how to write essays using chatgpt

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.

How to use ChatGPT for writing

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

Summarizing other works

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

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

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

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

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

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

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

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

Get daily insight, inspiration and deals in your inbox

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

How to use Pixel Studio to make AI images on your Google Pixel 9

I can’t wait for this underrated Apple Intelligence feature no one is talking about

OnePlus Buds Pro 3 review: a huge sonic upgrade from OnePlus' not-to-pricey buds

Most Popular

• 2 Nvidia RTX 4090 graphics card could soon be disappearing off the shelves, paving the way for RTX 5090 launch
• 3 Sonos Arc Ultra soundbar price and images supposedly leak yet again – but this price is lower, mercifully
• 4 iPadOS 18 is bricking some iPad Pro 2024 units, leading Apple to pull the update
• 5 How to use Pixel Studio to make AI images on your Google Pixel 9

• Link to facebook
• Link to linkedin
• Link to twitter
• Link to youtube
• Writing Tips

How to Write Your Essay Using ChatGPT

5-minute read

• 2nd May 2023

It’s tempting, isn’t it? You’ve read about and probably also witnessed how quickly ChatGPT can knock up text, seemingly in any genre or style and of any length, in less time than it takes you to make a cup of tea. However, getting ChatGPT to write your essay for you would be plagiarism . Universities and colleges are alive to the issue, and you may face serious academic penalties if you’re found to have used AI in that way.

So that’s that, right? Not necessarily.

This post is not about how to get ChatGPT to write your essay . It’s about how you can use the tool to help yourself write an essay .

What Is ChatGPT?

Let’s start with the basics. ChatGPT is one of several chatbots that can answer questions in a conversational style, as if the answer were coming from a human. It provides answers based on information it receives in development and in response to prompts you provide.

In that respect, like a human, ChatGPT is limited by the information it has. Where it lacks the information, it has a tendency to fill the gaps regardless . This action is dangerous if you’re relying on the accuracy of the information, and it’s another good reason you should not get ChatGPT to write your essay for you.

How Can You Use ChatGPT to Help With Your Essay?

Forget about the much talked-about writing skills of ChatGPT – writing is your thing here. Instead, think of ChatGPT as your assistant. Here are some ideas for how you can make it work for you.

Essay Prompts

If your task is to come up with your own essay topic but you find yourself staring at a blank page, you can use ChatGPT for inspiration. Your prompt could look something like this:

ChatGPT can offer several ideas. The choice of which one to write about (and you may, of course, still come up with one of your own) will be up to you, based on what interests you and the topic’s potential for in-depth analysis.

Essay Outlines

Having decided on your essay topic – or perhaps you’ve already been given one by your instructor – you may be struggling to figure out how to structure the essay. You can use ChatGPT to suggest an outline. Your prompt can be along these lines:

Just as you should not use ChatGPT to write an essay for you, you should not use it to research one – that’s your job.

If, however, you’re struggling to understand a particular extract, you can ask ChatGPT to summarize it or explain it in simpler terms.

Find this useful?

Subscribe to our newsletter and get writing tips from our editors straight to your inbox.

That said, you can’t rely on ChatGPT to be factually accurate in the information it provides, even when you think the information would be in its database, as we discovered in another post. Indeed, when we asked ChatGPT whether we should fact-check its information, the response was:

An appropriate use of ChatGPT for research would be to ask for academic resources for further reading on a particular topic. The advantage of doing this is that, in going on to locate and read the suggested resources, you will have checked that they exist and that the content is relevant and accurately set out in your essay.

Instead of researching the topic as a whole, you could use ChatGPT to generate suggestions for the occasional snippet of information, like this:

Before deciding which of its suggestions – if any – to include, you should ask ChatGPT for the source of the fact or statistic so you can check it and provide the necessary citation.

Referencing

Even reading the word above has probably made you groan. As if writing the essay isn’t hard enough, you then have to not only list all the sources you used, but also make sure that you’ve formatted them in a particular style. Here’s where you can use ChatGPT. We have a separate post dealing specifically with this topic, but in brief, you can ask something like this:

Where information is missing, as in the example above, ChatGPT will likely fill in the gaps. In such cases, you’ll have to ensure that the information it fills in is correct.

Proofreading

After finishing the writing and referencing, you’d be well advised to proofread your work, but you’re not always the best person to do so – you’d be tired and would likely read only what you expect to see. At least as a first step, you can copy and paste your essay into ChatGPT and ask it something like this:

You’ve got the message that you can’t just ask ChatGPT to write your essay, right? But in some areas, ChatGPT can help you write your essay, providing, as with any tool, you use it carefully and are alert to the risks.

We should point out that universities and colleges have different attitudes toward using AI – including whether you need to cite its use in your reference list – so always check what’s acceptable.

After using ChatGPT to help with your work, you can always ask our experts to look over it to check your references and/or improve your grammar, spelling, and tone. We’re available 24/7, and you can even try our services for free .

Share this article:

Post A New Comment

Got content that needs a quick turnaround? Let us polish your work. Explore our editorial business services.

Free email newsletter template.

Promoting a brand means sharing valuable insights to connect more deeply with your audience, and...

6-minute read

How to Write a Nonprofit Grant Proposal

If you’re seeking funding to support your charitable endeavors as a nonprofit organization, you’ll need...

9-minute read

How to Use Infographics to Boost Your Presentation

Is your content getting noticed? Capturing and maintaining an audience’s attention is a challenge when...

8-minute read

Why Interactive PDFs Are Better for Engagement

Are you looking to enhance engagement and captivate your audience through your professional documents? Interactive...

7-minute read

Seven Key Strategies for Voice Search Optimization

Voice search optimization is rapidly shaping the digital landscape, requiring content professionals to adapt their...

4-minute read

Five Creative Ways to Showcase Your Digital Portfolio

Are you a creative freelancer looking to make a lasting impression on potential clients or...

Make sure your writing is the best it can be with our expert English proofreading and editing.

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

• The Big Story
• Newsletters
• Steven Levy's Plaintext Column
• WIRED Classics from the Archive
• WIRED Insider
• WIRED Consulting

5 Ways ChatGPT Can Improve, Not Replace, Your Writing

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

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

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

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

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

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

ChatGPT is never short of ideas.

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

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

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

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

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

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

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

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

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

Get your names right with ChatGPT.

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

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

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

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

You Might Also Like …

In your inbox: The best and weirdest stories from WIRED’s archive

Elon Musk is a national security risk

Interview: Meredith Whittaker is out to prove capitalism wrong

How do you solve a problem like Polestar ?

Event: Join us for The Big Interview on December 3 in San Francisco

WIRED COUPONS

Turbo Tax Live Assisted - 10% off

H&R Block Coupons & Offers

Enjoy $15 Off Your Orders With Instacart Coupon

Dyson Airwrap deal: Free $60 Case + $40 Gift

Get Up To An Extra 45% Off September Sale

Vista Print Coupon Code: 20% Off Select Signage

• 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 52,117 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

How to Use ChatGPT for Research and Essays

Your changes have been saved

Email is sent

Email has already been sent

Please verify your email address.

You’ve reached your account maximum for followed topics.

For better or worse, OpenAI’s ChatGPT has become a big part of our lives. It’s become integral to gathering information, researching topics, and creating written works. And frankly, not using it might put you at a disadvantage academically.

However, this AI is not flawless; there is a method to use it to help with your essays and research. Using it the right way will help you avoid plagiarism issues or inaccurate information. Here, we’ll show you how to use ChatGPT to write an essay ethically, so it comes out as a quality, factual, and original piece.

1. Draw Your Outline Without ChatGPT

Assuming you already have an idea for your project, the first thing you should do before you hop on ChatGPT’s website is to prepare your thesis and outline without using AI. It’s a vital step to making sure the core of your essay actually comes from you.

If you use ChatGPT to prompt an outline for you, it could promote idea laziness, and you will find ChatGPT’s suggestions may have replaced the ones you could have produced on your own. So, get a piece of paper or a blank word processor page and create an outline for your essay.

Also, ChatGPT will avoid controversial topics—even in an outline. Therefore, you might find yourself with an outline missing vital pieces of historical sections if you rely on it. This bias is one of the major problems with OpenAI’s ChatGPT .

2. Prompt ChatGPT to Draw a Parallel Outline

Before you begin this section, if this is your first time using ChatGPT, you should read our guide on how to use ChatGPT . It will help you with creating an account and defining its capabilities. Once that’s out of the way, you can move on to the next step.

Now that you have an original outline, it doesn’t matter how basic it looks; you can use ChatGPT to create another outline. Craft a prompt with this template:

ChatGPT’s result is far more detailed than our outline. Here, you should adopt the parts of ChatGPT’s outline you would like to integrate into your own. Combine the best of the two and flesh out an outline that will guide you best as you write.

3. Create a ChatGPT Prompt for Each Section

Now that you have an outline with sections, you can begin to hack away at it section by section. Start with your introduction, where you will include your thesis statement. Ask ChatGPT to create multiple thesis statements on your idea, and choose the one that best encapsulates the major point you’re trying to communicate in your essay.

You can do something similar for all the other sections as well. Tell the AI to generate written pieces on your section topics. Don’t forget to add that it communicates the point in the tone you want. In most cases, essays should sound academic. Therefore, our prompt for each section looked like this:

Do not just copy and paste the information it generates; the next step is a vital second part of this methodology.

4. Confirm the Information With a Reputable Source

As you begin to write, you must check if the information you’re getting from ChatGPT is indeed correct. You must do this because ChatGPT occasionally hallucinates , coming up with its own facts and making up sources when you ask it to direct you to where it got its information. In some cases, it blatantly refuses to tell you at all where it got its data.

The free version of ChatGPT is not actively connected to the internet and cannot fetch information after September 2021. If you need this functionality, then it could be time to upgrade to ChatGPT Plus —especially if this is a tool you will be using heavily for work or school.

The bottom line is that you should use a reputable source (such as a book from an authority or an official website) to support every important statement you put down. You can also learn how to use Google to fact-check information .

5. Use ChatGPT for Examples and Breakdowns

It’s counterproductive to write about ideas that you don’t even understand yourself. When you reach a part of your essay that you don’t properly understand, you should go to ChatGPT and have it broken down for you.

That’s really the one thing you can count on ChatGPT to do in this process. It has good skill in crafting useful examples and explaining complicated ideas in a form you can easily understand. A popular way of phrasing a prompt to make ChatGPT explain something complicated is adding “explain like I’m five” to your prompt.

Here we used ChatGPT to break down hip and elbow dysplasia conditions in a way that is easier to understand. And it used analogies like jigsaw puzzles to paint a clearer image of what it might look like.

6. Write the Essay Yourself

As we’ve stated earlier, under no condition should you ask ChatGPT to write your whole essay for you. Not only is that lazy and deceitful, but it could also open you up to plagiarism and submitting incorrect information.

Ensure that every line in your essay is typed with your hands. Besides, if you’re writing an academic essay where you must cite sources, you will still need to corroborate all the points you’ve made with a corresponding authority. That means you’ll have to go and fact-check everything ChatGPT has written and find a corroborating source.

This could even take more time than just writing it yourself because the AI could have hallucinated some of its facts, leading you on a wild goose chase as you try to find a citation for something that doesn’t exist.

Lastly, ChatGPT doesn’t match the nuanced knowledge of a human professional in heavily specialized fields or journals that need up-to-date information. Reading a book or article by an expert, internalizing it, and writing it in your own words will give you far better results than relying on ChatGPT.

7. Polish the Style and Citation With ChatGPT

After writing, you can paste portions of your essay and ask ChatGPT to shorten, lengthen, or optimize the style. ChatGPT is good at mimicking popular styles, and you can use that to your advantage. If you want your writing to sound a little more professional, it can help rephrase it.

If you’re having trouble with citation styles and how to integrate them into your essay, you can present your essay to ChatGPT, give it your sources, and ask it to weld them together for you.

ChatGPT Is a Tool, Not a Solution

You can’t “ChatGPT” away academic or professional work; you must use it the same way you would use a tool. Take a calculator, for instance; it doesn’t replace the mathematician but improves the mathematician. You should use ChatGPT the same way a mathematician will use a calculator: for the boring, repetitive, rote work.

Let the ideas and story come from you and your experiences. And if you want to keep using ChatGPT as a student, make sure you know what you shouldn't do.

• Artificial Intelligence

• 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

How to Grade Essays with ChatGPT

Introduction.

The rise of large language models (LLMs) like OpenAI’s ChatGPT has opened exciting possibilities in essay grading. With its advanced natural language processing capabilities, ChatGPT offers a new dimension in assessing written work, potentially revolutionizing the grading process for educators and researchers. Let’s delve into how ChatGPT could potentially make essay grading easier, more efficient, and more accurate.

ChatGPT can analyze written content for various parameters, including content quality, argument structure, coherence, and adherence to guidelines. Whether you use a continuous scoring system (e.g., quality of writing) or a discrete one (e.g., essay positions), ChatGPT can be tailored to your specific needs, offering customized feedback for different writing styles and assignments. Literature also suggests that LLMs can significantly increase grading efficiency, alleviating some of the burden on educators (Abedi et al., 2023; Okonkwo & Ade-Ibijola, 2021; Richter et al., 2019). Imagine grading hundreds of essays and providing feedback on them – a time-consuming and tiring task. ChatGPT can automate the initial assessment, flagging essays that require further attention based on specific criteria. Additionally, ChatGPT can identify stylistic strengths and weaknesses, analyze the use of literary devices, and even point out potential inconsistencies in an argument’s logic. This could free up valuable educator time for student interaction and curriculum development.

However, caution against over-reliance on this new technology is adivsed in scenarios where biased or inaccurate models could unfairly impact individual students. It is essential to recognize both the potential advantages and limitations of LLMs. This blog post aims to delve into and reflect on ChatGPT’s capabilities for grading and classifying essays and to provide insights into the practical application of using ChatGPT in educational settings.

In this blog, we will explore:

• Essay grading with ChatGPT and ChatGPT API
• Steps for essay grading with ChatGPT API
• Steps for essay classification with ChatGPT API
• Cost & computation times

For steps 2 and 3, we will provide detailed instructions on how to access and set up the ChatGPT API, prepare and upload your text dataset, and efficiently grade or classify numerous essays. Additionally, we will compare the outcomes of human grading to those obtained through GPT grading.

## Essay Grading with ChatGPT and ChatGPT API

For a single essay, we can simply ask ChatGPT to grade as follows:

For multiple essays, we could request ChatGPT to grade each one individually. However, when dealing with a large number of essays (e.g., 50, 100, 1000, etc.), manually grading them in this way becomes a laborious and time-consuming task. In such cases, we can leverage the ChatGPT API service to evaluate numerous essays at once, providing greater flexibility and efficiency. ChatGPT API is a versatile tool that enables developers to integrate ChatGPT into their own applications, services, or websites. When you use the API, you also gain more control over the interaction, such as the ability to adjust temperature, maximum tokens, and the presence of system messages.

It is important to understand the distinctions between ChatGPT’s web interface and the pretrained models accessible through the OpenAI API .

ChatGPT’s web version provides a user-friendly chat interface, requiring no coding knowledge and offering features like integrated system tools. However, it is less customizable and is not designed for managing high volumes of requests. Additionally, due to its internal short-term memory span, previous conversations can influence later responses. In contrast, the OpenAI API offers pretrained models without a built-in interface, necessitating coding experience for integration. These models excel at managing large request volumes, but lack ChatGPT’s conversational memory; they process each input independently. This fundamental difference can lead to variations in the outputs generated by ChatGPT’s web interface and the OpenAI API.

Here’s an example of grading a single essay using the ChatAPI with Python:

Interestingly, this example produces a single score rather than the sentence generated above via the ChatGPT web interface. This difference could be attributed to the ChatGPT API interpreting the prompt more directly than the ChatGPT online service, even though they both use the same pretrained model. Alternatively, the variability in ChatGPT’s results might be due to inherent randomness in its responses.

By implementing a loop with multiple texts, we can acquire scores for an entire set of essays. Let’s see how to do that.

Steps for Essay Grading with ChatGPT API

Get and set up a chatgpt api key.

We assume that you have already installed the Python OpenAI library on your system and have an active OpenAI account. Setting up and obtaining access to the ChatGPT API involves the following steps:

Obtain an OpenAI key: Vist the OpenAI API website at https://platform.openai.com/api-keys and click +Create a new secret key button. Save your key securely, as you cannot regenerate the same code due to OpenAI’s security policies.

Set ip API key: In your Python script or notebook, set up the API key using the following code, replacing “YOUR-API-KEY” with your actual API key:

Load the text dataset

In this post, we will grade a series of essays about the iPad usage in schools

Score the multiple essays

Grading 50 essays takes only 25 seconds.

Compare human grading scores with GPT grading scores

For these data, we happend to have scores given by human raters as well, allowing us how similar the human scores are to the scores generated by ChatGPT.

Using the code provided in the accompanying script, we get the following:

A contigency table (confusion matrix) of the scores is:

The averages and standard deviations of human grading and GPT grading scores are 2.54 ( SD = 1.68) and 2.34 ( SD = 0.74), respectively. The correlation between them is 0.62, indicating a fairly strong positive linear relationship. Additionally, the Root Mean Squared Error (RMSE) is 1.36, providing a measure of the GPT’s prediction accuracy compared to the actual human grading scores.

Steps for Essay Classification with ChatGPT API

ChatGPT can be utilized not only for scoring essays but also for classifying essays based on some categorical variable such as writers’ opinions regarding iPad usage in schools. Here are the steps to guide you through the process, assuming you already have access to the ChatGPT API and have loaded your text dataset:

Classify multiple essays

Classifying 50 essays takes only 27 seconds.

We create a new column re_Stance_iPad based on the mapping of values from the existing Stance_iPad column. Except for AFF and NEG opinions, opinions on AMB, BAL, and NAR are unclear. Therefore, AMB, BAL, and NAR are combined as OTHER.

Compare human classification with GPT classification

ChatGPT achieves an accuracy of approximately 84%, demonstrating its correctness in classification. An F1 score of 0.84, reflecting the harmonic mean of precision and recall, signifies a well-balanced performance in terms of both precision and recall. Additionally, the Cohen’s Kappa value of 0.71, which measures the agreement between predicted and actual classifications while accounting for chance, indicates substantial agreement beyond what would be expected by chance alone.

Cost & Computation times

How long does it take to assess all essays.

Grading and classifying 50 essays each took 25 and 27 seconds , resulting in a rate of about 2 essays per second.

What is the cost of assessing all essays?

In this blog, we utilized GPT-3.5-turbo-0125. According to OpenAI’s pricing page , the cost for input processing is $0.0005 per 1,000 tokens, and for output, it is $0.0015 per 1,000 tokens, indicating that the ChatGPT API charges for both tokens sent out and tokens received.

The total expenditure for grading all essays —50 assessing essay quality and 50 for essay classification—was approximately $0.01 .

What are tokens and how to count them?

Tokens can be viewed as fragments of words. When the API receives prompts, it breaks down the input into tokens. These divisions do not always align with the beginning or end of words; tokens may include spaces and even parts of words. To grasp the concept of tokens and their length equivalencies better, here are some helpful rules of thumb:

• 1 token ≈ 4 characters in English.
• 1 token ≈ ¾ of a word.
• 100 tokens ≈ 75 words.
• 1 to 2 sentences ≈ 30 tokens.
• 1 paragraph ≈ 100 tokens.
• 1,500 words ≈ 2,048 tokens.

To get additional context on how tokens are counted, consider this:

The prompt at the beginning of this blog, requesting that OpenAI grade an essay, contains 129 tokens, and the output contains 12 tokens.

The input cost is $0.0000645, and the output cost is $0.000018.

ChatGPT provides an alternative approach to essay grading. This post has delved into the practical application of ChatGPT’s natural language processing capabilities, demonstrating how it can be used for efficient and accurate essay grading, with a comparison to human grading. The flexibility of ChatGPT is particularly evident when handling large volumes of essays, making it a viable alternative tool for educators and researchers. By employing the ChatGPT API key service, the grading process becomes not only streamlined but also adaptable to varying scales, from individual essays to hundreds or even thousands.

This technology has the potential to significantly enhance the efficiency of the grading process. By automating the assessment of written work, teachers and researchers can devote more time to other critical aspects of education. However, it’s important to acknowledge the limitations of current LLMs in this context. While they can assist in grading, relying solely on LLMs for final grades could be problematic, especially if LLMs are biased or inaccurate. Such scenarios could lead to unfair outcomes for individual students, highlighting the need for human oversight in the grading process. For large scale research, where we look at always across many essays, this is less of a concern (see e.g., Mozer et al., 2023)

The guide in this blog has provided a step-by-step walkthrough of setting up and accessing the ChatGPT API essay grading.

We also explored the reliability of ChatGPT’s grading, as compared to human grading. The moderate positive correlation of 0.62 attests to same consistency between human grading and ChatGPT’s evaluations. The classification results reveal that the model achieves an accuracy of approximately 84%, and the Cohen’s Kappa value of 0.71 indicates substantial agreement beyond what would be expected by chance alone. See the related study (Kim et al., 2024) for more on this.

In essence, this comprehensive guide underscores the transformative potential of ChatGPT in essay grading, presenting it as a valuable approach in the ever-evolving educational fields. This post gives an overview; we next dig in a bit more, thinking about prompt engineering + providing examples to improve accuracy.

Writer’s Comments

The api experience: a blend of ease and challenge.

Starting your journey with the ChatGPT API will be surprisingly smooth, especially if you have some Python experience. Copying and pasting code from this blog, followed by acquiring your own ChatGPT API and tweaking prompts and datasets, might seem like a breeze. However, this simplicity masks the underlying complexity. Bumps along the road are inevitable, reminding us that “mostly” easy does not mean entirely challenge-free.

The biggest hurdle you will likely face is mastering the art of crafting effective prompts. While ChatGPT’s responses are impressive, they can also be unpredictably variable. Conducting multiple pilot runs with 5-10 essays is crucial. Experimenting with diverse prompts on the same essays can act as a stepping stone, refining your approach and building confidence for wider application.

When things click, the benefits are undeniable. Automating the grading process with ChatGPT can save considerable time. Human graders, myself included, can struggle with maintaining consistent standards across a mountain of essays. ChatGPT, on the other hand, might be more stable when grading large batches in a row.

It is crucial to acknowledge that this method is not a magic bullet. Continuous scoring is not quite there yet, and limitations still exist. But the good news is that LLMs like ChatGPT are constantly improving, and new options are emerging.

Overall Reflections: A Journey of Discovery

The exploration of the ChatGPT API can be a blend of innovation, learning, and the occasional frustration. While AI grading systems like ChatGPT are not perfect, their ability to save time and provide consistent grading scheme makes them an intriguing addition to the educational toolkit. As we explore and refine these tools, the horizon for their application in educational settings seems ever-expanding, offering a glimpse into a future where AI and human educators work together to enhance the learning experience. Who knows, maybe AI will become a valuable partner in the grading process in the future!

Call to Action

Have you experimented with using ChatGPT for grading? Share your experiences and questions in the comments below! We can all learn from each other as we explore the potential of AI in education.

• Abedi, M., Alshybani, I., Shahadat, M. R. B., & Murillo, M. (2023). Beyond Traditional Teaching: The Potential of Large Language Models and Chatbots in Graduate Engineering Education. Qeios. https://doi.org/10.32388/MD04B0
• Kim, Y., Mozer, R., Miratrix, L., & Al-Ademi, S. (2024). ChatGPT vs. Machine Learning: Assessing the Efficacy and Accuracy of Large Language Models for Automated Essay Scoring (in preparation).
• Okonkwo, C. W., & Ade-Ibijola, A. (2021). Chatbots applications in education: A systematic review. Computers and Education: Artificial Intelligence, 2, 100033. https://doi.org/10.1016/j.caeai.2021.100033
• Pricing . (n.d.). OpenAI. Retrieved March 2, 2024, from https://openai.com/pricing#language-models
• Mozer, R., Miratrix, L., Relyea, J. E., & Kim, J. S. (2023). Combining Human and Automated Scoring Methods in Experimental Assessments of Writing: A Case Study Tutorial. Journal of Educational and Behavioral Statistics, 10769986231207886. https://doi.org/10.3102/10769986231207886
• Zawacki-Richter, O., Marín, V. I., Bond, M., & Gouverneur, F. (2019). Systematic review of research on artificial intelligence applications in higher education–where are the educators?. International Journal of Educational Technology in Higher Education, 16(1), 1-27. https://doi.org/10.1186/s41239-019-0171-0

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

26k Accesses

44 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

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

L2 writer engagement with automated written corrective feedback provided by ChatGPT: A mixed-method multiple case study

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)

User satisfaction with the service quality of ChatGPT

• Kim Shin Young
• Sang-Gun Lee
• Ga Youn Hong

Service Business (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.

7 advanced ChatGPT prompt-writing tips you need to know

We've discussed how to issue effective prompts in previous articles here on ZDNET.

Special Feature

The intersection of generative ai and engineering.

The surge of generative AI can harness tremendous potential for the engineering realm. It can also come with its challenges, as enterprises and engineers alike figure out the impact of AI on their roles, business strategies, data, solutions, and product development. What does the future roadmap look like for bringing generative AI into the software fold? ZDNET decodes from all angles.

In this article, we're going to take it up a level and look at more advanced AI prompting techniques. 

We have seven very interesting approaches that will give you a much better handle on how to communicate with ChatGPT and other generative AI tools.

Also:  6 skills you need to become an AI prompt engineer

Here's how to level up your ChatGPT usage .

1. Specify output format

When you ask a question or give an assignment to ChatGPT , you can specify how it formats the reply. Imagine that you're giving an assignment to a student, where you might specify how the assignment is to be formatted when it's turned in. Here are a few examples.

What are the longest highways in the United States? List only the top four in the form of a bullet list.

Present that information in a table.

2. Tell it to format in HTML

You can specify a lot about how the results are displayed. For example, you can have it generate a table that you can incorporate into a web page.

What are the longest highways in the United States? List only the top four. Present the results as HTML.

You can make that HTML code bigger by clicking the square in the upper-right corner of the screenshot. 

Also: The 10 best ChatGPT plugins (and how to make the most of them)

Here's where it gets interesting. You can also have the information presented using whatever style of HTML you like. There's a school of web design that doesn't like the traditional table tags, and prefers to present tables in the form of CSS -- and here's that version.

Present that information, but use CSS instead of table tags

3. Iterate with multiple attempts

You often need to work with the AI to help it get to the result you want. Take our previous CSS result. Here's what it looks like:

Unfortunately, that's not as pretty as I'd like. Let's see if we can remedy it.

Redo that, but please make sure the columns are all aligned. Make the headings a darker blue with white lettering presented in all capitals and bold. Make each data row a light gray, but vary the levels of gray so row 1 is light gray, row 2 is slightly darker, row 3 is light gray, and so on. Make sure the highway name is presented in bold.

I'm not going to include the generated code, because it's long. But we're getting closer:

Let's try again.

That output looks really good, but the columns are still not aligned. Make sure the columns are wide enough to accommodate the text without wrapping, left align everything, and make sure all the columns (including the headings) are perfectly aligned.

It's almost exactly what we're looking for, but the route is wrapping. Let's see if we can fix that.

That's almost exactly what I want, but the route is wrapping. Please make sure the route data doesn't wrap either. Keep each line of data on exactly one line.

Don't ever assume prompting is easy. But if you've ever taught programming to humans, this is exactly the sort of result you get back. It sometimes seems like they're being passive-aggressive, but it's more likely that you didn't specify your requirements carefully enough.

4. Don't be afraid to use long prompts or sets of prompts

It took quite a few iterations to put together a prompt that reliably generated highway information in the format I wanted. One key approach is to make sure your prompt is very specific, but also extensive enough to have enough information for the large language model to fully understand what you're asking.

Also: Microsoft unveils first professional certificate for generative AI skills

You may also need to modify your specification. I wound up removing the line:

Create a table that uses only CSS to format the rows, columns, and cells. Do not use HTML table tags.

Instead, I just told it how I wanted the table to look and let it decide how to implement it. Here's my full, rather long prompt:

I wrote that prompt in Sublime Text , a text editor, and then pasted it into ChatGPT. Here's the result, which is exactly what I wanted.

As you can see, it chose to add a title, which was fine. But now that I have a working prompt, I can add some additional tweaks. For example, I went back and modified the columns specifier:

Create columns for the index number (label this "#"), highway name, length, and route

I tried changing "Limit your answer to only the top four" to "Limit your answer to only the top 20", but the AI refused to fill in all the data for all 20. So, I removed that line entirely and added a new line at the very end of the prompt:

For the purpose of this project, please provide full data results for the top 20 highways.

This actually resulted in a partial HTML output. I had to tell the AI to continue, at which point it spit out the rest of the HTML, resulting in this:

5. Provide explicit constraints to a response

You just saw how I modified some response constraints for the number of answers and the columns I wanted presented. But you can use constraints for more open-ended questions as well.

Also: Human or bot? This Turing test game puts your AI-spotting skills to the test

There are limits to this type of prompt. Take this example:

Provide a summary of the key events in World War II as reported by major newspapers of the time.

Because the model wasn't trained on newspapers from World War II, it's unable to answer the question (although it does take a guess).

Likewise, you can't specify any results from "the last few years" since the model's data entry ends in 2021. That said, you can specify data that's within the scope of the model, like this:

List major space missions between 2010 and 2020

Note that we're limiting by date. But we can add further constraints. Let's limit the data to just missions from the U.S.:

List major space missions conducted by NASA between 2010 and 2020

You can also go back to the formatting approach we discussed and do something like this:

List all major space missions conducted between 2010 and 2020. Group them by nation and space agency. Make the name of the nation and space agency bold.

And you can get even more explicit. Here we include continents and specify that any continents without missions be excluded from the list.

List all major space missions conducted between 2010 and 2020. Group them by continent. Make the name of the continent bold and all capital letters. Make the nation and space agency name bold, with either title case or all caps if that's how the space agency formats its name (like NASA). If a continent did not have a space mission, do not include it on this list.

Interestingly, the AI decided to have a bit of a hallucinatory moment. It properly listed the missions and continents, but decided Russia was a continent. I ran the prompt in a second session, and that time it did not think Russia was a continent.

6. Tell it number of words, sentences, characters

Speaking of constraints, you may have noticed that ChatGPT tends not to be accurate when it comes to word count. If you tell it to limit its answer to 50 words, it sometimes goes long or short. That's because the language model works in tokens (representations of data) that do not directly correspond to individual words.

Also:   This AI chatbot sums up PDFs and answers your questions about them

For example, when I told ChatGPT to "Summarize the Game of Thrones TV show", I got back 294 words over six paragraphs. But you can try to limit the response. Try out a variety of limiting terms until you determine what works best for you. For example:

Summarize the Game of Thrones TV series in 50 words  Summarize the Game of Thrones TV series in 2 sentences  Summarize the Game of Thrones TV series in less than 200 characters  Summarize the Game of Thrones TV series so it will fit in a tweet

Here's another place to keep in mind the restrictions of the AI model. ChatGPT contains no training data after 2021. At that time, a tweet was limited to 280 characters. But as of February 2023, Twitter Blue (now X Premium) subscribers can have tweets as long as 4,000 characters. Telling ChatGPT to fit something in a tweet tells it to limit the response to 280 characters, because that was the sole limit back in its day.

7. Give the AI the opportunity to evaluate its answers

As we've discussed, the AI often hallucinates, providing very wrong answers. It is possible to construct conversations with the AI to arrive at more precise answers, by letting it provide intermediate conclusions. Take this simple request:

Word similar to devolve that begins with a B

As difficult as it might be to imagine, ChatGPT reliably fails with this request, often answering decay, degrade, degenerate, and other words that begin with a "D".

There are a couple of challenges with this deceptively simple prompt. First, "devolve" has multiple meanings. It can mean transfer or delegate, deteriorate or decline, or inherit or receive by succession. To get a proper answer, we need to be more specific and give the AI the general meaning we want it to pursue. It also doesn't hurt to help it determine meaning by telling it we're looking for a verb, rather than a noun.

Generate a verb that starts with the letter "B" and has a similar meaning to "devolve," specifically indicating the idea of something deteriorating or getting worse.

The problem is that ChatGPT has a very difficult time (again, due to how it represents knowledge in tokens) of determining the first letter of a word. So, it's best to give the AI time to figure that out.

Determine the first letter of the generated verb

This period is what AI experts call "giving it time to breathe". Rather than just rushing out with its first answer, this approach gives the AI time to consider whether its answer is correct.

Also:   The best AI art generators

Because the AI may not come up with the right answer the first time, ask it to repeat the steps until it does:

And here, it works its way through until it finds an answer:

Notice how it took the AI six tries before it found the right word, even though the criteria existed for the entire sequence. The second double-check "breathe" gave it the opportunity to evaluate its answer and continue until it succeeded.

Bonus tip: Access current web info

If you want to access information after 2021, you can do so by using ChatGPT Plus and the WebPilot plugin. ChatGPT Plus isn't free, but for $20/month, the service can provide some considerable added value. Here are a few articles I've written that detail how WebPilot can substantially expand your prompt:

• My two favorite ChatGPT Plus plugins and the remarkable things I can do with them
• ChatGPT's new web-browsing feature is a big disappointment. Use this plugin instead
• I needed a mechanic. Here's how ChatGPT Plus helped me skip reading online reviews

Final thoughts

One thing that's really important to note is that the AI won't necessarily do what you want right out of the gate. On the example using "devolve" above, it took me almost two hours and about 20 tries to find the formula that actually worked for the AI to reliably generate a result.

Also:   How I used ChatGPT and AI art tools to launch my Etsy business fast

While we're at it, keep in mind that the AI remembers what went on in the current session. So, while it might give you the right answer in the current session, the acid test is copying your prompt to a brand-new session and seeing if it works there.

Stay tuned, because not only will I be back with more advanced prompt tips, I'll also be doing some deeper dives into individual prompting problem solvers.

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

6 ways to write better ChatGPT prompts - and get the results you want faster

6 ai features iphone users can expect first on ios 18 (and what's coming later), 11 hidden windows touchpad tricks power users need to know.

GIT Learning Conference

ChatGPT for Academic Writing: Pros and Cons

Introduction

Modern technologies are increasingly penetrating the academic environment, becoming indispensable tools for students and researchers. Artificial intelligence (AI) has found widespread use, assisting in a range of tasks, including the preparation of academic papers, such as theses. However, it’s essential to understand how to utilize these technologies properly to ensure they serve as helpful assistants rather than sources of errors. In this article, we will explore how to effectively use AI, particularly ChatGPT, when working on diploma projects.

ChatGPT for Academic Writing

ChatGPT is an advanced AI language model developed by OpenAI, capable of generating human-like text based on the input it receives. With its deep learning capabilities, ChatGPT can help users with various writing tasks, ranging from content creation and summarization to brainstorming ideas. For academic writing, it can be a powerful tool to aid in drafting, organizing information, and even generating references. However, as with any technology, there are both benefits and limitations to using ChatGPT for academic purposes.

What ChatGPT can do for Academic Writing:

• Content Drafting: Provides coherent text structures for essays and reports.
• Summarization: Helps in condensing large pieces of academic material.
• Idea Generation: Supports brainstorming for research topics and thesis statements.

While these capabilities can provide support in academic writing, students should remain aware of its limitations.

The Cons of Using ChatGPT

Limited critical analysis skills.

One significant drawback of ChatGPT is its inability to perform deep critical analysis. Academic writing often requires nuanced interpretation and synthesis of ideas, which ChatGPT lacks the capacity to do effectively. It can process and reproduce existing information, but it cannot form original, critical arguments, a key component of high-level academic work.

Linguistic Errors and Unnatural Phrasing in German

While ChatGPT is trained in multiple languages, including German, it can still generate awkward or grammatically incorrect sentences, particularly when dealing with complex academic language. This may lead to errors in papers that require formal and precise communication. The use of AI-generated text in non-native languages may require significant post-editing to achieve clarity and fluency.

Information Distortion

Another downside is the potential for ChatGPT to distort facts or misunderstand the context of the information it is processing. Since it generates text based on patterns learned from vast datasets, the output can sometimes be inaccurate or misleading. This poses a risk for students relying on the tool for factual correctness in academic assignments.

Fabrication of Non-existent Sources

ChatGPT occasionally generates sources that don’t exist, which can cause significant problems when submitting academic work. Students need to manually verify every reference the AI provides to ensure it is real and accurate. Relying on fabricated sources can damage the credibility of the work and lead to penalties for academic misconduct.

Risk of Plagiarism

Although ChatGPT is capable of generating unique content, its reliance on existing data raises concerns about plagiarism. There’s always a risk that the generated content may resemble existing works too closely. Submitting AI-generated content without thorough originality checks can lead to unintentional plagiarism, putting students at risk of disciplinary action.

Lack of Originality

ChatGPT does not create ideas from scratch but works by recognizing patterns in pre-existing data. As a result, the content it generates lacks the originality and innovation required for academic papers. For high-level research projects, originality is crucial, and AI can hinder rather than help this process.

Use of Outdated Information

AI systems like ChatGPT are trained on data up until a certain point, meaning that they may provide outdated or irrelevant information, especially in rapidly evolving fields. Users need to be cautious when relying on ChatGPT for up-to-date research and cross-check the results with recent studies or articles.

For those seeking a more reliable and flexible solution for diploma thesis writing, ghostwriter for a diploma thesis services might be a better option, offering personalized and accurate academic support.

The Pros of Using ChatGPT

Accelerating the Research Process

One of the primary advantages of ChatGPT is its ability to accelerate the research process. By generating quick summaries of articles and presenting overviews of different topics, it can save students hours of preliminary research time. This allows students to focus on more critical parts of their paper, like data analysis and argument development.

Rewriting and Enhancing Text Originality

ChatGPT can help improve the originality of existing texts by rephrasing content to avoid direct duplication. This is particularly useful when paraphrasing is needed, ensuring that students meet originality standards without compromising on content quality.

Flexibility in Working with Various Topics

Due to its vast database, ChatGPT can generate content across a wide range of academic disciplines. Whether the subject is literature, science, or business, ChatGPT can assist in finding relevant materials and formulating basic content. This flexibility makes it a versatile tool for students from different fields.

Finding and Selecting Synonyms

When striving to improve the linguistic style of a paper, ChatGPT can help with synonym searches, ensuring that papers are not overly repetitive and that they maintain academic language standards. It can suggest alternative phrasing and words to enhance the overall readability of a text.

Automating Routine Tasks

ChatGPT excels in automating routine tasks that can otherwise consume valuable time. For instance, it can format bibliographies, generate lists of references, and produce standard document structures like tables of contents. This can be especially helpful when working on long academic documents like theses.

Translation and Adaptation of Foreign Sources

For students working with sources in foreign languages, ChatGPT can provide translations or adaptations, making it easier to integrate international research into their papers. This expands the breadth of material that students can include in their work, helping to make their papers more diverse and comprehensive.

Assisting in Data Analysis and Processing

While ChatGPT may not excel in deep analysis, it can assist in basic data interpretation. Students can use the tool to organize data, generate summaries, or perform initial analysis before diving into more complex statistical processes. This helps streamline the preparation phase of research projects.

ChatGPT offers a range of benefits for academic writing, from speeding up research to automating routine tasks and enhancing text originality. However, it also comes with limitations, particularly in its ability to perform critical analysis, avoid plagiarism, and ensure factual accuracy. Therefore, while ChatGPT can be a useful tool for students and researchers, it is essential to approach its use with caution, verifying the information it provides and supplementing AI-generated content with personal input.

For those who need more reliable and flexible support with their academic work, using ghostwriter services for a diploma thesis could provide a more tailored and accurate solution. As technologies like ChatGPT continue to evolve, they will likely play a growing role in academic writing, but human oversight remains indispensable for maintaining quality, originality, and ethical standards in academic research.

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 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.

OpenAI o1 codes a video game from a prompt. pic.twitter.com/aBEcehP0j8 — OpenAI (@OpenAI) September 12, 2024

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.

We’re partnering with Condé Nast to deepen the integration of quality journalism into ChatGPT and our SearchGPT prototype. https://t.co/tiXqSOTNAl — OpenAI (@OpenAI) August 20, 2024

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.

We’re starting to roll out advanced Voice Mode to a small group of ChatGPT Plus users. Advanced Voice Mode offers more natural, real-time conversations, allows you to interrupt anytime, and senses and responds to your emotions. pic.twitter.com/64O94EhhXK — OpenAI (@OpenAI) July 30, 2024

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.

We’re testing SearchGPT, a temporary prototype of new AI search features that give you fast and timely answers with clear and relevant sources. We’re launching with a small group of users for feedback and plan to integrate the experience into ChatGPT. https://t.co/dRRnxXVlGh pic.twitter.com/iQpADXmllH — OpenAI (@OpenAI) July 25, 2024

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 and Los Alamos National Laboratory announce partnership to study AI for bioscience research https://t.co/WV4XMZsHBA — OpenAI (@OpenAI) July 10, 2024

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.

We’ve trained a model, CriticGPT, to catch bugs in GPT-4’s code. We’re starting to integrate such models into our RLHF alignment pipeline to help humans supervise AI on difficult tasks: https://t.co/5oQYfrpVBu — OpenAI (@OpenAI) June 27, 2024

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.

We’re partnering with TIME and its 101 years of archival content to enhance responses and provide links to stories on https://t.co/LgvmZUae9M : https://t.co/xHAYkYLxA9 — OpenAI (@OpenAI) June 27, 2024

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.

The ChatGPT desktop app for macOS is now available for all users. Get faster access to ChatGPT to chat about email, screenshots, and anything on your screen with the Option + Space shortcut: https://t.co/2rEx3PmMqg pic.twitter.com/x9sT8AnjDm — OpenAI (@OpenAI) June 25, 2024

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 .

Apple is bringing ChatGPT to Siri and other first-party apps and capabilities across its operating systems #WWDC24 Read more: https://t.co/0NJipSNJoS pic.twitter.com/EjQdPBuyy4 — TechCrunch (@TechCrunch) June 10, 2024

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.

You're not alone, ChatGPT is down once again. pic.twitter.com/Ydk2vNOOK6 — TechCrunch (@TechCrunch) June 4, 2024

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 .

I am delighted that @theatlantic now has a strategic content & product partnership with @openai . Our stories will be discoverable in their new products and we'll be working with them to figure out new ways that AI can help serious, independent media : https://t.co/nfSVXW9KpB — nxthompson (@nxthompson) May 29, 2024

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.

Sharing this, recorded a few weeks ago. Most of the episode is about AI policy more broadly, but this was my first longform interview since the OpenAI investigation closed, so we also talked a bit about November. Thanks to @bilawalsidhu for a fun conversation! https://t.co/h0PtK06T0K — Helen Toner (@hlntnr) May 28, 2024

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.

We’ve heard questions about how we chose the voices in ChatGPT, especially Sky. We are working to pause the use of Sky while we address them. Read more about how we chose these voices: https://t.co/R8wwZjU36L — OpenAI (@OpenAI) May 20, 2024

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.

We're rolling out interactive tables and charts along with the ability to add files directly from Google Drive and Microsoft OneDrive into ChatGPT. Available to ChatGPT Plus, Team, and Enterprise users over the coming weeks. https://t.co/Fu2bgMChXt pic.twitter.com/M9AHLx5BKr — OpenAI (@OpenAI) May 16, 2024

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.

We’re partnering with Reddit to bring its content to ChatGPT and new products: https://t.co/xHgBZ8ptOE — OpenAI (@OpenAI) May 16, 2024

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.

ChatGPT can now read responses to you. On iOS or Android, tap and hold the message and then tap “Read Aloud”. We’ve also started rolling on web – click the "Read Aloud" button below the message. pic.twitter.com/KevIkgAFbG — OpenAI (@OpenAI) March 4, 2024

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.

We’re testing ChatGPT's ability to remember things you discuss to make future chats more helpful. This feature is being rolled out to a small portion of Free and Plus users, and it's easy to turn on or off. https://t.co/1Tv355oa7V pic.twitter.com/BsFinBSTbs — OpenAI (@OpenAI) February 13, 2024

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.”

Use temporary chat for conversations in which you don’t want to use memory or appear in history. pic.twitter.com/H1U82zoXyC — OpenAI (@OpenAI) February 13, 2024

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.

You can now bring GPTs into any conversation in ChatGPT – simply type @ and select the GPT. This allows you to add relevant GPTs with the full context of the conversation. pic.twitter.com/Pjn5uIy9NF — OpenAI (@OpenAI) January 30, 2024

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.

Expanding the platform for @OpenAIDevs : new generation of embedding models, updated GPT-4 Turbo, and lower pricing on GPT-3.5 Turbo. https://t.co/7wzCLwB1ax — OpenAI (@OpenAI) January 25, 2024

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.

Snapshot of how we’re preparing for 2024’s worldwide elections: • Working to prevent abuse, including misleading deepfakes • Providing transparency on AI-generated content • Improving access to authoritative voting information https://t.co/qsysYy5l0L — OpenAI (@OpenAI) January 15, 2024

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.

the GPT store is live! https://t.co/AKg1mjlvo2 fun speculation last night about which GPTs will be doing the best by the end of today. — Sam Altman (@sama) January 10, 2024

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.”

We build AI to empower people, including journalists. Our position on the @nytimes lawsuit: • Training is fair use, but we provide an opt-out • "Regurgitation" is a rare bug we're driving to zero • The New York Times is not telling the full story https://t.co/S6fSaDsfKb — OpenAI (@OpenAI) January 8, 2024

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.

GPT Store launching next week – OpenAI pic.twitter.com/I6mkZKtgZG — Manish Singh (@refsrc) January 4, 2024

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.

Bluesky addresses trust and safety concerns around abuse, spam, and more

The company is in various stages of developing and piloting a range of initiatives focused on dealing with bad actors, harassment, spam, fake accounts, video safety, and more.

Fal.ai, which hosts media-generating AI models, raises $23M from a16z and others

Fal.ai, a dev-focused platform for AI-generated audio, video, and images, today revealed that it’s raised $23 million in funding from investors including Andreessen Horowitz (a16z), Black Forest Labs co-founder Robin…

Bill requiring AM radio in new cars gets closer to law

A House committee overwhelmingly voted to approve a bill that would require new cars to be built with AM radio at no additional cost to the owner. The AM for…

HTC takes on Apple’s Vision Pro and PC Gaming with $1,000 Vive Focus Vision

The Vive Focus Vision has enough firepower under the hood to appeal to PC gamers tethered via the DisplayPort.

Fisker reverses course on making Ocean owners pay for recall repairs

The reversal comes as EV startup Fisker prepares to enter the fourth month of its Chapter 11 bankruptcy process.

Three new ways to personalize your iPhone’s Home Screen in iOS 18

iOS 18 offers the most control over the look and feel of your iPhone’s user interface than any other version of Apple’s mobile operating system to date.

LinkedIn scraped user data for training before updating its terms of service

LinkedIn may have trained AI models on user data without updating its terms. LinkedIn users in the U.S. — but not the EU, EEA, or Switzerland, likely due to those…

This Week in AI: Why OpenAI’s o1 changes the AI regulation game

Hiya, folks, welcome to TechCrunch’s regular AI newsletter. If you want this in your inbox every Wednesday, sign up here. It’s been just a few days since OpenAI revealed its latest…

US government ‘took control’ of a botnet run by Chinese government hackers, says FBI director

The FBI, NSA and other U.S. government agencies detailed a Chinese-government operation that used 260,000 of internet-connected devices to launch cyberattacks.

Luminate’s hair-saving chemo helmet nears release, as new funding goes toward home cancer care

The pitch sounds a bit sci-fi: a helmet called Lily that people undergoing chemotherapy wear to prevent hair loss, which is a common side effect of the treatment.

YouTube launches Communities, a Discord-like space for creators and fans to interact with each other

At its Made On YouTube event on Wednesday, the company announced a new dedicated space for creators to interact with their fans and viewers. The space, called “Communities,” is kind…

Amazon adds PayPal as a payment option to Buy with Prime

Amazon’s Buy with Prime program, which lets shoppers with a Prime membership purchase items from third-party stores and check out using their Amazon account, is getting a new payment option:…

Edera is building a better Kubernetes and AI security solution from the ground up

Edera, a startup looking to simplify and improve how Kubernetes containers and AI workloads are secured by offering a new hypervisor, today announced that it has raised a $5 million…

YouTube unveils ‘Hype,’ a new way for fans to help smaller creators grow their reach

YouTube creators no longer have to rely solely on the recommendation algorithm, search results, or collabs to help them grow their audience. At the company’s Made On YouTube event on…

Last Week: Amplify your brand by hosting a Side Event at TechCrunch Disrupt 2024

Extend the buzz of TechCrunch Disrupt 2024 beyond the main event by hosting an exclusive Side Event. Expose your brand to 10,000 Disrupt attendees and the surrounding Bay Area tech…

YouTube Shorts to integrate Veo, Google’s AI video model 

The main attraction of YouTube’s Made On YouTube event on Wednesday morning was, you guessed it, artificial intelligence. The company announced that it is integrating Google DeepMind’s AI video generation…

YouTube Studio now lets creators brainstorm video ideas with the help of AI

At its Made On YouTube event on Wednesday, the company announced that creators can now brainstorm ideas for videos with the help of AI right within YouTube Studio. YouTube will…

Era Ventures raises $88M first fund for transforming the ‘built’ environment

The real estate market and many real estate-focused startups were hit hard when mortgage rates skyrocketed in 2022, but that didn’t stop industry veteran Clelia Warburg Peters from leaving her…

Generative AI startup Runway inks deal with a major Hollywood studio

Runway, a startup developing AI video tools, including video-generating models, has partnered with Lionsgate — the studio behind the “John Wick” and “Twilight” franchises — to train a custom video…

The 22-year-old building Roblox developer tools to make gaming more efficient

Gamebeast is a live operations tooling platform that lets developers modify games without needing to release a new version or interrupt an ongoing game.

Apple Intelligence will support German, Italian, Korean, Portuguese, and Vietnamese in 2025

Apple announced Wednesday that its generative AI offering will be available in even more languages in 2025. Additions to Apple Intelligence include English (India), English (Singapore), German, Italian, Korean, Portuguese,…

Featured Article

iPhone 16 Pro Max review: A $1,200 glimpse at a more intelligent future

The iPhone 16’s headliner features are Apple Intelligence, which will be rolled out next month, and its camera system.

Here’s how Apple is making iPhone 16 more repairable

The most interesting of the bunch is a new adhesive design that can be loosened by applying low voltage from a 9-volt battery.

Nurture teaches kids important life skills through interactive gameplay and entertainment

Parents understand the challenge of keeping young kids engaged in online learning. Nurture is a new app designed for children aged 4 to 7 that features interactive content and games…

Google nets court win against EU’s $1.7B AdSense antitrust decision

Google has succeeded in overturning a $1.7 billion antitrust penalty handed down by the European Union back in March 2019.

23andMe sees independent board directors quit en masse

23andMe, the personal genomics company, went public in early 2021 via a merger with a blank check company that valued it at $3.5 billion. Then its fortunes began to sink.…

Governor Newsom on California AI bill SB 1047: ‘I can’t solve for everything’

California governor Gavin Newsom said there are 38 bills on his desk that would create laws around artificial intelligence on Tuesday, but one looms larger than all of them: SB…

Amazon taps long-time exec to lead India business as competition intensifies

Amazon has named long-time executive Samir Kumar as the new head of its India consumer business, a month after its domestic business’ head resigned.

Al Gore roasts corporations and politicians, comparing their climate crisis promises to ‘New Year’s resolutions’

Al Gore has enjoyed a very successful career, including as a U.S. senator, U.S. Vice President, U.S. presidential nominee, and even Nobel Peace Prize winner in 2007 for “informing the…

California’s 5 new AI laws crack down on election deepfakes and actor clones

On Tuesday, California governor Gavin Newsom signed some of America’s toughest laws yet regulating the artificial intelligence sector. Three of these laws crack down on AI deepfakes that could influence…

ChatGPT Guide for Students

Understanding chatgpt, different courses will have different policies, when to use chatgpt, tips for using chatgpt, attribution.

• Fact Checking is Always Needed
• Citing Generative AI

Contact a Librarian

Your faculty reference librarians are available to advise you through all aspects of the research process.

• In-person : drop by the Information Desk
• Text:  (209) 666-3235
• ​ Email:    [email protected]
• Phone : Merced Library: (209) 384-6083
• Phone : Los Banos Library: (209) 384-6434

Using ChatGPT Effectively  Remember to always verify the information it gives you.

Check with your instructor for each course to find out the policy on using chatgpt or similar tools..

• Consult your syllabus. Many instructors will explicitly state whether their class will use Chat GPT or similar tools and if you are allowed to incorporate them into your class assignments.

What is ChatGPT good for and not good for?

Remember,  you'll always need to verify the information,  because chatgpt will sometimes make things ups (known as "hallucination.") what is it good for.

• Brainstorming ideas
• Narrowing your topic ideas for a research paper, and keywords for searching in library databases. See  Generate Topics for Your Research Paper with ChatGPT .
• Explaining information in ways that are easy to understand
• Summarizing and outlining
• Asking questions  (be sure to fact check the results)  You can ask a million questions without fear of being judged.
• Translating text to different languages (not completely fluent in every language)
• Helping write or debug computing code

What is it not so good for?

• Perplexity AI    <-- our top recommendation
• Microsoft Copilot 
• Gemini  
• Asking for any information that would have dire consequences if it was incorrect (such as health, financial, legal advice, and so on). This is because of its tendency to sometimes make up answers, but still sound very confident.

What is prompting?

Simply, it's what you type into the chat box.

The way you prompt makes a huge difference in the output that ChatGPT gives you. So it's worth learning some tips.

Always verify the information it gives you..

Think of ChatGPT as your personal intern. They need very specific instructions, and they need you to verify the information.

ChatGPT sometimes makes things up.  That's because it's designed to write in a way that sounds like human writing. It's not designed to know facts.

Tips for writing effective prompts

• Give it some context or a role to play.
• Give it very detailed instructions, including how you would like the results formatted.
• Keep conversing and asking for changes. Ask it to revise the answer in various ways.

1. A role could be, "Act as an expert in [fill in the blank]." 

Act as an expert community organizer. Act as a high school biology teacher. Act as a comedian.

2. Example prompt:

Act as an expert academic librarian. I’m writing a research paper for Sociology and I need help coming up with a topic. I’m interested in topics related to climate change. Please give me a list of 10 topic ideas related to climate change.  

3.Example of changes: (keep conversing until you get something useful)

Now give me some sub-topics or research questions for [one of those topics]. And give me a list of keywords and phrases I can use to search for that topic in library databases and Google Scholar.   Or...

I didn't like any of those topics. Please give me 10 more.

More Tips for ChatGPT

• Sometimes it gets confused if you change topics in the middle of a conversation. When you want to  change the subject, start a new chat.  
• It will remember what you've said in the course of a conversation, so  you don't have to repeat everything again.  Just continue like you're talking to your intern.  
• Don't ask ChatGPT (free version) for a list of sources.  It will make them up. Instead use library search, library databases, or Google Scholar.  
• Choose an output format.  In addition to paragraphs it can give you a table, a bulleted list, ascii art, multiple choice quiz questions, emojis, computer code, and more.  
• In ChatGPT  you can see a history of your conversations  and in the settings you can delete your history and turn off the saving of future history. You can also export your history and save it on your own computer.  
• Remember,  don't enter any personal, private data in ChatGPT , because OpenAI may use your input to help improve the model. The free version is a research experiment.  If you don't want your data used to help improve ChatGPT, you can turn it off in the settings (which means it also won't save your previous chats for your own viewing).

Tutorials on ChatGPT and Generative AI

To learn more, try our new tutorials about ChatGPT.  They contain short videos (3 min or less), and quiz questions for self-review of what you learned.

• The technology behind ChatGPT
• How does ChatGPT aim to prevent harmful use?
• What is generative AI?
• Using ChatGPT effectively

This guide is based on  "Student Guide to ChatGPT"  by  University of Arizona Libraries  is licensed under  CC BY 4.0

• Next: Fact Checking is Always Needed >>
• Last Updated: Sep 17, 2024 2:31 PM
• URL: https://libguides.mccd.edu/ChatGPT

Affiliate 💸

Get started free

Literature Search

How to Summarize a Research Paper Using ChatGPT In 5 Simple Steps

Learn how to summarize a research paper using ChatGPT in 5 simple steps. Get clear, concise summaries with ease and efficiency.

Sep 16, 2024

In the whirlwind of academia, juggling a mountain of research papers can feel like trying to catch a greased pig at a county fair. With endless pages to sift through, even a seasoned researcher can feel buried. That’s where AI steps in, offering tools like ChatGPT to make summarizing research papers a breeze. This guide will show you how to use AI to turn lengthy, jargon-filled texts into concise, digestible summaries, leaving you more time to use the information. And that’s where Otio's AI research and writing partner comes in handy. Designed to help you write and research efficiently, it’s an indispensable tool for anyone looking to streamline their literature search .

Table Of Contents

What is a research summary, how to write a research summary, can chatgpt summarize research papers, 10 best chatgpt alternatives for summarizing research papers, pros and cons of chatgpt, supercharge your researching ability with otio — try otio for free today.

A research summary gives you a snapshot of a study—usually an article from a peer-reviewed academic journal. Consider it a concise overview of what the researchers did, why they did it, what they found, and what those findings mean. 

This type of assignment is widespread in U.S. colleges because it teaches students how to engage with academic papers, which are crucial for sharing new ideas and evidence in many fields. A research summary mirrors the sections of the article it focuses on, like the abstract, introduction, methods, results, and discussion.

Related Reading

• Systematic Review Vs Meta Analysis • Impact Evaluation • How To Critique A Research Article • How To Synthesize Sources • Annotation Techniques • Skimming And Scanning • Types Of Literature Reviews • Literature Review Table • Literature Review Matrix • How To Increase Reading Speed And Comprehension • How To Read Research Papers • How To Summarize A Research Paper • Literature Gap

Kick Off with a Quick Skim

Start by quickly reading the article to understand the overall content. Understand which sections hold more weight and require your focus. This initial step helps you gauge how important different lines of evidence are. Ensure you've got a handle on your professor's guidelines before diving deeper. While skimming, decide if you'll tackle the summary yourself or lean on a research paper writing service for support.

Know the Topic Inside and Out

Dive into the topic and article. You need to become quite familiar with the subject matter. Sometimes, it's crucial to explore the current state of knowledge, definitions, and models to grasp the content thoroughly. When it comes to the paper, understand the analysis questions, hypotheses, evidence, and implications. A thorough understanding will allow you to summarize the content efficiently and accurately.

Jot Down Notes as You Read

While reading, make concise notes. You could summarize each paragraph with a brief sentence that captures the critical idea. But don't go overboard with writing as you read. You might find that some sections initially seem vital but lose their importance later on. Highlight or underline only the most critical evidence to avoid clutter.

Build a Draft with Key Evidence

Once you're ready, start assembling a draft . Pull together the critical evidence and notes from each section. Ensure that all parts typical of a research summary are included. This helps you create a clear and complete summary of the paper.

Hunt for Extra Literature

If you need to form a critical view, look for additional literature. This might involve judgments about the study's limitations or finding contradictory evidence. This step is vital if your summary requires a critical perspective.

Ready to streamline your research workflow? Let Otio be your AI research and writing partner — try Otio for free today!

AI chatbots like ChatGPT can help you summarize long articles, research papers, and books. If you need a summary for school or work and time is tight, ChatGPT can help you grasp the main points. Just remember, while ChatGPT is a valuable tool , it's not always best to let it do all the work for you.

• Literature Search Template • ChatGPT Prompts For Research • How To Find Gaps In Research • Research Journal Example • How To Find Limitations Of A Study • How To Do A Literature Search • Research Concept Map • Meta-Analysis Methods • How To Identify Bias In A Source • Search Strategies For Research • Literature Search Template • How To Read A Research Paper Quickly • How to summarize a research article • How To Evaluate An Article • ChatGPT Summarize Paper • How To Take Notes For A Research Paper

Get Set Up: Preparing ChatGPT for Action

First, access the ChatGPT console. Navigate to the Settings menu and activate Plugins under Beta Features. Then, click the GPT-4 icon and enter the Plugin Store. Search for and install the "Askyourpdf" plugin. Switch from default to Plugins to enable it. This sets the stage for summarizing your research.

Uploading Documents: Choose Your Method

You have options to upload your document, each suited to different situations. If your paper is online, provide a URL ending in ".pdf" or another compatible format. For files stored on Google Drive or Dropbox , supply the link. If the document is on your device, upload it directly to askyourpdf.com/upload. Each method has pros and cons, so choose the one that suits you best.

Summarize Like a Pro: Using the Right Prompts

With your document uploaded, it’s time to summarize. Enter a clear and specific prompt in the ChatGPT console. Consider asking for key findings, methodologies, and limitations. Your prompt guides the AI to provide the information you need.

Otio is your AI-native workspace for tackling content overload. It’s designed for knowledge workers, researchers, and students who struggle with fragmented, manual tools. Otio streamlines your workflow by letting you easily collect, extract, and create content. With Otio, you can gather data sources, extract critical takeaways using AI-generated notes, and draft outputs faster. It’s your research and writing partner.

2. Quillbot

Quillbot is a powerful paraphrasing tool supporting 23 languages, including English, German, and French. It features a built-in grammar checker and plagiarism detector to ensure your content is unique and meets quality standards. Quillbot also offers summarization tools, readability improvements, and a citation creator.

Built-in grammar and spelling checker.

Plagiarism detector for unique content.

Synonym slider for creative phrasing.

Character limitations on free and paid plans.

Some users need to catch up on grammar errors.

Jasper, formerly known as Jarvis, has evolved beyond copywriting to become an all-in-one marketing tool. It offers AI text generation for various projects, from landing pages to complete marketing campaigns. Jasper’s collaborative features allow teams to work seamlessly on projects with Kanban and calendar views. It also includes a Chrome extension and tools like Remix for reworking content.

Comprehensive features and templates.

Intuitive system for easy use.

Long-form assistant for content creation.

It can be expensive.

Output quality may vary.

Copy.ai provides AI-powered rephrasing tools to help writers overcome writer’s block. It offers a built-in plagiarism checker, spelling tool, and Chrome extension. Users can also create custom templates for specific needs.

Plagiarism and spelling checker.

Chrome extension for easy access.

Customizable templates.

Some tools may need to be more helpful for non-marketers.

Content output can be random for specific needs.

Rytr is an AI writing tool for generating copywriting content on various topics. It’s ideal for creating post and caption ideas, SEO meta titles, emails, and more. Rytr supports over 40 use cases, and paid users can train the tool for specific needs.

Affordable pricing.

Compact, user-friendly interface.

Supports multiple languages.

Content quality could be better.

Initial learning curve.

6. ProWritingAid

ProWritingAid offers AI-powered rephrasing and rewriting, coupled with human expertise. Users can access built-in features or consult writing experts, including college professors. It’s known for its ease of use and excellent customer service.

User-friendly interface.

Free trial without credit card requirements.

Excellent customer support.

It could be better for high-word-count projects.

There are limited options in the free version.

Anyword is a data-driven AI tool for enterprise marketing teams . It uses data analytics to help teams understand their audience and create resonant content. Anyword offers templates for marketing content and advanced features like predictive scores for compelling copy.

AI and data analytics for more intelligent decisions.

Improves content engagement and conversion rates.

Generates various marketing copy types.

The learning curve for predictive scoring.

Complexity may not suit small teams or individual creators.

8. Writesonic

Writesonic is a blogging tool and AI writing assistant powered by GPT-4 technology. It includes a Sonic Editor for rewriting content and a Paraphraser for creative rephrasing. Writesonic integrates with LinkedIn, YouTube, and Facebook Ads.

Over 100 features, including text-to-art capabilities.

GPT-4 technology for up-to-date content.

Integrations with popular platforms.

The free version lacks additional user support.

Credit limits for content creation.

9. Frase.io

Frase.io is an AI writing tool for generating content, optimizing articles for SEO, and providing writing suggestions. Its templates and outline builder help create article structures that align with searcher intent, increasing search rankings.

Comprehensive research tools.

All-in-one content creation suite.

Helpful content optimization features.

No free plan is available.

Overemphasis on keywords.

10. Speedwrite

Speedwrite is an AI writer that refines content in seconds. Users can input research, add unique ideas, and hit “predict” to get updated content with improved sentence structure and phrasing.

Simple, distraction-free interface.

Quick text generation for new ideas.

Lacks additional tools like spell checkers.

Limited customer support.

1. Grasp Key Ideas Fast

ChatGPT can distill the essence of a research paper quickly. It takes the abstract or introduction and boils it down to one sentence. This is perfect for researchers who need to understand the main argument without digging through pages of text.

2. Spot Gaps in Research

If you’re trying to find where the literature falls short, ChatGPT can help. It summarizes related papers, pointing out areas yet to be fully explored.

3. Tailor Messages for Different Audiences

Whether you’re explaining findings to a fellow researcher or a general audience, ChatGPT can adjust the summary to fit. It tailors the complexity to suit whoever you’re talking to.

4. Save Time and Energy

Summarizing papers can be a grind. ChatGPT automates this process, freeing researchers to focus on more critical tasks.

1. Nuance Gets Lost

ChatGPT tends to oversimplify complex ideas. This can strip away essential details and insights crucial for understanding the research deeply.

2. Risk of Misinterpretation

The model might need to understand technical terms or nuanced arguments, especially in specialized areas. This could lead to inaccurate or misleading summaries.

3. Lacks Critical Analysis

While ChatGPT can summarize, it doesn’t evaluate. It won't tell you if the arguments hold water, which is often needed to grasp academic research fully.

4. Misses Important Context

The summaries might overlook essential background information, assumptions, or study limitations, leading to potential misunderstandings.

5. Can’t Handle Complex Data

ChatGPT can’t interpret graphs, charts, or detailed equations. These are often vital to research papers, which can be a significant limitation.

6. Bias in Summarization

Since ChatGPT is trained on diverse data, it might introduce biases or leave out essential counterpoints in the paper.

7. No Understanding of Ethics or Citations

The model doesn’t provide proper citations or distinguish between the author’s ideas and referenced works, which is crucial for academic integrity.

8. Generalizes Across Fields

ChatGPT might not fully grasp field-specific methodologies or concepts, especially in niche or emerging research areas.

Let Otio be your AI research and writing partner . Try Otio for free today!

Knowledge workers, researchers, and students are drowning in content. With information multiplying at breakneck speed, its management tools have become fragmented and cumbersome. Consider trying to stitch together bookmarks, read-it-later apps, and note-taking tools to keep your head above water. And the flood isn’t stopping. More content is being created every second. The need for a unified solution is clear.

Enter Otio: Your AI-Native Workspace

Otio simplifies the chaos by offering a single AI-native workspace for researchers. You can collect various data sources, from bookmarks and tweets to YouTube videos and books. But Otio doesn’t stop at collecting. It extracts critical takeaways with AI-generated notes and offers source-grounded Q&A chat. And when you’re ready to create, Otio helps draft outputs using your collected sources. It’s about moving from the reading list to the first draft faster.

AI-Generated Notes: Your New Research Ally

Researchers love Otio’s AI-generated notes on all bookmarks. Whether you’re dealing with PDFs, articles, or videos, Otio provides detailed insights. When you have questions, Otio enables you to chat with individual links or entire knowledge bases, just like you chat with ChatGPT. It’s like having a research partner who’s always ready to help.

AI-Assisted Writing: Get to the Finish Line Faster

Otio also helps you write research papers and essays faster. With AI-assisted writing, you can quickly draft, revise, and polish your work. It’s about getting to the finish line faster and with less stress. So why settle for a patchwork of tools when you can have one AI-native workspace? Try Otio for free today.

• Paragraph Graphic Organizer • Sequence Graphic Organizer • Best AI for Research • Sharly AI Alternatives • AI For Summarizing Research Papers • Literature Review Tools • How To Identify Theoretical Framework In An Article • Graduate School Reading • Research Tools • AI For Academic Research • Research Paper Organizer • Best AI Tools For Research • Zotero Alternatives • Zotero Vs Endnote • ChatGPT For Research Papers • ChatGPT Literature Review • Mendeley Alternative • Unriddle AI Alternatives • Literature Matrix Generator • Research Assistant • Research Tools • Research Graphic Organizer • Good Websites for Research • Research Paper Graphic Organizer • Graphic Organizer Examples • Summary Graphic Organizer • Who What When Where Why Graphic Organizer • Research Project Graphic Organizer • Research Note Taking Graphic Organizer • Graphic Organizer Research Paper Outline • Research Essay Graphic Organizer • Research Notes Graphic Organizer • Translational Research Graphic Organizer • Research Graphic Organizer Template

Sep 17, 2024

How To Summarize Research Paper ChatGPT Method In 6 Simple Steps

Sep 15, 2024

Literature Review

7 Best Research Graphic Organizer Template

Join over 80,000 researchers changing the way they read & write

Chrome Extension

© 2024 Frontdoor Labs Ltd.

Terms of Service

Privacy Policy

Refund Policy

Join over 50,000 researchers changing the way they read & write

Join thousands of other scholars and researchers

Try Otio Free

© 2023 Frontdoor Labs Ltd.

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

• Using ChatGPT for Assignments | Tips & Examples

Using ChatGPT for Assignments | Tips & Examples

Published on February 13, 2023 by Jack Caulfield and Tobias Solis. Revised on November 16, 2023.

People are still figuring out the best use cases for ChatGPT , the popular chatbot based on a powerful AI language model. This article provides some ideas for how to use ChatGPT and other AI tools to assist with your academic writing .

These tools can assist you with the following steps when writing a paper, thesis , or dissertation :

• Developing a research question
• Creating an outline
• Generating literature ideas

Paraphrasing and summarizing text

• Getting feedback

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

Developing a research question with chatgpt, creating an outline of your paper with chatgpt, generate literature ideas, getting feedback from chatgpt, limitations of chatgpt, other interesting articles, frequently asked questions.

You can use ChatGPT to help you formulate a clear and concise research question by generating and improving potential questions.

With the help of ChatGPT, you can develop a large number of possible research questions within a short time. This is a great way to generate ideas and different approaches to a topic.

However, make sure that the generated questions make sense and meet your needs. As you can see from our example, you can keep working with ChatGPT to adapt its suggestions to your needs (or just edit the text directly if you already have a clear idea of what you want).

First input

Develop three possible research questions on the following topic: “The influence of social media on political opinion formation.”

ChatGPT output

• To what extent does exposure to diverse political perspectives on social media affect individuals’ political opinions and behaviors?
• How does the personalized algorithm of social media platforms shape the formation of political opinions among its users?
• What are the underlying factors that determine the effect of social media on political opinion formation, and how can they be measured and analyzed?

Second input

Based on the second research question, develop three further research questions on the topic of polarization in US politics.

• Build my scientific method, qualitative discourse analysis, into each question
• Include the term “filter bubble” in each question
• How does the filter bubble effect on social media platforms contribute to the polarization of political attitudes in the US? A qualitative discourse analysis.
• What is the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US? A qualitative discourse analysis.
• How does the influence of filter bubbles on social media affect the ability of individuals to engage in productive political discourse across ideological divides in the US? A qualitative discourse analysis.

Third input

Try to incorporate “qualitative discourse analysis” into the questions themselves, instead of using it as a separate sentence.

• How does a qualitative discourse analysis of filter bubble effect on social media platforms contribute to understanding the polarization of political attitudes in the US?
• What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US?
• How does a qualitative discourse analysis of the influence of filter bubbles on social media inform our understanding of the ability of individuals to engage in productive political discourse across ideological divides in the US?

Check for common mistakes

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

Fix mistakes for free

You can also use ChatGPT to help you draft a research paper outline or thesis outline . To do this, try generating possible headings and subheadings and then improving them. ChatGPT can help to generate a clear and well-structured outline, especially if you keep adjusting the structure with its help.

However, it doesn’t have a deep understanding of your topic. As a result, inappropriate headings may sometimes be generated. It’s important to check that the outline makes sense and covers all the points needed to answer your research question.

You should also ensure that the headings and subheadings follow a logical structure. Scribbr’s Proofreading & Editing service can help you with this.

Create an outline for an academic research paper with the following research question:

“What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US?”

The paper will be about 8 pages long.

• Background information on filter bubbles and political echo chambers
• Purpose of the study
• Research question
• Thesis statement
• Definition and concept of filter bubbles
• Definition and concept of political echo chambers
• Previous studies on the role of filter bubbles in perpetuating and reinforcing political echo chambers
• Critiques and limitations of previous studies
• Research design
• Participants
• Data collection and analysis
• Validity and reliability
• Findings from qualitative discourse analysis
• Results related to the research question
• Implications of the findings
• Interpretation of the results
• Comparison with previous studies
• Limitations of the study
• Implications for future research
• Summary of the results
• Implications for understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers
• Conclusion and recommendations for future research
• List of references used in the paper
• Data collection materials
• Examples of qualitative data analysis

This seems like too much information to fit into only 8 pages. Can you condense the outline, for example removing the appendices and simplifying the structure?

• Background on filter bubbles and political echo chambers
• Definition of filter bubbles and political echo chambers
• Previous studies on the role of filter bubbles
• Limitations of previous studies
• Implications for understanding the role of filter bubbles
• Final thoughts

ChatGPT can be a useful way to generate ideas regarding what sources you might use in your work. Try asking it for suggestions about where to look and what to consider.

However, we advise against using it to find sources directly. It’s not designed for this and, if asked to do it, often just creates fake sources and presents them as real. Search a database like Google Scholar instead.

What types of sources could I use to write a paper on the following research question?

When writing a paper on the contribution of qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US, you could use the following types of sources:

• Academic journals and articles: These are a good place to start when you’re looking for information on specific topics and they can provide you with in-depth analysis and perspectives on the topic at hand.
• Books and book chapters: These sources can provide comprehensive overviews of a particular topic and can also offer theoretical frameworks and historical perspectives.
• Government reports and studies: Government agencies, such as the Federal Communications Commission (FCC), may have conducted studies on the role of filter bubbles in perpetuating political echo chambers.
• News articles and media reports: These sources can provide insight into the current state of the issue, as well as opinions from various stakeholders.
• Online sources: Websites, blogs, and online forums can provide a range of perspectives on the topic and can also be useful in exploring the experiences of individuals who are affected by filter bubbles and political echo chambers.
• Data and statistics: Relevant data and statistics on the prevalence and impact of filter bubbles and political echo chambers in the US can be useful in providing evidence to support your arguments.
• Expert interviews and focus groups: Conducting expert interviews or focus groups with individuals who have experience with or knowledge of the topic can provide valuable insights and perspectives that can be used to support your arguments.

You can also try using ChatGPT to paraphrase or summarize text. ChatGPT can quickly condense the text or generate a number of different paraphrases of the same idea. You can keep typing “again” in the chat until you are satisfied with the result.

This kind of paraphrasing/summarizing can be helpful to, for example, non-native speakers who want to improve the fluency of their text. However, be careful. The outputs often:

• Contain grammatical errors
• Include false information

So you should always check the output to make sure it’s correct. If you’re unsure, you can run the text through the Scribbr Grammar Checker and cross-reference the information against other, more credible sources .

An alternative is to use the Scribbr Paraphrasing Tool or Scribbr’s free text summarizer , which were designed specifically for these purposes.

Paraphrase the following text:

“A filter bubble results from a social media algorithm’s attempts to cater to an individual user based on data such as their search history and previous behavior on the site. It results in the user only being presented with information that confirms their biases.”

Restructure the sentences and use other phrasings for the following parts:

• “results from”
• “only being presented with”

“A filter bubble is created when a social media algorithm customizes its content for a particular user based on their data, such as their search history and past actions on the platform. This leads to the user being confined to information that reinforces their pre-existing beliefs.” Note We strongly advise against having ChatGPT write text for you and trying to pass it off as your own work. This is academically dishonest and is widely considered plagiarism . It will usually result in an automatic fail, as well as other potential consequences .

Don't submit your assignments before you do this

The academic proofreading tool has been trained on 1000s of academic texts. Making it the most accurate and reliable proofreading tool for students. Free citation check included.

Try for free

You can also use ChatGPT to get feedback on the argumentation and structure of your paper and suggestions for improvements.

An advantage of this is that you can get feedback from ChatGPT on different text excerpts at any time. However, one downside is that ChatGPT does not have a deep understanding of your research question, so its feedback and suggestions may be shallow or inappropriate.

This kind of feedback cannot replace input from an experienced academic supervisor who’s familiar with your topic. Use ChatGPT feedback as a supplement, not a substitute for human feedback.

If you need in-depth feedback on your writing from someone with academic expertise, try Scribbr’s Proofreading & Editing service .

[Text you want to get feedback on.]

Thank you for submitting your research paper for review. Let me provide you with my constructive criticism:

Clarity of Explanations: Overall, the explanations are clear and concise, but there are a few areas that could benefit from additional clarification. For example, in the first paragraph, you mention “the mental lexicon,” but do not provide a definition or further explanation for what this is. It would also be helpful to provide a definition of “lemma.”

Smoothness of Language: The language in the paper is generally smooth, but there are a few instances where it could be refined. For example, the sentence “The symptoms vary from adding superfluous words and taking pauses to hoarseness of the voice” could be rephrased to “The symptoms of these disorders can range from excessive use of words and pauses to hoarseness.”

Structure of Text: The structure of the text is clear, with each paragraph building on the previous one. However, the transition between the first two paragraphs could be smoother. Perhaps you could add a sentence or two to bridge the gap between the two topics.

Even though ChatGPT is a powerful writing tool, you should keep the following limitations in mind:

No original research

Risk of plagiarism, fake sources, fake “facts”.

ChatGPT was trained using existing texts, and the texts created by the AI are based on this data. It’s not capable of doing its own research, only of synthesizing sources that it was trained on.

Additionally, because the texts that it was trained on only go up to 2021, it’s unfamiliar with more recent world events, cultural trends, and developments in different fields of research. This means it may provide outdated information.

Because ChatGPT was trained using existing text, the AI tends to reuse that content in a way that may be considered plagiarism. The AI may copy text from an online publication in its responses.

Additionally, using ChatGPT to write your assignment for you is considered plagiarism regardless of where it got the content from, because you’re passing off something you didn’t write as your own work.

ChatGPT was trained on a wide variety of sources, but it’s not able to accurately tell you what sources it’s using for any given output. Worse, it has a tendency to make up sources that don’t actually exist when you ask.

In addition, ChatGPT is not designed as a citation generator and cannot add correctly formatted citations to your work. Instead, try a tool designed for this purpose, like the Scribbr Citation Generator .

ChatGPT is not always trustworthy when it comes to giving you factually correct information. While it doesn’t deliberately lie, it also doesn’t have “knowledge” in a traditional sense, and it lacks the ability to verify its claims.

Instead, its responses are based on recognizing and reproducing patterns that it has seen in other texts. This means that if it doesn’t “know” something, it tends to guess. And its guesses are presented with full confidence, just like established facts.

So it’s very important that you carefully check any factual claims made by ChatGPT against more credible sources —and don’t cite ChatGPT as a source of factual information for your research.

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
• Deep learning
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

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

You can use ChatGPT to assist in the writing process for your research paper , thesis , or dissertation in the following ways:

• Paraphrasing text

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.

No, it is not possible to cite your sources with ChatGPT . You can ask it to create citations, but it isn’t designed for this task and tends to make up sources that don’t exist or present information in the wrong format. ChatGPT also cannot add citations to direct quotes in your text.

Instead, use a tool designed for this purpose, like the Scribbr Citation Generator .

But you can use ChatGPT for assignments in other ways, to provide inspiration, feedback, and general writing advice.

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.

Caulfield, J. & Solis, T. (2023, November 16). Using ChatGPT for Assignments | Tips & Examples. Scribbr. Retrieved September 18, 2024, from https://www.scribbr.com/ai-tools/chatgpt-assignments/

Is this article helpful?

Jack Caulfield

Other students also liked, writing strong research questions | criteria & examples, how to create a structured research paper outline | example, student guide: information literacy | meaning & examples, "i thought ai proofreading was useless but..".

I've been using Scribbr for years now and I know it's a service that won't disappoint. It does a good job spotting mistakes”

Is ChatGPT real writing?

By erica keswin.

Last week I was creating a document for an upcoming project. The person who helped me create the document casually called upon ChatGPT to insert some placeholder text for the copy that I would be ultimately writing.

I thought—NO WAY! Not my work. As a writer, I like my own voice, and I’m going to use it.

But then, reading through the AI generated text, I realized it was kind of a good place to start. It gave me a basic (if somewhat dumbed down) draft to edit. But at the same time, I noticed that simply leaving in what the chatbot produced wouldn’t have sounded like me—at all!

In other words…

We still need the human touch in this age of AI.

Or as I like to say, we need to find the sweet spot between tech and connect.

Speaking of which, one of the most important modules in my upcoming cohort, Managers on a Mission: How to Become a Great Human Leader, is called Find the Sweet Spot Between Tech and Connect.

This is where we’ll dive into how you can leverage all that’s great about technology (like ChatGPT). But you’ll also learn how and why you need to put it “in its place.”

If you’re a manager (and managers do a lot of writing!) looking for practical, actionable tools and tips to lead better, consider joining us soon as we have just TWO SPOTS LEFT!

We start October 1st, and over nine-weeks you’ll learn how to become a great human leader. The best part? We’ll use tech—WhatsApp—to form a very human community of fellow managers.

Are you in?

I can’t wait to work together.

About Erica

Erica Keswin is an internationally sought-after speaker, bestselling author, and workplace strategist who partners with some of the most well-known companies in the world on how to bring their human to work. For the past two decades, Erica’s work has defined what it means to be a human leader. Erica’s Human Workplace Trilogy: Bring Your Human to Work, Rituals Roadmap, and The Retention Revolution was published by McGraw Hill and each debuted as a Wall Street Journal bestseller. 

When Erica isn’t writing books, she delivers keynotes, leads workshops, and coaches top-of-class companies and individuals to help them improve their performance by honoring relationships in today’s hybrid workplace.

Revolutionary Speaking Programs to Develop Human Leaders

Join my newsletter for regular updates.

Five Ways to Embrace Your Humanity in the Age of AI

Explore the site, connect with erica, about erica keswin.

Erica Keswin is an internationally sought-after speaker, bestselling author, and workplace strategist who partners with some of the most well-known companies in the world on how to bring their human to work. For the past two decades, Erica’s work has defined what it means to be a human leader. Erica’s Human Workplace Trilogy: Bring Your Human to Work , Rituals Roadmap , and The Retention Revolution was published by McGraw Hill and each debuted as a Wall Street Journal bestseller. 

Terms & Conditions

Privacy policy.

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 a Paper with ChatGPT | Tips & Examples

How to Write a Paper with ChatGPT | Tips & Examples

Published on 17 August 2023 by Koen Driessen .

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
• Summarise and paraphrase text
• Provide 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

Brainstorming research questions, developing a methodology, creating an outline, finding sources, summarising 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?”

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

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 analyse 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, organise 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.

B. Existing studies on cognitive and skill development benefits of virtual reality training

C. Comparison of virtual reality-based training with traditional training methods

D. Gaps in the literature and research limitations

III. Theoretical Framework

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 Organisations: Look for reports and publications from government agencies and non-profit organisations 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 summarise 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 specialised tools featured on Scribbr’s AI writing resources page, 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 specialised 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 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.

No, having ChatGPT write your college essay can negatively impact your application in numerous ways. ChatGPT outputs are unoriginal and lack personal insight.

Furthermore, Passing off AI-generated text as your own work is considered academically dishonest . AI detectors may be used to detect this offense, and it’s highly unlikely that any university will accept you if you are caught submitting an AI-generated admission essay.

However, you can use ChatGPT to help write your college essay during the preparation and revision stages (e.g., for brainstorming ideas and generating 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 Reference Generator.

Driessen, K. (2023, August 17). How to Write a Paper with ChatGPT | Tips & Examples. Scribbr. Retrieved 18 September 2024, from https://www.scribbr.co.uk/using-ai-tools/chatgpt-paper/

Is this article helpful?

Koen Driessen

Other students also liked, how to write good chatgpt prompts, chatgpt citations | formats & examples, ethical implications of chatgpt.

More From Forbes

5 ways to use chatgpt for b2b saas marketing (prompts included).

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

This illustration photograph taken on October 30, 2023, shows the logo of ChatGPT, a language ... [+] model-based chatbot developed by OpenAI, on a smartphone in Mulhouse, eastern France. (Photo by SEBASTIEN BOZON / AFP) (Photo by SEBASTIEN BOZON/AFP via Getty Images)

Is your B2B SaaS marketing stuck in a rut? You know the feeling—endless hours spent churning out content that barely gets noticed, juggling multiple campaigns with lackluster results, and constantly playing catch-up with your competition. It's like running on a hamster wheel: You're working hard, but you're not really getting anywhere.

Enter ChatGPT, the AI-powered tool ready to help you escape the rut and achieve success. Here are five ways to use ChatGPT for your marketing, complete with sample prompts to get you started.

1. Create content that resonates, not just accumulates

Use ChatGPT to create content that resonates, not just accumulates

Let's be real: Reading generic content is as exciting as watching paint dry. ChatGPT changes that, letting you research, organize, and write initial content drafts at the speed of need. It's like having a marketing team that knows each of your customers personally. Feed ChatGPT information about your personas, use cases, pain points, triggers, and other relevant data points, and it can churn out outlines and drafts of blog posts, whitepapers, and case studies that speak directly to your target audience's pain points and aspirations. Toss the drafts over to your expert editor , and you’ll wind up with excellent content that actually gets read , not just scrolled past.

Try this prompt to write a blog post

Act like an expert blog post writer with expertise in [the construction industry]. Write a blog post for [project managers] in the industry who are struggling to [keep projects on time and under budget].

iOS 18: Apple Just Gave iPhone Users 33 Reasons To Update Now

Samsung rolls out major feature update to millions of galaxy phones, ‘diddy’ arrest: 50 cent, charlamagne tha god and other celebrities react, 2. deploy a chatbot that closes deals while you sleep.

Use ChatGPT to create a chatbot conversation

Imagine having your top sales rep working 24/7, never missing a beat, and always ready with a perfectly tailored response. That's ChatGPT-powered chatbots in a nutshell. They qualify leads, book demos, and even nurture prospects down the funnel, all while sounding remarkably human. It's like adding rocket fuel to your lead generation efforts.

Try this prompt to create a chatbot conversation

Act like an expert salesperson in the [data labeling] industry. Create a [fun] chatbot conversation that qualifies leads based on company size, industry, and budget.

3. Design email campaigns that dodge the spam folder

Use ChatGPT to create an email nurture sequence

Ditch the "spray and pray" approach to email marketing. ChatGPT can help you craft subject lines that scream "Open me!" and emails that actually get read. Feed the tool your data, and it’ll dive deep into customer behavior and create personalized email sequences that guide your leads toward a sale. Get ready for open rates that'll make your competitors green with envy.

Try this prompt to create a follow-up email nurture sequence

Act like an email marketing expert with significant expertise in the [cloud security] industry. Generate a series of emails that nurture leads who have [downloaded a whitepaper about cloud security].

4. Get more from your content and sprinkle in SEO

Use ChatGPT to repurpose content and sprinkle it with SEO magic

ChatGPT can also act as your content's personal makeover artist. It can transform long-winded whitepapers into compelling blog posts and bite-sized social media posts, turn webinar transcripts into engaging articles, and even sprinkle in some SEO magic to make sure your content gets the organic attention it deserves. It's like having a marketing intern who never sleeps—and doesn't need to be paid.

Try this prompt to repurpose and atomize content

Act like a LinkedIn content expert with deep knowledge about how [IT professionals] think, read, and buy. Repurpose this [webinar transcript] into a series of [LinkedIn] posts targeting those [IT professionals].

5. Outsmart your competition with data, not guesswork

Use ChatGPT to uncover—and soar past—your competitors' strategies

Want to know what your competitors are really up to? ChatGPT is your spy in the digital world. It dissects competitors’ content, uncovers hidden opportunities, and helps you create unique selling propositions that make you stand out. It's like having a marketing strategist and competitive analyst on your team, working around the clock to keep you ahead of the curve.

Try this prompt to find gaps in your competitor’s strategy

Act like an expert marketing strategist. Analyze [Competitor Name]'s website and marketing materials. Identify their key messages, target audience, and any gaps in their strategy.

The future of B2B SaaS marketing Is now—are you in?

Raise your hand if you're in with using ChatGPT for your B2B SaaS business!

ChatGPT is a game-changing, AI-powered sidekick ready to turn your content from meh to marvelous . It's also an always-on idea generator, tireless content creator, and 24/7 lead nurturing machine.

Don’t let another day go by watching your competitors zoom ahead. Grab the prompts, fire up ChatGPT, and start transforming your marketing strategy today. Your future self, prospects, and bottom line will thank you.

• Editorial Standards
• Reprints & Permissions

Join The Conversation

One Community. Many Voices. Create a free account to share your thoughts. 

Forbes Community Guidelines

Our community is about connecting people through open and thoughtful conversations. We want our readers to share their views and exchange ideas and facts in a safe space.

In order to do so, please follow the posting rules in our site's  Terms of Service.   We've summarized some of those key rules below. Simply put, keep it civil.

Your post will be rejected if we notice that it seems to contain:

• False or intentionally out-of-context or misleading information
• Insults, profanity, incoherent, obscene or inflammatory language or threats of any kind
• Attacks on the identity of other commenters or the article's author
• Content that otherwise violates our site's  terms.

User accounts will be blocked if we notice or believe that users are engaged in:

• Continuous attempts to re-post comments that have been previously moderated/rejected
• Racist, sexist, homophobic or other discriminatory comments
• Attempts or tactics that put the site security at risk
• Actions that otherwise violate our site's  terms.

So, how can you be a power user?

• Stay on topic and share your insights
• Feel free to be clear and thoughtful to get your point across
• ‘Like’ or ‘Dislike’ to show your point of view.
• Protect your community.
• Use the report tool to alert us when someone breaks the rules.

Thanks for reading our community guidelines. Please read the full list of posting rules found in our site's  Terms of Service.