committee of the University of Passau. We further confirm that our study protocol is in accordance with all relevant guidelines.

Questionnaire

The questionnaire consists of three parts: first, a brief self-assessment regarding the English skills of the participants which is based on the Common European Framework of Reference for Languages (CEFR) 43 . We have six levels ranging from ‘comparable to a native speaker’ to ‘some basic skills’ (see supplementary material S3 ). Then each participant was shown six essays. The participants were only shown the generated text and were not provided with information on whether the text was human-written or AI-generated.

The questionnaire covers the seven categories relevant for essay assessment shown below (for details see supplementary material S3 ):

Topic and completeness

Logic and composition

Expressiveness and comprehensiveness

Language mastery

Vocabulary and text linking

Language constructs

These categories are used as guidelines for essay assessment 44 established by the Ministry for Education of Lower Saxony, Germany. For each criterion, a seven-point Likert scale with scores from zero to six is defined, where zero is the worst score (e.g. no relation to the topic) and six is the best score (e.g. addressed the topic to a special degree). The questionnaire included a written description as guidance for the scoring.

After rating each essay, the participants were also asked to self-assess their confidence in the ratings. We used a five-point Likert scale based on the criteria for the self-assessment of peer-review scores from the Association for Computational Linguistics (ACL). Once a participant finished rating the six essays, they were shown a summary of their ratings, as well as the individual ratings for each of their essays and the information on how the essay was generated.

Computational linguistic analysis

In order to further explore and compare the quality of the essays written by students and ChatGPT, we consider the six following linguistic characteristics: lexical diversity, sentence complexity, nominalization, presence of modals, epistemic and discourse markers. Those are motivated by previous work: Weiss et al. 25 observe the correlation between measures of lexical, syntactic and discourse complexities to the essay gradings of German high-school examinations while McNamara et al. 45 explore cohesion (indicated, among other things, by connectives), syntactic complexity and lexical diversity in relation to the essay scoring.

Lexical diversity

We identify vocabulary richness by using a well-established measure of textual, lexical diversity (MTLD) 46 which is often used in the field of automated essay grading 25 , 45 , 47 . It takes into account the number of unique words but unlike the best-known measure of lexical diversity, the type-token ratio (TTR), it is not as sensitive to the difference in the length of the texts. In fact, Koizumi and In’nami 48 find it to be least affected by the differences in the length of the texts compared to some other measures of lexical diversity. This is relevant to us due to the difference in average length between the human-written and ChatGPT-generated essays.

Syntactic complexity

We use two measures in order to evaluate the syntactic complexity of the essays. One is based on the maximum depth of the sentence dependency tree which is produced using the spaCy 3.4.2 dependency parser 49 (‘Syntactic complexity (depth)’). For the second measure, we adopt an approach similar in nature to the one by Weiss et al. 25 who use clause structure to evaluate syntactic complexity. In our case, we count the number of conjuncts, clausal modifiers of nouns, adverbial clause modifiers, clausal complements, clausal subjects, and parataxes (‘Syntactic complexity (clauses)’). The supplementary material in S2 shows the difference between sentence complexity based on two examples from the data.

Nominalization is a common feature of a more scientific style of writing 50 and is used as an additional measure for syntactic complexity. In order to explore this feature, we count occurrences of nouns with suffixes such as ‘-ion’, ‘-ment’, ‘-ance’ and a few others which are known to transform verbs into nouns.

Semantic properties

Both modals and epistemic markers signal the commitment of the writer to their statement. We identify modals using the POS-tagging module provided by spaCy as well as a list of epistemic expressions of modality, such as ‘definitely’ and ‘potentially’, also used in other approaches to identifying semantic properties 51 . For epistemic markers we adopt an empirically-driven approach and utilize the epistemic markers identified in a corpus of dialogical argumentation by Hautli-Janisz et al. 52 . We consider expressions such as ‘I think’, ‘it is believed’ and ‘in my opinion’ to be epistemic.

Discourse properties

Discourse markers can be used to measure the coherence quality of a text. This has been explored by Somasundaran et al. 53 who use discourse markers to evaluate the story-telling aspect of student writing while Nadeem et al. 54 incorporated them in their deep learning-based approach to automated essay scoring. In the present paper, we employ the PDTB list of discourse markers 55 which we adjust to exclude words that are often used for purposes other than indicating discourse relations, such as ‘like’, ‘for’, ‘in’ etc.

Statistical methods

We use a within-subjects design for our study. Each participant was shown six randomly selected essays. Results were submitted to the survey system after each essay was completed, in case participants ran out of time and did not finish scoring all six essays. Cronbach’s \(\alpha\) 56 allows us to determine the inter-rater reliability for the rating criterion and data source (human, ChatGPT-3, ChatGPT-4) in order to understand the reliability of our data not only overall, but also for each data source and rating criterion. We use two-sided Wilcoxon-rank-sum tests 57 to confirm the significance of the differences between the data sources for each criterion. We use the same tests to determine the significance of the linguistic characteristics. This results in three comparisons (human vs. ChatGPT-3, human vs. ChatGPT-4, ChatGPT-3 vs. ChatGPT-4) for each of the seven rating criteria and each of the seven linguistic characteristics, i.e. 42 tests. We use the Holm-Bonferroni method 58 for the correction for multiple tests to achieve a family-wise error rate of 0.05. We report the effect size using Cohen’s d 59 . While our data is not perfectly normal, it also does not have severe outliers, so we prefer the clear interpretation of Cohen’s d over the slightly more appropriate, but less accessible non-parametric effect size measures. We report point plots with estimates of the mean scores for each data source and criterion, incl. the 95% confidence interval of these mean values. The confidence intervals are estimated in a non-parametric manner based on bootstrap sampling. We further visualize the distribution for each criterion using violin plots to provide a visual indicator of the spread of the data (see Supplementary material S4 ).

Further, we use the self-assessment of the English skills and confidence in the essay ratings as confounding variables. Through this, we determine if ratings are affected by the language skills or confidence, instead of the actual quality of the essays. We control for the impact of these by measuring Pearson’s correlation coefficient r 60 between the self-assessments and the ratings. We also determine whether the linguistic features are correlated with the ratings as expected. The sentence complexity (both tree depth and dependency clauses), as well as the nominalization, are indicators of the complexity of the language. Similarly, the use of discourse markers should signal a proper logical structure. Finally, a large lexical diversity should be correlated with the ratings for the vocabulary. Same as above, we measure Pearson’s r . We use a two-sided test for the significance based on a \(\beta\) -distribution that models the expected correlations as implemented by scipy 61 . Same as above, we use the Holm-Bonferroni method to account for multiple tests. However, we note that it is likely that all—even tiny—correlations are significant given our amount of data. Consequently, our interpretation of these results focuses on the strength of the correlations.

Our statistical analysis of the data is implemented in Python. We use pandas 1.5.3 and numpy 1.24.2 for the processing of data, pingouin 0.5.3 for the calculation of Cronbach’s \(\alpha\) , scipy 1.10.1 for the Wilcoxon-rank-sum tests Pearson’s r , and seaborn 0.12.2 for the generation of plots, incl. the calculation of error bars that visualize the confidence intervals.

Out of the 111 teachers who completed the questionnaire, 108 rated all six essays, one rated five essays, one rated two essays, and one rated only one essay. This results in 658 ratings for 270 essays (90 topics for each essay type: human-, ChatGPT-3-, ChatGPT-4-generated), with three ratings for 121 essays, two ratings for 144 essays, and one rating for five essays. The inter-rater agreement is consistently excellent ( \(\alpha >0.9\) ), with the exception of language mastery where we have good agreement ( \(\alpha =0.89\) , see Table  2 ). Further, the correlation analysis depicted in supplementary material S4 shows weak positive correlations ( \(r \in 0.11, 0.28]\) ) between the self-assessment for the English skills, respectively the self-assessment for the confidence in ratings and the actual ratings. Overall, this indicates that our ratings are reliable estimates of the actual quality of the essays with a potential small tendency that confidence in ratings and language skills yields better ratings, independent of the data source.

Table  2 and supplementary material S4 characterize the distribution of the ratings for the essays, grouped by the data source. We observe that for all criteria, we have a clear order of the mean values, with students having the worst ratings, ChatGPT-3 in the middle rank, and ChatGPT-4 with the best performance. We further observe that the standard deviations are fairly consistent and slightly larger than one, i.e. the spread is similar for all ratings and essays. This is further supported by the visual analysis of the violin plots.

The statistical analysis of the ratings reported in Table  4 shows that differences between the human-written essays and the ones generated by both ChatGPT models are significant. The effect sizes for human versus ChatGPT-3 essays are between 0.52 and 1.15, i.e. a medium ( \(d \in [0.5,0.8)\) ) to large ( \(d \in [0.8, 1.2)\) ) effect. On the one hand, the smallest effects are observed for the expressiveness and complexity, i.e. when it comes to the overall comprehensiveness and complexity of the sentence structures, the differences between the humans and the ChatGPT-3 model are smallest. On the other hand, the difference in language mastery is larger than all other differences, which indicates that humans are more prone to making mistakes when writing than the NLG models. The magnitude of differences between humans and ChatGPT-4 is larger with effect sizes between 0.88 and 1.43, i.e., a large to very large ( \(d \in [1.2, 2)\) ) effect. Same as for ChatGPT-3, the differences are smallest for expressiveness and complexity and largest for language mastery. Please note that the difference in language mastery between humans and both GPT models does not mean that the humans have low scores for language mastery (M=3.90), but rather that the NLG models have exceptionally high scores (M=5.03 for ChatGPT-3, M=5.25 for ChatGPT-4).

When we consider the differences between the two GPT models, we observe that while ChatGPT-4 has consistently higher mean values for all criteria, only the differences for logic and composition, vocabulary and text linking, and complexity are significant. The effect sizes are between 0.45 and 0.5, i.e. small ( \(d \in [0.2, 0.5)\) ) and medium. Thus, while GPT-4 seems to be an improvement over GPT-3.5 in general, the only clear indicator of this is a better and clearer logical composition and more complex writing with a more diverse vocabulary.

We also observe significant differences in the distribution of linguistic characteristics between all three groups (see Table  3 ). Sentence complexity (depth) is the only category without a significant difference between humans and ChatGPT-3, as well as ChatGPT-3 and ChatGPT-4. There is also no significant difference in the category of discourse markers between humans and ChatGPT-3. The magnitude of the effects varies a lot and is between 0.39 and 1.93, i.e., between small ( \(d \in [0.2, 0.5)\) ) and very large. However, in comparison to the ratings, there is no clear tendency regarding the direction of the differences. For instance, while the ChatGPT models write more complex sentences and use more nominalizations, humans tend to use more modals and epistemic markers instead. The lexical diversity of humans is higher than that of ChatGPT-3 but lower than that of ChatGPT-4. While there is no difference in the use of discourse markers between humans and ChatGPT-3, ChatGPT-4 uses significantly fewer discourse markers.

We detect the expected positive correlations between the complexity ratings and the linguistic markers for sentence complexity ( \(r=0.16\) for depth, \(r=0.19\) for clauses) and nominalizations ( \(r=0.22\) ). However, we observe a negative correlation between the logic ratings and the discourse markers ( \(r=-0.14\) ), which counters our intuition that more frequent use of discourse indicators makes a text more logically coherent. However, this is in line with previous work: McNamara et al. 45 also find no indication that the use of cohesion indices such as discourse connectives correlates with high- and low-proficiency essays. Finally, we observe the expected positive correlation between the ratings for the vocabulary and the lexical diversity ( \(r=0.12\) ). All observed correlations are significant. However, we note that the strength of all these correlations is weak and that the significance itself should not be over-interpreted due to the large sample size.

Our results provide clear answers to the first two research questions that consider the quality of the generated essays: ChatGPT performs well at writing argumentative student essays and outperforms the quality of the human-written essays significantly. The ChatGPT-4 model has (at least) a large effect and is on average about one point better than humans on a seven-point Likert scale.

Regarding the third research question, we find that there are significant linguistic differences between humans and AI-generated content. The AI-generated essays are highly structured, which for instance is reflected by the identical beginnings of the concluding sections of all ChatGPT essays (‘In conclusion, [...]’). The initial sentences of each essay are also very similar starting with a general statement using the main concepts of the essay topics. Although this corresponds to the general structure that is sought after for argumentative essays, it is striking to see that the ChatGPT models are so rigid in realizing this, whereas the human-written essays are looser in representing the guideline on the linguistic surface. Moreover, the linguistic fingerprint has the counter-intuitive property that the use of discourse markers is negatively correlated with logical coherence. We believe that this might be due to the rigid structure of the generated essays: instead of using discourse markers, the AI models provide a clear logical structure by separating the different arguments into paragraphs, thereby reducing the need for discourse markers.

Our data also shows that hallucinations are not a problem in the setting of argumentative essay writing: the essay topics are not really about factual correctness, but rather about argumentation and critical reflection on general concepts which seem to be contained within the knowledge of the AI model. The stochastic nature of the language generation is well-suited for this kind of task, as different plausible arguments can be seen as a sampling from all available arguments for a topic. Nevertheless, we need to perform a more systematic study of the argumentative structures in order to better understand the difference in argumentation between human-written and ChatGPT-generated essay content. Moreover, we also cannot rule out that subtle hallucinations may have been overlooked during the ratings. There are also essays with a low rating for the criteria related to factual correctness, indicating that there might be cases where the AI models still have problems, even if they are, on average, better than the students.

One of the issues with evaluations of the recent large-language models is not accounting for the impact of tainted data when benchmarking such models. While it is certainly possible that the essays that were sourced by Stab and Gurevych 41 from the internet were part of the training data of the GPT models, the proprietary nature of the model training means that we cannot confirm this. However, we note that the generated essays did not resemble the corpus of human essays at all. Moreover, the topics of the essays are general in the sense that any human should be able to reason and write about these topics, just by understanding concepts like ‘cooperation’. Consequently, a taint on these general topics, i.e. the fact that they might be present in the data, is not only possible but is actually expected and unproblematic, as it relates to the capability of the models to learn about concepts, rather than the memorization of specific task solutions.

While we did everything to ensure a sound construct and a high validity of our study, there are still certain issues that may affect our conclusions. Most importantly, neither the writers of the essays, nor their raters, were English native speakers. However, the students purposefully used a forum for English writing frequented by native speakers to ensure the language and content quality of their essays. This indicates that the resulting essays are likely above average for non-native speakers, as they went through at least one round of revisions with the help of native speakers. The teachers were informed that part of the training would be in English to prevent registrations from people without English language skills. Moreover, the self-assessment of the language skills was only weakly correlated with the ratings, indicating that the threat to the soundness of our results is low. While we cannot definitively rule out that our results would not be reproducible with other human raters, the high inter-rater agreement indicates that this is unlikely.

However, our reliance on essays written by non-native speakers affects the external validity and the generalizability of our results. It is certainly possible that native speaking students would perform better in the criteria related to language skills, though it is unclear by how much. However, the language skills were particular strengths of the AI models, meaning that while the difference might be smaller, it is still reasonable to conclude that the AI models would have at least comparable performance to humans, but possibly still better performance, just with a smaller gap. While we cannot rule out a difference for the content-related criteria, we also see no strong argument why native speakers should have better arguments than non-native speakers. Thus, while our results might not fully translate to native speakers, we see no reason why aspects regarding the content should not be similar. Further, our results were obtained based on high-school-level essays. Native and non-native speakers with higher education degrees or experts in fields would likely also achieve a better performance, such that the difference in performance between the AI models and humans would likely also be smaller in such a setting.

We further note that the essay topics may not be an unbiased sample. While Stab and Gurevych 41 randomly sampled the essays from the writing feedback section of an essay forum, it is unclear whether the essays posted there are representative of the general population of essay topics. Nevertheless, we believe that the threat is fairly low because our results are consistent and do not seem to be influenced by certain topics. Further, we cannot with certainty conclude how our results generalize beyond ChatGPT-3 and ChatGPT-4 to similar models like Bard ( https://bard.google.com/?hl=en ) Alpaca, and Dolly. Especially the results for linguistic characteristics are hard to predict. However, since—to the best of our knowledge and given the proprietary nature of some of these models—the general approach to how these models work is similar and the trends for essay quality should hold for models with comparable size and training procedures.

Finally, we want to note that the current speed of progress with generative AI is extremely fast and we are studying moving targets: ChatGPT 3.5 and 4 today are already not the same as the models we studied. Due to a lack of transparency regarding the specific incremental changes, we cannot know or predict how this might affect our results.

Our results provide a strong indication that the fear many teaching professionals have is warranted: the way students do homework and teachers assess it needs to change in a world of generative AI models. For non-native speakers, our results show that when students want to maximize their essay grades, they could easily do so by relying on results from AI models like ChatGPT. The very strong performance of the AI models indicates that this might also be the case for native speakers, though the difference in language skills is probably smaller. However, this is not and cannot be the goal of education. Consequently, educators need to change how they approach homework. Instead of just assigning and grading essays, we need to reflect more on the output of AI tools regarding their reasoning and correctness. AI models need to be seen as an integral part of education, but one which requires careful reflection and training of critical thinking skills.

Furthermore, teachers need to adapt strategies for teaching writing skills: as with the use of calculators, it is necessary to critically reflect with the students on when and how to use those tools. For instance, constructivists 62 argue that learning is enhanced by the active design and creation of unique artifacts by students themselves. In the present case this means that, in the long term, educational objectives may need to be adjusted. This is analogous to teaching good arithmetic skills to younger students and then allowing and encouraging students to use calculators freely in later stages of education. Similarly, once a sound level of literacy has been achieved, strongly integrating AI models in lesson plans may no longer run counter to reasonable learning goals.

In terms of shedding light on the quality and structure of AI-generated essays, this paper makes an important contribution by offering an independent, large-scale and statistically sound account of essay quality, comparing human-written and AI-generated texts. By comparing different versions of ChatGPT, we also offer a glance into the development of these models over time in terms of their linguistic properties and the quality they exhibit. Our results show that while the language generated by ChatGPT is considered very good by humans, there are also notable structural differences, e.g. in the use of discourse markers. This demonstrates that an in-depth consideration not only of the capabilities of generative AI models is required (i.e. which tasks can they be used for), but also of the language they generate. For example, if we read many AI-generated texts that use fewer discourse markers, it raises the question if and how this would affect our human use of discourse markers. Understanding how AI-generated texts differ from human-written enables us to look for these differences, to reason about their potential impact, and to study and possibly mitigate this impact.

Data availability

The datasets generated during and/or analysed during the current study are available in the Zenodo repository, https://doi.org/10.5281/zenodo.8343644

Code availability

All materials are available online in form of a replication package that contains the data and the analysis code, https://doi.org/10.5281/zenodo.8343644 .

Ouyang, L. et al. Training language models to follow instructions with human feedback (2022). arXiv:2203.02155 .

Ruby, D. 30+ detailed chatgpt statistics–users & facts (sep 2023). https://www.demandsage.com/chatgpt-statistics/ (2023). Accessed 09 June 2023.

Leahy, S. & Mishra, P. TPACK and the Cambrian explosion of AI. In Society for Information Technology & Teacher Education International Conference , (ed. Langran, E.) 2465–2469 (Association for the Advancement of Computing in Education (AACE), 2023).

Ortiz, S. Need an ai essay writer? here’s how chatgpt (and other chatbots) can help. https://www.zdnet.com/article/how-to-use-chatgpt-to-write-an-essay/ (2023). Accessed 09 June 2023.

Openai chat interface. https://chat.openai.com/ . Accessed 09 June 2023.

OpenAI. Gpt-4 technical report (2023). arXiv:2303.08774 .

Brown, T. B. et al. Language models are few-shot learners (2020). arXiv:2005.14165 .

Wang, B. Mesh-Transformer-JAX: Model-Parallel Implementation of Transformer Language Model with JAX. https://github.com/kingoflolz/mesh-transformer-jax (2021).

Wei, J. et al. Finetuned language models are zero-shot learners. In International Conference on Learning Representations (2022).

Taori, R. et al. Stanford alpaca: An instruction-following llama model. https://github.com/tatsu-lab/stanford_alpaca (2023).

Cai, Z. G., Haslett, D. A., Duan, X., Wang, S. & Pickering, M. J. Does chatgpt resemble humans in language use? (2023). arXiv:2303.08014 .

Mahowald, K. A discerning several thousand judgments: Gpt-3 rates the article + adjective + numeral + noun construction (2023). arXiv:2301.12564 .

Dentella, V., Murphy, E., Marcus, G. & Leivada, E. Testing ai performance on less frequent aspects of language reveals insensitivity to underlying meaning (2023). arXiv:2302.12313 .

Guo, B. et al. How close is chatgpt to human experts? comparison corpus, evaluation, and detection (2023). arXiv:2301.07597 .

Zhao, W. et al. Is chatgpt equipped with emotional dialogue capabilities? (2023). arXiv:2304.09582 .

Keim, D. A. & Oelke, D. Literature fingerprinting : A new method for visual literary analysis. In 2007 IEEE Symposium on Visual Analytics Science and Technology , 115–122, https://doi.org/10.1109/VAST.2007.4389004 (IEEE, 2007).

El-Assady, M. et al. Interactive visual analysis of transcribed multi-party discourse. In Proceedings of ACL 2017, System Demonstrations , 49–54 (Association for Computational Linguistics, Vancouver, Canada, 2017).

Mennatallah El-Assady, A. H.-J. & Butt, M. Discourse maps - feature encoding for the analysis of verbatim conversation transcripts. In Visual Analytics for Linguistics , vol. CSLI Lecture Notes, Number 220, 115–147 (Stanford: CSLI Publications, 2020).

Matt Foulis, J. V. & Reed, C. Dialogical fingerprinting of debaters. In Proceedings of COMMA 2020 , 465–466, https://doi.org/10.3233/FAIA200536 (Amsterdam: IOS Press, 2020).

Matt Foulis, J. V. & Reed, C. Interactive visualisation of debater identification and characteristics. In Proceedings of the COMMA workshop on Argument Visualisation, COMMA , 1–7 (2020).

Chatzipanagiotidis, S., Giagkou, M. & Meurers, D. Broad linguistic complexity analysis for Greek readability classification. In Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications , 48–58 (Association for Computational Linguistics, Online, 2021).

Ajili, M., Bonastre, J.-F., Kahn, J., Rossato, S. & Bernard, G. FABIOLE, a speech database for forensic speaker comparison. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16) , 726–733 (European Language Resources Association (ELRA), Portorož, Slovenia, 2016).

Deutsch, T., Jasbi, M. & Shieber, S. Linguistic features for readability assessment. In Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications , 1–17, https://doi.org/10.18653/v1/2020.bea-1.1 (Association for Computational Linguistics, Seattle, WA, USA \(\rightarrow\) Online, 2020).

Fiacco, J., Jiang, S., Adamson, D. & Rosé, C. Toward automatic discourse parsing of student writing motivated by neural interpretation. In Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022) , 204–215, https://doi.org/10.18653/v1/2022.bea-1.25 (Association for Computational Linguistics, Seattle, Washington, 2022).

Weiss, Z., Riemenschneider, A., Schröter, P. & Meurers, D. Computationally modeling the impact of task-appropriate language complexity and accuracy on human grading of German essays. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications , 30–45, https://doi.org/10.18653/v1/W19-4404 (Association for Computational Linguistics, Florence, Italy, 2019).

Yang, F., Dragut, E. & Mukherjee, A. Predicting personal opinion on future events with fingerprints. In Proceedings of the 28th International Conference on Computational Linguistics , 1802–1807, https://doi.org/10.18653/v1/2020.coling-main.162 (International Committee on Computational Linguistics, Barcelona, Spain (Online), 2020).

Tumarada, K. et al. Opinion prediction with user fingerprinting. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021) , 1423–1431 (INCOMA Ltd., Held Online, 2021).

Rocca, R. & Yarkoni, T. Language as a fingerprint: Self-supervised learning of user encodings using transformers. In Findings of the Association for Computational Linguistics: EMNLP . 1701–1714 (Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 2022).

Aiyappa, R., An, J., Kwak, H. & Ahn, Y.-Y. Can we trust the evaluation on chatgpt? (2023). arXiv:2303.12767 .

Yeadon, W., Inyang, O.-O., Mizouri, A., Peach, A. & Testrow, C. The death of the short-form physics essay in the coming ai revolution (2022). arXiv:2212.11661 .

TURING, A. M. I.-COMPUTING MACHINERY AND INTELLIGENCE. Mind LIX , 433–460, https://doi.org/10.1093/mind/LIX.236.433 (1950). https://academic.oup.com/mind/article-pdf/LIX/236/433/30123314/lix-236-433.pdf .

Kortemeyer, G. Could an artificial-intelligence agent pass an introductory physics course? (2023). arXiv:2301.12127 .

Kung, T. H. et al. Performance of chatgpt on usmle: Potential for ai-assisted medical education using large language models. PLOS Digital Health 2 , 1–12. https://doi.org/10.1371/journal.pdig.0000198 (2023).

Article   Google Scholar  

Frieder, S. et al. Mathematical capabilities of chatgpt (2023). arXiv:2301.13867 .

Yuan, Z., Yuan, H., Tan, C., Wang, W. & Huang, S. How well do large language models perform in arithmetic tasks? (2023). arXiv:2304.02015 .

Touvron, H. et al. Llama: Open and efficient foundation language models (2023). arXiv:2302.13971 .

Chung, H. W. et al. Scaling instruction-finetuned language models (2022). arXiv:2210.11416 .

Workshop, B. et al. Bloom: A 176b-parameter open-access multilingual language model (2023). arXiv:2211.05100 .

Spencer, S. T., Joshi, V. & Mitchell, A. M. W. Can ai put gamma-ray astrophysicists out of a job? (2023). arXiv:2303.17853 .

Cherian, A., Peng, K.-C., Lohit, S., Smith, K. & Tenenbaum, J. B. Are deep neural networks smarter than second graders? (2023). arXiv:2212.09993 .

Stab, C. & Gurevych, I. Annotating argument components and relations in persuasive essays. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers , 1501–1510 (Dublin City University and Association for Computational Linguistics, Dublin, Ireland, 2014).

Essay forum. https://essayforum.com/ . Last-accessed: 2023-09-07.

Common european framework of reference for languages (cefr). https://www.coe.int/en/web/common-european-framework-reference-languages . Accessed 09 July 2023.

Kmk guidelines for essay assessment. http://www.kmk-format.de/material/Fremdsprachen/5-3-2_Bewertungsskalen_Schreiben.pdf . Accessed 09 July 2023.

McNamara, D. S., Crossley, S. A. & McCarthy, P. M. Linguistic features of writing quality. Writ. Commun. 27 , 57–86 (2010).

McCarthy, P. M. & Jarvis, S. Mtld, vocd-d, and hd-d: A validation study of sophisticated approaches to lexical diversity assessment. Behav. Res. Methods 42 , 381–392 (2010).

Article   PubMed   Google Scholar  

Dasgupta, T., Naskar, A., Dey, L. & Saha, R. Augmenting textual qualitative features in deep convolution recurrent neural network for automatic essay scoring. In Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications , 93–102 (2018).

Koizumi, R. & In’nami, Y. Effects of text length on lexical diversity measures: Using short texts with less than 200 tokens. System 40 , 554–564 (2012).

spacy industrial-strength natural language processing in python. https://spacy.io/ .

Siskou, W., Friedrich, L., Eckhard, S., Espinoza, I. & Hautli-Janisz, A. Measuring plain language in public service encounters. In Proceedings of the 2nd Workshop on Computational Linguistics for Political Text Analysis (CPSS-2022) (Potsdam, Germany, 2022).

El-Assady, M. & Hautli-Janisz, A. Discourse Maps - Feature Encoding for the Analysis of Verbatim Conversation Transcripts (CSLI lecture notes (CSLI Publications, Center for the Study of Language and Information, 2019).

Hautli-Janisz, A. et al. QT30: A corpus of argument and conflict in broadcast debate. In Proceedings of the Thirteenth Language Resources and Evaluation Conference , 3291–3300 (European Language Resources Association, Marseille, France, 2022).

Somasundaran, S. et al. Towards evaluating narrative quality in student writing. Trans. Assoc. Comput. Linguist. 6 , 91–106 (2018).

Nadeem, F., Nguyen, H., Liu, Y. & Ostendorf, M. Automated essay scoring with discourse-aware neural models. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications , 484–493, https://doi.org/10.18653/v1/W19-4450 (Association for Computational Linguistics, Florence, Italy, 2019).

Prasad, R. et al. The Penn Discourse TreeBank 2.0. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08) (European Language Resources Association (ELRA), Marrakech, Morocco, 2008).

Cronbach, L. J. Coefficient alpha and the internal structure of tests. Psychometrika 16 , 297–334. https://doi.org/10.1007/bf02310555 (1951).

Article   MATH   Google Scholar  

Wilcoxon, F. Individual comparisons by ranking methods. Biom. Bull. 1 , 80–83 (1945).

Holm, S. A simple sequentially rejective multiple test procedure. Scand. J. Stat. 6 , 65–70 (1979).

MathSciNet   MATH   Google Scholar  

Cohen, J. Statistical power analysis for the behavioral sciences (Academic press, 2013).

Freedman, D., Pisani, R. & Purves, R. Statistics (international student edition). Pisani, R. Purves, 4th edn. WW Norton & Company, New York (2007).

Scipy documentation. https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.pearsonr.html . Accessed 09 June 2023.

Windschitl, M. Framing constructivism in practice as the negotiation of dilemmas: An analysis of the conceptual, pedagogical, cultural, and political challenges facing teachers. Rev. Educ. Res. 72 , 131–175 (2002).

Download references

Open Access funding enabled and organized by Projekt DEAL.

Author information

Authors and affiliations.

Faculty of Computer Science and Mathematics, University of Passau, Passau, Germany

Steffen Herbold, Annette Hautli-Janisz, Ute Heuer, Zlata Kikteva & Alexander Trautsch

You can also search for this author in PubMed   Google Scholar

Contributions

S.H., A.HJ., and U.H. conceived the experiment; S.H., A.HJ, and Z.K. collected the essays from ChatGPT; U.H. recruited the study participants; S.H., A.HJ., U.H. and A.T. conducted the training session and questionnaire; all authors contributed to the analysis of the results, the writing of the manuscript, and review of the manuscript.

Corresponding author

Correspondence to Steffen Herbold .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Additional information

Publisher's note.

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

Supplementary Information

Supplementary information 1., supplementary information 2., supplementary information 3., supplementary tables., supplementary figures., rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Herbold, S., Hautli-Janisz, A., Heuer, U. et al. A large-scale comparison of human-written versus ChatGPT-generated essays. Sci Rep 13 , 18617 (2023). https://doi.org/10.1038/s41598-023-45644-9

Download citation

Received : 01 June 2023

Accepted : 22 October 2023

Published : 30 October 2023

DOI : https://doi.org/10.1038/s41598-023-45644-9

Share this article

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

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

Provided by the Springer Nature SharedIt content-sharing initiative

This article is cited by

Defense against adversarial attacks: robust and efficient compressed optimized neural networks.

• Insaf Kraidia
• Afifa Ghenai
• Samir Brahim Belhaouari

Scientific Reports (2024)

AI-driven translations for kidney transplant equity in Hispanic populations

• Oscar A. Garcia Valencia
• Charat Thongprayoon
• Wisit Cheungpasitporn

Solving Not Answering. Validation of Guidance for Writing Higher-Order Multiple-Choice Questions in Medical Science Education

• Maria Xiromeriti
• Philip M. Newton

Medical Science Educator (2024)

How will the state think with ChatGPT? The challenges of generative artificial intelligence for public administrations

• Thomas Cantens

AI & SOCIETY (2024)

ChatGPT-3.5 im Hochschul-E-Assessment: Prüfungsleistung, akademische Integrität und zukünftige Bewertungsansätze

• Tobias Moebert
• Evgenia Samoilova
• Axel Wiepke

Informatik Spektrum (2024)

By submitting a comment you agree to abide by our Terms and Community Guidelines . If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Quick links

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

Sign up for the Nature Briefing: AI and Robotics newsletter — what matters in AI and robotics research, free to your inbox weekly.

Have a thesis expert improve your writing

Check your thesis for plagiarism in 10 minutes, generate your apa citations for free.

• Knowledge Base

Using AI tools

• How to Write an Essay with ChatGPT | Tips & Examples

How to Write an Essay with ChatGPT | Tips & Examples

Published on 26 June 2023 by Koen Driessen .

Passing off AI-generated text as your own work is widely considered plagiarism. However, when used correctly, generative AI tools like ChatGPT can legitimately help guide your writing process.

These tools are especially helpful in the preparation and revision stages of your essay writing.

You can use ChatGPT to:

• Write a research question
• Develop an outline
• Find relevant source information
• Summarise or paraphrase text
• Get feedback

Instantly correct all language mistakes in your text

Be assured that you'll submit flawless writing. Upload your document to correct all your mistakes.

Table of contents

Writing a research question, developing an outline, finding source recommendations, summarising/paraphrasing text, getting feedback, other interesting articles, frequently asked questions.

You can use ChatGPT to brainstorm potential research questions or to narrow down your thesis statement . Begin by inputting a description of the research topic or assigned question. Then include a prompt like “Write 3 possible research questions on this topic”.

You can make the prompt as specific as you like. For example, you can include the writing level (e.g., high school essay, college essay), perspective (e.g., first person) and the type of essay you intend to write (e.g., argumentative , descriptive , expository , or narrative ).

You can also mention any facts or viewpoints you’ve gathered that should be incorporated into the output.

If the output doesn’t suit your topic, you can click “Regenerate response” to have the tool generate a new response. You can do this as many times as you like, and you can try making your prompt more specific if you struggle to get the results you want.

Example: Using ChatGPT to write a research question

• Generate three possible research questions for an argumentative high school essay on the following topic: “The long-term impact of the Covid-19 pandemic.”
• To what extent has the Covid-19 pandemic exacerbated existing social inequalities and what measures can be taken to address these disparities in the long term?
• How has the Covid-19 pandemic transformed education systems, and what are the potential long-term implications for students’ learning outcomes and educational equity?
• What lessons can be learned from the Covid-19 pandemic to enhance global preparedness and response to future public health crises, and how can these lessons be effectively implemented in the long term?
• Based on the second question, develop three further research questions with a specific focus on distance learning.
• What are the long-term effects of widespread adoption of distance learning during the Covid-19 pandemic on students’ academic performance, motivation, and overall educational outcomes?
• How has the shift to distance learning impacted the social and emotional well-being of students, and what strategies can be implemented to address any negative consequences in the long term?
• What are the key factors that contribute to the success of distance learning programs, and how can educational institutions and policymakers ensure equitable access to quality education in the long term, especially for marginalized and underserved student populations?

The only proofreading tool specialized in correcting academic writing

The academic proofreading tool has been trained on 1000s of academic texts and by native English editors. Making it the most accurate and reliable proofreading tool for students.

Correct my document today

Once you’ve decided on a research question, you can use ChatGPT to develop an essay outline . This can help keep you on track by giving you a clear idea of what topics you want to discuss and in what order.

Do this by prompting ChatGPT to create an outline for a specific research question, mentioning any topics or points you want to discuss. You can also mention the writing level and the intended length of your essay so that the tool generates an appropriate outline.

You can then refine this by further prompting ChatGPT or editing the outline manually until it meets your requirements.

Examples: Using ChatGPT to generate an essay outline

• Develop an outline for an argumentative high school essay with the following research question: “What are the long-term effects of widespread adoption of distance learning during the Covid-19 pandemic on students’ academic performance and overall educational outcomes?”The essay will be about 4 pages long.
• Background information on the Covid-19 pandemic and the shift to distance learning
• Thesis statement: The widespread adoption of distance learning during the Covid-19 pandemic has had both positive and negative long-term effects on students’ academic performance and overall educational outcomes.
• Increased flexibility and personalized learning opportunities
• Access to a wider range of resources and educational materials
• Development of self-directed learning skills
• Critiques and limitations of previous studies
• Lack of face-to-face interaction and reduced social engagement
• Increased potential for distractions and lack of structure
• Technological barriers and unequal access to resources
• Examination of studies and data on academic achievement during distance learning
• Analysis of long-term effects on educational attainment and future opportunities
• Discussion of potential implications for college admissions and career readiness
• Strategies for promoting student engagement and motivation in distance learning
• Importance of teacher-student communication and support
• Addressing technological disparities and ensuring equitable access to resources
• Recap of the main points discussed
• Emphasize the need for further research and long-term planning to optimize distance learning experiences
• Restate the thesis and provide a final thought on the potential long-term effects of distance learning on students’ academic performance and overall educational outcomes

Once you know the scope of your essay, you can find relevant primary and secondary sources to support your argument.

However, we don’t recommend prompting ChatGPT to generate a list of sources as it occasionally makes mistakes (like listing nonexistent sources). Instead, it’s a good idea to use ChatGPT to get suggestions for the types of sources relevant to your essay and track them down using a credible research database or your institution’s library.

When you have found relevant sources, use a specialised tool like the Scribbr Citation Generator to cite them in your essay.

Example: Using ChatGPT to find sources

• What types of sources can I use to write an essay on the following research question?”What are the long-term effects of widespread adoption of distance learning during the Covid-19 pandemic on students’ academic performance and overall educational outcomes?”
• Academic Journals and Research Articles: Look for scholarly articles and research studies published in peer-reviewed academic journals. These sources often provide in-depth analysis, empirical evidence, and statistical data on the long-term effects of distance learning.
• Educational and Government Reports: Reports published by educational institutions, government agencies, or educational organizations can offer valuable insights into the impact of distance learning on academic performance and educational outcomes. These reports may include surveys, case studies, and data analysis specific to the Covid-19 pandemic and distance learning.
• Official Websites and Publications: Explore the official websites of educational institutions, education ministries, or educational technology companies. They often publish articles, white papers, or research findings related to distance learning and its effects on students’ academic performance.
• Expert Interviews or Opinion Pieces: Seek out interviews or opinion pieces from experts in the field of education, distance learning, or pedagogy. These sources can provide valuable perspectives and insights on the long-term effects of distance learning on students’ educational outcomes.
• Online Databases and Digital Libraries: Utilize online databases and digital libraries such as JSTOR, Google Scholar, or academic databases provided by your educational institution. These platforms offer a wide range of scholarly articles, research papers, and publications that can support your arguments.
• Surveys and Studies Conducted by Educational Institutions: Some schools or universities may have conducted their own surveys or studies to evaluate the impact of distance learning on students. Check if your educational institution has published any research findings or survey results that are relevant to your topic.

During your writing process, you can use ChatGPT as a summarising tool to condense text to its essential ideas or as a paraphraser to rephrase text in clear, accessible language. Using ChatGPT in these ways can help you to understand complex material, express your own ideas more clearly, and avoid repetition.

Simply input the relevant text and prompt the tool to summarise or paraphrase it. Alternatively, you can use Scribbr’s free text summariser and Scribbr’s free paraphrasing tool , which are specifically designed for these purposes.

Example: Using ChatGPT to summarise/paraphrase

• Paraphrase the following text using clear language:”Engaging in an extensive examination of the intricate interplay between remote instructional methods and academic achievement necessitates consideration of diverse factors, including the pedagogical efficacy of virtual platforms, the socioemotional ramifications of reduced face-to-face interactions, the equitable accessibility of technological resources, and the potential long-lasting implications for students’ educational trajectories and future opportunities.”
• To thoroughly explore the connection between remote teaching methods and academic success, it is crucial to take into account various factors. These factors include evaluating how well virtual platforms support effective teaching, understanding the impact of limited in-person interactions on students’ emotional well-being, ensuring fair access to technology resources, and recognizing the potential long-term effects on students’ educational paths and future prospects.

Once you’ve written your essay, you can prompt ChatGPT to provide feedback and recommend improvements.

You can indicate how the tool should provide feedback (e.g., “Act like a university professor examining papers”) and include the specific points you want to receive feedback on (e.g., consistency of tone, clarity of argument, appropriateness of evidence).

While this is not an adequate substitute for an experienced academic supervisor, it can help you with quick preliminary feedback.

You can also use ChatGPT to check grammar mistakes. However, ChatGPT sometimes misses errors and on rare occasions may even introduce new grammatical mistakes. We suggest using a tool like Scribbr’s free grammar checker , which is designed specifically for this purpose. Or, for more in-depth feedback, try Scribbr’s proofreading and editing service .

Example: Using ChatGPT for feedback

• Feedback the above text with regard to consistency of tone, clarity of argument, appropriateness of evidence, and coherence of structure.
• Clarity of Argument: The argument could be further clarified by explicitly connecting the discussed factors to their impact on academic performance. For example, explicitly stating how the proficiency of virtual platforms and equitable access to technology affect academic performance would strengthen the clarity of the argument.
• Appropriateness of Evidence: The evidence provided is generally appropriate and relevant. To enhance the strength of the evidence, consider incorporating specific examples, research studies, or statistics that directly support the discussed factors and their impact on academic performance. This would provide stronger evidence for the claims made.
• Coherence of Structure: The structure of the text is coherent, with a clear introduction, body paragraphs addressing different factors, and a conclusion. To improve coherence, consider adding transitional phrases or sentences at the beginning or end of paragraphs to facilitate the smooth flow of ideas between paragraphs. This would enhance the overall structure and make it easier for the reader to follow the argument.

Overall, the text demonstrates a consistent tone, a clear argument, appropriate evidence, and a coherent structure. Clarifying the argument by explicitly connecting the factors to their impact, incorporating stronger evidence, and adding transitional phrases for better coherence would further enhance the text’s effectiveness. Note Passing off AI-generated text as your own work is generally considered plagiarism (or at least academic dishonesty ) and may result in an automatic fail and other negative consequences . AI detectors may be used to detect this offence.

If you want more tips on using AI tools , understanding plagiarism , and citing sources , make sure to check out some of our other articles with explanations, examples, and formats.

• Citing ChatGPT
• Best grammar checker
• Best paraphrasing tool
• ChatGPT in your studies
• Is ChatGPT trustworthy?
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

• Citation styles
• In-text citation
• Citation examples
• Annotated bibliography

Yes, you can use ChatGPT to summarise text . This can help you understand complex information more easily, summarise the central argument of your own paper, or clarify your research question.

You can also use Scribbr’s free text summariser , which is designed specifically for this purpose.

Yes, you can use ChatGPT to paraphrase text to help you express your ideas more clearly, explore different ways of phrasing your arguments, and avoid repetition.

However, it’s not specifically designed for this purpose. We recommend using a specialised tool like Scribbr’s free paraphrasing tool , which will provide a smoother user experience.

Using AI writing tools (like ChatGPT ) to write your essay is usually considered plagiarism and may result in penalisation, unless it is allowed by your university. Text generated by AI tools is based on existing texts and therefore cannot provide unique insights. Furthermore, these outputs sometimes contain factual inaccuracies or grammar mistakes.

However, AI writing tools can be used effectively as a source of feedback and inspiration for your writing (e.g., to generate research questions ). Other AI tools, like grammar checkers, can help identify and eliminate grammar and punctuation mistakes to enhance your writing.

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

Driessen, K. (2023, June 26). How to Write an Essay with ChatGPT | Tips & Examples. Scribbr. Retrieved 27 September 2024, from https://www.scribbr.co.uk/using-ai-tools/chatgpt-essays/

Is this article helpful?

Koen Driessen

Other students also liked, how to write good chatgpt prompts, how to use chatgpt in your studies, how to use chatgpt | basics & tips.

Advanced AI Essay Writer

20,000 AI-powered essays generated daily

Write unique, high-quality essays in seconds

Instantly generate any essay type.

Get your content after just few words , or go step by step.

Full control of each step

Check the references

Edit your references using popular reference types like APA or MLA

How Smodin makes Essay Writing Easy

Generate different types of essays with smodin, instantly find sources for any sentence.

Our AI research tool in the essay editor interface makes it easy to find a source or fact check any piece of text on the web. It will find you the most relevant or related piece of information and the source it came from. You can quickly add that reference to your document references with just a click of a button. We also provide other modes for research such as “find support statistics”, “find supporting arguments”, “find useful information”, and other research methods to make finding the information you need a breeze. Make essay writing and research easy with our AI research assistant.

Easily Cite References

Our essay generator makes citing references in MLA and APA styles for web sources and references an easy task. The essay writer works by first identifying the primary elements in each source, such as the author, title, publication date, and URL, and then organizing them in the correct format required by the chosen citation style. This ensures that the references are accurate, complete, and consistent. The product provides helpful tools to generate citations and bibliographies in the appropriate style, making it easier for you to document your sources and avoid plagiarism. Whether you’re a student or a professional writer, our essay generator saves you time and effort in the citation process, allowing you to focus on the content of your work.

Produce Better Essays than ChatGPT

Our essay generator is designed to produce the best possible essays, with several tools available to assist in improving the essay, such as editing outlines, title improvements, tips and tricks, length control, and AI-assisted research. Unlike ChatGPT, our AI writer can find sources and assist in researching for the essay, which ensures that the essay is backed by credible and relevant information. Our essay generator offers editing assistance and outlines to improve the structure and flow of the essay. This feature is especially useful for students who may struggle with essay organization and require guidance on how to present their ideas coherently. Another advantage of our AI essay writer over ChatGPT is that it is designed explicitly for essay writing, ensuring that the output is of high quality and meets the expectations of the instructor or professor. While ChatGPT may be able to generate essays, there is no guarantee that the content will be relevant, accurate or meet the requirements of the assignment.

Easily Avoid Plagiarism

Our AI generated essays are 100% unique and plagiarism free. Worried about AI detection? Worry no more, use our AI Detection Remover to remove any AI Plagiarism produced from the essay generator.

Testimonials

Millions of users love Smodin's AI Writing Features

Smodin.io is an exceptional app that offers a range of outstanding features designed to help users with their research and content creation needs. One of the app's most impressive features is the Article 2.0, which generates high-quality articles and provides references for further study. The app's ChatIn feature and Research Paper generator are also incredibly unique, allowing users to conduct thorough research on the internet and find genuine paraphrased papers. One of the most impressive aspects of Smodin.io is its customer service team. The team is highly responsive, always available to help, and goes the extra mile to understand users' issues and offer solutions. This level of commitment to customer satisfaction is commendable and sets Smodin.io apart from its competitors. Another notable feature of Smodin.io is its continuous improvement. Every time you use the app, you'll notice new features that have been added based on feedback and recommendations. This level of attention to user feedback is remarkable, and it shows the app's developers' commitment to ensuring that Smodin.io remains the best in the market. I highly recommend Smodin.io to anyone looking for a reliable and efficient research and content creation tool.

I like this app. This app is useful mainly for student

Nice product

© 2024 Smodin LLC

ChatGPT: Everything you need to know about the AI-powered chatbot

ChatGPT, OpenAI’s text-generating AI chatbot, has taken the world by storm since its launch in November 2022. What started as a tool to hyper-charge productivity through writing essays and code with short text prompts has evolved into a behemoth used by more than 92% of Fortune 500 companies .

That growth has propelled OpenAI itself into becoming one of the most-hyped companies in recent memory. And its latest partnership with Apple for its upcoming generative AI offering, Apple Intelligence, has given the company another significant bump in the AI race.

2024 also saw the release of GPT-4o, OpenAI’s new flagship omni model for ChatGPT. GPT-4o is now the default free model, complete with voice and vision capabilities. But after demoing GPT-4o, OpenAI paused one of its voices , Sky, after allegations that it was mimicking Scarlett Johansson’s voice in “Her.”

OpenAI is facing internal drama, including the sizable exit of co-founder and longtime chief scientist Ilya Sutskever as the company dissolved its Superalignment team. OpenAI is also facing a lawsuit from Alden Global Capital-owned newspapers , including the New York Daily News and the Chicago Tribune, for alleged copyright infringement, following a similar suit filed by The New York Times last year.

Here’s a timeline of ChatGPT product updates and releases, starting with the latest, which we’ve been updating throughout the year. And if you have any other questions, check out our ChatGPT FAQ here.

Timeline of the most recent ChatGPT updates

September 2024, august 2024, february 2024, january 2024.

• ChatGPT FAQs

OpenAI rolls out Advanced Voice Mode with more voices and a new look

After a delay, OpenAI is finally rolling out Advanced Voice Mode to an expanded set of ChatGPT’s paying customers. AVM is also getting a revamped design — the feature is now represented by a blue animated sphere instead of the animated black dots that were presented back in May. OpenAI is highlighting improvements in conversational speed, accents in foreign languages, and five new voices as part of the rollout.

YouTuber finds a way to run ChatGPT on a graphing calculator

A video from YouTube creator ChromaLock showcased how to modify a TI-84 graphing calculator so that it can connect to the internet and access ChatGPT , touting it as the “ultimate cheating device.” As demonstrated in the video, it’s a pretty complicated process for the average high school student to follow — but it might stoke more concerns from teachers about the ongoing concerns about ChatGPT and cheating in schools.

OpenAI announces OpenAI o1, a new model that can fact-check itself

OpenAI unveiled a preview of OpenAI o1 , also known as “Strawberry.” The collection of models are available in ChatGPT and via OpenAI’s API: o1-preview and o1 mini. The company claims that o1 can more effectively reason through math and science and fact-check itself by spending more time considering all parts of a command or question.

Unlike ChatGPT, o1 can’t browse the web or analyze files yet, is rate-limited and expensive compared to other models. OpenAI says it plans to bring o1-mini access to all free users of ChatGPT, but hasn’t set a release date.

A hacker was able to trick ChatGPT into giving instructions on how to make bombs

An artist and hacker found a way to jailbreak ChatGPT to produce instructions for making powerful explosives, a request that the chatbot normally refuses. An explosives expert who reviewed the chatbot’s output told TechCrunch that the instructions could be used to make a detonatable product and was too sensitive to be released. 

OpenAI reaches 1 million paid users of its corporate offerings

OpenAI announced it has surpassed 1 million paid users for its versions of ChatGPT intended for businesses, including ChatGPT Team, ChatGPT Enterprise and its educational offering, ChatGPT Edu. The company said that nearly half of OpenAI’s corporate users are based in the US.

Volkswagen rolls out its ChatGPT assistant to the US

Volkswagen is taking its ChatGPT voice assistant experiment to vehicles in the United States. Its ChatGPT-integrated Plus Speech voice assistant is an AI chatbot based on Cerence’s Chat Pro product and a LLM from OpenAI and will begin rolling out on September 6 with the 2025 Jetta and Jetta GLI models.

OpenAI inks content deal with Condé Nast

As part of the new deal, OpenAI will surface stories from Condé Nast properties like The New Yorker, Vogue, Vanity Fair, Bon Appétit and Wired in ChatGPT and SearchGPT. Condé Nast CEO Roger Lynch implied that the “multi-year” deal will involve payment from OpenAI in some form and a Condé Nast spokesperson told TechCrunch that OpenAI will have permission to train on Condé Nast content.

Our first impressions of ChatGPT’s Advanced Voice Mode

TechCrunch’s Maxwell Zeff has been playing around with OpenAI’s Advanced Voice Mode, in what he describes as “the most convincing taste I’ve had of an AI-powered future yet.” Compared to Siri or Alexa, Advanced Voice Mode stands out with faster response times, unique answers and the ability to answer complex questions. But the feature falls short as an effective replacement for virtual assistants.

OpenAI shuts down election influence operation that used ChatGPT

OpenAI has banned a cluster of ChatGPT accounts linked to an Iranian influence operation that was generating content about the U.S. presidential election. OpenAI identified five website fronts presenting as both progressive and conservative news outlets that used ChatGPT to draft several long-form articles, though it doesn’t seem that it reached much of an audience.

OpenAI finds that GPT-4o does some weird stuff sometimes

OpenAI has found that GPT-4o, which powers the recently launched alpha of Advanced Voice Mode in ChatGPT, can behave in strange ways. In a new “red teaming” report, OpenAI reveals some of GPT-4o’s weirder quirks, like mimicking the voice of the person speaking to it or randomly shouting in the middle of a conversation.

ChatGPT’s mobile app reports its biggest month yet

After a big jump following the release of OpenAI’s new GPT-4o “omni” model, the mobile version of ChatGPT has now seen its biggest month of revenue yet. The app pulled in $28 million in net revenue from the App Store and Google Play in July, according to data provided by app intelligence firm Appfigures.

OpenAI could potentially catch students who cheat with ChatGPT

OpenAI has built a watermarking tool that could potentially catch students who cheat by using ChatGPT — but The Wall Street Journal reports that the company is debating whether to actually release it. An OpenAI spokesperson confirmed to TechCrunch that the company is researching tools that can detect writing from ChatGPT, but said it’s taking a “deliberate approach” to releasing it.

ChatGPT’s advanced Voice Mode starts rolling out to some users

OpenAI is giving users their first access to GPT-4o’s updated realistic audio responses. The alpha version is now available to a small group of ChatGPT Plus users, and the company says the feature will gradually roll out to all Plus users in the fall of 2024. The release follows controversy surrounding the voice’s similarity to Scarlett Johansson, leading OpenAI to delay its release.

OpenAI announces new search prototype, SearchGPT

OpenAI is testing SearchGPT, a new AI search experience to compete with Google. SearchGPT aims to elevate search queries with “timely answers” from across the internet, as well as the ability to ask follow-up questions. The temporary prototype is currently only available to a small group of users and its publisher partners, like The Atlantic, for testing and feedback.

OpenAI could lose $5 billion this year, report claims

A new report from The Information , based on undisclosed financial information, claims OpenAI could lose up to $5 billion due to how costly the business is to operate. The report also says the company could spend as much as $7 billion in 2024 to train and operate ChatGPT.

OpenAI unveils GPT-4o mini

OpenAI released its latest small AI model, GPT-4o mini . The company says GPT-4o mini, which is cheaper and faster than OpenAI’s current AI models, outperforms industry leading small AI models on reasoning tasks involving text and vision. GPT-4o mini will replace GPT-3.5 Turbo as the smallest model OpenAI offers. 

OpenAI partners with Los Alamos National Laboratory for bioscience research

OpenAI announced a partnership with the Los Alamos National Laboratory to study how AI can be employed by scientists in order to advance research in healthcare and bioscience. This follows other health-related research collaborations at OpenAI, including Moderna and Color Health.

OpenAI makes CriticGPT to find mistakes in GPT-4

OpenAI announced it has trained a model off of GPT-4, dubbed CriticGPT , which aims to find errors in ChatGPT’s code output so they can make improvements and better help so-called human “AI trainers” rate the quality and accuracy of ChatGPT responses.

OpenAI inks content deal with TIME

OpenAI and TIME announced a multi-year strategic partnership that brings the magazine’s content, both modern and archival, to ChatGPT. As part of the deal, TIME will also gain access to OpenAI’s technology in order to develop new audience-based products.

OpenAI delays ChatGPT’s new Voice Mode

OpenAI planned to start rolling out its advanced Voice Mode feature to a small group of ChatGPT Plus users in late June, but it says lingering issues forced it to postpone the launch to July. OpenAI says Advanced Voice Mode might not launch for all ChatGPT Plus customers until the fall, depending on whether it meets certain internal safety and reliability checks.

ChatGPT releases app for Mac

ChatGPT for macOS is now available for all users . With the app, users can quickly call up ChatGPT by using the keyboard combination of Option + Space. The app allows users to upload files and other photos, as well as speak to ChatGPT from their desktop and search through their past conversations.

Apple brings ChatGPT to its apps, including Siri

Apple announced at WWDC 2024 that it is bringing ChatGPT to Siri and other first-party apps and capabilities across its operating systems. The ChatGPT integrations, powered by GPT-4o, will arrive on iOS 18, iPadOS 18 and macOS Sequoia later this year, and will be free without the need to create a ChatGPT or OpenAI account. Features exclusive to paying ChatGPT users will also be available through Apple devices .

House Oversight subcommittee invites Scarlett Johansson to testify about ‘Sky’ controversy

Scarlett Johansson has been invited to testify about the controversy surrounding OpenAI’s Sky voice at a hearing for the House Oversight Subcommittee on Cybersecurity, Information Technology, and Government Innovation. In a letter, Rep. Nancy Mace said Johansson’s testimony could “provide a platform” for concerns around deepfakes.

ChatGPT experiences two outages in a single day

ChatGPT was down twice in one day: one multi-hour outage in the early hours of the morning Tuesday and another outage later in the day that is still ongoing. Anthropic’s Claude and Perplexity also experienced some issues.

The Atlantic and Vox Media ink content deals with OpenAI

The Atlantic and Vox Media have announced licensing and product partnerships with OpenAI . Both agreements allow OpenAI to use the publishers’ current content to generate responses in ChatGPT, which will feature citations to relevant articles. Vox Media says it will use OpenAI’s technology to build “audience-facing and internal applications,” while The Atlantic will build a new experimental product called Atlantic Labs .

OpenAI signs 100K PwC workers to ChatGPT’s enterprise tier

OpenAI announced a new deal with management consulting giant PwC . The company will become OpenAI’s biggest customer to date, covering 100,000 users, and will become OpenAI’s first partner for selling its enterprise offerings to other businesses.

OpenAI says it is training its GPT-4 successor

OpenAI announced in a blog post that it has recently begun training its next flagship model to succeed GPT-4. The news came in an announcement of its new safety and security committee, which is responsible for informing safety and security decisions across OpenAI’s products.

Former OpenAI director claims the board found out about ChatGPT on Twitter

On the The TED AI Show podcast, former OpenAI board member Helen Toner revealed that the board did not know about ChatGPT until its launch in November 2022. Toner also said that Sam Altman gave the board inaccurate information about the safety processes the company had in place and that he didn’t disclose his involvement in the OpenAI Startup Fund.

ChatGPT’s mobile app revenue saw biggest spike yet following GPT-4o launch

The launch of GPT-4o has driven the company’s biggest-ever spike in revenue on mobile , despite the model being freely available on the web. Mobile users are being pushed to upgrade to its $19.99 monthly subscription, ChatGPT Plus, if they want to experiment with OpenAI’s most recent launch.

OpenAI to remove ChatGPT’s Scarlett Johansson-like voice

After demoing its new GPT-4o model last week, OpenAI announced it is pausing one of its voices , Sky, after users found that it sounded similar to Scarlett Johansson in “Her.”

OpenAI explained in a blog post that Sky’s voice is “not an imitation” of the actress and that AI voices should not intentionally mimic the voice of a celebrity. The blog post went on to explain how the company chose its voices: Breeze, Cove, Ember, Juniper and Sky.

ChatGPT lets you add files from Google Drive and Microsoft OneDrive

OpenAI announced new updates for easier data analysis within ChatGPT . Users can now upload files directly from Google Drive and Microsoft OneDrive, interact with tables and charts, and export customized charts for presentations. The company says these improvements will be added to GPT-4o in the coming weeks.

OpenAI inks deal to train AI on Reddit data

OpenAI announced a partnership with Reddit that will give the company access to “real-time, structured and unique content” from the social network. Content from Reddit will be incorporated into ChatGPT, and the companies will work together to bring new AI-powered features to Reddit users and moderators.

OpenAI debuts GPT-4o “omni” model now powering ChatGPT

OpenAI’s spring update event saw the reveal of its new omni model, GPT-4o, which has a black hole-like interface , as well as voice and vision capabilities that feel eerily like something out of “Her.” GPT-4o is set to roll out “iteratively” across its developer and consumer-facing products over the next few weeks.

OpenAI demos real-time language translation with its latest GPT-4o model. pic.twitter.com/pXtHQ9mKGc — TechCrunch (@TechCrunch) May 13, 2024

OpenAI to build a tool that lets content creators opt out of AI training

The company announced it’s building a tool, Media Manager, that will allow creators to better control how their content is being used to train generative AI models — and give them an option to opt out. The goal is to have the new tool in place and ready to use by 2025.

OpenAI explores allowing AI porn

In a new peek behind the curtain of its AI’s secret instructions , OpenAI also released a new NSFW policy . Though it’s intended to start a conversation about how it might allow explicit images and text in its AI products, it raises questions about whether OpenAI — or any generative AI vendor — can be trusted to handle sensitive content ethically.

OpenAI and Stack Overflow announce partnership

In a new partnership, OpenAI will get access to developer platform Stack Overflow’s API and will get feedback from developers to improve the performance of their AI models. In return, OpenAI will include attributions to Stack Overflow in ChatGPT. However, the deal was not favorable to some Stack Overflow users — leading to some sabotaging their answer in protest .

U.S. newspapers file copyright lawsuit against OpenAI and Microsoft

Alden Global Capital-owned newspapers, including the New York Daily News, the Chicago Tribune, and the Denver Post, are suing OpenAI and Microsoft for copyright infringement. The lawsuit alleges that the companies stole millions of copyrighted articles “without permission and without payment” to bolster ChatGPT and Copilot.

OpenAI inks content licensing deal with Financial Times

OpenAI has partnered with another news publisher in Europe, London’s Financial Times , that the company will be paying for content access. “Through the partnership, ChatGPT users will be able to see select attributed summaries, quotes and rich links to FT journalism in response to relevant queries,” the FT wrote in a press release.

OpenAI opens Tokyo hub, adds GPT-4 model optimized for Japanese

OpenAI is opening a new office in Tokyo and has plans for a GPT-4 model optimized specifically for the Japanese language. The move underscores how OpenAI will likely need to localize its technology to different languages as it expands.

Sam Altman pitches ChatGPT Enterprise to Fortune 500 companies

According to Reuters, OpenAI’s Sam Altman hosted hundreds of executives from Fortune 500 companies across several cities in April, pitching versions of its AI services intended for corporate use.

OpenAI releases “more direct, less verbose” version of GPT-4 Turbo

Premium ChatGPT users — customers paying for ChatGPT Plus, Team or Enterprise — can now use an updated and enhanced version of GPT-4 Turbo . The new model brings with it improvements in writing, math, logical reasoning and coding, OpenAI claims, as well as a more up-to-date knowledge base.

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

ChatGPT no longer requires an account — but there’s a catch

You can now use ChatGPT without signing up for an account , but it won’t be quite the same experience. You won’t be able to save or share chats, use custom instructions, or other features associated with a persistent account. This version of ChatGPT will have “slightly more restrictive content policies,” according to OpenAI. When TechCrunch asked for more details, however, the response was unclear:

“The signed out experience will benefit from the existing safety mitigations that are already built into the model, such as refusing to generate harmful content. In addition to these existing mitigations, we are also implementing additional safeguards specifically designed to address other forms of content that may be inappropriate for a signed out experience,” a spokesperson said.

OpenAI’s chatbot store is filling up with spam

TechCrunch found that the OpenAI’s GPT Store is flooded with bizarre, potentially copyright-infringing GPTs . A cursory search pulls up GPTs that claim to generate art in the style of Disney and Marvel properties, but serve as little more than funnels to third-party paid services and advertise themselves as being able to bypass AI content detection tools.

The New York Times responds to OpenAI’s claims that it “hacked” ChatGPT for its copyright lawsuit

In a court filing opposing OpenAI’s motion to dismiss The New York Times’ lawsuit alleging copyright infringement, the newspaper asserted that “OpenAI’s attention-grabbing claim that The Times ‘hacked’ its products is as irrelevant as it is false.” The New York Times also claimed that some users of ChatGPT used the tool to bypass its paywalls.

OpenAI VP doesn’t say whether artists should be paid for training data

At a SXSW 2024 panel, Peter Deng, OpenAI’s VP of consumer product dodged a question on whether artists whose work was used to train generative AI models should be compensated . While OpenAI lets artists “opt out” of and remove their work from the datasets that the company uses to train its image-generating models, some artists have described the tool as onerous.

A new report estimates that ChatGPT uses more than half a million kilowatt-hours of electricity per day

ChatGPT’s environmental impact appears to be massive. According to a report from The New Yorker , ChatGPT uses an estimated 17,000 times the amount of electricity than the average U.S. household to respond to roughly 200 million requests each day.

ChatGPT can now read its answers aloud

OpenAI released a new Read Aloud feature for the web version of ChatGPT as well as the iOS and Android apps. The feature allows ChatGPT to read its responses to queries in one of five voice options and can speak 37 languages, according to the company. Read aloud is available on both GPT-4 and GPT-3.5 models.

https://twitter.com/openai/status/1764712432939995549

OpenAI partners with Dublin City Council to use GPT-4 for tourism

As part of a new partnership with OpenAI, the Dublin City Council will use GPT-4 to craft personalized itineraries for travelers, including recommendations of unique and cultural destinations, in an effort to support tourism across Europe.

A law firm used ChatGPT to justify a six-figure bill for legal services

New York-based law firm Cuddy Law was criticized by a judge for using ChatGPT to calculate their hourly billing rate . The firm submitted a $113,500 bill to the court, which was then halved by District Judge Paul Engelmayer, who called the figure “well above” reasonable demands.

ChatGPT experienced a bizarre bug for several hours

ChatGPT users found that ChatGPT was giving nonsensical answers for several hours , prompting OpenAI to investigate the issue. Incidents varied from repetitive phrases to confusing and incorrect answers to queries. The issue was resolved by OpenAI the following morning.

Match Group announced deal with OpenAI with a press release co-written by ChatGPT

The dating app giant home to Tinder, Match and OkCupid announced an enterprise agreement with OpenAI in an enthusiastic press release written with the help of ChatGPT . The AI tech will be used to help employees with work-related tasks and come as part of Match’s $20 million-plus bet on AI in 2024.

ChatGPT will now remember — and forget — things you tell it to

As part of a test, OpenAI began rolling out new “memory” controls for a small portion of ChatGPT free and paid users, with a broader rollout to follow. The controls let you tell ChatGPT explicitly to remember something, see what it remembers or turn off its memory altogether. Note that deleting a chat from chat history won’t erase ChatGPT’s or a custom GPT’s memories — you must delete the memory itself.

https://twitter.com/OpenAI/status/1757469997742666052

OpenAI begins rolling out “Temporary Chat” feature

Initially limited to a small subset of free and subscription users, Temporary Chat lets you have a dialogue with a blank slate. With Temporary Chat, ChatGPT won’t be aware of previous conversations or access memories but will follow custom instructions if they’re enabled.

But, OpenAI says it may keep a copy of Temporary Chat conversations for up to 30 days for “safety reasons.”

https://twitter.com/OpenAI/status/1757470007381082382

ChatGPT users can now invoke GPTs directly in chats

Paid users of ChatGPT can now bring GPTs into a conversation by typing “@” and selecting a GPT from the list. The chosen GPT will have an understanding of the full conversation, and different GPTs can be “tagged in” for different use cases and needs.

https://twitter.com/OpenAI/status/1752391522081980855

ChatGPT is reportedly leaking usernames and passwords from users’ private conversations

Screenshots provided to Ars Technica found that ChatGPT is potentially leaking unpublished research papers, login credentials and private information from its users. An OpenAI representative told Ars Technica that the company was investigating the report.

ChatGPT is violating Europe’s privacy laws, Italian DPA tells OpenAI

OpenAI has been told it’s suspected of violating European Union privacy , following a multi-month investigation of ChatGPT by Italy’s data protection authority. Details of the draft findings haven’t been disclosed, but in a response, OpenAI said: “We want our AI to learn about the world, not about private individuals.”

OpenAI partners with Common Sense Media to collaborate on AI guidelines

In an effort to win the trust of parents and policymakers, OpenAI announced it’s partnering with Common Sense Media to collaborate on AI guidelines and education materials for parents, educators and young adults. The organization works to identify and minimize tech harms to young people and previously flagged ChatGPT as lacking in transparency and privacy .

OpenAI responds to Congressional Black Caucus about lack of diversity on its board

After a letter from the Congressional Black Caucus questioned the lack of diversity in OpenAI’s board, the company responded . The response, signed by CEO Sam Altman and Chairman of the Board Bret Taylor, said building a complete and diverse board was one of the company’s top priorities and that it was working with an executive search firm to assist it in finding talent. 

OpenAI drops prices and fixes ‘lazy’ GPT-4 that refused to work

In a blog post , OpenAI announced price drops for GPT-3.5’s API, with input prices dropping to 50% and output by 25%, to $0.0005 per thousand tokens in, and $0.0015 per thousand tokens out. GPT-4 Turbo also got a new preview model for API use, which includes an interesting fix that aims to reduce “laziness” that users have experienced.

https://twitter.com/OpenAI/status/1750636119321120942

OpenAI bans developer of a bot impersonating a presidential candidate

OpenAI has suspended AI startup Delphi, which developed a bot impersonating Rep. Dean Phillips (D-Minn.) to help bolster his presidential campaign. The ban comes just weeks after OpenAI published a plan to combat election misinformation, which listed “chatbots impersonating candidates” as against its policy.

OpenAI announces partnership with Arizona State University

Beginning in February, Arizona State University will have full access to ChatGPT’s Enterprise tier , which the university plans to use to build a personalized AI tutor, develop AI avatars, bolster their prompt engineering course and more. It marks OpenAI’s first partnership with a higher education institution.

Winner of a literary prize reveals around 5% her novel was written by ChatGPT

After receiving the prestigious Akutagawa Prize for her novel The Tokyo Tower of Sympathy, author Rie Kudan admitted that around 5% of the book quoted ChatGPT-generated sentences “verbatim.” Interestingly enough, the novel revolves around a futuristic world with a pervasive presence of AI.

Sam Altman teases video capabilities for ChatGPT and the release of GPT-5

In a conversation with Bill Gates on the Unconfuse Me podcast, Sam Altman confirmed an upcoming release of GPT-5 that will be “fully multimodal with speech, image, code, and video support.” Altman said users can expect to see GPT-5 drop sometime in 2024.

OpenAI announces team to build ‘crowdsourced’ governance ideas into its models

OpenAI is forming a Collective Alignment team of researchers and engineers to create a system for collecting and “encoding” public input on its models’ behaviors into OpenAI products and services. This comes as a part of OpenAI’s public program to award grants to fund experiments in setting up a “democratic process” for determining the rules AI systems follow.

OpenAI unveils plan to combat election misinformation

In a blog post, OpenAI announced users will not be allowed to build applications for political campaigning and lobbying until the company works out how effective their tools are for “personalized persuasion.”

Users will also be banned from creating chatbots that impersonate candidates or government institutions, and from using OpenAI tools to misrepresent the voting process or otherwise discourage voting.

The company is also testing out a tool that detects DALL-E generated images and will incorporate access to real-time news, with attribution, in ChatGPT.

https://twitter.com/OpenAI/status/1746986660892741927

OpenAI changes policy to allow military applications

In an unannounced update to its usage policy , OpenAI removed language previously prohibiting the use of its products for the purposes of “military and warfare.” In an additional statement, OpenAI confirmed that the language was changed in order to accommodate military customers and projects that do not violate their ban on efforts to use their tools to “harm people, develop weapons, for communications surveillance, or to injure others or destroy property.”

ChatGPT subscription aimed at small teams debuts

Aptly called ChatGPT Team , the new plan provides a dedicated workspace for teams of up to 149 people using ChatGPT as well as admin tools for team management. In addition to gaining access to GPT-4, GPT-4 with Vision and DALL-E3, ChatGPT Team lets teams build and share GPTs for their business needs.

OpenAI’s GPT store officially launches

After some back and forth over the last few months, OpenAI’s GPT Store is finally here . The feature lives in a new tab in the ChatGPT web client, and includes a range of GPTs developed both by OpenAI’s partners and the wider dev community.

To access the GPT Store, users must be subscribed to one of OpenAI’s premium ChatGPT plans — ChatGPT Plus, ChatGPT Enterprise or the newly launched ChatGPT Team.

https://twitter.com/sama/status/1745135061731803571?s=20

Developing AI models would be “impossible” without copyrighted materials, OpenAI claims

Following a proposed ban on using news publications and books to train AI chatbots in the U.K., OpenAI submitted a plea to the House of Lords communications and digital committee. OpenAI argued that it would be “impossible” to train AI models without using copyrighted materials, and that they believe copyright law “does not forbid training.”

OpenAI claims The New York Times’ copyright lawsuit is without merit

OpenAI published a public response to The New York Times’s lawsuit against them and Microsoft for allegedly violating copyright law, claiming that the case is without merit.

In the response , OpenAI reiterates its view that training AI models using publicly available data from the web is fair use. It also makes the case that regurgitation is less likely to occur with training data from a single source and places the onus on users to “act responsibly.”

https://twitter.com/OpenAI/status/1744419710635229424?s=20

OpenAI’s app store for GPTs planned to launch next week

After being delayed in December , OpenAI plans to launch its GPT Store sometime in the coming week, according to an email viewed by TechCrunch. OpenAI says developers building GPTs will have to review the company’s updated usage policies and GPT brand guidelines to ensure their GPTs are compliant before they’re eligible for listing in the GPT Store. OpenAI’s update notably didn’t include any information on the expected monetization opportunities for developers listing their apps on the storefront.

https://twitter.com/refsrc/status/1742970484256366629

OpenAI moves to shrink regulatory risk in EU around data privacy

In an email, OpenAI detailed an incoming update to its terms, including changing the OpenAI entity providing services to EEA and Swiss residents to OpenAI Ireland Limited. The move appears to be intended to shrink its regulatory risk in the European Union, where the company has been under scrutiny over ChatGPT’s impact on people’s privacy.

What is ChatGPT? How does it work?

ChatGPT is a general-purpose chatbot that uses artificial intelligence to generate text after a user enters a prompt, developed by tech startup OpenAI . The chatbot uses GPT-4, a large language model that uses deep learning to produce human-like text.

When did ChatGPT get released?

November 30, 2022 is when ChatGPT was released for public use.

What is the latest version of ChatGPT?

Both the free version of ChatGPT and the paid ChatGPT Plus are regularly updated with new GPT models. The most recent model is GPT-4o .

Can I use ChatGPT for free?

There is a free version of ChatGPT that only requires a sign-in in addition to the paid version, ChatGPT Plus .

Who uses ChatGPT?

Anyone can use ChatGPT! More and more tech companies and search engines are utilizing the chatbot to automate text or quickly answer user questions/concerns.

What companies use ChatGPT?

Multiple enterprises utilize ChatGPT, although others may limit the use of the AI-powered tool .

Most recently, Microsoft announced at it’s 2023 Build conference that it is integrating it ChatGPT-based Bing experience into Windows 11. A Brooklyn-based 3D display startup Looking Glass utilizes ChatGPT to produce holograms you can communicate with by using ChatGPT.  And nonprofit organization Solana officially integrated the chatbot into its network with a ChatGPT plug-in geared toward end users to help onboard into the web3 space.

What does GPT mean in ChatGPT?

GPT stands for Generative Pre-Trained Transformer.

What is the difference between ChatGPT and a chatbot?

A chatbot can be any software/system that holds dialogue with you/a person but doesn’t necessarily have to be AI-powered. For example, there are chatbots that are rules-based in the sense that they’ll give canned responses to questions.

ChatGPT is AI-powered and utilizes LLM technology to generate text after a prompt.

Can ChatGPT write essays?

Can chatgpt commit libel.

Due to the nature of how these models work , they don’t know or care whether something is true, only that it looks true. That’s a problem when you’re using it to do your homework, sure, but when it accuses you of a crime you didn’t commit, that may well at this point be libel.

We will see how handling troubling statements produced by ChatGPT will play out over the next few months as tech and legal experts attempt to tackle the fastest moving target in the industry.

Does ChatGPT have an app?

Yes, there is a free ChatGPT mobile app for iOS and Android users.

What is the ChatGPT character limit?

It’s not documented anywhere that ChatGPT has a character limit. However, users have noted that there are some character limitations after around 500 words.

Does ChatGPT have an API?

Yes, it was released March 1, 2023.

What are some sample everyday uses for ChatGPT?

Everyday examples include programing, scripts, email replies, listicles, blog ideas, summarization, etc.

What are some advanced uses for ChatGPT?

Advanced use examples include debugging code, programming languages, scientific concepts, complex problem solving, etc.

How good is ChatGPT at writing code?

It depends on the nature of the program. While ChatGPT can write workable Python code, it can’t necessarily program an entire app’s worth of code. That’s because ChatGPT lacks context awareness — in other words, the generated code isn’t always appropriate for the specific context in which it’s being used.

Can you save a ChatGPT chat?

Yes. OpenAI allows users to save chats in the ChatGPT interface, stored in the sidebar of the screen. There are no built-in sharing features yet.

Are there alternatives to ChatGPT?

Yes. There are multiple AI-powered chatbot competitors such as Together , Google’s Gemini and Anthropic’s Claude , and developers are creating open source alternatives .

How does ChatGPT handle data privacy?

OpenAI has said that individuals in “certain jurisdictions” (such as the EU) can object to the processing of their personal information by its AI models by filling out  this form . This includes the ability to make requests for deletion of AI-generated references about you. Although OpenAI notes it may not grant every request since it must balance privacy requests against freedom of expression “in accordance with applicable laws”.

The web form for making a deletion of data about you request is entitled “ OpenAI Personal Data Removal Request ”.

In its privacy policy, the ChatGPT maker makes a passing acknowledgement of the objection requirements attached to relying on “legitimate interest” (LI), pointing users towards more information about requesting an opt out — when it writes: “See here  for instructions on how you can opt out of our use of your information to train our models.”

What controversies have surrounded ChatGPT?

Recently, Discord announced that it had integrated OpenAI’s technology into its bot named Clyde where two users tricked Clyde into providing them with instructions for making the illegal drug methamphetamine (meth) and the incendiary mixture napalm.

An Australian mayor has publicly announced he may sue OpenAI for defamation due to ChatGPT’s false claims that he had served time in prison for bribery. This would be the first defamation lawsuit against the text-generating service.

CNET found itself in the midst of controversy after Futurism reported the publication was publishing articles under a mysterious byline completely generated by AI. The private equity company that owns CNET, Red Ventures, was accused of using ChatGPT for SEO farming, even if the information was incorrect.

Several major school systems and colleges, including New York City Public Schools , have banned ChatGPT from their networks and devices. They claim that the AI impedes the learning process by promoting plagiarism and misinformation, a claim that not every educator agrees with .

There have also been cases of ChatGPT accusing individuals of false crimes .

Where can I find examples of ChatGPT prompts?

Several marketplaces host and provide ChatGPT prompts, either for free or for a nominal fee. One is PromptBase . Another is ChatX . More launch every day.

Can ChatGPT be detected?

Poorly. Several tools claim to detect ChatGPT-generated text, but in our tests , they’re inconsistent at best.

Are ChatGPT chats public?

No. But OpenAI recently disclosed a bug, since fixed, that exposed the titles of some users’ conversations to other people on the service.

What lawsuits are there surrounding ChatGPT?

None specifically targeting ChatGPT. But OpenAI is involved in at least one lawsuit that has implications for AI systems trained on publicly available data, which would touch on ChatGPT.

Are there issues regarding plagiarism with ChatGPT?

Yes. Text-generating AI models like ChatGPT have a tendency to regurgitate content from their training data.

More TechCrunch

Get the industry’s biggest tech news, techcrunch daily news.

Every weekday and Sunday, you can get the best of TechCrunch’s coverage.

Startups Weekly

Startups are the core of TechCrunch, so get our best coverage delivered weekly.

TechCrunch Fintech

The latest Fintech news and analysis, delivered every Tuesday.

TechCrunch Mobility

TechCrunch Mobility is your destination for transportation news and insight.

X faces additional $1.9M fine to end ban in Brazil

X (formerly Twitter) could soon resume service in Brazil — if it’s willing to pay an additional fine. Reuters and other publications have reported on an order from the country’s…

Meta rethinks smart glasses with Orion

Meta Connect 2024 was this week, showcasing new hardware and software to support two of the company’s big ambitions: AI and the metaverse. CEO Mark Zuckerberg announced new Quest headsets,…

Brian Williams might host a live election night special for Amazon

Amazon Prime Video could be getting into the live news business, if only for one night. Variety reports that the company is in talks with longtime NBC and MSNBC news…

Judge is unimpressed by Apple’s deadline extension request in Epic Games dispute

Apple faces a looming deadline to produce what it says are more than 1 million documents related to recent App Store changes. On Friday, Judge Thomas S. Hixson denied the…

Meta offers a glimpse through its supposed iPhone killer: Orion

For years, Silicon Valley and Wall Street have questioned Mark Zuckerberg’s decision to invest tens of billions of dollars into Reality Labs. This week, Meta’s wearables division unveiled a prototype…

VCs expect a surge in startups offering lower rate mortgages, other loans now that the Feds cut rates

When the U.S. Feds cut interest rates by half a percentage point last week, it was a dash of good news for venture capitalists backing one particularly beleaguered class of…

Robot hand can detach from arm, crawl over to objects, and pick them up

The video debuted along with a research paper of the same name at IEEE’s International Conference on Robotics and Automation in Rotterdam this week.

Best iPad apps to boost productivity and make your life easier

There are many iPad apps to help you organize recipes; sync tasks across devices; be more productive; and manage your notes.

Why Index Ventures is bulking up its investment team in NYC

While online discourse would make it seem that venture has retreated to the Bay Area, with San Francisco being the most important place to build a startup, Index Ventures is…

A Russian warlord said he’ll take Cybertrucks into Ukraine; some experts think that’s unwise

In August, a Russian warlord posted a video on Telegram, showing a pair of Cybertrucks patrolling a road in Chechnya, armed seemingly with heavy machine guns. Leaving aside unanswerable (for…

WordPress.org temporarily lifts its ban on WP Engine

WordPress.org has lifted its ban on hosting provider WP Engine until October 1, after putting a block on it earlier this week. The block prevented several sites from updating their…

The WordPress vs. WP Engine drama, explained

The world of WordPress, one of the most popular technologies for creating and hosting websites, is going through a very heated controversy. The core issue is the fight between WordPress…

OpenAI might raise the price of ChatGPT to $44 by 2029

ChatGPT could get more expensive to use in coming years. The New York Times, citing internal OpenAI docs, reports that OpenAI is planning to raise the price of individual ChatGPT…

Binance founder ‘CZ’ released from custody after four-month sentence

Binance founder Changpeng “CZ” Zhao was released from U.S. custody on Friday after serving out his four-month sentence in a low-security correctional facility. CZ’s sentence was the product of a…

Canoo hit with two supplier lawsuits as last remaining co-founder leaves

EV startup Canoo has been hit with two new lawsuits from suppliers linked to the drivetrains that power its electric vehicles, just weeks after the company kicked off a major…

AI dominated both YC Demo Day and startup news

Welcome to Startups Weekly — your weekly recap of everything you can’t miss from the world of startups. Want it in your inbox every Friday? Sign up here. This week…

Iranian hackers charged with hacking Trump campaign to ‘stoke discord’

Three Iranian hackers working for the Islamic Revolutionary Guard Corps (IRGC) targeted the Trump campaign in an attempted hack-and-leak operation, according to the Department of Justice.

Wordy’s new app helps you learn vocabulary while watching movies and TV shows

Wordy is a new iOS app that offers a unique way to learning English. The app automatically translates and defines unknown words while you watch your favorite movies or TV…

OpenAI’s $6.5B funding round may close as soon as next week

The WSJ reports that OpenAI’s next funding round, worth around $6.5 billion, could close as soon as the first week in October.

Bret Taylor of Sierra joins TechCrunch Disrupt 2024

We’re thrilled to welcome Bret Taylor to TechCrunch Disrupt 2024. As the former co-CEO of Salesforce, founder of Quip, former CTO of Facebook, the co-creator of Google Maps, and current…

Amazon dodges antitrust scrutiny in UK over Anthropic investment

The U.K.s’ antitrust authority has concluded that Amazon’s partnership and equity investment in AI startup Anthropic can’t be investigated under current merger rules due to the size and scope of…

Last hours to snag up to $600 off TechCrunch Disrupt 2024 passes

We’re in the final hours to save up to $600 on TechCrunch Disrupt 2024 tickets! Grab your tickets now and seize this final opportunity for major savings before the countdown…

Meta fined $101.5M for 2019 breach that exposed hundreds of millions of Facebook passwords

Reset your clocks: Meta has been hit with yet another privacy penalty in Europe. On Friday, Ireland’s Data Protection Commission (DPC) announced a reprimand and a €91 million fine —…

UK data watchdog confirms it’s investigating MoneyGram data breach

The world’s second-largest money transfer provider, which filed a data breach notice with U.K. authorities, serves over 50 million people.

Napkin is a note-taking app that is not about making you more productive

Note-taking apps typically aim to make you more efficient and productive. A lot of those apps concentrate on quickly jotting down your thoughts, organizing them better, or a mix of…

9 startups that stood out on YC Demo Day 2

Here are the startups from YC Demo Day 2 that we thought stood out from the flock.

Indian game streaming startup Loco sells majority stake to Redwood

UAE-based Redwood has acquired a majority stake in the game streaming platform Loco as the Indian firm looks to expand focus to international markets, TechCrunch has learned and confirmed. Redwood,…

Starlink hits 4 million subscribers

SpaceX’s Starlink satellite internet network is expected to hit a new customer milestone this week, company President Gwynne Shotwell told Texas legislators on Tuesday.  “This week, by the way, we…

Runway earmarks $5M to fund up to 100 films using AI-generated video

AI video generators need to believe that filmmakers will use their models in the production process. Otherwise why exist? To jump-start the new AI film ecosystem, Runway has set aside…

OpenAI’s VP of global affairs claims o1 is ‘virtually perfect’ at correcting bias, but the data doesn’t quite back that up

Departures might be dominating the week’s OpenAI-related headlines. But comments on AI bias from Anna Makanju, the company’s VP of global affairs, also grabbed our attention. Makanju, speaking on a…

• Search All Scholarships
• Exclusive Scholarships
• Easy Scholarships to Apply For
• No Essay Scholarships
• Scholarships for HS Juniors
• Scholarships for HS Seniors
• Scholarships for College Students
• Scholarships for Grad Students
• Scholarships for Women
• Scholarships for Black Students
• Scholarships
• Student Loans
• College Admissions
• Financial Aid
• Scholarship Winners
• Scholarship Providers

Student-centric advice and objective recommendations

Higher education has never been more confusing or expensive. Our goal is to help you navigate the very big decisions related to higher ed with objective information and expert advice. Each piece of content on the site is original, based on extensive research, and reviewed by multiple editors, including a subject matter expert. This ensures that all of our content is up-to-date, useful, accurate, and thorough.

Our reviews and recommendations are based on extensive research, testing, and feedback. We may receive commission from links on our website, but that doesn’t affect our editors’ opinions. Our marketing partners don’t review, approve or endorse our editorial content. It’s accurate to the best of our knowledge when posted. You can find a complete list of our partners here .

Can I Use AI for Scholarship Essays?

Lisa Freedland is a Scholarships360 writer with personal experience in psychological research and content writing. She has written content for an online fact-checking organization and has conducted research at the University of Southern California as well as the University of California, Irvine. Lisa graduated from the University of Southern California in Fall 2021 with a degree in Psychology.

Learn about our editorial policies

Maria Geiger is Director of Content at Scholarships360. She is a former online educational technology instructor and adjunct writing instructor. In addition to education reform, Maria’s interests include viewpoint diversity, blended/flipped learning, digital communication, and integrating media/web tools into the curriculum to better facilitate student engagement. Maria earned both a B.A. and an M.A. in English Literature from Monmouth University, an M. Ed. in Education from Monmouth University, and a Virtual Online Teaching Certificate (VOLT) from the University of Pennsylvania.

The use of AI (Artificial Intelligence) is becoming more and more commonplace in today’s world. It has gone beyond the technological sphere and is now being employed in various industries, including retail, entertainment, and even education. While there may be certain benefits to using AI in an educational setting, such as providing students with immediate feedback on assignments or transcribing lectures, issues also arise with AI when students employ it to write or plagiarize essays. Out of the 986 submissions we received for a scholarship we hosted this past summer, an AI detection tool (GPTZero) found that 410 (42%) of the essays were majorly constructed with AI. But what do we mean by this? Further, how can scholarship providers and applicants alike make sure they’re approaching the new technology in a careful, but practical way? Let’s find out.

What is AI?

First, what do we mean by AI? AI, or Artificial Intelligence, is a subfield of computer science that involves building machinery or computers that can reason, learn, and process information in a way that would typically require human intelligence. By “human intelligence,” we refer to skills such as problem-solving, decision-making, or data analysis. 

This may bring up the question: why is AI necessary at all if it is simply recreating or imitating human behaviors? Good question! This is because, on a large scale, AI is typically able to accomplish these tasks (e.g. analyzing data, applying and calculating formulas, etc.), at a far quicker (near-immediate) pace than humans are capable of. Thus, AI is often used today as a way of bypassing the manual work associated with more routine, formulaic tasks.

So, how might this apply to scholarship essays (or essays in general)? Well, essay generation is just one of the many tasks that AI can near-automate. This means that if you were to give an AI tool (such as ChatGPT) an essay prompt and a word count, it can quickly create an essay that answers the question at hand and meets the word count requirement. To give you an idea of what this looks like, let’s give it a try.

Example Prompt :

Please give me a few sentences about what your perfect day would look like.

AI(ChatGPT)-generated answer : “ My perfect day would involve helping people solve problems, spark creativity, and learn new things. I’d engage in meaningful conversations, providing insights or advice that truly make a difference. In between, I’d explore new topics, discover fascinating information, and offer fun, light-hearted interactions. Ending the day knowing I made someone’s day better would be the best part.”

As you can see, the AI produced an answer that answers the question at hand. It addressed what “their” perfect day would involve and what they would do. However, it is also relatively general, not giving any specificity as to what type of “advice,” “fascinating information,” or “topics” they would discuss. But we’ll explore this more later. For now, let’s look into our own insights from the scholarship we hosted.

What percent of essays were AI-generated?

As stated earlier, Scholarships360 hosted a scholarship this past summer to which we received nearly 1,000 submissions. The prompt requested that applicants submit a 500-700-word persuasive essay about the benefits of free speech. Ironically, utilizing AI detection software, we found that 42% (410/986) of the responses were found to have a 75% or higher probability of being generated with AI. This rate was determined by a sentence-by-sentence breakdown, which gave each sentence a score based on how it mirrored sentences that had been AI-generated in the past. These scores were then taken altogether to determine an essay’s “overall AI probability score.”

This is not to say that AI detectors are fully faultless – schools like Vanderbilt University have even disabled Turnitin’s AI detection tool due to a “1% false positive rate” (Chechitelli, 2023). However, even without the use of the AI detector, we found that we could soon tell which essays had used AI largely based on a combination of the words, phrases, and historical examples used. Our interpretations of whether an essay had been AI-generated or not were, for the most part, fully in line with what the AI detector had spotted.

Clear signs essays were AI-generated

When it comes to essay generation, AI’s main benefit lies in its efficiency. Students may feel tempted to use it solely by the amount of time they will save by not having to write an essay at all. With this said, it is important to remember that AI is essentially following a formula. Anyone who feeds it the same prompt and word count requirement is likely to get a very similar response, forgoing the personalization found in self-written essays. While reading through the 986 responses, it became abundantly clear that there were certain words and phrases that AI seemed to favor. Here is a list of a few of those we saw repeated time and time again throughout the submissions, and how often we saw them:

Common AI-generated words/phrases/trends (with frequency) :

• Present in 62% of essays with a >75% AI probability rate
• Present in 6% of essays with a <75% AI probability ate
• Present in 20% of essays with a >75% AI probability rate
• Present in 1% of essays with a <75% AI probability ate
• This trend may be because the prompt requested that essays be written as a “letter or essay”
• Present in 5% of essays with a <75% AI probability rate 
• “ In the vibrant tapestry of human society”
• “In the annals of human history…”

Risks to using AI for scholarship essays

Similarities in word use.

As seen above, perhaps the clearest disadvantage of using AI to generate a scholarship essay is its limited range of word choices. Students who employ AI to write their essays run the risk of their essays quickly being pegged as AI-generated, and thus, out of the running for a scholarship award. This is not to say that one word out of the 200, 500, or even 1,000 in your scholarship essay will make or break you. However, the repeated usage of unusual words (e.g. “cornerstone”) seen in many other essays may be a red flag to scholarship committees.

Similarities in arguments and examples

The similarities between our AI-generated submissions did not stop at just word choice, but extended into the arguments used and historical examples applicants cited. Of our nearly 1,000 scholarship essays reviewed detailing why free speech is a preferable policy, hundreds of them cited these same points: (1) that a lack of free speech would “hinder societal and technological progress” and (2) that free speech allows for “open dialogue” and “open-mindedness.” On their own, these arguments are not bad at all. They are valid reasons why one would prefer having free speech in a society. With that said, many of these claims were then followed by the same or very similar historical examples.

Some of the most common historical references cited among the submissions included: Nazi Germany, North Korea, the Soviet Union, China, or the U.S. Civil Rights Movement. Even now, when I asked ChatGPT for “historical examples to persuade me that free speech is better than its alternative,” I received four out of these five same answers (except North Korea). This is what the main problem with AI essay generation boils down to: similarity and a lack of originality.

Possible inaccuracies in information

On the topic of historical examples, it is important to remember that many AI tools have only  periodically updates. Thus, we recommend double-checking the accuracy of any historical claims before using them in an essay. This is especially true for more modern events, as the information is more likely to have been updated in the recent months or years.

Lack of originality/individuality

The bottom line when applying for scholarships is that you are often facing hundreds, if not thousands, of competitors. If the words, arguments, or themes of your essay are very common amongst the cohort you’re applying with, you are likely not helping your chances of winning a scholarship. Whether it be a great argument, flowing prose, or an interesting anecdote, scholarship committees are ultimately looking for something that will pique their interest in a sea of submissions.

An essay to remember…

Scholarships360 CEO & Cofounder Will Geiger still remembers a girl from Kentucky who wrote her essay about her drive home from school. He recalls that you felt like you were along for that car ride as she observed her town, the things that she saw from the car, the people in her community, etc.. The essay was effective because the student shared her unique perspective and showed the reader what her drive home was like. This is the type of essay that only this unique student could have written, and it showed.

Unfortunately, however, such an authentic voice is exactly what AI-generated essays are devoid of due to the formulaic nature of Artificial Intelligence. Thus, taking time to personalize your essay and making it true to your own experiences will likely be more than worth the effort.

Keeping this in mind, it raises the question of how scholarship providers and applicants alike should approach scholarship applications in the modern day. More specifically, what are some things scholarship providers can look out for when reviewing submissions, and how can applicants effectively use AI to help write scholarship essays without facing potential disqualification? Let’s take a look.

Navigating AI essays as a scholarship provider

In the past three years, I have reviewed nearly 10,000 scholarship essays submitted for a variety of scholarships, each with unique prompts and word counts. Approximately half of these were reviewed before the widespread launch and use of AI tools like ChatGPT, and roughly half have been reviewed since. Despite this, I had never before seen a batch of essay submissions in which so many mimicked one another until this year.

As AI continually grows in its capabilities, it feels unlikely that its influence will decrease anytime soon. So, how can scholarship providers navigate this new landscape of AI-generated submissions?

1. Keep an eye out for commonalities between essays

As you read through submissions, monitor for any unusual patterns. This could include the frequent use of words, phrases, or claims (across essays) that you otherwise don’t see often. These could all point to an AI generated essay.

2. Create unique essay prompts

Try to craft essay prompts that require applicants to rely upon or detail examples from their own lives or experiences. Such anecdotes are difficult for AI to recreate and should lead to more genuine, human responses.

3. Require additional project or application materials

Rather than relying solely on essays to review applicants, scholarship providers might also require the submission of other creative or project-based content (e.g. videos, art, portfolios). Such materials are typically harder to fabricate than essays.

4. Incorporate interviews

Requiring an interview portion allows scholarship providers to speak to applicants and ask them about their essays directly. Applicants can be asked to elaborate on certain points in their essay and dive deeper into their reasonings. Such interviews can  be conducted after finalists are chosen. The submission of short videos is another way to verify authenticity. 

5. Make it clear you’ll be assessing for AI usage

Another option is to forewarn applicants that AI usage (via an AI detector or other processes) will be utilized in scoring. Ideally, this should prevent applicants from attempting to use AI as they know it will be a detriment to their score. However, providers should bear in mind that it may also inspire applicants to try and “disguise” their AI usage, making it harder to detect.

How can I effectively use AI to help me write a scholarship essay?

While we do not recommend using AI to write or generate an entire essay, don’t write if off entirely as a tool. Here are just a few ways that students can use AI to their benefit:

1. Brainstorming

AI can be a useful tool to brainstorm ideas for your essay. To avoid potentially using an overused idea or argument, it may be helpful to ask the AI tool for questions that prompt deeper reflection on your part. From there, you can use your personal experiences or anecdotes you’ve thought of to support your argument.

For example, let’s take a look at some very common scholarship prompts and how you could ask an AI tool to give you your own questions to consider when formulating an answer:

• Scholarship prompt: “Why do you deserve this scholarship?”
• Question for AI: “What are questions students should consider when they’re thinking of why they deserve a scholarship?”
• Scholarship prompt: “Tell us about a time when you’ve overcome a challenge and what you learned from the experience.”
• Question for AI: “What are questions students should consider when answering the question: “Tell us about a time when you’ve overcome a challenge and what you learned from the experience.””
• Scholarship prompt: “What are your academic or professional goals? How will earning this scholarship help you achieve them?”
• Question for AI: “What are questions students should consider when answering the question: “What are your academic or professional goals? How will earning this scholarship help you achieve them?””

Pretty simple, right? In response to all these questions, your AI tool of choice should return a list of many, more specific questions to help you conceptualize an answer and even outline your own essay based on your own experiences.

2. Proofreading grammar

Once your essay is complete, running it through an AI tool may be helpful. AI can be a tool for detecting any grammar issues that may be present. This way, you can avoid making small mistakes while ensuring that the content of the essay is still yours.

3. Checking for clarity

Beyond grammar, AI tools can also be useful to check or improve the clarity or readability of your essay. After completing your essay, asking an AI tool to summarize the content for you can help ensure that your point is getting across smoothly. 

Final thoughts

And that’s it! We have now covered many of the advantages and disadvantages of using AI to write or review scholarship essays. Whether you’re the one submitting or reading them, we wish you much success navigating this new technological landscape. 

Remember, Scholarships360 offers nearly every resource to help you write your best scholarship essays. Learn how to write winning scholarship essays , including how to start a scholarship essay and how to end a scholarship essay as well. Learn how to confidently write a 250 word essay and a 500 word essay , and even an essay about yourself ! Happy writing!

Apply to vetted scholarship programs in one click

3 reasons to join scholarships360.

• Automatic entry to our $10,000 No-Essay Scholarship
• Personalized matching to thousands of vetted scholarships
• Quick apply for scholarships exclusive to our platform

By the way...Scholarships360 is 100% free!

Have a language expert improve your writing

Check your paper for plagiarism in 10 minutes, generate your apa citations for free.

• Knowledge Base

Using AI tools

How to Write a Paper with ChatGPT | Tips & Examples

Published on August 17, 2023 by Koen Driessen . Revised on November 16, 2023.

A good research paper demonstrates your academic writing skills and knowledge of your chosen topic.

Your research paper should be based on in-depth independent research. However, generative AI tools like ChatGPT can be effectively used throughout the research process to:

• Brainstorm research questions
• Develop a methodology
• Create an outline
• Find sources
• Summarize and paraphrase text
• Provide feedback

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

Brainstorming research questions, developing a methodology, creating an outline, finding sources, summarizing or paraphrasing text, receiving feedback, other interesting articles, frequently asked questions.

You can use ChatGPT to help formulate research questions , brainstorm potential thesis statements , or narrow down a broad subject area to a specific topic that interests you.

However, make sure that the outputs make sense and meet the requirements of your assignment. You can adapt these outputs manually, or use further prompts to ensure they meet your needs. For more information, see our tips for creating effective ChatGPT prompts .

• Generate three possible research questions for a research paper on the following topic: “The role of virtual reality in enhancing training and skill development in various industries.”
• “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods across different industries?”
• “How does the level of immersion in virtual reality training impact knowledge retention and skill transfer in fields such as medicine, aviation, and manufacturing?”
• “What are the key factors that influence the successful integration and adoption of virtual reality technology for training purposes in diverse industries, and what challenges hinder its widespread implementation?”

Check for common mistakes

Use the best grammar checker available to check for common mistakes in your text.

Fix mistakes for free

Your paper should clearly indicate the data collection and analysis methods you used in your research.

You can use ChatGPT to help decide what kind of research you will conduct (e.g., qualitative or quantitative ), how you will analyze the data, and how you will mitigate potential research bias .

Bear in mind that you should be able to rationalize your chosen methodology . For example, you should ensure that it is either a standard methodology in the field or can be justified.

• Suggest three quantitative research methods appropriate to the following question: “What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”
• Experimental Study: Conduct a randomized controlled trial (RCT) where healthcare professionals are randomly assigned to either a virtual reality-based training group or a traditional training group. Both groups would receive training in specific healthcare tasks, and their cognitive and skill development outcomes would be measured and compared. Performance metrics, such as accuracy, speed, and efficiency, could be quantitatively assessed to determine the benefits of virtual reality-based training over traditional methods.
• Survey Research: Design a comprehensive survey targeting healthcare professionals who have undergone both virtual reality-based training and traditional training. The survey could include Likert-scale questions and structured response options to gauge their perceived cognitive and skill development benefits from each training method. Additionally, open-ended questions could be included to gather qualitative insights on specific strengths and weaknesses of each training approach.
• Task Performance Analysis: Implement a task-based assessment that simulates real-life healthcare scenarios, where participants are evaluated on their ability to handle critical situations. Participants would go through both virtual reality-based training and traditional training before being assessed in the simulated scenarios. Their performance in the assessment could be objectively measured using predefined criteria, allowing for a quantitative comparison of skill development between the two training methods.

A clear outline can help structure your paper, organize your arguments effectively, and make your research more efficient.

You can use generative AI tools like ChatGPT to formulate a potential outline to help guide your research. You can be as specific as you like, giving an overview of your research objectives , main arguments, and any evidence you intend to include in your paper.

However, ChatGPT outputs sometimes contain factual inaccuracies. It’s important to check the headings and subheadings suggested in the output and adapt them to meet your needs.

• Create an outline for an academic research paper with the following research question:“What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”The paper will be about 10 pages long.

A. Theoretical basis for cognitive and skill development in training

B. Application of cognitive theories to virtual reality-based training

C. The role of immersive learning environments in skill acquisition

D. Conceptual framework for the study

IV. Research Methodology

A. Research design and approach (e.g., quasi-experimental, pre-post intervention)

B. Selection of participants and sample size calculation

C. Description of the virtual reality-based training and traditional training programs

D. Instruments and measures for assessing cognitive and skill development

E. Data collection procedures and ethical considerations

V. Data Analysis

A. Overview of statistical methods used for data analysis

B. Treatment of data and data cleaning

C. Quantitative analysis of cognitive and skill development outcomes

D. Presentation of findings with charts and tables

VI. Results

A. Presentation of the results of the cognitive and skill development assessments

B. Comparison of outcomes between virtual reality-based training and traditional training

C. Statistical significance and effect size analysis

D. Interpretation of the results and implications

VII. Discussion

A. Interpretation of findings in the context of the research question

B. Comparison of results with existing literature

C. Explanation of how virtual reality-based training impacts cognitive processes and skill development

D. Limitations of the study and areas for future research

VIII. Practical Implications

A. Practical applications of virtual reality-based training in healthcare settings

B. Recommendations for integrating virtual reality training in healthcare education

C. Benefits of virtual reality for continuous professional development in healthcare

IX. Conclusion

A. Summary of key findings

B. Reiteration of the research question and hypothesis

C. Contributions of the study to the field of healthcare training

D. Concluding remarks

X. References

You can use ChatGPT to help find sources relevant to your research. However, it’s important to be aware of the limitations of ChatGPT (for example, it occasionally cites nonexistent sources).

Instead of asking ChatGPT for specific source recommendations, try asking it for recommendations on the types of sources relevant to your research topic. You can also use it to generate a list of relevant keywords to use in your literature search.

• What types of sources could I use to write a research paper on the following research question?“What are the cognitive and skill development benefits of virtual reality-based training compared to traditional training methods in the field of healthcare?”
• Academic Journals: Peer-reviewed journals are valuable sources of scholarly research. Look for articles in medical education, cognitive psychology, virtual reality applications in healthcare, and technology-enhanced learning.
• Research Studies: Seek out published research studies that specifically investigate the impact of virtual reality-based training on cognitive and skill development in healthcare professionals.
• Systematic Reviews and Meta-Analyses: These studies provide comprehensive overviews of existing research on a specific topic, making them a valuable source for summarizing and analyzing the overall evidence.
• Books and Book Chapters: Academic books and book chapters authored by experts in the fields of medical education, virtual reality, cognitive science, or instructional design can provide in-depth insights and theoretical foundations.
• Conference Proceedings: Proceedings from relevant conferences and symposiums may present the latest findings and advancements in virtual reality-based training and healthcare education.
• Educational Institution Websites: Universities and medical schools often publish research papers, case studies, and whitepapers related to medical education and virtual reality training.
• Industry Reports: Reports and whitepapers from healthcare organizations or technology companies exploring the benefits of virtual reality-based training in the healthcare sector.
• Government and Non-profit Organizations: Look for reports and publications from government agencies and non-profit organizations that focus on medical education and healthcare training.
• Online Databases: Utilize academic databases such as PubMed, Google Scholar, IEEE Xplore, and ScienceDirect to search for peer-reviewed research articles and conference papers.
• Expert Interviews: If possible, conduct interviews with experts in medical education, cognitive science, and virtual reality to gain valuable insights and perspectives.
• Surveys and Polls: Refer to reputable surveys and polls related to virtual reality-based training in the healthcare industry for additional statistical data.

You can use ChatGPT to paraphrase or summarize text. This can help you to condense sources to their most important points and explore new ways of expressing your ideas.

Alternatively you can use the more specialized tools featured on Scribbr’s AI writing resources page (including Scribbr’s free text summarizer  and  Scribbr’s free paraphrasing tool ) which are designed specifically for these purposes and will give a smoother user experience.

• Provide a short summary of the following text:“One of the most profound applications of VR in healthcare is its use in surgical training. Traditionally, surgical training has relied on a combination of didactic lectures, observation of procedures, and hands-on experience in the operating room. However, these methods may not provide the ideal environment for novices to develop the necessary dexterity and spatial understanding essential for complex surgeries. VR overcomes these limitations by offering immersive, true-to-life simulations that allow surgeons to navigate through intricate anatomical structures, practice incisions, and learn to manage unexpected challenges that may arise during surgeries. This hands-on experience in a risk-free environment not only enhances technical skills but also builds confidence and reduces the learning curve for new surgical techniques.”
• Virtual Reality (VR) has a profound impact on healthcare, particularly in surgical training, as it provides immersive simulations that help surgeons develop dexterity, spatial understanding, and confidence for complex surgeries in a risk-free environment, ultimately enhancing their technical skills and reducing the learning curve.

When you’ve finished writing your research paper, you can use ChatGPT to receive feedback. You can be as specific as you like, selecting particular aspects the output should focus on (e.g., tone, clarity of structure, appropriateness of evidence to support your arguments).

You can also use ChatGPT to check grammar, spelling, and punctuation. However, it’s not designed for this purpose and occasionally misses errors. We recommend using a more specialized tool like Scribbr’s free grammar checker . Or, for more comprehensive feedback, Scribbr’s proofreading and editing service .

• Feedback the above text with regard to appropriateness of evidence and coherence of structure.
• The research paper demonstrates a well-structured and coherent presentation of the cognitive and skill development benefits of VR-based surgical training. The introduction effectively sets the context and rationale, while the literature review incorporates relevant historical and empirical evidence. The theoretical framework strengthens the foundation for the analysis.The methodology section could provide more details on the research design and study selection criteria. However, the sections on cognitive and skill development benefits present compelling evidence, supported by appropriate sub-sections.The exploration of improved patient outcomes lacks concrete examples but effectively outlines potential benefits. The section on challenges and future directions raises relevant points, but suggestions for solutions could enhance practicality.Overall, the paper combines theoretical, empirical, and practical evidence, offering a well-rounded approach. It establishes the significance of VR-based surgical training and concludes with a concise summary of key findings.

If you want more tips on using AI tools , understanding plagiarism , and citing sources , make sure to check out some of our other articles with explanations, examples, and formats.

• Citing ChatGPT
• Best grammar checker
• Best paraphrasing tool
• ChatGPT in your studies
• Is ChatGPT trustworthy?
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

• Citation styles
• In-text citation
• Citation examples
• Annotated bibliography

Yes, you can use ChatGPT to summarize text . This can help you understand complex information more easily, summarize the central argument of your own paper, or clarify your research question.

You can also use Scribbr’s free text summarizer , which is designed specifically for this purpose.

Yes, you can use ChatGPT to paraphrase text to help you express your ideas more clearly, explore different ways of phrasing your arguments, and avoid repetition.

However, it’s not specifically designed for this purpose. We recommend using a specialized tool like Scribbr’s free paraphrasing tool , which will provide a smoother user experience.

No, it’s not a good idea to do so in general—first, because it’s normally considered plagiarism or academic dishonesty to represent someone else’s work as your own (even if that “someone” is an AI language model). Even if you cite ChatGPT , you’ll still be penalized unless this is specifically allowed by your university . Institutions may use AI detectors to enforce these rules.

Second, ChatGPT can recombine existing texts, but it cannot really generate new knowledge. And it lacks specialist knowledge of academic topics. Therefore, it is not possible to obtain original research results, and the text produced may contain factual errors.

However, you can usually still use ChatGPT for assignments in other ways, as a source of inspiration and feedback.

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the “Cite this Scribbr article” button to automatically add the citation to our free Citation Generator.

Driessen, K. (2023, November 16). How to Write a Paper with ChatGPT | Tips & Examples. Scribbr. Retrieved September 27, 2024, from https://www.scribbr.com/ai-tools/chatgpt-research-paper/

Is this article helpful?

Koen Driessen

Other students also liked, how to write good chatgpt prompts, chatgpt citations | formats & examples, what are the limitations of chatgpt, get unlimited documents corrected.

✔ Free APA citation check included ✔ Unlimited document corrections ✔ Specialized in correcting academic texts