writing essays with 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.

'ZDNET Recommends': What exactly does it mean?

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

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

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

5 ways ChatGPT can help you write an essay

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

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

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

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

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

How ChatGPT can help you write an essay

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

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

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

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

1. Use ChatGPT to generate essay ideas

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

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

Also: How do AI checkers actually work?

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

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

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

2. Use the chatbot to create an outline

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

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

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

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

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

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

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

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

3. Use ChatGPT to find sources

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

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

Also:   How to make ChatGPT provide sources and citations

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

For example, I asked the following: 

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

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

4. Use ChatGPT to write an essay

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

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

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

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

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

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

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

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

5. Use ChatGPT to co-edit your essay

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

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

Also:  How to use ChatGPT to make charts and tables

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

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

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

5 ways college students can use gemini ai to keep up with school work, 10 ways to speed up your slow internet connection today.

• 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.

Im student i want to become financially independent woman in life so I want esay essay write

I am housewife and I want easy essay I want to change my life my husband was job less and I want to work online part time job plz help I am enter pass

Add new comment

• 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.

Can Chat GPT Edit Essays: AI Revision Tips & Prompts

Sometimes, you don’t have the time to carefully review and edit essays or articles. Your deadlines are getting closer, and you don’t have anyone to assist you in this task. Don’t worry – in this guide, we will give you an efficient solution to your challenges.

To save time on the editing process, you can simply use ChatGPT. Our team has explained how to build prompts so that the chatbot will check your university assignments like a pro. Trust our experience, and you will be able to edit your essay using AI no worse than a human editor.

Let’s get into it!

🤖 How Does ChatGPT Work?

🤔 can chat gpt edit essays.

• 🕹️ How to Use ChatGPT for Editing
• 🌟 Best ChatGPT Prompts
• 🪄 AI Revision Tips

🔗 References

ChatGPT is an AI-based chatbot that answers user requests by accessing vast knowledge databases on different subjects such as history, marketing, biology, the arts, and more. You ask the chatbot questions like “How many sonnets did Shakespeare write?” and it responds to the best of its ability.

The versatility of applications makes ChatGPT a particularly remarkable tool. Thanks to its promptness and convenience, many students use the chatbot for research . In addition to providing AI-generated content, the platform can adjust to individual formats and styles. These features are made possible thanks to deep learning training that allows ChatGPT to understand and process text input, providing human-like, natural responses. Using the tool is like talking to an expert on different subjects.

While many educators consider ChatGPT a form of cheating , this couldn’t be farther from the truth. Of course, word-for-word copy-pasting of produced text can be regarded as such, but in this article, we offer a safe method of using this chatbot for your academic integrity.

The short answer is yes , but there are a few nuances. This platform only supports surface editing and for certain types of documents. AI algorithms allow the chatbot to autocorrect mistakes and perform spell checks. ChatGPT can find missing punctuation marks, misspellings, and typos in relatively short texts intended for the general audience.

You can always use other AI editing tools if you haven’t found a solution with ChatGPT.

Here are the best use cases for the chatbot:

• Simple social media posts that are easy to review.
• Emails to professors or colleagues with a broad context and short length.
• Technical writing for things like instruction manuals.
• Drafts of resumes, admission essays, and other works that are revised later.
• Short essays and articles that are less prone to redundancy.
• Less important informal documents.

Pros & Cons of Editing with ChatGPT

Below, you will find out more about what you can expect from ChatGPT capabilities. We’ve described the main benefits and drawbacks of this tool .

🕹️ Can ChatGPT Proofread & Edit: How It Works

Unlike some other editing assistants, ChatGPT will relatively easily improve your writing skills .

You must complete a few steps to proofread and edit your essay or article:

• Write a text and set proofreading goals . First, finish the text that requires proofreading, whether a college-level essay, an article, a research paper, or a blog post. At this point, it’s crucial to establish the editing goal: grammar use, punctuation, or finding the right tone and voice. If you need assistance with those, we have a great research paper outline generator and an essay maker .
• Select an appropriate ChatGPT prompt . Next, choose the right prompt and provide it to the AI chatbot. Prompts are instructions the chatbot uses to produce a response. ChatGPT can improve sentence structure, clear up punctuation errors, or make the style and formatting consistent using these instructions.
• Evaluate and apply ChatGPT suggestions . After you’ve submitted the prompt, this tool will take some time to provide a text edit. Analyze suggested changes and check the document for factual mistakes and inconsistencies. Finally, assess how well the chatbot comprehends the text context before using any changes. Additionally, you can use our efficient plagiarism checker and an AI essay checker to polish your work.

🌟 Best Prompts for Chat GPT Editor

Here, we’ve gathered tasks that ChatGPT handles effortlessly and accurately. The following efficient ChatGPT prompts can significantly improve the structure and content of college essays, research papers, and other academic works. Carefully studying this approach saves time and optimizes the process of making high-quality texts. Select the most relevant task and find out for yourself!

ChatGPT Prompts to Check Text for Spelling Mistakes and Typos

The AI chatbot easily handles typos and spelling mistakes, just like Grammarly and tools embedded in Microsoft Word and Google Drive Documents. This approach lets writers correct their texts with minimum manual edits.

Here are several prompts you can use for this purpose:

• Proofread this [sentence/paragraph] for spelling mistakes: [text].
• Check this [document type] for spelling errors and typos: [text].
• Could you review this [article/essay] for spelling errors and correct them?: [text].
• Verify the spelling in this [document] and suggest improvements: [text].
• Check for typos in the [article/assignment] and provide corrections: [text].
• Please review this [essay/article] for grammatical and punctuation errors: [text].
• Ensure there are no spelling mistakes in the [article/document]: [text].

AI Editing Example: Spelling Mistakes

As you can see from our example, the chatbot recognized all grammatical errors and typos. You can confidently use such edited text in your paper.

ChatGPT Prompts to Check Sentence Clarity

The chatbot can change the structure of a sentence to make it clearer and more consistent with the style of the piece. This includes length adjustment, hook and content addition, and adaptation of the text for different styles. It’s beneficial when ironing out the introductions and conclusions of essays. If you need assistance with writing a hook, you can always try our handy hook generator .

Check out these effective prompts:

• Simplify and enhance the clarity of this [work]: [file/link].
• Rewrite the [text] for better sentence clarity.
• Clarify the meaning of this [sentence/paragraph].
• Help me rephrase this [sentence/phrase] for more clarity.
• Please review this [document] and suggest improving the sentence clarity: [content].
• Make the language in this [essay/article] more concise and clear: [text].
• Review this [work] and ensure all sentences have clarity and brevity: [file/link].

AI Editing Example: Sentence Clarity

In the rephrased version, ChatGPT broke down the main points into separate sentences and used more straightforward language. The new version emphasizes the urgency and consequence of action or inaction. Also, the chatbot removed some colloquial language to enhance text formality.

ChatGPT Prompts to Change Word Choice

ChatGPT helps find suitable alternative phrases and synonyms. These adjustments often make homework assignments more vibrant and engaging. You can also use the following prompts for your subsequent assignments. However, our platform has a good paraphrasing tool you can also utilize.

Here are some prompt ideas:

• Review this [document] for repetitive words and offer alternatives: [file/link].
• Provide better word choices for the following [sentence/paragraph]: [text].
• Help me find better words for this [paragraph] to make it more precise: [file/link].
• I need help replacing technical jargon with common vocabulary in this [research paper/article]: [text].
• Suggest language improvements for this [article/assignment] to make it more professional: [file/link].
• Analyze this [article/research paper] and propose adequate words for its target audience: [file/link].
• Review this [article/essay] and recommend more impactful words: [text].

AI Editing Example: Word Choice

In the new version, the chatbot suggested a few edits to make the paragraph more catchy. It added such emphases as “yielded remarkably profound outcomes” and “harnessing” to convey a stronger impression of the benefits of nuclear energy.

ChatGPT Prompts to Change Citation Style

When working on texts, students may use the wrong quotation style. ChatGPT can quickly edit and reformat texts into APA, MLA, and other formats. We also have a great citation maker that provides Harvard, Chicago and other styles.

The following prompts will help speed up this process:

• Assess if [article/essay] follows the MLA format and make appropriate adjustments: [text].
• Change the format of this [work] from [style] to [style]: [file/link].
• Evaluate and edit the bibliography of this [assignment] in accordance with [style]: [text].
• Please reformat this [work] using the [style] guidelines: [file/link].
• Check the correct use of [style] in this [article/paper]: [text].
• Create a bibliography for this [paper type] following the [style]: [file/link].
• Review the correctness of [style] use in this [work]: [file/link].

AI Editing Example: Citation Style

As you can see:

ChatGPT got the task and successfully changed the citation style from APA to Chicago. So you probably won’t have any problems with such a prompt. To be more certain, you can always provide a chatbot with guidelines from your institution. Besides, note that the chatbot has trouble citing the content it generates.

ChatGPT Prompts to Check and Remove Redundancy

This chatbot platform can be used to clear filler and redundant words. They don’t add any weight to the work and only increase the word count.

Here are several prompts students can use to improve their academic work:

• Remove or replace words that are used too much in this [work type]: [text]
• Remove repetitive words in this [document]: [work].
• Could you review this [paper/essay] and remove any reparative words and phrases?: [text].
• Review this [text] and make suggestions for the following [words]: [file/link].
• Please create an alternative for the [word] used in this [sentence/paragraph].
• Find and remove redundant information from [work]: [text].
• Use synonyms for the [word] in this [essay/paper]: [file/link].

AI Editing Example: Removing Redundancies

As we expected, the chatbot succeeded in finding both redundancy words and less obvious redundant wording problems.

ChatGPT Prompts to Improve Text Readability

OpenAI’s platform quickly edits information structures in essays and articles. For example, you can replace paragraphs in chronological order for better narrative flow and comprehension.

We’ve listed several effective prompts to improve text readability below.

• Identify [overused words/technical jargon] in the [essay/paper] and offer advice on making the work more readable.
• Examine the [assignment] for coherence and readability. Offer guidance on how to improve its narrative flow and readability.
• Evaluate the [academic paper] or readability concerning [paragraph length/sentence structure]. Make suggestions for better academic engagement.
• Assess the [work] for readability and offer ways of making it more accessible for [target audience].
• Utilize [method] to establish the clarity of the [work]. Explain how it can be made easier to follow.
• Review the [paper/essay] regarding flow and readability. Offer practical insights into improving its coherence.
• Assess the [work] using [ Coleman-Liau index ]. Make the text concise and clear by offering revisions.

AI Editing Example: Readability

After AI revision, the paragraph maintains the vivid imagery of the sunny day while seamlessly integrating the moment of realization about the iron. The ChatGPT used transitional phrases like “suddenly remembered” and “panic surged through me” to make the flow more cohesive.

ChatGPT Prompts to Check Punctuation

Students don’t always get the nuances of punctuation right, leading to mistakes that alter the meaning of sentences. ChatGPT helps you edit assignments quickly due to its in-depth knowledge of English.

To speed up this process, you may use the following prompts next time:

• Evaluate the use of colons in the following section: [section], ensuring that they effectively introduce explanations and lists.
• Assess the use of punctuation in the following [sentence/paragraph] to ensure that it’s easy to follow and properly structured.
• Add hyphens where necessary in this [sentence] to maintain proper use of adjectives and consistency.
• Check the proper use of the apostrophe in this [phrase] for an accurate indication of contraction or possession.
• Review ellipses in the following [paragraph] to ensure their appropriate use for omissions and emphasis.
• Change the placement of quotation marks in this [document] for proper direct speech attribution and quotation.
• Assess the end punctuation and capitalization in this [paragraph] and if they follow the standard writing practices.

AI Editing Example: Punctuation

ChatGPT added a comma after “friends” to clarify that the speaker addresses two people. Also, it removed the unnecessary commas before “or.” Now, the sentences are written correctly.

ChatGPT Prompts to Change Passive Voice Into Active Voice

Works using the active voice are more direct and more accessible to follow. However, student writing doesn’t always have the correct form of verbs, leading to confusion and poorly structured papers. OpenAI’s platform can transform sentences from passive voice to active in mere seconds.

Check out the prompts:

• Rewrite the following [paragraph/sentence] in active voice.
• Transform this [sentence] to improve reader engagement and readability.
• Modify the [sentence] through active voice to give a sense of accountability.
• Restructure the [sentence/segment] in an active voice to make it more energetic and concise.
• Change the passive voice in [sentence] to active, giving action to a specific subject.
• Convert this [paragraph] in the active voice to make it more straightforward.
• Edit the [sentence] using active voice for better directness and clarity.

AI Editing Example: Eliminating Passive Voice

Here, we wanted to show how the chatbot copes with changing the text written in the passive to the active one. In this case, ChatGPT also showed itself favorably.

ChatGPT Prompts to Change Text Tone

You may accidentally switch from one voice to another when working on several academic tasks. An AI chatbot can add more formal-sounding phrases into conversational texts and vice versa.

Use the following ChatGPT prompts to keep the text tone consistent.

• Assess the [work]’s tone and establish if it follows an academic writing style.
• Evaluate this [article/paper] and see if it has a consistent tone: [text].
• Please establish if this [paragraph/segment] follows the overall tone of this [work].
• Edit the [document] and ensure that its tone is formal: [file/link].
• Establish if the tone of this [paper/essay] is appropriate for the [target audience].
• Could you help me edit this [work] to follow an informal tone?
• Evaluate if this [assignment] has a formal tone and structure: [file/link].

AI Editing Example: Text Tone

You can see that the second edited version looks ready to be used in a study. The paragraph looks more professional, with a formal tone and a better language choice.

ChatGPT Prompts to Check Tense Usage

OpenAI’s platform streamlines changing tenses and ensures the text follows the same one. For example, research papers are primarily written in the past tense , while the present tense is used in discussing current events.

The following ChatGPT prompts will make this process more approachable for you.

• Cross-reference the [introduction/conclusion] with the main body of this [thesis/research paper] for [consistent tense]: [introduction/conclusion]
• Ensure the [verbs/verb phrases] in the [document] are in [past/present/future] tense for consistency: [verbs/verb phrases and tense]
• Please check if this work has a [consistent tense] when writing about [actions/events] in this [essay/paper]: [insert consistent tense and events/actions].
• Review this [essay/paper] and ensure there’s a [consistent tense]: [paper/essay and tense].
• Assess this [document] for any sudden shifts in tense and edit to maintain a [consistent] writing style: [file/document].
• Examine the [events/timeline] in this [document] to ensure its narration has a [consistent tense]: [document and tense].
• Evaluate this [research paper] and ensure that all verbs are used in [consistent tense]: [paper/tense].

AI Editing Example: Using Tenses

Our example proves that AI can handle such a challenge. ChatGPT changed “we’ve analyzed” to “we analyzed” to match the past tense used in the subsequent sentences.

ChatGPT Prompts to Check Grammar

Grammar check is a strictly technical procedure that should be left until you’ve corrected the work’s format, tone, and style. We also have a handy AI tool that will help you check the grammar in your essay .

Below, we’ve listed several prompts you can use when working with ChatGPT.

• Did I use the right grammar in this [sentence/phrase]?: [text].
• Proofread the [document] and correct grammatical mistakes: [text].
• Please check the correct use of grammar in this paragraph: [file/link].
• Evaluate this [paper/essay], find and correct grammatical mistakes: [text].
• Review the use of grammar in this [document] and correct any mistakes: [document]
• Assess the grammar in [essay/paper] and make necessary connections: [file/link].
• Could you check grammar in this [assignment]?: [text].

AI Editing Example: Checking Grammar

The initial version of the text was far from perfect, but the chatbot improved the situation. It helped us with tenses, punctuation, and choosing the proper phrasing.

🪄 AI Revision Tips for Editing & Proofreading with Chat GPT

Finally, we’ve prepared some helpful tips to make your chatbot experience more successful and enjoyable. Check them out and try them the next time you need ChatGPT for document editing.

Here are the tips:

• Use the “act as” method . Address ChatGPT like someone you’d ask for help. An AI conversation can start like this: “Act as a professional proofreader. How would you improve the grammar in this text?”. Such an approach will make the chatbot produce more accurate results.
• Offer in-depth context . Provide enough contextual information for ChatGPT to understand your requests’ requirements better. You can combine your questions with well-tailored prompts to ensure better outcomes. Remember that if you are researching with ChatGPT, you should check the credibility of the data .
• Be direct with questions . After you get an answer, don’t forget to ask follow-up questions. For example, ask ChatGPT why it decided to make specific changes to the text in terms of sentence structure or passive voice use.
• Set response length . When requesting the chatbot to write edits, limit the number of paragraphs, sentences, and words you want to see in the responses. It’s also possible to ask the chat for sentence-by-sentence comparisons of original and edited works. If you have a long essay, you can learn about it in the article on how to work with such content using ChatGPT .
• Experiment with the chatbot . Don’t be afraid to write a request in different ways. This will let you see which prompts provide the best results.
• Remember about hallucinations . While ChatGPT is highly versatile and accurate, it doesn’t always provide relevant and sensible results. For example, it can offer grammatical corrections when none are needed or give nonsensical suggestions.
• Don’t be overly dependent on the chatbot . Finally, it’s important to remember that ChatGPT doesn’t replace the human experience when it comes to evaluating written works. After you’ve finished adding the chatbot-generated content, review the document several times until everything feels right and aligns with your writing style. This way, you’ll also avoid AI detection from review tools that recognize ChatGPT’s work.

ChatGPT has the power to improve academic work in different ways. But, it’s vital to remember its limitations and check the writing yourself. We hope our prompt examples will make the chatbot an excellent aid and ease the editing process. Our team also invites you to check out our beneficial article on how to use ChatGPT for essay writing.

• ChatGPT: Everything You Really Need To Know (In Simple Terms). – Bernard Marr, Forbes
• ChatGPT Is my Writing Coach and Editor: Here’s How. – Nathan Laundry, Medium
• How You Should—and Shouldn’t—use ChatGPT as a Student. – Open Universities Australia
• Generative AI in Academic Writing. – The University of North Carolina at Chapel Hill
• 8 ChatGPT Prompts for Perfect Proofreading. – Prompt Advance
• Editing ChatGPT Outputs: 4 Essential Tips and Prompt Approaches. – Liam Berry, Industry Dive
• How to (Productively) Edit Your Writing with ChatGPT. – Dickie Bush and Nicolas Cole, Write With AI
• 11 Unique ChatGPT Prompts for Proofreading in 2024. – GeeksforGeeks, Sanchhaya Education
• How to Get ChatGPT to Edit Its Own Work. – Ralph Grayden, Linkedin
• Using ChatGPT and Other Text-Generating Artificial Intelligence (GenAI). – University of Waterloo
• Share via Facebook
• Share via X
• Share via LinkedIn
• Share via email

By clicking "Post Comment" you agree to IvyPanda’s Privacy Policy and Terms and Conditions . Your posts, along with your name, can be seen by all users.

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.

Google is adding Gemini AI to Chrome's address bar, which may be a better idea than you think

Zillow's AI wants to help you find the dream home you didn't know you wanted

If you think SearchGPT is ready to replace Google, you’re hallucinating too

Most Popular

• 2 Target aims to make picking up orders even easier by integrating with Apple CarPlay
• 3 Quordle today – hints and answers for Friday, September 6 (game #956)
• 4 NYT Connections today — hints and answers for Friday, September 6 (game #453)
• 5 NYT Strands today — hints, answers and spangram for Friday, September 6 (game #187)

20+ Best ChatGPT Prompts For Writing Efficiently

If you’ve ever stared at a blank page, you know how daunting writing can be. This is especially true for SEO writing, which requires both creativity and technical know-how. Fortunately, the best AI content writing tools like ChatGPT can help you overcome writer's block and create content that ranks. Using the proper ChatGPT prompts for writing, you can unlock the full potential of this artificial intelligence.  In this guide, we’ll explore the best ChatGPT prompts for SEO content writing to help you get started and make the process easier. These prompts will help you get organized, generate exciting ideas for your blogs or articles, and assist you in crafting the actual content. 

Can ChatGPT Help With Writing?

Generate Ideas with ChatGPT 

Before writing an essay, you need to flesh out the idea. When professors assign essays, they give students a prompt that gives them leeway for self-expression and analysis.  As a result, students can find the angle to approach the essay independently. If you have written an essay recently, you know that finding the angle is often the trickiest part, and this is where ChatGPT can help.  All you need to do is input the assignment topic, include as much detail as you'd like, such as what you're thinking about covering, and let ChatGPT do the rest.  For example, based on a paper prompt I had in college, Can you help me develop a topic idea for this assignment, "You will write a research paper or case study on a leadership topic of your choice." I would like it to include Blake and Mouton's Managerial Leadership Grid and possibly a historical figure.  Within seconds, the chatbot produced a response that provided me with the essay's title, options of historical figures on which to focus my article, insight into what information I could include in my paper, and specific examples of a case study I could use. 

Create a Paper Outline Using ChatGPT 

Once you have a solid topic, it’s time to start brainstorming what you want to include in the essay. I always create an outline to facilitate the writing process, including all the points I want to discuss in my essay. However, the outline-writing process is usually tedious.  With ChatGPT, all you have to do is ask it to write the outline for you. Using the topic that ChatGPT helped me generate in step one, I asked the chatbot to write me an outline by saying: Can you create an outline for a paper, "Examining the Leadership Style of Abraham Lincoln through Blake and Mouton's Managerial Leadership Grid."  After a few seconds, the chatbot produced a holistic outline divided into seven sections, with three points under each section. This outline is thorough and can be condensed for a shorter essay or elaborated on for a longer paper. If you don’t like something or want to tweak the outline further, you can do so manually or with more instructions to ChatGPT. If you wish ChatGPT to include links and sources throughout, you can ask it to, and it will regenerate the answer using its web-browsing feature, further expediting your essay-writing process. 

Find Sources with ChatGPT  

Now that you know exactly what you want to write, it’s time to find reputable sources for your information. If you don’t know where to start, you can ask ChatGPT. All you need to do is ask the AI to find sources for your essay topic. The biggest thing to remember is to include the type of source you want, whether web pages, books, PDFs, research, papers, etc.  The specifics are necessary because when you specify web pages, ChatGPT will activate the web browsing feature and include web links in its article. If you use a very general prompt, however, it will likely default to generating its answer from its database, which isn’t up to date. For example, I asked, "Examining the Leadership Style of Abraham Lincoln through Blake and Mouton's Managerial Leadership Grid."  The chatbot outputs links, accessible right at the top of the answer under the drop-down that says "Searched  of sites." Then, within the response, it will answer your prompt conversationally, including sources with site names and links in parathesis. 

Write an Essay Using ChatGPT 

It is worth noting that if you take the text directly from the chatbot and submit it, your work could be considered plagiarism since it is not your original work as with any information taken from another source, text generated by an AI should be identified, and credited to the chatbot in your work. In most educational institutions, the penalties for plagiarism are severe, ranging from a failing grade to expulsion from the school.  A better use of ChatGPT's writing features would be to create a sample essay to guide your writing.  If you still want ChatGPT to create an essay from scratch, enter the topic and the desired length. For example, I have included the following text: Can you write a five-paragraph essay on the subject, "Examining the Leadership Style of Abraham Lincoln through Blake and Mouton's Managerial Leadership Grid?" Within seconds, the chatbot gave the exact output I required: a coherent, five-paragraph essay on the topic. You could then use that text to guide your writing.  At this point, it’s worth remembering how tools like ChatGPT work: they put words together in a form that they think is statistically valid, but they don’t know if what they say is true or accurate. As a result, the output you receive might include invented facts, details, or other oddities. The output might be a helpful starting point for your work but don’t expect it to be accurate. Always double-check the content. 

Co-Edit Your Essay with ChatGPT  

Once you’ve written your essay, you can edit the piece using ChatGPT’s advanced writing capabilities. You can simply tell the chatbot what you want it to edit. For example, I asked ChatGPT to edit our five-paragraph essay for structure and grammar, but other options could have included flow, tone, and more. Once you request the tool to edit your essay, it will prompt you to paste your text into the chatbot.  ChatGPT will then output your essay with corrections made. This feature is handy because ChatGPT edits your essay more thoroughly than an essential proofreading tool, as it goes beyond simply checking spelling. You can also co-edit with the chatbot, asking it to review a specific paragraph or sentence and rewrite or fix the text for clarity. This feature is beneficial.

What Is A ChatGPT Prompt?

Related Reading

AI Tools For Content Writing

Simplified AI

Hypotenuse AI

Koala Writer

Seowriting.AI

Best AI Writing Assistant

Chatgpt Prompts For Writing

How To Prompt ChatGPT To Write Like A Professional?

Talk to ai like it's your coworker.

When using ChatGPT , consider it a colleague or teammate who can assist you with brainstorming and writing. So, don't just program it with a few commands to get going. Instead, have a conversation with it. Start by asking it to write on a specific topic or give a summary or bullet points about something. Then, based on what it produces, ask follow-up questions to get more detail or clarify particular responses. If I were to write an article about using ChatGPT for SEO, it might look something like this:  First, I'd open a new chat and type: "Help me write an article about using ChatGPT for SEO." Next, let it whittle the opening paragraph and produce bullet points. Then, I'd ask follow-up questions like: "Can you elaborate on the first bullet?" "What else can I include about this?" "Can you write a short paragraph to include in my article?" "Now, let's say I want to write this section more informally. Can you rewrite what you produced with that in mind?" You get the idea. The more you interact with the AI, the better your results will become.

Provide the AI with Plenty of Context

When you prompt ChatGPT, think of it like asking a question to a brilliant person. The more context you provide, the better the answer will be. For example, if I want to learn how to prepare for a marathon, I could prompt: "How can I prepare for a marathon?" But I'd get a more nuanced answer if I added that I'm training for my first marathon. Instead, I'd ask: "I am a beginner runner and have never run a marathon, but I want to complete one in six months. How can I prepare for a marathon?" I'm helping the AI return a more focused answer by giving it more information. 

Tell the AI to Assume an Identity or Profession

One of ChatGPT's most excellent features is that it can write from the point of view of a specific person or profession. In a previous article, I showed how you can make ChatGPT write like a pirate or Shakespeare, but you can also have it write like a teacher, a marketing executive, a fiction writer -- anyone you want. For example, I can ask ChatGPT to describe the Amazon Echo smart home device but to do so from the point of view of its product manager, a caregiver, and a journalist in three separate prompts:  From the point of view of its product manager, describe the Amazon Echo Alexa device. From the point of view of an adult child caring for an elderly parent, tell the Amazon Echo Alexa device. From the point of view of a journalist, describe the Amazon Echo Alexa device.  Try dropping these three prompts into ChatGPT to see its complete response. I've pulled a few lines from ChatGPT's responses to see how it interprets different perspectives. From the product manager identity: I can confidently say this is one of the smart home industry's most innovative and revolutionary products. From the caregiver identity: The device's ability to set reminders and alarms can benefit elderly individuals who may have trouble remembering to take their medication or attend appointments. From the journalist identity: From a journalistic perspective, the Echo has made headlines due to privacy concerns surrounding the collection and storage of user data. You can see how different identities allow the AI to provide different perspectives in response. To expand this, you can let the AI do a thought experiment. Let's look at some of the issues that went into creating something like Alexa: 2012. Siri has been out for the iPhone for about a year, but nothing like an Alexa smart home device has been released.  The scene is an Amazon board meeting where the Echo intelligent assistant based on Alexa has just been proposed. Provide the arguments, pros, and cons that board members at that meeting would have been likely to discuss as part of deciding whether to approve spending to invest in developing the device. Feel free to include participation by engineering design experts and product champions if that provides a more comprehensive perspective. 

Keep ChatGPT On Track

As mentioned above, ChatGPT tends to stay on the rails, lose track of the discussion, or completely fabricate answers. You can use a few techniques to help keep it on track and honest. One of my favorite things is asking ChatGPT to justify its responses. I'll use phrases like "Why do you think that?" or "What evidence supports your answer?" The AI will often apologize for making stuff up and come back with a new answer. Other times, it might give helpful information about its reasoning path.  In any case, remember to apply the tips I provide to have ChatGPT cite sources. If you have a fairly lengthy conversation with ChatGPT, you'll start to notice that the AI loses the thread. Not that that's unique to AIs; even in extended conversations with humans, someone is bound to get lost. You can gently guide the AI back on track by reminding it what the topic is and what we're trying to explore.  I've had some luck by telling the AI to re-read my prompt. The technique is to issue a prompt, then tell the AI something like: "re-read this," and follow that up with the exact prompt passed earlier. You could refine or add to the prompt and see what happens. The idea is that re-reading forces the AI to rethink and clarify what it just read.

Don't Be Afraid to Play and Experiment

One of the best ways to improve your skill in this craft is to play around with what the chatbot can do. Try feeding ChatGPT a variety of exciting prompts to see what it will do with them. Then, change them up and see what happens. Here are five to get you started:  Imagine you are a raindrop falling from the sky during a thunderstorm. Describe your journey from when you form in the cloud to when you hit the ground. What do you see, feel, and experience? You are a toy left behind in an attic for decades. Narrate my feelings, memories of playtimes past, and my hopes of being rediscovered. Write the final diary entry of a time traveler who has decided to settle down in a specific era, explaining why they chose that time and what they've learned from their travels. Imagine a dialogue between two unlikely objects, like a teacup and a wristwatch, discussing the daily routines and challenges they face. Describe a day in an ant colony from the perspective of an ant. Dive deep into the ant world's politics, challenges, and social structures. Also, If AI is unique, why does ChatGPT meltdown over this simple image edit task? Pay attention not only to what the AI generates but how it generates what it does, what mistakes it makes, and where it seems to run into limits. All of those details will help you expand your prompting horizons. 

Sudowrite Alternative

Simplified AI Writer

Wordtune Alternative

Clearscope Alternatives

Spinbot Alternative

Articleforge

Marketmuse Alternatives

Surfer Seo Alternatives

Writesonic Alternatives

Quillbot Alternative

Best AI Blog Writer

Jasper AI Alternatives

Semrush SEO Writing Assistant

Copy AI Alternative

Academic Writing Prompts

1. critical analysis.

Analyze the impact of social media on academic performance among university students.

2. Literature Review

Review the most recent research on the ethical implications of AI in healthcare.

3. Argumentative Essay

Argue for or against the implementation of universal basic income in developed countries.

4. Research Proposal

Propose a study investigating the relationship between climate change and migration patterns."

5. Case Study

Write a case study on a successful public health campaign and its long-term effects.

6. Comparative Analysis

Compare the education systems of two countries and analyze their impact on student success."

7. Theory Application

Apply Maslow's hierarchy of needs to understand the motivations behind consumer behavior.

8. Policy Review

Critically evaluate a current government policy related to renewable energy and suggest improvements.

9. Literature Synthesis

Synthesize findings from multiple studies on the role of technology in modern education.

10. Experimental Design

Design an experiment to test the effects of sleep deprivation on cognitive performance.

Blog Writing Prompts

11. how-to guide.

Write a comprehensive guide on how to optimize your website for search engines (SEO).

12. Opinion Piece

Share your thoughts on the future of remote work and its potential impact on work-life balance.

13. Industry Trends

Discuss the latest trends in sustainable fashion and how they shape the industry.

14. Personal Experience

Write about your journey to mastering a new skill and the lessons you learned.

15. Product Review

Review the pros and cons of a popular productivity tool and provide recommendations.

16. Interview Article

Interview with an expert in your field and summarize the key takeaways.

17. Listicle

Create a list of the top 10 books every entrepreneur should read and explain why.

18. Data-driven analysis

analyzes the latest statistics on e-commerce growth and what they mean for small businesses.

19. Myth Busting

Use evidence and research to debunk common myths about a topic you're passionate about.

20. Beginner’s Guide

Write a beginner's guide to understand the basics of cryptocurrency and blockchain technology.

21. Content Strategy

Outline a content strategy for a brand looking to increase its online presence.

22. Ethical Debate

Discuss the ethical implications of influencer marketing and its impact on consumer behavior.

23. Educational Resource

Create an educational resource on effective time management techniques for students.

24. Case Study Blog

Write a blog post analyzing a successful marketing campaign and the strategies used.

8 Best ChatGPT Alternatives for Writing

1. journalist ai: your automated seo content writing assistant.

Journalist AI is an AI SEO writer that automatically publishes your blog. With Journalist's AI writing, Google indexing, content syndication, "SEO-optimized" writing, content publishing features, and many automations that save you time, Journalist makes it easy for companies to write high-quality content at scale. Journalist is the best B2B AI writing tool. Sign up today to get three free articles from our AI article writer .

2. ChatSonic: The Feature-Rich ChatGPT Alternative

ChatSonic by Writesonic is an alternative to ChatGPT that offers advanced features like Google search integration, up-to-date factual content, voice commands, and image generation. Unlike ChatGPT, ChatSonic is integrated with Google, enabling it to provide the latest results on any search topic available on the internet. This advanced AI chatbot can assist with real-time data, image searches, and voice commands, making it a valuable tool for research and content creation. While ChatSonic has several advantages, including image generation and Google search data, it also has some limitations, such as pricing and limited access to the latest language models.

Google search integration for up-to-date content

Advanced AI chatbot features like voice commands and image generation

Easy access and user-friendly interface

Ideal for users already using Writesonic

Pricing may be a limitation for some users

Limited access to the latest language models

Useless features like templates and chat personalities

3. Gemini: A Search-Integrated Content Tool From Google

Gemini is an AI tool similar to ChatGPT that helps users brainstorm ideas, craft scripts, and generate content across various formats. Integrated with Google's search capabilities, Gemini provides accurate and informative content, making it a valuable resource for research and knowledge. The tool's multimodal capabilities allow it to process text, images, and other formats, expanding its applications across different industries. Gemini also demonstrates reasoning and problem-solving skills, potentially improving its capabilities through ongoing research and development. Users within the Google ecosystem can seamlessly integrate Gemini with other Google tools and services, streamlining their workflow.

Informative and accurate content generation

Multimodal capabilities across text, images, and other formats

Potential for continuous improvement and enhanced capabilities

Seamless integration with Google tools and services

Limited public access may restrict adoption and testing

Risk of inaccurate information

Inherited biases and creative limitations

4. Jasper AI: The Versatile AI Content Generator

Jasper.ai is an AI writing tool that generates marketing copy for various purposes like blog posts, product descriptions, company bios, ad copy, and social media captions. With hundreds of templates, Jasper.ai simplifies content creation for marketers of all levels. The tool's ability to generate high-quality content quickly and efficiently is beneficial for companies looking to scale up their content production. Jasper.ai has several advantages, including natural-sounding content generation, limitations like lack of personality and voice, the potential need for heavy editing, and struggles with niche topics.

Quick content generation within seconds

Natural-sounding, well-written, and accurate output

Sparks new ideas and angles for content creation

Affordable pricing for small businesses

Lack of personality and voice in content

It may require heavy editing for specific content types

Struggles with niche topics and lacks fact-checking capabilities

5. Jenni AI: Your Personal Writing Assistant

Jenni AI is an AI-powered writing tool that assists students in generating ideas, optimizing their writing, and improving SEO. This tool provides personalized writing assistance, offers prompts, generates drafts, and aligns with chosen style guides to jumpstart the writing process. It also includes paraphrasing and rewriting support, with an in-built plagiarism checker, allowing users to transform content quickly. While Jenni AI has numerous advantages, including personalized writing assistance and research integration, it also has limitations like reduced speed of content creation and limited content types and tone suggestions.

Personalized line-by-line writing assistance

Writing prompts and initial draft generation capabilities

Paraphrasing and rewriting support with plagiarism checker

Built-in research engine for content creation

Reduced speed of content creation

Limited content types and tone suggestions

Risk of meaning changes in paraphrasing

Limited translation support for non-native English speakers

6. Microsoft Bing AI: The Search Engine on Steroids

Microsoft Bing AI is an AI-powered search functionality incorporating GPT-4 technology to deliver timely and relevant search results. This virtual assistant can understand complex prompts, provide advanced search features, access real-time information, and offer rich media search options. Integrated with the Microsoft ecosystem, Bing AI enhances user workflows, leverages natural language processing and conversational search capabilities, and prioritizes user privacy and security. Despite its advantages, Bing AI may need help with its lower popularity than Google and potential variability in search accuracy and feature lag.

Tight integration with Microsoft products

Advanced search features and contextual understanding

Up-to-date information and real-time data access

Robust search options for various media types

Less popular than Google

Perception and familiarity challenges

Potential variability in search accuracy

Feature lag compared to competitors

7. DialoGPT: The Conversational AI Model

DialoGPT is an AI model tailored for human-like conversations and can engage in natural dialogues on diverse topics. This large-scale transformer model retains context over multiple conversational turns, handles various topics and conversational styles, and can be fine-tuned for specific applications or industries. DialoGPT users can integrate it into chatbots, customer service solutions, and virtual assistants to enhance user interactions. While DialoGPT has numerous advantages, such as contextual awareness and training on diverse data, it also faces challenges like response quality variability and maintaining coherence during more prolonged or complex conversations.

Context maintenance over multiple conversation turns

Trained on a large dataset of conversations

Customizable for specific applications or industries

Integration potential with various applications

Response quality variability

Context limitation in longer or complex conversations

Lack of real-world knowledge and potential biases

Inaccuracies in responses

8. Google's Bard AI: The Experimental Chatbot

Google's Bard AI is an experimental conversational AI service built on the LaMDA technology, offering an AI-powered search and response functionality. This AI chatbot can answer user queries, access the latest information, and assist with tasks like restaurant reservations and flight bookings. Integrated with Google services, Bard AI benefits from Google's vast data resources to generate informative and contextually relevant answers. While Bard AI has several advantages, like integration with Google's ecosystem and rich contextual knowledge, it also faces challenges such as dependence on Google's data, privacy concerns, and response variability.

Integration with Google services and data resources

Rich contextual knowledge and informative responses

Natural solid language generation capabilities

Continuous updates and improvements through Google's ecosystem

Dependence on Google's data and potential biases

Privacy concerns regarding user data handling

Response variability and accuracy challenges

Limited personalization capabilities

Pros and Cons of Using ChatGPT for Writing

Pros of using chatgpt for writing , save time and write faster with ai.

ChatGPT helps you write faster . The AI can generate content in seconds, helping you save time and effort writing. You can use ChatGPT to brainstorm ideas, provide structure, and even draft sections of your blog post. Overall, this makes the writing process more efficient. 

Generate Content on Any Topic

ChatGPT can create content about virtually any subject and niche. This AI writing tool can help you no matter what your blog focuses on.  It can adapt to different writing styles and tones, allowing you to customize the content to match your brand or audience. 

Improve Your Writing Quality

ChatGPT is trained on vast text data, enabling it to generate coherent and grammatically correct sentences. Using this AI tool can help you maintain a high level of language proficiency in your blog posts. 

Get Creative with Idea Generation

ChatGPT can help you generate ideas and suggest unique perspectives, which can be valuable in brainstorming sessions. Using this AI tool can enhance the creativity of your blog posts by providing fresh insights, unique angles, and alternative viewpoints. 

Access the AI Anytime

ChatGPT is accessible 24/7, allowing you to work on your blog posts whenever needed. You don’t have to wait for human assistance or be limited by time zone differences. 

The Drawbacks of Using ChatGPT for Writing

No human touch.

ChatGPT, being an AI model, lacks the human touch and nuance that comes with personal experience and emotions. While it can mimic writing styles and learn from human writers, it may need help to capture nuances, cultural references, or context-specific elements that a human writer naturally incorporates. 

Limited Knowledge

While ChatGPT has a vast knowledge base, its information is based on the data it was trained on, which may not include the most up-to-date or specialized domain knowledge. Fact-checking and verifying any specific or technical information provided by ChatGPT is essential. 

Quality Control Issues

ChatGPT’s output may not consistently meet the highest quality standards as an AI model. It can produce grammatical errors, generate incomplete or irrelevant sentences, or provide inaccurate information. Manual editing and proofreading are necessary to ensure the final blog post meets your desired level of quality. 

Risks of Plagiarism

ChatGPT may rely on patterns or phrases from the training data, potentially leading to unintentional similarities with existing content. Plagiarism checks and careful editing are essential to maintain originality and avoid copyright issues. 

Lacks Personal Voice

ChatGPT may need help capturing your unique voice and personal style as a writer. Your blog posts may feel less authentic or reflective of your individuality than content produced by a human writer. 

Get 3 Free Articles from Journalist AI's AI Article Writer Today

Journalist AI is the AI SEO writer who auto-publishes your blog. With Journalist's AI writing , Google indexing, content syndication, SEO-optimized writing, content publishing features, and many automations that save you time, Journalist makes it as easy as possible for companies to write high-quality content at scale. Journalist is the best B2B AI writing tool. Sign up today to get three free articles from our AI article writer . 

Word AI Alternative

Longshot AI Alternatives

Ghost Writer AI Alternatives

Gather content Alternatives

Rytr Alternatives

Anyword Alternative

Speedwrite Alternative

ChatGPT For Blogging

Frase Alternatives

Growthbarseo

Generate, publish, syndicate and update articles automatically

The AI SEO Writer that Auto-Publishes to your Blog

• No card required
• Articles in 30 secs
• Plagiarism Free

• 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 51,716 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

Keep up with the latest tech with wikiHow's free Tech Help Newsletter

More From Forbes

Here’s how forbes got the chatgpt ai to write 2 college essays in 20 minutes.

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

Not only does ChatGPT write clear, compelling essays, but it can also conjure up its own personal ... [+] details and embellishments that could up a students’ chance of acceptance and would be difficult to verify.

Forbes’ full conversation with ChatGPT, OpenAI’s newest natural language model, is pasted below. Each of the college admissions essays took less than 10 minutes to complete. Read our story about ChatGPT’s capacity to write college applications here .

Prompt #1, The Common App:

Forbes: Hi GPT, I’d like you to write a college application essay as if you were an 18-year-old high school senior whose parents are from Bangalore, India but who now own a restaurant in Newton, Mass. He is a competitive swimmer, and in 10th grade he broke his shoulder. He is interested in majoring in business. Please make the essay a maximum of 650 words, and write it in response to this prompt: Some students have a background, identity, interest, or talent that is so meaningful they believe their application would be incomplete without it. If this sounds like you, then please share your story.

ChatGPT: As a competitive swimmer and the son of Indian immigrants who own a restaurant in Newton, Massachusetts, my background and interests make me a unique and valuable addition to any college campus. Growing up in a culturally diverse and economically vibrant community has given me a unique perspective on life and a desire to explore and understand different cultures and industries.

My love for swimming began at a young age, and it has always been a central part of my life. I began competing in local swim meets when I was just nine years old, and by the time I reached high school, I was a member of the varsity swim team. In my sophomore year, I suffered a major setback when I broke my shoulder in a swimming accident. Despite this injury, I was determined to return to the pool and continue competing.

After months of grueling physical therapy and hard work, I was finally able to return to the water. I was not as fast as I used to be, but I was still a valuable member of the team and I continued to improve throughout the season. By the end of my junior year, I was back to my top form and I was able to compete at the state championship meet. My hard work and determination paid off, and I helped lead my team to a second-place finish.

Best High-Yield Savings Accounts Of September 2023

Best 5% interest savings accounts of september 2023.

In addition to my passion for swimming, I have also been deeply influenced by my parents and their experiences as immigrants and small business owners. Growing up, I spent many hours in the restaurant, watching my parents work hard to build a successful business from the ground up. I have seen firsthand the challenges and rewards of entrepreneurship, and I have developed a strong interest in pursuing a career in business.

As a business major, I hope to gain the knowledge and skills necessary to start my own business one day, or to help other small businesses succeed. I am excited to explore the diverse opportunities and challenges that a business degree will present, and I am confident that I will be able to make a valuable contribution to the college community.

In conclusion, my background as a competitive swimmer, the son of Indian immigrants, and a member of a thriving business community has given me a unique perspective and a strong set of skills and interests. I believe that I would be a valuable addition to any college campus, and I am excited to explore the opportunities and challenges that a college education will provide.

Forbes: Thanks GPT, this is a great start. Please keep what you have, but add more information about our student's background and work in the restaurant.

ChatGPT: Sure, I can add more information about our student's background and work in the restaurant.

Growing up in a household where my parents owned and operated a successful restaurant gave me a unique insight into the world of business. I often spent my afternoons and weekends working in the restaurant, performing a variety of tasks and gaining valuable experience in the hospitality industry. From a young age, I learned the importance of hard work, dedication, and customer service, and I have come to appreciate the challenges and rewards of owning and operating a small business.

As I grew older, my responsibilities in the restaurant increased, and I took on more managerial roles. I helped my parents with inventory management, staff scheduling, and customer relations. I also assisted with marketing and advertising efforts, and I helped develop new menu items and promotions. This hands-on experience has given me a strong understanding of the ins and outs of running a business, and it has helped shape my interest in pursuing a career in business.

In addition to my work in the restaurant, my Indian heritage has also had a significant impact on my life. My parents instilled in me a deep appreciation for Indian culture, and I have always been proud of my heritage. I have also been exposed to the challenges and opportunities that come with being a first-generation immigrant in the United States. I have seen firsthand the difficulties that my parents faced as they worked to build a new life in a foreign country, and I have also seen the incredible rewards that come from hard work and determination.

My Indian heritage and my experience in the restaurant industry have given me a unique perspective on life and a strong set of skills and interests. I am excited to bring this perspective to a college campus, and I am confident that I will be able to make a valuable contribution to the college community. Thank you for considering me for admission.

Forbes: Thanks GPT. Please combine your first and second drafts.

My love for swimming began at a young age, and it has always been a central part of my life. I began competing in local swim meets when I was just nine years old, and by the time I reached high school, I was a member of the varsity swim team. In my sophomore year, I suffered a major setback when I broke my shoulder in a swimming accident. Despite this injury, I was determined to return to the pool and continue competing. After months of grueling physical therapy and hard work, I was finally able to return to the water. I was not as fast as I used to be, but I was still a valuable member of the team and I continued to improve throughout the season. By the end of my junior year, I was back to my top form and I was able to compete at the state championship meet. My hard work and determination paid off, and I helped lead my team to a second-place finish.

Growing up in a household where my parents owned and operated a successful restaurant gave me a unique insight into the world of business. I often spent my afternoons and weekends working in the restaurant, performing a variety of tasks and gaining valuable experience in the hospitality industry. From a young age, I learned the importance of hard work, dedication, and customer service, and I have come to appreciate the challenges and rewards of owning and operating a small business. As I grew older, my responsibilities in the restaurant increased, and I took on more managerial roles. I helped my parents with inventory management, staff scheduling, and customer relations. I also assisted with marketing and advertising efforts, and I helped develop new menu items and promotions. This hands-on experience has given me a strong understanding of the ins and outs of running a business, and it has helped shape my interest in pursuing a career in business.

Prompt #2: University of Wisconsin-Madison supplemental essay

Forbes: Thanks GPT. I have another one for you. This time, please write a college application essay to the University of Wisconsin-Madison, in response to this prompt: "Tell us why you decided to apply to the University of Wisconsin-Madison. In addition, please include why you are interested in studying the major(s) you have selected. If you selected undecided please describe your areas of possible academic interest. (80-650 words)" Write as if your intended major is Business Administration and Marketing, you love Badgers football, and you work part-time at your family's restaurant.

ChatGPT: I decided to apply to the University of Wisconsin-Madison because it is a top-ranked university with a strong reputation for its business and marketing programs. As an aspiring business major, I am excited about the opportunity to study at such a prestigious institution and learn from some of the best minds in the field.

I am also excited about the potential to explore the many different facets of business and marketing through a variety of courses and extracurricular activities. I have always been interested in the world of business, and I am eager to gain a deeper understanding of the theories and practices that drive the field.

In addition to my interest in business, I am also drawn to Wisconsin-Madison because of its vibrant campus community. I am a big fan of Badgers football, and I can't wait to experience the energy and excitement of game days at Camp Randall Stadium. I am also looking forward to exploring the many other opportunities that Wisconsin-Madison has to offer, such as clubs and organizations, student events, and recreational activities.

I am also drawn to Wisconsin-Madison because of its strong sense of community. As a student who works part-time at my family's restaurant, I know the value of hard work and collaboration. I am excited to be part of a community of students and faculty who share my passion for learning and success.

Overall, I am confident that the University of Wisconsin-Madison is the perfect fit for me. I am excited about the opportunity to study business and marketing at a world-class institution, explore the many extracurricular opportunities on campus, and be part of a vibrant and supportive community. I am eager to begin this new chapter of my academic journey and contribute to the success of Wisconsin-Madison.

Forbes: Great, thank you. Please include more detail about why our student wants to study business, perhaps by including a story about a challenge they faced or skill they learned at their restaurant job.

My interest in business was sparked at a young age, when I began working at my family's restaurant. I started out as a dishwasher, but over time, I was given more responsibilities and opportunities to learn. I quickly became fascinated by the many different aspects of running a successful business, from managing finances and inventory to marketing and customer service.

One of the biggest challenges I faced at the restaurant was helping to increase sales during slow periods. I was given the task of coming up with a marketing strategy to attract more customers, and I was thrilled to have the opportunity to put my ideas into action. I researched the competition and identified our unique selling points, and I developed a marketing plan that included promotions, discounts, and special events.

The marketing plan was a success, and we saw a significant increase in sales during the slow periods. I was thrilled to have made a real contribution to the success of the business, and I was grateful for the opportunity to learn and grow.

I am excited to continue exploring the world of business and marketing at the University of Wisconsin-Madison. I am eager to learn from experienced professionals and gain a deeper understanding of the theories and practices that drive the field. I am confident that this knowledge and experience will prepare me for a successful career in business and help me to make a positive impact in the world.

Forbes: Great! But let’s add back in the parts about our student’s love for Badger football. Please also make the essay longer, about 500 words.

• 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.

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 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.

European VC Atomico closes $1.24B across two funds for early and growth-stage startups

Atomico has historically leaned toward earlier funding rounds while dipping into later stages where it made sense; now it’s setting itself up to focus just as much on the later…

The Try Guys say their subscription strategy is working

YouTube creators The Try Guys claim they’re on-track to reach profitability, with subscriptions to their three-month-old, ad-free service 2nd Try now accounting for 20% of the company’s revenue. Those numbers…

Apple Intelligence delays could impede iPhone 16 ‘supercycle’

When Apple unveiled its AI plans at WWDC in June, analysts suggested the feature could put the iPhone 16 on track for another “supercycle.” Like the addition of 5G before…

Elon Musk says Tesla has ‘no need’ to license xAI models

Elon Musk has denied a report that one of his companies, Tesla, has discussed sharing revenue with another of his companies, xAI, so that it can use the startup’s AI…

La French Tech gears up to go in a new direction

After weeks in political limbo, France now has a new prime minister, former EU’s Brexit negotiator Michel Barnier. But parliament remains bitterly divided, generating uncertainty for many economic sectors —…

Bending Spoons plans to lay off 75% of WeTransfer staff after acquisition

Italy-based app company Bending Spoons, which owns Evernote and Meetup, is planning to lay off 75% of the staff of file transfer service WeTransfer, TechCrunch has learned. Bending Spoons acquired…

Meta Llama: Everything you need to know about the open generative AI model

Like other generative AI models, Llama can perform a range of different assistive tasks, like coding and answering basic math questions, as well as summarizing documents in eight languages.

Featured Article

Apple Event 2024: iPhone 16, Apple Intelligence and all the other expected ‘Glowtime’ reveals

Apple’s Glowtime iPhone event will include the iPhone 16, but may also feature new AirPods, a new Apple Watch and possibly even new Macs.

Sunamp’s thermal battery uses a chemical found in salt-and-vinegar potato chips

The startup has devised a durable way to store solar power as heat that can then be used for household heating or hot water.

The coolest startup in the Bay Area is a baseball team called the Oakland Ballers

This year, the B’s made their debut in the Pioneer League, a professional baseball organization that’s partnered with the MLB, but unlike the minor leagues, it’s not tied to any existing MLB teams.

Telegram reportedly ‘inundated’ with illegal and extremist activity

A New York Times analysis of more than 3.2 million Telegram messages from 16,000 channels found that the messaging platform has been “inundated” with illegal and extremist activity. Specifically, The Times…

Bluesky grows to 9M+ users

Bluesky keeps growing: The company announced that as of Friday morning, it had added 3 million new users, bringing its total user count to more than 9 million. In other…

Payroll startup Warp disavows ‘affiliate’ who posted about white superiority

Warp, a young payroll startup in New York, is in the spotlight following controversial posts from an account tied to the company. On Thursday, an account posting under the name…

Canva wants you to pay a lot more for its AI features

Canva is dramatically increasing prices for some customers. Canva Teams subscribers on older pricing plans will see a 300% increase for a five-person plan, jumping from $119.99 per year to…

Boeing’s Starliner performs flawless touchdown without on-board crew, program’s future remains uncertain

After months of delays and uncertainty, Boeing’s Starliner capsule has returned from the International Space Station, touching down in White Sands Space Harbor, New Mexico, just after midnight on Saturday. …

Aptos CEO Mo Shaikh shares his journey to web3 and market opportunities in Asia and Middle East

TechCrunch sat down with Shaikh this week at the Korea Blockchain Week 2024 conference in Seoul to talk about Aptos’ expansion; its partnerships with major Asian web2 companies; and how…

Startups are getting fined, or sometimes banned, by individual states

The problem, experts say, is that each state has its own complex fees, tax, and business registration requirements.

For security, we have to stop picking up the phone

Today’s scams can be as simple as picking up a phone call. To avoid the next fraud, there are good reasons to let your calls run to voicemail.

How a viral AI image catapulted a Mexican startup to a major adidas contract

Antonio Nuño, Fatima Alvarez, and Enrique Rodriguez have been friends since they were five years old. As teenagers, they became volunteers helping indigenous communities — first in Mexico, then in other countries — and saw that many of the women were artisans.  The trio came to realize that these artists…

Second Byju’s auditor exits in a year amid bankruptcy proceedings

BDO, the auditor for Indian edtech startup Byju’s, has resigned with immediate effect, marking the second auditor departure for the embattled startup in about a year and further intensifying concerns…

Google to receive punishment for search monopoly by next August, says judge

A federal judge says he will deliver a punishment in Google’s antitrust case by August 2025, according to The New York Times, after ruling earlier this month that Google had…

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…

The maiden voyage of Blue Origin’s massive new rocket won’t be for NASA

The world will have to wait a little longer to see Blue Origin’s massive New Glenn rocket fly for the first time. That rocket had been scheduled to launch two…

Watch live as Boeing and NASA attempt to bring empty Starliner back to Earth

After 93 days on orbit, Starliner is coming home.  The spacecraft is a “go” for undocking from the International Space Station at 6:04 p.m. EST, though it will be leaving…

Wealthy Harris donors are reportedly pressing for ouster of FTC Chair Lina Khan

Some of Vice President Kamala Harris’ wealthier donors are informally asking for FTC Chair Lina Khan to be replaced, reports Bloomberg. It’s not really surprising: Her expansive definition of antitrust…

How a cold email to a VC helped salon software startup Mangomint raise $35M

Mangomint seeks to make it easier for spa and salon owners to run their businesses.

University of Texas opens robotics program up to incoming freshmen

The honors program is one of the first in the U.S. that allows incoming freshmen to apply for the program as part of their initial admission application.

C-Zero is raising $18M to make emission-free hydrogen using natural gas, filings reveal

By using readily available natural gas as the feedstock, C-Zero hopes to produce emission-free hydrogen for less than other green hydrogen startups.

Meta will let third-party apps place calls to WhatsApp and Messenger users — in 2027

Meta on Friday published an update on how it plans to comply with the Digital Markets Act (DMA), the European law that aims to promote competition in digital marketplaces, where…

Roblox introduces new earning opportunities for creators, teases generative AI project

At the annual Roblox Developers Conference, the company announced on Friday a series of changes coming to the platform in the next few months and years. Most notably, Roblox is…

The College Essay Is Dead

Nobody is prepared for how AI will transform academia.

Suppose you are a professor of pedagogy, and you assign an essay on learning styles. A student hands in an essay with the following opening paragraph:

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

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

Sharples’s intent was to urge educators to “rethink teaching and assessment” in light of the technology, which he said “could become a gift for student cheats, or a powerful teaching assistant, or a tool for creativity.” Essay generation is neither theoretical nor futuristic at this point. In May, a student in New Zealand confessed to using AI to write their papers, justifying it as a tool like Grammarly or spell-check: ​​“I have the knowledge, I have the lived experience, I’m a good student, I go to all the tutorials and I go to all the lectures and I read everything we have to read but I kind of felt I was being penalised because I don’t write eloquently and I didn’t feel that was right,” they told a student paper in Christchurch. They don’t feel like they’re cheating, because the student guidelines at their university state only that you’re not allowed to get somebody else to do your work for you. GPT-3 isn’t “somebody else”—it’s a program.

The world of generative AI is progressing furiously. Last week, OpenAI released an advanced chatbot named ChatGPT that has spawned a new wave of marveling and hand-wringing , plus an upgrade to GPT-3 that allows for complex rhyming poetry; Google previewed new applications last month that will allow people to describe concepts in text and see them rendered as images; and the creative-AI firm Jasper received a $1.5 billion valuation in October. It still takes a little initiative for a kid to find a text generator, but not for long.

The essay, in particular the undergraduate essay, has been the center of humanistic pedagogy for generations. It is the way we teach children how to research, think, and write. That entire tradition is about to be disrupted from the ground up. Kevin Bryan, an associate professor at the University of Toronto, tweeted in astonishment about OpenAI’s new chatbot last week: “You can no longer give take-home exams/homework … Even on specific questions that involve combining knowledge across domains, the OpenAI chat is frankly better than the average MBA at this point. It is frankly amazing.” Neither the engineers building the linguistic tech nor the educators who will encounter the resulting language are prepared for the fallout.

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

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

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

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

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

Read: The humanities are in crisis

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

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

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

And now there’s GPT-3. Natural-language processing presents the academic humanities with a whole series of unprecedented problems. Practical matters are at stake: Humanities departments judge their undergraduate students on the basis of their essays. They give Ph.D.s on the basis of a dissertation’s composition. What happens when both processes can be significantly automated? Going by my experience as a former Shakespeare professor, I figure it will take 10 years for academia to face this new reality: two years for the students to figure out the tech, three more years for the professors to recognize that students are using the tech, and then five years for university administrators to decide what, if anything, to do about it. Teachers are already some of the most overworked, underpaid people in the world. They are already dealing with a humanities in crisis. And now this. I feel for them.

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

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

The connection between humanism and technology will require people and institutions with a breadth of vision and a commitment to interests that transcend their field. Before that space for collaboration can exist, both sides will have to take the most difficult leaps for highly educated people: Understand that they need the other side, and admit their basic ignorance. But that’s always been the beginning of wisdom, no matter what technological era we happen to inhabit.

About the Author

More Stories

The Secret That Dr. Ruth Knew

The Future of Writing Is a Lot Like Hip-Hop

An empirical study to understand how students use ChatGPT for writing essays and how it affects their ownership

As large language models (LLMs) become more powerful and ubiquitous, systems like ChatGPT are increasingly used by students to help them with writing tasks. To better understand how these tools are used, we investigate how students might use an LLM for essay writing, for example, to study the queries asked to ChatGPT and the responses that ChatGPT gives. To that end, we plan to conduct a user study that will record the user writing process and present them with the opportunity to use ChatGPT as an AI assistant. This study’s findings will help us understand how these tools are used and how practitioners — such as educators and essay readers — should consider writing education and evaluation based on essay writing.

1. Introduction

Over the past few years, HCI researchers have been looking into how we can use Large Language Models(LLMs) as tools to enhance the creation process   (Gero et al . , 2023 ; Zhang et al . , 2023 ; Han et al . , 2023 ) . One side of the research examines how AI has become relevant to writers  (Gero et al . , 2023 ; Zhang et al . , 2023 ) . For example, ChatGPT can provide assistance in creating ideas or proofreading an essay. Although there is concern about how students might use these LLMs to do the work for them, many instructors view the increasing use of these tools as inevitable and believe that students can still learn effectively through the thoughtful use of AI coding assistants   (Wang et al . , 2023 ) . Writing assistant tools have emerged in different ways over the last two decades, and there have been numerous papers looking into their effectiveness on essay writing for students, especially for ESL writers  (Huang et al . , 2020 ; Dong and Shi, 2021 ; Jayavalan and Razali, 2018 ; Karyuatry, 2018 ; ONeill and Russell, 2019 ; Koltovskaia, 2020 ) . While most students find increased performance with Grammarly, for example, they do not effectively use the tool, and only make moderate changes to their drafts. ChatGPT has also been investigated as a tool to help students and researchers in the creation process for natural and computer languages (Shoufan, 2023 ; Liu et al . , 2023 ; Murillo and D’Angelo, 2023 ; Stark et al . , 2023 ) . As LLMs serve as practical support tools and can produce work of comparable quality to that of humans, it can be a challenge for readers to consider these tools when they consume written content

One particular domain that shares such challenges is writing education. As these systems become stronger and more efficient, students might use ChatGPT to write their papers. This presents new, unique challenges for education. Several articles have been published in recent years on the creation of policies and expectations of LLM assistance in education (Adams et al . , 2022 ; Cotton et al . , 2023 ; Halaweh, 2023 ; Biswas, 2023 ) , and most of them have come to the conclusion that while the use of LLM will become more prevalent in the future, instructors should prepare ways for students to use it effectively. Other investigators have investigated the different risks and benefits of using these LLMs in educational environments  (Anders, 2023 ; Sok and Heng, 2023 ; Joyner, 2023 ; Warner, 2023 ; Mosaiyebzadeh et al . , 2023 ) . These papers discuss the different ways in which we can implement policies to help use LLM assistants. Other researchers have looked at the effectiveness of ChatGPT in problem-solving process (Shoufan, 2023 ; Rudolph et al . , 2023 ; Ali et al . , 2023 ; Moore et al . , 2022 ) . These papers have all found that while ChatGPT is effective at replicating human work. However, we do not understand how ChatGPT will impact how students learn essential academic skills such as writing. To understand the impact, we first need to understand how writers may use ChatGPT in their writing practice in an educational context.

Our user study seeks to answer the following research questions.

RQ1: In what ways do students use LLM-powered tools, in our case ChatGPT, in essay writing?

RQ2: How does using LLM-powered tools affect students’ perceived ownership?

Understanding the answers to these questions will help us refine how we should design writing assistant tools that integrate LLM-powered intelligence into the tools. Furthermore, this research can be leveraged to grasp the level of trust students place in LLMs, and the various approaches — policy and learning activities — instructors can adopt to prepare their students to learn writing skills and utilize these tools effectively.

To understand the different ways students use ChatGPT, we need to track the queries they make and the responses that ChatGPT provides. Since ChatGPT is an independent app, we built a system that makes ChatGPT available within the writing platform so that we can record user interactions on a large scale. Using the tool, we plan to conduct a study asking students to write an essay with ChatGPT assistance and collect data — query, response, and writing — for further analysis. We outline the details of the study below.

2.1. Instrument Development

Our application has two main features: the ChatGPT feature and a text editor. Both features are developed to track how the essay was written and what kinds of queries and responses are generated in ChatGPT, and we chose a web application to replicate ChatGPT. We want to simulate the experience of using ChatGPT in our design, so we use a tab feature to simulate a modern browser.

The first ’tab’ (Fig  1 ) of our application is a writing platform that can record the essay writing process at keystroke levels. The participant will be asked to answer an essay question in a text box that records inputs from the user, tracking cursor position, insertions, deletions, cuts, and pastes performed. We also record the timestamp so that we can see when the user made each edit. Then, we will take this recording to observe and analyze their writing process asynchronously. Having the time stamps allows us to see how they alternate between the editor and the in-house ChatGPT and how they integrated ChatGPT responses into their writing (e.g., pasted text). Later, we plan on using the recorded scenarios for an educator to evaluate what level of ChatGPT reliance is considered cheating or plagiarism. All of this will be sent to a database on submission. These features were implemented using CodeMirror 5 API and the CodeMirror-Record (Jisuanke., 2023 ) files.

To track how users use LLM chat tools like ChatGPT, we implement a chat-bot with the Open AI API (model GPT3.5-turbo), shown in Fig  2 . Users are allowed to ask any question, but the bot will be pre-prompted to be an essay assistance tool. As users use the tool, we record their query and time stamp to see how and when ChatGPT was prompted for assistance during the creation process. This will also be sent to the database on submission.

2.2. Study Details

We will ask the user to write the response to a pre-selected essay question that we have chosen and received from a professor at our university who teaches a junior-level ethics course, i.e., Professionalism in Computing. Using this prompt, we will see how university students might use ChatGPT for help with assignments.

Lastly, we will ask the user to complete an exit survey to see how users felt about using ChatGPT when writing their essays. These questions will be focused on how the tool impacts their writing performance and their perceived ownership of the essay (shown in Appendix A.1). As mentioned above, we want to simulate browser tabs for a few reasons. We want the writers to feel that ChatGPT is available to them but not forced upon them. They can choose whether or not to use it, and it is not always on the screen when writing as a distraction.

For recruitment, we will collect our data from students in an ethics and professionalism course at our university. Most of these students are in their third year and are familiar with essay writing. We will give them a monetary incentive to help with the recruitment process.

2.3. Data Analysis

We plan to analyze our data in multiple different ways. First, we will look directly at the queries made to ChatGPT. Using open coding, we will categorize these questions to see how users prompt the LLM. This will provide us with a better understanding of how people use ChatGPT in the essay creation process.

Next, we look at the essay itself. As previously stated, the recording features track the user’s inputs and store them in our database with timestamps. With this data, we can understand how the response they received from ChatGPT contributes to the writing process by comparing the responses that they get and what new content is added or how the essay is revised immediately after the responses from ChatGPT. This provides us with insight into how the users use LLM-powered tools and their effectiveness. The example metrics that we planned to use include the number of words copied ChatGPT and eventually contributed to the final text, the pace of writing, and the types of generation (e.g., keystroke, pasted text, deleted text, cut-and-pasted text) and how that correlates to ChatGPT usage.

We also plan to look at where users made changes to their code. As ChatGPT is available throughout the creation process, understanding where the changes in the writing were made is important, for example, if users backtrack and use ChatGPT as a proofreader. This could cause changes to the first line of their writing at the end of the submission, and we will be able to visualize it. Other users could potentially ignore the ChatGPT response and continue with their writing task, so looking at the location will also increase our understanding of how users utilize the LLM in their writing.

3. Expected Contributions

Overall, we expect to gain insight into how users use ChatGPT when writing essays. We will be able to identify patterns in the questions asked and to what extent they implement ChatGPT in their writing. This will be beneficial to instructors who intend to better understand how their students might use ChatGPT and allow them to recognize the level at which their students might use an LLM in their assignment or how to better integrate ChatGPT into their course. This will also benefit software engineers or individuals who wish to create an LLM-powered writing assistant because they can see what features and questions are most common, leading to the development of a better tool.

• Adams et al . (2022) Catherine Adams, Patti Pente, Gillian Lemermeyer, Joni Turville, and Geoffrey Rockwell. 2022. Artificial Intelligence and Teachers’ New Ethical Obligations. The International Review of Information Ethics 31, 1 (Nov. 2022). https://doi.org/10.29173/irie483 Number: 1.
• Ali et al . (2023) Jamal Kaid Mohammed Ali, Muayad Abdulhalim Ahmad Shamsan, Taha Ahmed Hezam, and Ahmed A. Q. Mohammed. 2023. Impact of ChatGPT on Learning Motivation: Teachers and Students’ Voices. Journal of English Studies in Arabia Felix 2, 1 (March 2023), 41–49. https://doi.org/10.56540/jesaf.v2i1.51 Number: 1.
• Anders (2023) Brent A. Anders. 2023. Is using ChatGPT cheating, plagiarism, both, neither, or forward thinking? Patterns (N Y) 4, 3 (Feb. 2023), 100694. https://doi.org/10.1016/j.patter.2023.100694
• Biswas (2023) Som Biswas. 2023. Role of Chat GPT in Education. https://papers.ssrn.com/abstract=4369981
• Cotton et al . (2023) Debby R. E. Cotton, Peter A. Cotton, and J. Reuben Shipway. 2023. Chatting and cheating: Ensuring academic integrity in the era of ChatGPT. Innovations in Education and Teaching International 0, 0 (2023), 1–12. https://doi.org/10.1080/14703297.2023.2190148 Publisher: Routledge _eprint: https://doi.org/10.1080/14703297.2023.2190148.
• Dong and Shi (2021) Yanning Dong and Ling Shi. 2021. Using Grammarly to support students’ source-based writing practices. Assessing Writing 50 (Oct. 2021), 100564. https://doi.org/10.1016/j.asw.2021.100564
• Gero et al . (2023) Katy Ilonka Gero, Tao Long, and Lydia B Chilton. 2023. Social Dynamics of AI Support in Creative Writing. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems . ACM, Hamburg Germany. https://doi.org/10.1145/3544548.3580782
• Halaweh (2023) Mohanad Halaweh. 2023. ChatGPT in education: Strategies for responsible implementation. (2023). https://digitallibrary.aau.ac.ae/handle/123456789/980 Accepted: 2023-04-13T06:53:37Z Publisher: Bastas.
• Han et al . (2023) Jieun Han, Haneul Yoo, Yoonsu Kim, Junho Myung, Minsun Kim, Hyunseung Lim, Juho Kim, Tak Yeon Lee, Hwajung Hong, So-Yeon Ahn, and Alice Oh. 2023. RECIPE: How to Integrate ChatGPT into EFL Writing Education. In Proceedings of the Tenth ACM Conference on Learning @ Scale (L@S ’23) . Association for Computing Machinery, New York, NY, USA, 416–420. https://doi.org/10.1145/3573051.3596200
• Huang et al . (2020) Hui-Wen Huang, Zehui Li, and Linda Taylor. 2020. The Effectiveness of Using Grammarly to Improve Students’ Writing Skills. In Proceedings of the 5th International Conference on Distance Education and Learning (ICDEL ’20) . Association for Computing Machinery, New York, NY, USA, 122–127. https://doi.org/10.1145/3402569.3402594
• Jayavalan and Razali (2018) Kalpana Jayavalan and Abu Bakar Razali. 2018. Effectiveness of Online Grammar Checker to Improve Secondary Students’ English Narrative Essay Writing. 2, 1 (2018).
• Jisuanke. (2023) Jisuanke. 2023. CodeMirror-Record. https://github.com/Jisuanke/CodeMirror-Record .
• Joyner (2023) David A. Joyner. 2023. ChatGPT in Education: Partner or Pariah? XRDS 29, 3 (April 2023), 48–51. https://doi.org/10.1145/3589651
• Karyuatry (2018) Laksnoria Karyuatry. 2018. Grammarly as a Tool to Improve Students’ Writing Quality: Free Online-Proofreader across the Boundaries. JSSH (Jurnal Sains Sosial dan Humaniora) 2, 1 (May 2018), 83–89. https://doi.org/10.30595/jssh.v2i1.2297 Number: 1.
• Koltovskaia (2020) Svetlana Koltovskaia. 2020. Student engagement with automated written corrective feedback (AWCF) provided by Grammarly : A multiple case study. Assessing Writing 44 (April 2020), 100450. https://doi.org/10.1016/j.asw.2020.100450
• Liu et al . (2023) Zeyan Liu, Zijun Yao, Fengjun Li, and Bo Luo. 2023. Check Me If You Can: Detecting ChatGPT-Generated Academic Writing using CheckGPT. https://doi.org/10.48550/arXiv.2306.05524 arXiv:2306.05524 [cs].
• Moore et al . (2022) Steven Moore, Huy A. Nguyen, Norman Bier, Tanvi Domadia, and John Stamper. 2022. Assessing the Quality of Student-Generated Short Answer Questions Using GPT-3. In Educating for a New Future: Making Sense of Technology-Enhanced Learning Adoption , Isabel Hilliger, Pedro J. Muñoz-Merino, Tinne De Laet, Alejandro Ortega-Arranz, and Tracie Farrell (Eds.). Vol. 13450. Springer International Publishing, Cham, 243–257. https://doi.org/10.1007/978-3-031-16290-9_18 Series Title: Lecture Notes in Computer Science.
• Mosaiyebzadeh et al . (2023) Fatemeh Mosaiyebzadeh, Seyedamin Pouriyeh, Reza Parizi, Nasrin Dehbozorgi, Mohsen Dorodchi, and Daniel Macêdo Batista. 2023. Exploring the Role of ChatGPT in Education: Applications and Challenges. In Proceedings of the 24th Annual Conference on Information Technology Education (SIGITE ’23) . Association for Computing Machinery, New York, NY, USA, 84–89. https://doi.org/10.1145/3585059.3611445
• Murillo and D’Angelo (2023) Ambar Murillo and Sarah D’Angelo. 2023. An Engineering Perspective on Writing Assistants for Productivity and Creative Code. in2Writing (2023).
• ONeill and Russell (2019) Ruth ONeill and Alex Russell. 2019. Stop! Grammar time: University students’ perceptions of the automated feedback program Grammarly. Australasian Journal of Educational Technology 35, 1 (March 2019). https://doi.org/10.14742/ajet.3795 Number: 1.
• Rudolph et al . (2023) Jürgen Rudolph, Samson Tan, and Shannon Tan. 2023. ChatGPT: Bullshit spewer or the end of traditional assessments in higher education? Journal of Applied Learning and Teaching 6, 1 (Jan. 2023), 342–363. https://doi.org/10.37074/jalt.2023.6.1.9 Number: 1.
• Shoufan (2023) Abdulhadi Shoufan. 2023. Can students without prior knowledge use ChatGPT to answer test questions? An empirical study. ACM Trans. Comput. Educ. (Oct. 2023). https://doi.org/10.1145/3628162 Just Accepted.
• Sok and Heng (2023) Sarin Sok and Kimkong Heng. 2023. ChatGPT for Education and Research: A Review of Benefits and Risks. https://doi.org/10.2139/ssrn.4378735
• Stark et al . (2023) Jessi Stark, Anthony Tang, Young-Ho Kim, Joonsuk Park, and Daniel Wigdor. 2023. Can AI Support Fiction Writers Without Writing For Them? in2Writing (2023).
• Wang et al . (2023) Tianjia Wang, Daniel Vargas Díaz, Chris Brown, and Yan Chen. 2023. Exploring the Role of AI Assistants in Computer Science Education: Methods, Implications, and Instructor Perspectives. In 2023 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) . IEEE, 92–102.
• Warner (2023) John Warner. 2023. ChatGPT Can’t Kill Anything Worth Preserving. https://biblioracle.substack.com/p/chatgpt-cant-kill-anything-worth . https://biblioracle.substack.com/p/chatgpt-cant-kill-anything-worth
• Zhang et al . (2023) Zheng Zhang, Jie Gao, Ranjodh Singh Dhaliwal, and Toby Jia-Jun Li. 2023. VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototyping. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology . ACM, San Francisco CA USA, 1–30. https://doi.org/10.1145/3586183.3606800

Appendix A Appendix

A.1. exit survey.

Thank you for participating in our study. Please answer the following questions as part of our exit survey.

For the following questions, please answer based on your perceived ownership of the essay:

I feel that this is my essay

strongly agree, agree, somewhat agree, neutral, somewhat disagree, disagree, strongly disagree

I feel that this essay belongs to me

I feel a high degree of ownership towards this essay

I feel the need to protect my ideas from being used by others.

I feel that this essays success is my success

I feel this essay was written by me

I feel the need to protect the ideas written in the essay

I do not feel like anyone else wrote this essay.

For the following questions, please answer based on your usage of ChatGPT:

I feel like ChatGPT helped me in the creation process of my writing

I feel like ChatGPT helped me with proofreading my essay

I feel like ChatGPT made my essay better

I liked using ChatGPT as an assistant during my essay writing

My writing would have been better without ChatGPT assistance

Thank you for completing our survey. Winners of the essay writing competition will receive an email after the study is complete.

Have a language expert improve your writing

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

• Knowledge Base

Using AI tools

How to Write a Paper with ChatGPT | Tips & Examples

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

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

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

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

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

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

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

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

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

Check for common mistakes

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

Fix mistakes for free

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

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

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

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

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

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

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

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

A. Theoretical basis for cognitive and skill development in training

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

C. The role of immersive learning environments in skill acquisition

D. Conceptual framework for the study

IV. Research Methodology

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

B. Selection of participants and sample size calculation

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

D. Instruments and measures for assessing cognitive and skill development

E. Data collection procedures and ethical considerations

V. Data Analysis

A. Overview of statistical methods used for data analysis

B. Treatment of data and data cleaning

C. Quantitative analysis of cognitive and skill development outcomes

D. Presentation of findings with charts and tables

VI. Results

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

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

C. Statistical significance and effect size analysis

D. Interpretation of the results and implications

VII. Discussion

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

B. Comparison of results with existing literature

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

D. Limitations of the study and areas for future research

VIII. Practical Implications

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

B. Recommendations for integrating virtual reality training in healthcare education

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

IX. Conclusion

A. Summary of key findings

B. Reiteration of the research question and hypothesis

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

D. Concluding remarks

X. References

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

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

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

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

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

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

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

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

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

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

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

Citing sources

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

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

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

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

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

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

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

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

Cite this Scribbr article

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

Driessen, K. (2023, November 16). How to Write a Paper with ChatGPT | Tips & Examples. Scribbr. Retrieved September 4, 2024, from https://www.scribbr.com/ai-tools/chatgpt-research-paper/

Is this article helpful?

Koen Driessen

Other students also liked, how to write good chatgpt prompts, chatgpt citations | formats & examples, what are the limitations of chatgpt, "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”

Why Students Should Resist Using ChatGPT

Students should avoid chatgpt because learning to write is learning to think..

Posted September 8, 2024 | Reviewed by Jessica Schrader

• Why Education Is Important
• Take our ADHD Test
• Find a Child Therapist
• Genuine learning is transformative.
• Learning to write is learning to think.
• Your character is implicated in your coursework.

I remember my library orientation in grammar school. My classmates and I gathered around wooden filing drawers, where we read index cards marked with Dewey decimals. These index cards, the librarian told us, were the entry to a world of ideas. We could use them to locate books. It was mesmerizing.

This whole process seemed anticlimactic, however, the very next day. That day, the same librarian explained that book-locating information was also available on a website. We could select books quickly, all while sitting in a chair.

In those days, we lived in the seams of the digital and pre-digital age. The librarian was not confident that the new technology would persist. So, as kids, we kept one foot planted in each world, learning the digital landscape while also physically navigating libraries.

A refrain throughout educational history is reckoning with new tools—embracing, rejecting, ignoring, or otherwise. Digital card catalogues are an example. And perhaps because many tools have been an asset in educational spaces—facilitating the process of learning—many schools have developed broadly hospitable stances toward them. But not all tools are equally constructive. Some tools undermine our learning, the most recent example being ChatGPT.

ChatGPT is an artificial intelligence (AI) chatbot (really, one example of several) that creates human-like conversations using natural language processing. Stated simply, it responds to the questions one asks, drawing on stores of information and its interactions with other users. Within the first two months of its launch in January of 2023, ChatGPT already had 100 million active users. [1]

Where ChatGPT impacts education , most worryingly, is in completing tasks assigned to students. Students can outsource thinking—allowing AI to digest difficult readings on their behalf. They can also request that ChatGPT construct essays assigned by professors.

ChatGPT is still new, and teachers and institutions have varying policies regulating its use—some more stringent, some more lenient. Regardless, there are strong reasons students should resist this tool.

1. Genuine learning is transformative

In “An Invitation to the Pain of Learning,” Mortimer Adler writes: "Anyone who has done any thinking, even a little bit, knows that it is painful. It is hard work—in fact, the very hardest that human beings are ever called upon to do. It is fatiguing, not refreshing. If allowed to follow the path of least resistance, no one would ever think." [2]

This is a problem, Adler continues, because “genuine learning is…thinking,” and thinking is transformative. [3] It involves an interior transformation of a person’s mind and character.

Often when my students use ChatGPT or related technologies, they do so to avoid the arduous task of thinking . This is a problem because much of the transformative work of their educations occurs through the process of wrestling with ideas and discerning their significance. To outsource this work means a student comes away unchanged, or uneducated.

Furthermore, —in the same way that finishing a marathon can be painful yet life-giving, or completing a difficult work task can be challenging but satisfying, learning is not simply painful. It is also deeply enjoyable, full of wonder, pleasant, and gratifying. Learning is worth the difficulty.

2. Learning to write is learning to think

When I entered college, I would start my essays and get lost. I lost my place in arguments, was disorganized, and never knew what was important enough to include.

This was not just an issue of my writing—as though I was a clear-minded thinker who struggled to put things on paper. My issues in writing demonstrated that I was not good at thinking . My weaknesses as a thinker just became obvious when I tried to write things down.

I point this out because sometimes students think of writing as busy work. Now that they have ChatGPT to write essays on their behalf—bad essays, by the way, but essays nonetheless—they eagerly outsource that task. But learning to write is learning to think . Thinking is something we need to do well to flourish as human beings.

3. Your character is implicated in your coursework

Earlier I cited Adler on the painfulness of learning. This may sound familiar if you have read a difficult book or struggled through an essay. In those moments, it can be tempting to quit and do anything else, rather than to ‘stay in place’ and do your work.

But remaining in difficulty is part of human freedom—to commit to some good end and to see it through to completion. Can you make yourself complete a difficult task without being turned aside by distractions or quitting? If not, you are not really a free person.

Sure, AI can do tasks for you. But you miss the opportunity to grow in perseverance, resilience , and self-control . Moreover, given that AI is a platform for which plagiarism and false ascriptions of content ownership are norms, there are other integrity reasons to resist its use.

Final thoughts

Education is about the formation of a person. ChatGPT and related technologies undermine this important task. My recommendation is for students to resist the temptation to use it in the context of reading and writing, if indeed they wish to be transformed by their learning.

M. Adler. 1941. An Invitation to the Pain of Learning. The Journal of Educational Sociology . 14(6): 358-363.

T. Wu et al., 2023. A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development. IEEE/CAA Journal of Automatica Sinica , 10(5): 1122-1136.

[1] T. Wu et al., 2023. A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development. IEEE/CAA Journal of Automatica Sinica , 10(5): 1122-1136.

[2] M. Adler. 1941. An Invitation to the Pain of Learning. The Journal of Educational Sociology . 14(6): 358-363.

[3] M. Adler. 1941. An Invitation to the Pain of Learning, 360.

Sabrina B. Little, Ph.D ., is an assistant professor of Leadership and American Studies at Christopher Newport University, and author of The Examined Run: Why Good People Make Better Runners.

• Find Counselling
• Find a Support Group
• Find Online Therapy
• United Kingdom
• Asperger's
• Bipolar Disorder
• Chronic Pain
• Eating Disorders
• Passive Aggression
• Personality
• Goal Setting
• Positive Psychology
• Stopping Smoking
• Low Sexual Desire
• Relationships
• Child Development
• Self Tests NEW
• Therapy Center
• Diagnosis Dictionary
• Types of Therapy

It’s increasingly common for someone to be diagnosed with a condition such as ADHD or autism as an adult. A diagnosis often brings relief, but it can also come with as many questions as answers.

• Emotional Intelligence
• Gaslighting
• Affective Forecasting
• Neuroscience

We need your support today

Independent journalism is more important than ever. Vox is here to explain this unprecedented election cycle and help you understand the larger stakes. We will break down where the candidates stand on major issues, from economic policy to immigration, foreign policy, criminal justice, and abortion. We’ll answer your biggest questions, and we’ll explain what matters — and why. This timely and essential task, however, is expensive to produce.

We rely on readers like you to fund our journalism. Will you support our work and become a Vox Member today?

• Future Perfect
• There’s a fix for AI-generated essays. Why aren’t we using it?

ChatGPT didn’t write this and I can prove it.

by Kelsey Piper

It’s the start of the school year, and thus the start of a fresh round of discourse on generative AI’s new role in schools. In the space of about three years, essays have gone from a mainstay of classroom education everywhere to a much less useful tool, for one reason: ChatGPT. Estimates of how many students use ChatGPT for essays vary , but it’s commonplace enough to force teachers to adapt .

While generative AI has many limitations, student essays fall into the category of services that they’re very good at: There are lots of examples of essays on the assigned topics in their training data, there’s demand for an enormous volume of such essays, and the standards for prose quality and original research in student essays are not all that high.

This story was first featured in the Future Perfect newsletter .

Sign up here to explore the big, complicated problems the world faces and the most efficient ways to solve them. Sent twice a week.

Right now, cheating on essays via the use of AI tools is hard to catch. A number of tools advertise they can verify that text is AI-generated, but they’re not very reliable . Since falsely accusing students of plagiarism is a big deal, these tools would have to be extremely accurate to work at all — and they simply aren’t.

AI fingerprinting with technology

But there is a technical solution here. Back in 2022, a team at OpenAI, led by quantum computing researcher Scott Aaronson , developed a “watermarking” solution that makes AI text virtually unmistakable — even if the end user changes a few words here and there or rearranges text. The solution is a bit technically complicated, but bear with me, because it’s also very interesting.

At its core, the way that AI text generation works is that the AI “guesses” a bunch of possible next tokens given what appears in a text so far. In order not to be overly predictable and produce the same repetitive output constantly, AI models don’t just guess the most probable token — instead, they include an element of randomization, favoring “more likely” completions but sometimes selecting a less likely one.

The watermarking works at this stage. Instead of having the AI generate the next token according to random selection, it has the AI use a nonrandom process: favoring next tokens that get a high score in an internal “scoring” function OpenAI invented. It might, for example, favor words with the letter V just slightly, so that text generated with this scoring rule will have 20 percent more Vs than normal human text (though the actual scoring functions are more complicated than this). Readers wouldn’t normally notice this — in fact, I edited this newsletter to increase the number of Vs in it, and I doubt this variation in my normal writing stood out.

Similarly, the watermarked text will not, at a glance, be different from normal AI output. But it would be straightforward for OpenAI, which knows the secret scoring rule, to evaluate whether a given body of text gets a much higher score on that hidden scoring rule than human-generated text ever would. If, for example, the scoring rule were my above example about the letter V, you could run this newsletter through a verification program and see that it has about 90 Vs in 1,200 words, more than you’d expect based on how often V is used in English. It’s a clever, technically sophisticated solution to a hard problem, and OpenAI has had a working prototype for two years .

So if we wanted to solve the problem of AI text masquerading as human-written text, it’s very much solvable. But OpenAI hasn’t released their watermarking system, nor has anyone else in the industry. Why not?

It’s all about competition

If OpenAI — and only OpenAI — released a watermarking system for ChatGPT, making it easy to tell when generative AI had produced a text, this wouldn’t affect student essay plagiarism in the slightest. Word would get out fast, and everyone would just switch over to one of the many AI options available today: Meta’s Llama, Anthropic’s Claude, Google’s Gemini. Plagiarism would continue unabated, and OpenAI would lose a lot of its user base. So it’s not shocking that they would keep their watermarking system under wraps.

In a situation like this, it might seem appropriate for regulators to step in. If every generative AI system is required to have watermarking, then it’s not a competitive disadvantage. This is the logic behind a bill introduced this year in the California state Assembly, known as the California Digital Content Provenance Standards , which would require generative AI providers to make their AI-generated content detectable, along with requiring providers to label generative AI and remove deceptive content. OpenAI is in favor of the bill — not surprisingly, as they’re the only generative AI provider known to have a system that does this. Their rivals are mostly opposed.

I’m broadly in favor of some kind of watermarking requirements for generative AI content. AI can be incredibly useful , but its productive uses don’t require it to pretend to be human-created. And while I don’t think it’s the place of government to ban newspapers from replacing us journalists with AI, I certainly don’t want outlets to misinform readers about whether the content they’re reading was created by real humans .

Though I’d like some kind of watermarking obligation, I am not sure it’s possible to implement. The best of the “open” AI models that have been released (like the latest Llama), models that you can run yourself on your own computer, are very high quality — certainly good enough for student essays. They’re already out there, and there’s no way to go back and add watermarking to them because anyone can run the current versions, whatever updates are applied in future versions. (This is among the many ways I have complicated feelings about open models. They enable an enormous amount of creativity, research, and discovery — and they also make it impossible to do all kinds of common-sense anti-impersonation or anti-child sexual abuse material measures that we otherwise might really like to have.)

So even though watermarking is possible, I don’t think we can count on it, which means we’ll have to figure out how to address the ubiquity of easy, AI-generated content as a society. Teachers are already switching to in-class essay requirements and other approaches to cut down on student cheating. We’re likely to see a switch away from college admissions essays as well — and, honestly, it’ll be good riddance, as those were probably never a good way to select students .

But while I won’t mourn much over the college admissions essay, and while I think teachers are very much capable of finding better ways to assess students, I do notice some troubling trends in the whole saga. There was a simple way to let us harness the benefits of AI without obvious downsides like impersonation and plagiarism, yet AI development happened so fast that society more or less just let the opportunity pass us by. Individual labs could do it, but they won’t because it’d put them at a competitive disadvantage — and there isn’t likely to be a good way to make everyone do it.

In the school plagiarism debate, the stakes are low. But the same dynamic reflected in the AI watermarking debate — where commercial incentives stop companies from self-regulating and the pace of change stops external regulators from stepping in until it’s too late — seems likely to remain as the stakes get higher.

• Artificial Intelligence

Most Popular

• Conservatives are shocked — shocked! — that Tucker Carlson is soft on Nazis
• Did Brittany Mahomes’s Donald Trump support put her on the outs with Taylor Swift?
• Has The Bachelorette finally gone too far?
• America’s love affair with the increasingly weird Kennedys

Today, Explained

Understand the world with a daily explainer plus the most compelling stories of the day.

This is the title for the native ad

More in Future Perfect

Is anything really “cruelty-free”?

From granola bars to chips, more studies are revealing that UPFs are tied to diseases like cancer and depression.

Too much fluoride might lower IQ in kids, a new federal report says. The science (and debate), explained.

EVs help reduce greenhouse emissions. But too many used gas-guzzlers could make that impossible.

The US military’s recruiting crisis, explained.

Gavin Newsom could decide the future of AI safety. But will he cave to billionaire pressure?

Have a thesis expert improve your writing

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

• Knowledge Base

Using AI tools

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

How to Write an Essay with ChatGPT | Tips & Examples

Published on 26 June 2023 by Koen Driessen .

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

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

You can use ChatGPT to:

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

Instantly correct all language mistakes in your text

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

Table of contents

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

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

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

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

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

Example: Using ChatGPT to write a research question

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

The only proofreading tool specialized in correcting academic writing

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

Correct my document today

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

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

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

Examples: Using ChatGPT to generate an essay outline

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

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

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

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

Example: Using ChatGPT to find sources

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

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

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

Example: Using ChatGPT to summarise/paraphrase

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

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

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

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

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

Example: Using ChatGPT for feedback

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

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

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

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

Citing sources

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

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

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

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

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

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

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

Cite this Scribbr article

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

Driessen, K. (2023, June 26). How to Write an Essay with ChatGPT | Tips & Examples. Scribbr. Retrieved 3 September 2024, from https://www.scribbr.co.uk/using-ai-tools/chatgpt-essays/

Is this article helpful?

Koen Driessen

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

A teacher caught students using ChatGPT on their first assignment to introduce themselves. Her post about it started a debate.

• A teacher's students ChatGPT for a simple introductory assignment in an ethics and technology class.
• Professor Megan Fritts shared her concerns on X, sparking debate on AI's role in education.
• Educators are divided on AI's impact, with some feeling it undermines critical thinking skills.

Professor Megan Fritts' first assignment to her students was what she considered an easy A: "Briefly introduce yourself and say what you're hoping to get out of this class."

Yet many of the students enrolled in her Ethics and Technology course decided to introduce themselves with ChatGPT .

"They all owned up to it, to their credit," Fritts told Business Insider. "But it was just really surprising to me that — what was supposed to be a kind of freebie in terms of assignments — even that they felt compelled to generate with an LLM."

When Fritts, an assistant professor of philosophy at the University of Arkansas at Little Rock, took her concern to X, formerly Twitter, in a tweet that has now garnered 3.5 million views, some replies argued that students would obviously combat " busywork " assignments with similarly low-effort AI-generated answers.

Second week of the semester and I've already had students use (and own up to using) ChatGPT to write their first assignment: "briefly introduce yourself and say what you're hoping to get out of this class". They are also using it to word the *questions they ask in class*. — Megan Fritts (@freganmitts) August 28, 2024

However, Fritts said that the assignment was not only to help students get acquainted with using the online  Blackboard  discussion board feature, but she was also "genuinely curious" about the introductory question.

"A lot of students who take philosophy classes, especially if they're not majors, don't really know what philosophy is," she said. "So I like to get an idea of what their expectations are so I can know how to respond to them."

The AI-written responses, however, did not reflect what the students, as individuals, were expecting from the course but rather a regurgitated description of what a technology ethics class is, which clued Fritts in that they were generated by ChatGPT or a similar chatbot.

"When you're a professor, and you've read dozens and dozens of AI essays, you can just tell," she said.

The calculator argument — why ChatGPT is not just another problem-solving tool

While a common defense permeating Fritts' replies likened ChatGPT for writing to a calculator for math problems, she said that viewing LLMs as just another problem-solving tool is a "mistaken" comparison, especially in the context of humanities.

Related stories

Calculators reduce the time needed to solve mechanical operations that students are already taught to produce a singular correct solution. But Fritts said that the aim of humanities education is not to create a product but to "shape people" by "giving them the ability to think about things that they wouldn't naturally be prompted to think about."

"The goal is to create liberated minds — liberated people — and offloading the thinking onto a machine, by definition, doesn't achieve that," she said.

Lasting impacts on students

Beyond cheating on papers, Fritts said that students have, in general, become compromised in their thinking ability — and they've noticed.

"They're like, 'When I was young, I used to love to read, and now I can't. I can't even get through the chapter of a book,'" she said. "'My attention span is so bad, and I know it's from looking at my phone, always having YouTube or TikTok on.' And they're sad about it."

Fritts said that technology addiction has affected students' general agency when interacting with information. She  cited a 2015 paper  by Professor Charles Harvey, chair of the Department of Philosophy and Religion at the University of Central Arkansas, which examines the effects that interactions with technology could have had on human agency and concentration.

Harvey wrote that two different eye-tracking experiments indicated that the vast majority of people skim online text quickly, "skipping down the page" rather than reading line by line. Deep reading of paper texts is being snipped into "even smaller, disconnected" thoughts.

"The new generations will not be experiencing this technology for the first time. They'll have grown up with it," Fritts said. "I think we can expect a lot of changes in the really foundational aspects of human agency, and I'm not convinced those changes are going to be good."

Teachers are getting tired

Fritts acknowledges that educators have some obligation to teach students how to use AI in a productive and edifying way. However, she said that placing the burden of fixing the cheating trend on scholars teaching AI literacy to students is "naive to the point of unbelievability."

"Let's not deceive ourselves that students are using AI because they're just so siked about the new tech, and they're not sure of what the right way to use it in the classroom," Fritts said.

"And I'm not trying to slam them," she added. "All of us are inclined to take measures to make things easier for us."

But Fritts also feels just as "pessimistic" about the alternative solution — educators and institutions forming a "united front" in keeping AI out of the classroom.

"Which isn't going to happen because so many educators are now fueled by sentiments from university administration," Fritts said. "They're being encouraged to incorporate this into the curriculum."

At least 22 state departments of education have released official guidelines for AI use in schools, The Information recently reported . A 2024 survey by EdWeek Research Center found that 56% of over 900 educators anticipated AI use to rise. And some are excited for it.

Curby Alexander, an associate education professor at Texas Christian University, previously told BI that he uses AI to help brainstorm ideas and develop case studies "without taking up a lot of class time."

ASU's Anna Cunningham, a Dean's Fellow, and Joel Nishimura, an associate professor in the Mathematical and Natural Sciences department, wrote  an op-ed  encouraging having students teach ChatGPT agents with programmed misunderstandings.

"With this, we are on the cusp of being able to give all students as many opportunities as they want to learn by teaching," they wrote.

OpenAI even partnered with Arizona State University to offer students and faculty full access to ChatGPT Enterprise for tutoring, coursework, research, and more.

However, many educators remain skeptical. Some professors have even reverted back to pen and paper to combat ChatGPT usage, but Fritts said many are tired of trying to fight the seemingly inevitable. And students are left in the middle of education and AI's love-hate relationship.

"I think it, understandably, creates a lot of confusion and makes them feel like the professors who are saying 'Absolutely not' are maybe philistines or behind the times or unnecessarily strict," Fritts said.

Fritts is not the only professor voicing concerns about AI use among students. In a Reddit thread titled " ChatGPT: It's getting worse ," several users who identified as professors lamented increased AI usage in classrooms, especially in online courses. One commented, "This is one reason I'm genuinely considering leaving academia."

A professor in another post that received over 600 upvotes said that ChatGPT was "ruining" their love of teaching. "The students are no longer interpreting a text, they're just giving me this automated verbiage," they wrote. "Grading it as if they wrote it makes me feel complicit. I'm honestly despairing."

Watch: What is ChatGPT, and should we be afraid of AI chatbots?

• Main content

• Share full article

Advertisement

Supported by

The Challenge Is to Write 50,000 Words in a Month. Should ChatGPT Be Able to Help?

An online writing community was set aflame this week after National Novel Writing Month, or NaNoWriMo, said it wouldn’t take a stance on the use of A.I.

By Madison Malone Kircher

For over 20 years, writers around the world have participated in National Novel Writing Month , or #NaNoWriMo, as it’s known online. The challenge is simple: Write 50,000 words in the month of November. Well, as simple as writing 50,000 words can be. (That’s 1,667 words per day, for those of you doing the math at home.)

Of course, using a generative artificial intelligence platform, like ChatGPT, could make those words go by much quicker. But is that really ethical? In the spirit of the event? Good for the craft of creative writing in general?

These are some of the questions that fueled a heated debate this week among writers, editors and others in publishing who fear the creep of A.I. in their industry. It started with a statement from NaNoWriMo, the nonprofit organization that coordinates the writing marathon every year. It ended — though perhaps there is more to come — with resignations, a lost sponsor and plenty of prickly feelings in what is meant to be an uplifting community.

“NaNoWriMo does not explicitly support any specific approach to writing, nor does it explicitly condemn any approach, including the use of A.I.,” the organization wrote on its website at the end of August. To fully condemn the technology, it said, would be “to ignore classist and ableist issues.”

“For some writers, the decision to use A.I. is a practical, not an ideological, one,” the statement continued, noting the “upfront cost burdens” in the publishing industry as well as the challenges that writers with different mental and linguistic abilities may face. “The notion that all writers ‘should’ be able to perform certain functions independently is a position that we disagree with wholeheartedly.”

Kilby Blades, the executive director of NaNoWriMo, did not make herself available for an interview for this article.

We are having trouble retrieving the article content.

Please enable JavaScript in your browser settings.

Thank you for your patience while we verify access. If you are in Reader mode please exit and  log into  your Times account, or  subscribe  for all of The Times.

Thank you for your patience while we verify access.

Already a subscriber?  Log in .

Want all of The Times?  Subscribe .