how to write an essay using chatgpt

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

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

Last Updated: June 2, 2024 Fact Checked

Getting ChatGPT to Write the Essay

Using ai to help you write, expert interview.

This article was written by Bryce Warwick, JD and by wikiHow staff writer, Nicole Levine, MFA . Bryce Warwick is currently the President of Warwick Strategies, an organization based in the San Francisco Bay Area offering premium, personalized private tutoring for the GMAT, LSAT and GRE. Bryce has a JD from the George Washington University Law School. This article has been fact-checked, ensuring the accuracy of any cited facts and confirming the authority of its sources. This article has been viewed 48,492 times.

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

Things You Should Know

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

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

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

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

Tyrone Showers

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

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

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

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

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

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

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

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

Expert Q&A

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

• Using ChatGPT to write or assist with your essay may be against your instructor's rules. Make sure you understand the consequences of using ChatGPT to write or assist with your essay. Thanks Helpful 1 Not Helpful 0
• ChatGPT-written essays may include factual inaccuracies, outdated information, and inadequate detail. [3] X Research source Thanks Helpful 0 Not Helpful 0

You Might Also Like

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

• ↑ https://help.openai.com/en/articles/6783457-what-is-chatgpt
• ↑ https://platform.openai.com/examples/default-essay-outline
• ↑ https://www.ipl.org/div/chatgpt/

About This Article

• Send fan mail to authors

Is this article up to date?

Featured Articles

Trending Articles

Watch Articles

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

wikiHow Tech Help Pro:

Level up your tech skills and stay ahead of the curve

• 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.

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...

How to Ace Slack Messaging for Contractors and Freelancers

Effective professional communication is an important skill for contractors and freelancers navigating remote work environments....

3-minute read

How to Insert a Text Box in a Google Doc

Google Docs is a powerful collaborative tool, and mastering its features can significantly enhance your...

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

• 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

A Comprehensive Guide to Essay Grading with ChatGPT

Introduction.

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

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

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

In this blog, we will explore:

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

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

## Essay Grading with ChatGPT and ChatGPT API

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

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

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

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

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

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

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

Steps for Essay Grading with ChatGPT API

Get and set up a chatgpt api key.

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

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

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

Load the text dataset

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

Score the multiple essays

Grading 50 essays takes only 25 seconds.

Compare human grading scores with GPT grading scores

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

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

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

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

Steps for Essay Classification with ChatGPT API

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

Classify multiple essays

Classifying 50 essays takes only 27 seconds.

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

Compare human classification with GPT classification

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

Cost & Computation times

How long does it take to assess all essays.

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

What is the cost of assessing all essays?

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

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

What are tokens and how to count them?

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

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

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

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

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

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

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

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

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

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

Writer’s Comments

The api experience: a blend of ease and challenge.

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

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

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

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

Overall Reflections: A Journey of Discovery

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

Call to Action

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

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

Celebrating 150 years of Harvard Summer School. Learn about our history.

Should I Use ChatGPT to Write My Essays?

Everything high school and college students need to know about using — and not using — ChatGPT for writing essays.

Jessica A. Kent

ChatGPT is one of the most buzzworthy technologies today.

In addition to other generative artificial intelligence (AI) models, it is expected to change the world. In academia, students and professors are preparing for the ways that ChatGPT will shape education, and especially how it will impact a fundamental element of any course: the academic essay.

Students can use ChatGPT to generate full essays based on a few simple prompts. But can AI actually produce high quality work, or is the technology just not there yet to deliver on its promise? Students may also be asking themselves if they should use AI to write their essays for them and what they might be losing out on if they did.

AI is here to stay, and it can either be a help or a hindrance depending on how you use it. Read on to become better informed about what ChatGPT can and can’t do, how to use it responsibly to support your academic assignments, and the benefits of writing your own essays.

What is Generative AI?

Artificial intelligence isn’t a twenty-first century invention. Beginning in the 1950s, data scientists started programming computers to solve problems and understand spoken language. AI’s capabilities grew as computer speeds increased and today we use AI for data analysis, finding patterns, and providing insights on the data it collects.

But why the sudden popularity in recent applications like ChatGPT? This new generation of AI goes further than just data analysis. Instead, generative AI creates new content. It does this by analyzing large amounts of data — GPT-3 was trained on 45 terabytes of data, or a quarter of the Library of Congress — and then generating new content based on the patterns it sees in the original data.

It’s like the predictive text feature on your phone; as you start typing a new message, predictive text makes suggestions of what should come next based on data from past conversations. Similarly, ChatGPT creates new text based on past data. With the right prompts, ChatGPT can write marketing content, code, business forecasts, and even entire academic essays on any subject within seconds.

But is generative AI as revolutionary as people think it is, or is it lacking in real intelligence?

The Drawbacks of Generative AI

It seems simple. You’ve been assigned an essay to write for class. You go to ChatGPT and ask it to write a five-paragraph academic essay on the topic you’ve been assigned. You wait a few seconds and it generates the essay for you!

But ChatGPT is still in its early stages of development, and that essay is likely not as accurate or well-written as you’d expect it to be. Be aware of the drawbacks of having ChatGPT complete your assignments.

It’s not intelligence, it’s statistics

One of the misconceptions about AI is that it has a degree of human intelligence. However, its intelligence is actually statistical analysis, as it can only generate “original” content based on the patterns it sees in already existing data and work.

It “hallucinates”

Generative AI models often provide false information — so much so that there’s a term for it: “AI hallucination.” OpenAI even has a warning on its home screen , saying that “ChatGPT may produce inaccurate information about people, places, or facts.” This may be due to gaps in its data, or because it lacks the ability to verify what it’s generating. 

It doesn’t do research  

If you ask ChatGPT to find and cite sources for you, it will do so, but they could be inaccurate or even made up.

This is because AI doesn’t know how to look for relevant research that can be applied to your thesis. Instead, it generates content based on past content, so if a number of papers cite certain sources, it will generate new content that sounds like it’s a credible source — except it likely may not be.

There are data privacy concerns

When you input your data into a public generative AI model like ChatGPT, where does that data go and who has access to it? 

Prompting ChatGPT with original research should be a cause for concern — especially if you’re inputting study participants’ personal information into the third-party, public application. 

JPMorgan has restricted use of ChatGPT due to privacy concerns, Italy temporarily blocked ChatGPT in March 2023 after a data breach, and Security Intelligence advises that “if [a user’s] notes include sensitive data … it enters the chatbot library. The user no longer has control over the information.”

It is important to be aware of these issues and take steps to ensure that you’re using the technology responsibly and ethically. 

It skirts the plagiarism issue

AI creates content by drawing on a large library of information that’s already been created, but is it plagiarizing? Could there be instances where ChatGPT “borrows” from previous work and places it into your work without citing it? Schools and universities today are wrestling with this question of what’s plagiarism and what’s not when it comes to AI-generated work.

To demonstrate this, one Elon University professor gave his class an assignment: Ask ChatGPT to write an essay for you, and then grade it yourself. 

“Many students expressed shock and dismay upon learning the AI could fabricate bogus information,” he writes, adding that he expected some essays to contain errors, but all of them did. 

His students were disappointed that “major tech companies had pushed out AI technology without ensuring that the general population understands its drawbacks” and were concerned about how many embraced such a flawed tool.

Explore Our High School Programs

How to Use AI as a Tool to Support Your Work

As more students are discovering, generative AI models like ChatGPT just aren’t as advanced or intelligent as they may believe. While AI may be a poor option for writing your essay, it can be a great tool to support your work.

Generate ideas for essays

Have ChatGPT help you come up with ideas for essays. For example, input specific prompts, such as, “Please give me five ideas for essays I can write on topics related to WWII,” or “Please give me five ideas for essays I can write comparing characters in twentieth century novels.” Then, use what it provides as a starting point for your original research.

Generate outlines

You can also use ChatGPT to help you create an outline for an essay. Ask it, “Can you create an outline for a five paragraph essay based on the following topic” and it will create an outline with an introduction, body paragraphs, conclusion, and a suggested thesis statement. Then, you can expand upon the outline with your own research and original thought.

Generate titles for your essays

Titles should draw a reader into your essay, yet they’re often hard to get right. Have ChatGPT help you by prompting it with, “Can you suggest five titles that would be good for a college essay about [topic]?”

The Benefits of Writing Your Essays Yourself

Asking a robot to write your essays for you may seem like an easy way to get ahead in your studies or save some time on assignments. But, outsourcing your work to ChatGPT can negatively impact not just your grades, but your ability to communicate and think critically as well. It’s always the best approach to write your essays yourself.

Create your own ideas

Writing an essay yourself means that you’re developing your own thoughts, opinions, and questions about the subject matter, then testing, proving, and defending those thoughts. 

When you complete school and start your career, projects aren’t simply about getting a good grade or checking a box, but can instead affect the company you’re working for — or even impact society. Being able to think for yourself is necessary to create change and not just cross work off your to-do list.

Building a foundation of original thinking and ideas now will help you carve your unique career path in the future.

Develop your critical thinking and analysis skills

In order to test or examine your opinions or questions about a subject matter, you need to analyze a problem or text, and then use your critical thinking skills to determine the argument you want to make to support your thesis. Critical thinking and analysis skills aren’t just necessary in school — they’re skills you’ll apply throughout your career and your life.

Improve your research skills

Writing your own essays will train you in how to conduct research, including where to find sources, how to determine if they’re credible, and their relevance in supporting or refuting your argument. Knowing how to do research is another key skill required throughout a wide variety of professional fields.

Learn to be a great communicator

Writing an essay involves communicating an idea clearly to your audience, structuring an argument that a reader can follow, and making a conclusion that challenges them to think differently about a subject. Effective and clear communication is necessary in every industry.

Be impacted by what you’re learning about : 

Engaging with the topic, conducting your own research, and developing original arguments allows you to really learn about a subject you may not have encountered before. Maybe a simple essay assignment around a work of literature, historical time period, or scientific study will spark a passion that can lead you to a new major or career.

Resources to Improve Your Essay Writing Skills

While there are many rewards to writing your essays yourself, the act of writing an essay can still be challenging, and the process may come easier for some students than others. But essay writing is a skill that you can hone, and students at Harvard Summer School have access to a number of on-campus and online resources to assist them.

Students can start with the Harvard Summer School Writing Center , where writing tutors can offer you help and guidance on any writing assignment in one-on-one meetings. Tutors can help you strengthen your argument, clarify your ideas, improve the essay’s structure, and lead you through revisions. 

The Harvard libraries are a great place to conduct your research, and its librarians can help you define your essay topic, plan and execute a research strategy, and locate sources. 

Finally, review the “ The Harvard Guide to Using Sources ,” which can guide you on what to cite in your essay and how to do it. Be sure to review the “Tips For Avoiding Plagiarism” on the “ Resources to Support Academic Integrity ” webpage as well to help ensure your success.

Sign up to our mailing list to learn more about Harvard Summer School

The Future of AI in the Classroom

ChatGPT and other generative AI models are here to stay, so it’s worthwhile to learn how you can leverage the technology responsibly and wisely so that it can be a tool to support your academic pursuits. However, nothing can replace the experience and achievement gained from communicating your own ideas and research in your own academic essays.

About the Author

Jessica A. Kent is a freelance writer based in Boston, Mass. and a Harvard Extension School alum. Her digital marketing content has been featured on Fast Company, Forbes, Nasdaq, and other industry websites; her essays and short stories have been featured in North American Review, Emerson Review, Writer’s Bone, and others.

5 Key Qualities of Students Who Succeed at Harvard Summer School (and in College!)

This guide outlines the kinds of students who thrive at Harvard Summer School and what the programs offer in return.

Harvard Division of Continuing Education

The Division of Continuing Education (DCE) at Harvard University is dedicated to bringing rigorous academics and innovative teaching capabilities to those seeking to improve their lives through education. We make Harvard education accessible to lifelong learners from high school to retirement.

How to Use ChatGPT for Research and Essays

Your changes have been saved

Email Is sent

Please verify your email address.

You’ve reached your account maximum for followed topics.

GPT-4 vs. GPT-4 Turbo vs. GPT-4o: What's the Difference

Llama 3 vs. gpt-4: which is better, why scammers love using whatsapp and telegram to slide into your dms.

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

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

1. Draw Your Outline Without ChatGPT

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

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

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

2. Prompt ChatGPT to Draw a Parallel Outline

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

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

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

3. Create a ChatGPT Prompt for Each Section

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

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

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

4. Confirm the Information With a Reputable Source

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

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

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

5. Use ChatGPT for Examples and Breakdowns

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

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

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

6. Write the Essay Yourself

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

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

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

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

7. Polish the Style and Citation With ChatGPT

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

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

ChatGPT Is a Tool, Not a Solution

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

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

• Artificial Intelligence

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.

This new OpenAI Sora rival makes frighteningly realistic AI videos – and you can try it soon

More Android phones can finally talk to the Google Gemini AI in Google Messages

Report: The Apple Vision Pro 2 has been put on ice

Most Popular

• 2 Apple quietly released a new operating system that almost nobody noticed — unnamed OS surfaces in Private Cloud Compute blog as Apple goes ballistic on AI
• 3 Google fully launches VPN for Pixel users
• 4 A walking expert says walking 10,000 steps a day is 'irrelevant' if you’re not doing this one thing
• 5 Company backed by Bill Gates has begun construction of an revolutionary, 'affordable' nuclear power station — TerraPower's Natrium reactor uses sodium which could be key to quenching AI's energy thirst
• 2 Hate going back to the office? Microsoft Teams might have just solved one of the biggest return-to-office problems
• 3 Microsoft’s embarrassment over Recall fiasco gets worse as Windows 11 feature becomes the butt of Apple exec’s joke
• 4 Bill Gates-backed TerraPower begins construction of sodium-cooled Natrium nuclear reactor
• 5 Oracle, Microsoft and OpenAI join forces to meet the expected demand from Apple Intelligence

• View on Facebook Page (Opens in a new tab)
• View our Twitter Page (Opens in a new tab)
• View our Instagram Page (Opens in a new tab)
• View our Youtube Page (Opens in a new tab)

How to Ethically Use ChatGPT to Write an Essay

You’re here because you want to know how to get ChatGPT to write an essay for you, and I’m here to say you shouldn’t do that outright—but there are ways you can get ChatGPT or other AI services to help with your paper. To put it plainly, ChatGPT can absolutely write a paper for you, but you need to be careful that it matches up with the specific instructions your professor gave you and that it’s not going to get you in trouble for cheating. I won’t proselytize about how getting AI to write your essay is wrong and deprives you of the opportunity to learn, but I will warn you that there are pros and cons to doing it—and to avoid trouble, you may still have to do some work. 

If you want ChatGPT to write your whole essay…

If you’re in a time crunch and really want AI to produce a full paper, it can be done. You’ll enter the essay prompt into ChatGPT and give clear instructions. However, ChatGPT may say no to certain requests. For instance, I inputted, “Write me a 1,500-word essay on the role of aqueducts in ancient Rome’s success as an empire using six outside sources cited in MLA.” The AI refused, then told me it could write an outline and give me the six sources it used for my own research. It did that, which was helpful, but it did not write the whole paper as requested. 

I tried again, thinking maybe its aversion was to my request for an essay: “Write 1,500 words on the role of aqueducts in ancient Rome’s success as an empire using six outside sources cited in MLA.” The software told me doing that would be “too lengthy,” then regurgitated the outline and source suggestions from before. 

Ultimately, I had success working in chunks. I asked for a 100-word introduction to an essay on the topic and for ChatGPT to tell me its sources. Sure enough, I got the introduction, plus the sources it used. You could theoretically go chunk by chunk, asking the AI to create an intro, body paragraphs, and conclusion. You’ll still have to add in your citations manually, but it will give them to you. 

Don’t have ChatGPT write the whole paper, though

Here’s the thing: While you can find a workaround to get ChatGPT to write a whole paper, you’re already still going to be doing the work of adding in citations—and you could easily get busted. Teachers can use free software to detect AI in writing and some of them are even getting crafty, inserting unrelated prompts in white text to catch you copying and pasting the instructions into ChatGPT. For instance, if your professor wants an essay on the decline of local news funding over the last 10 years, they might add white text that says something like, “Include two sentences on Madonna’s impact on popular culture.” You might not notice that when you copy and paste it into ChatGPT and if you don’t read over the work the AI spits back out, you’ll turn in something that inexplicably references the Queen of Pop and your professor will know what you did right away. Even if your professor isn't using tricks like that (and a lot of them are, according to their own posts on social media), a quick scan of your work for words you wouldn't normally use could signal to them that it's time to run your paper through an AI checker.

How to use ChatGPT for help writing a school paper

Your best bet is still to write the paper yourself using ChatGPT’s help, which will still shave a lot of time off your researching and brainstorming process. Where AI really shines when it comes to essays is in creating outlines, as shown above with that Roman aqueducts example. While it wouldn’t generate the whole paper, ChatGPT did provide me with nine different subcategories for exploration, from “historical context of ancient Rome” to “agricultural expansion and economic growth” and “military advantage.” Each of those subcategories came with bullet points of what should be touched on in their associated paragraph, plus ChatGPT pointed out which sources could be used to gather the information. If I followed the outline to the T, I’d easily have a six- or seven-page paper and never have to brainstorm or labor over where I was going with it. Put simply, you should rely on ChatGPT for outlines if you’re struggling to come up with ideas or just don’t have the time to structure a whole paper. 

If you end up asking the software to write a few paragraphs, you can—and should —rewrite them. That will take a little time, yes, but rewriting the paragraphs in your own words will help you look less suspicious and will also teach you about what you’re writing about—and that can only benefit you if your teacher asks a follow-up question or puts some of the content on an upcoming test. 

In conclusion, can you make ChatGPT write an essay? Yes, if you’re patient. Should you make ChatGPT write an essay? No, you should not. 

How to use ChatGPT to write an essay

Reviewed By: Steve Hook

Table of Contents

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Here are a couple examples:

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

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

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

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

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

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

Essential AI Tools

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

• FREE 7 DAY TRIAL
• Find out more

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

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

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

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

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

NOW READ The best  free AI essay writer  tools.

How to use ChatGPT to write an essay on mobile

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

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

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

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

• NOW READ Can universities detect ChatGPT?

Funmi Somoye

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

How to use Snapchat Dreams – step-by-step guide to…

How to slow down a video on snapchat –…, how to get a yellow heart on snapchat –…, how to hide and unhide chats on snapchat.

Home — Blog — AI Hacks and Tips — How to Use ChatGPT to Write an Essay without Plagiarizing: Can You Use ChatGPT?

How to Use ChatGPT to Write an Essay without Plagiarizing: Can You Use ChatGPT?

In recent years, artificial intelligence (AI) has revolutionized various fields, and academic writing is no exception. One of the most intriguing questions on the minds of many students and educators is: "Can you use ChatGPT for college essays effectively?" This article delves into the potential and limitations of using ChatGPT for academic writing, providing valuable insights for college students, academic writers, and educators.

ChatGPT, developed by OpenAI, is a state-of-the-art AI language model designed to generate human-like text based on the input it receives. Unlike traditional AI, which often follows rigid rules and programming, ChatGPT uses advanced Natural Language Processing (NLP) to understand and generate text in a more fluid and dynamic manner. This enables it to produce content that closely mimics human writing, making it an appealing tool for various writing tasks, including academic essays.

ChatGPT and Academic Writing

The question "Can you use ChatGPT for college essays?" is increasingly relevant as more students explore technological aids to streamline their writing processes. ChatGPT is trained on a diverse range of internet text, making it capable of producing coherent and contextually relevant responses. This diverse training allows it to cover a wide array of topics and produce essays that are well-structured and informative. However, it's important to understand both the potential and the limitations of using this technology for academic purposes.

How to Use ChatGPT to Write an Essay Without Plagiarizing

One of the main concerns when using AI for academic writing is plagiarism. So, how to use ChatGPT to write an essay without plagiarizing? The key lies in treating ChatGPT as a tool for inspiration and guidance rather than a source for verbatim text. Here are some practical tips:

• Generate Outlines and Ideas : Use ChatGPT to brainstorm and generate outlines for your essay. This can help you structure your thoughts and identify key points to cover in your writing.
• Draft Sections : Let ChatGPT draft sections of your essay, but always review and revise the content. Make sure to add your own voice and insights to avoid direct plagiarism.
• Edit and Cite : Always edit the generated text to align with your writing style. Additionally, if ChatGPT provides factual information or specific data, be sure to cite the original sources properly.

While ChatGPT excels at generating text, it can sometimes produce content that lacks depth or originality, particularly in the context of academic writing. Therefore, it's crucial to use it judiciously and supplement its output with your own critical thinking and analysis.

In conclusion, while ChatGPT offers impressive capabilities for generating text, including academic essays, it should be used as a supplementary tool rather than a replacement for genuine student effort. By understanding how to use ChatGPT to write an essay without plagiarizing, students can benefit from its strengths while maintaining academic integrity.

How ChatGPT Works

ChatGPT operates on advanced Natural Language Processing (NLP) technology, which empowers it to understand and generate text based on the context provided. Leveraging vast amounts of data, ChatGPT is trained using sophisticated machine learning algorithms. This training enables it to recognize patterns and structures in human language, making it capable of producing coherent and contextually relevant responses. For instance, when a user inputs a prompt asking for help with a "ChatGPT essay," the model processes the information and generates a response that aligns with the given input.

Many students often wonder, "Can you use ChatGPT for college essays?" The answer is nuanced. While ChatGPT can indeed assist in the brainstorming and drafting phases, it's crucial to use it responsibly to avoid issues of plagiarism. When thinking about "how to use ChatGPT to write an essay without plagiarizing," it's important to treat the model as a tool for generating ideas and structuring content. Always ensure that the final essay reflects your own analysis, voice, and original thoughts.

Despite its impressive capabilities, ChatGPT has its limitations. It may struggle with tasks requiring deep critical thinking or complex reasoning. Additionally, it can sometimes generate content that is overly generic or lacks specificity, which can be a drawback for academic writing that demands originality and depth. Therefore, while ChatGPT can be a valuable aid in drafting or brainstorming, it should not replace the critical thinking and originality required in academic work.

In summary, ChatGPT is a powerful tool for generating text and can be particularly useful for tasks like drafting an essay. However, students should always use it responsibly to ensure their work remains original and plagiarism-free. By understanding its strengths and limitations, you can effectively incorporate ChatGPT into your essay-writing process, enhancing your productivity without compromising academic integrity.

The Ethics of Using AI in Academic Writing

Using AI tools like ChatGPT for academic writing raises several ethical concerns. Academic integrity is paramount, and universities have strict policies against plagiarism and the use of unauthorized aids. While ChatGPT can assist in generating ideas and content, students must ensure that their work remains original and properly cited.

Plagiarism is a significant concern when using AI-generated content. Universities have policies that explicitly prohibit submitting work that is not entirely the student's own. Expert opinions vary, but many academic sources emphasize the importance of maintaining the integrity of one's work while leveraging AI as a tool for enhancement rather than replacement.

Benefits of Using ChatGPT as a Writing Aid

Despite some ethical concerns, ChatGPT offers numerous advantages as a writing aid, particularly for students looking to enhance their essays. Here are some key benefits of using ChatGPT for essay writing:

• Idea Generation and Brainstorming : One of the primary advantages of using ChatGPT is its ability to help students brainstorm and generate ideas. When facing writer's block, students often ask, "Can you use ChatGPT for college essays?" The answer is yes, as ChatGPT can provide a wealth of ideas and inspiration that can spark creativity and lead to more engaging and well-rounded essays.
• Language Skill Improvement : By examining AI-generated examples, students can learn a lot about language structure, vocabulary, and style. This aspect of ChatGPT can be particularly useful for those looking to improve their writing skills. Knowing how to use ChatGPT to write an essay without plagiarizing is essential; students should use the AI-generated content as a learning tool rather than copying it verbatim.
• Draft Refinement and Polishing : Another significant benefit of ChatGPT is its ability to help refine and polish drafts. The AI can offer valuable suggestions for improvement, such as identifying weak points in the content or suggesting better word choices. However, students should view these suggestions as starting points to further develop their work.
• Overcoming Writer's Block : ChatGPT can assist students in overcoming writer's block by providing various prompts and ideas. This feature can be particularly helpful for those who struggle to get started on their essays or need a push to continue writing.

Risks and Limitations of Using ChatGPT for College Essays

When considering whether to use ChatGPT for college essays, it's important to be aware of its risks and limitations. One major concern is the lack of critical thinking and deep analysis in AI-generated content. Academic writing demands a nuanced understanding of the subject matter, along with the ability to present well-constructed arguments and counterarguments, which ChatGPT may find challenging to produce effectively.

Another issue is the potential for generic content. AI-generated text can sometimes miss the personal touch and unique perspective that human writing inherently offers. Moreover, ChatGPT is not equipped to accurately cite sources, creating a risk of academic misconduct if not properly managed. To use ChatGPT to write an essay without plagiarizing, it is crucial to carefully review and modify the content, ensuring that it meets academic standards and includes proper citations.

Best Practices for Using ChatGPT in Essay Writing

In today's digital age, leveraging advanced tools like ChatGPT can significantly enhance the essay writing process. However, to maintain academic integrity, students must adhere to certain best practices when using ChatGPT for their essays. The question often arises: "Can you use ChatGPT for college essays?" The answer is yes, but it should be done thoughtfully and ethically.

First, use ChatGPT as a brainstorming partner. When starting your "chatgpt essay," let the AI help you generate ideas and create an outline. This initial step can provide a solid foundation for your essay, making the writing process smoother and more organized.

Prompting ChatGPT effectively is crucial. By giving clear and specific instructions, you can steer the AI to produce relevant and useful content. However, it's essential to verify and fact-check the information generated by ChatGPT to ensure its accuracy. This step addresses the concern, "Can ChatGPT write essays without plagiarizing?" While ChatGPT can generate original content, it's still important to cross-check and supplement the AI's output with your own research and knowledge.

Incorporate your personal experiences and insights to add depth and originality to your essay. This approach not only enriches the content but also ensures that your voice and perspective are evident throughout the piece. After generating the content, spend time revising and editing to align the AI-generated text with your unique writing style.

In summary, ChatGPT can be a valuable tool in essay writing if used correctly. By following these best practices, you can effectively utilize ChatGPT for college essays while maintaining originality and academic integrity.

Case Studies: ChatGPT in Action

Brainstorming essay topics.

One of the most common challenges for students is figuring out where to start when writing an essay. Imagine you need to write an essay on climate change but are unsure about which angle to take. Here’s where ChatGPT comes in handy. By inputting a broad prompt like "Discuss the impact of climate change on global agriculture," ChatGPT can provide a range of essay topics and angles to consider. This can help narrow down your focus and give you a solid starting point for your research. So, can you use ChatGPT for college essays? Absolutely, it can be an invaluable tool for brainstorming and topic generation.

Outlining an Argumentative Essay

Another way ChatGPT can assist is by helping you outline your essay. Suppose you're tasked with writing an argumentative essay on the benefits of renewable energy. ChatGPT can generate a basic structure and suggest key points to cover. For instance, it might outline an introduction, followed by sections on the environmental benefits, economic advantages, and potential challenges of renewable energy sources. This not only saves time but also provides a clear roadmap for your writing. Naturally, the question arises: can ChatGPT write essays without plagiarizing? While ChatGPT can generate original content, it's still crucial to ensure that the final essay is uniquely yours and properly cited.

Generating Counterarguments

In academic writing, presenting counterarguments is essential for a balanced and well-rounded essay. ChatGPT can help generate these counterarguments by offering different perspectives on the topic at hand. For example, if you're arguing in favor of renewable energy, ChatGPT can suggest potential drawbacks or challenges, such as the initial cost of implementation or issues related to energy storage. This helps in creating a more nuanced and comprehensive essay.

Expert Insights: Interviews with Educators

Perspectives from Writing Instructors

Writing instructors generally agree that while AI tools like ChatGPT can be beneficial, they should not replace the foundational skills of writing. According to Professor Jane Smith, a writing instructor at XYZ University, "AI can be a useful tool for generating ideas and improving drafts, but students must develop their critical thinking and writing skills independently."

Views of University Administrators

University administrators emphasize the importance of academic integrity and caution against over-reliance on AI tools. Dr. John Doe, a university dean, states, "AI should be used as a supplementary tool, not a crutch. We encourage students to use AI for brainstorming and refining their work, but the final product must be their own."

Opinions of AI Ethics Researchers

AI ethics researchers highlight the need for clear guidelines and policies when using AI in academic writing. Dr. Emily Brown, an AI ethics researcher, notes, "While AI can enhance the writing process, it is essential to establish ethical boundaries and ensure that students understand the limitations and responsibilities associated with AI-generated content."

The Future of AI in Academic Writing

The future of AI in academic writing holds exciting possibilities. As AI technology continues to evolve, we can expect more advanced and sophisticated tools that offer even greater support for students and educators. However, this also means that academic policies will need to adapt to address the ethical implications and ensure the responsible use of AI.

Human creativity and critical thinking will always play a vital role in academic writing. While AI can assist in various aspects of the writing process, the unique perspectives and insights that humans bring cannot be replaced.

In conclusion, ChatGPT offers significant potential as a writing aid for college essays, providing valuable support in brainstorming, idea generation, and refining drafts. However, it is essential to use AI responsibly and maintain academic integrity by ensuring that the final work remains original and properly cited.

By following best practices and leveraging AI as a supplementary tool, students can enhance their writing skills and produce high-quality essays. As AI technology continues to advance, it will be crucial to strike a balance between utilizing its capabilities and preserving the human element in academic writing.

We use cookies to personalyze your web-site experience. By continuing we’ll assume you board with our cookie policy .

Get the Reddit app

Subreddit dedicated to discussions on the advanced capabilities and professional applications of ChatGPT.

Using ChatGPT for academic essays

Hi there I have done another video on using chat for education. I show how you can plan, your essay, ask clarifying questions, rewrite parts of your work and mark your essay with feedback before submission video is 7 min long I tried to keep as focused as possible to not waste anyone time. Happy to answer any other questions you may have. I actually have written an essay for this video which is crazy :P

https://youtu.be/SpSP5CWhOK8

Chat description for TL:DW

In this video, I show you how to write an essay using chart GPT as your assistant. The video is divided into chapters, making it easy for you to navigate through it. I aim to keep it brief and productive for you.

I start the chart by giving it a prompt to explain the context of our conversation. In this case, we are writing an assessment for a university level course in health and social care, with the chart acting as my mentor and assistant, who is an expert in the field. I will be bouncing ideas off the chart and asking for help with my work.

The topic I found was posted online from one of the social care degrees assignments. The topic is about the legislative framework for health, safety and risk management in a work setting. The chart provided me with an outline, which includes introduction, Health and Safety at Work Act 1974, Management of Health and Safety at Work Regulations and reporting of injuries.

I asked the chart to give me three points to include in the introduction, and it gave me legal requirements, responsibilities of employers, employee wellbeing and workplace productivity. I then asked for a list of five relevant registration regulations and a list of key provisions in the Health and Safety at Work Act.

Using my knowledge in health and social care, I was able to write my first draft of the essay using the information provided by the chart. I then used my grading scheme to grade my essay and receive feedback from the chart. The chart acted as a British university professor who is strict and critical of student work, providing constructive criticism to help shape students into the best they can be.

The essay was graded at 7 out of 10, and the chart provided me with five pieces of feedback and five potential improvements. The chart also suggested how I could make the introduction stronger by including a physics statement and provided me with a suggestion for the conclusion.

In conclusion, using chart GPT as an assistant was helpful in writing my essay. It provided me with an outline, points to include in my introduction and conclusion, and gave me feedback to improve my work. I was able to use my knowledge in the field to make the most of the information provided by the chart.

Search results for

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

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

Published on March 12, 2023

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

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

JUMP TO KEY SECTIONS

Can ChatGPT write student essays?

Can professors tell if you use chatgpt.

• Should you use ChatGPT to write an essay?

How to use ChatGPT to write an essay

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

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

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

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

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

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

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

Should I use ChatGPT to write an essay?

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

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

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

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

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

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

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

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

You might like

Get science-backed answers as you write with Paperpal's Research feature

What’s the Best ChatGPT Alternative for Academic Writing?

Mastering academic writing takes years of dedicated practice. However, with the emergence of AI tools based on large language models like ChatGPT, navigating the initial stages of this competitive landscape feels almost effortless. ChatGPT and ChatGPT alternatives can automate the more tedious tasks in research, potentially freeing up time for more creative and intellectually stimulating activities. The resulting sense of accomplishment and focus on core academic strengths could boost self-esteem.  

However, concerns exist about academics’ over-reliance on the tool and its potential drawbacks in an academic setting. This ChatGPT review highlights the benefits and risks associated with the tool for research and academic writing and suggests a free ChatGPT alternative to ensure responsible and ethical use of AI tools in academic writing. 

Table of Contents

• What is ChatGPT and How Does it Work?  
• Why do novice researchers and PhD students rely on ChatGPT for academic writing?  
• Pros of ChatGPT  
• Cons of ChatGPT 
• ChatGPT Pricing Plans 
• What is the best free alternative to ChatGPT for academic writing?  
• Paperpal’s Pricing Plans  
• Who Should Use ChatGPT? 
• Who Should Use Paperpal? 

Frequently Asked Questions

What is chatgpt and how does it work.

Launched in November 2022 by OpenAI, ChatGPT is an AI tool that combines a chatbot and virtual assistant. Powered by large language models, it lets you guide your conversation with ChatGPT in terms of length, formality, style, and even the specific language used. 

ChatGPT is built on OpenAI’s proprietary series of generative pre-trained transformer (GPT) models and is fine-tuned to deliver naturally flowing conversations using a combination of supervised learning and reinforcement learning from real-time human feedback. 1  

While its core function is to hold conversations like a human, ChatGPT’s true strength lies in its versatility. ChatGPT can generate different types of content. Its capabilities extend further to translating languages, answering your questions in an informative way, and even simulating experiences like a chatroom game. 

Why do novice researchers and PhD students rely on ChatGPT for academic writing ?

Novice researchers and PhD students rely on ChatGPT or ChatGPT alternatives for several reasons: 

• Limited research experience: Novice researchers may struggle to write a research synopsis or article for the first time due to lack of experience in research processes. 
• Unclear research question: Endless literature search and defining a clear research question or hypothesis is a universal challenge.  
• Time management: Heavy workload and submission deadlines can make it difficult for researchers to carve out dedicated research time. 
• Academic writing formats: Unfamiliarity with formatting and style requirements for academic journals can lead to errors. 
• English language barrier: For non-native English speakers, expressing ideas clearly and concisely can be challenging. 
• Resource limitations: Limited access to research databases, specialized software, or adequate peer/mentor feedback can hinder research writing quality. 

Is ChatGPT Safe for Research and Academic Use: Pros and Cons of ChatGPT

ChatGPT’s ability to understand natural language and revert with coherent and relevant responses makes it an attractive option for academics. However, there are critical challenges to overcome when using ChatGPT in research: the possibility of plagiarism and academic dishonesty. Let’s explore them below. 

Pros of ChatGPT

• Can spark ideas and overcome writer’s block: ChatGPT can help brainstorm topics, generate outlines, formulate research questions, and suggest different ways to phrase your arguments. 
• Improve academic writing style, fluency and efficiency: For novice researchers and PhD students, ChatGPT can help maintain academic writing proficiency, improve flow, and make your writing more concise. 
• Can translate and summarize research in other languages: For non-native researchers, ChatGPT can help in expressing your ideas clearly in English as well as translate research to your preferred language.  

Get 3x more language suggestions tailored to academic writing. Start writing now!  

Cons of ChatGPT

• AI trained on a generic database: ChatGPT is trained on a generic database, so it often fails to provide support tailored to academic context.  
• Risk of misinformation: If you’re relying on ChatGPT for literature review, the tool might suggest articles from predatory journals, without proper verification. Unlike academic databases, ChatGPT doesn’t check for source quality or credibility. It might recommend fabricated, biased, outdated, or poorly researched articles. 
• Prompt writing hassles: Large language models like ChatGPT rely heavily on how you instruct them. Crafting clear prompts with specific context is crucial (prompt engineering). This helps ensure the generated content aligns with your needs. The downside? For research, poorly phrased prompts in ChatGPT can lead to unreliable, incomplete, or even misleading information.  
• Informal language and nuances: Academic writing requires precise wording to express subtle distinctions. You need a formal tone that establishes your credibility and conveys complex ideas clearly. ChatGPT might use simpler terms that miss the mark, leading to a superficial understanding of the topic. 
• AI hallucination: If you ask ChatGPT to find and cite sources for you, it will do so, but they could be inaccurate or even made up. It can also generate factually incorrect information, which can lead to serious repercussions in academia. OpenAI even has a warning on its home screen, saying that ‘ChatGPT may produce inaccurate information about people, places, or facts.’ 1  
• Data privacy concerns: ChatGPT uses your data to train its models. If your research notes include sensitive data, you no longer have control over the information once it is in the chatbot library, unless you opt-out. 2  
• Ethical ambiguity around plagiarism: While ChatGPT doesn’t directly copy, it can unintentionally rephrase and reuse ideas from existing sources without proper citation. ChatGPT cannot distinguish between original sources and can weave information from various sources without acknowledging them. This can be flagged as plagiarism even if it’s not a deliberate attempt. 

ChatGPT Pricing Plans

ChatGPT offers both free and paid subscription plans for individuals and teams. Here’s what you get with each:  

• Free Plan – This plan allows users to access ChatGPT using the GPT-3.5 model without any cost. It’s a great option for new users who want to explore the capabilities of ChatGPT without financial commitment. However, this model is only trained on data till September 2021, so may not be able to provide more updated support.  
• ChatGPT Plus ($20/month): This plan avoids wait times and provides users with faster responses even during peak hours. It also unlocks features like image generation, interactive tables and charts, and priority access to OpenAI’s latest functionalities as they’re released. 
• ChatGPT Team ($25/month): This plan includes ChatGPT Plus with the ability to create and share custom GPTs within a workspace; it also comes with an admin console for workspace management. 
• ChatGPT Enterprise (Customized Pricing): Tailored for large organizations, this plan offers everything included in ChatGPT Team with unlimited high-speed access to GPT-4 and other tools, expanded context windows, and enhanced security and administrative controls. 

Looking for a ChatGPT alternative for academic writing? Try Paperpal  

What is the best free alternative to ChatGPT for academic writing?

Paperpal , a comprehensive AI academic writing assistant is the preferred free alternative to ChatGPT for more than 1Mn+ academics. Trained on millions of scholarly articles and leveraging over 22 years of STM expertise, Paperpal understands and preserves academic context. This ensures that its language suggestions and AI-generated text not only meets stringent linguistic standards but also aligns with academic writing conventions.  

Paperpal as a free ChatGPT alternative provides you with an effortless writing experience with:  

• In-depth Language Checks: Tailored for academic text, Paperpal provides 200+ language suggestions based on scientific contexts, while retaining domain-specific terminology, scientific jargon, and non-English words.   
• Search and Cite: Get science-backed answers with verified citations to your questions from over 250 million research articles across all key disciplines. Paperpal’s AI ranks these papers based on their relevance to your query, and generates a concise, fact-based response summarizing the insights from the top 10 articles. You can also save relevant articles to your Citation Library, which helps you to research, write and cite on-the go. 

Fig 1: Finding existing literature on a research topic using Paperpal Research

• Predictive Writing: If you’re struggling to convey ideas into written content, simply add a starting sentence of over 10 words, and Paperpal’s Write will predict 3 possible suggestions for a follow-up sentence based on context, writing requirements, or custom instructions. With Paperpal Write , you can expand existing content, write a counterargument, or get custom outputs based on prompts. 
• Plagiarism Checker: Paperpal checks your paper for similarity against Turnitin’s extensive database of 100 billion online webpages and provides you with a free similarity score. You can also choose the detailed plagiarism report with color-coded results and side-by-side comparisons to help you address actionable items, cite overlooked sources, and avoid accidental plagiarism .   
• Contextual Synonyms: Struggling with academic vocabulary? Just highlight a word and Paperpal instantly dives into a vast database of high-impact research, analyzing how similar words have been used in published papers. It then presents you with a list of relevant academic vocabulary alternatives , ranked by their usage and context, so you’re always using the right words.     
• Academic Translation: Translating academic text with ChatGPT often introduces avoidable distractions and unnecessary context-switching, leading to miscommunication. On the other hand, Paperpal leverages DeepL to provide accurate academic translation from 28 languages to English without changing the context or meaning.    
• Academic Consistency Checks: Paperpal’s consistency checks ensure style uniformity in the presentation of p-values, symbols, and statistics. With consistency checks, this ChatGPT alternative saves a lot of proofreading time for researchers and students.  
• Generative AI Writing Templates: Paperpal’s generative AI writing features allow users to generate outlines and titles, create abstracts, summaries, study highlights, or craft powerful emails to journals in a click – and without the need of writing extensive prompts.   
• Rewrite: Paperpal also provides accurate paraphrasing and instant word reduction to help you meet prescribed word counts. Unlike other ChatGPT alternatives, Paperpal also ensures a formal academic tone and retains the meaning of your work in the output.  
• Submission Readiness – Paperpal knows that academics need to check several elements to ensure their work is submission ready, which is why it offers 30+ language and technical compliance pre-submission checks to boost your manuscript’s chance of acceptance.    

Paperpal’s Pricing Plans

Free Plan:   

Compared to ChatGPT’s free version, Paperpal offers a wider variety of features that are tailored to enhance academic writing. You get access to the following features:  

• Language suggestions – 200/month  
• Rewrite (Paraphrase, Trim, and more) 
• Research (Search and Cite)  
• Templates to kickstart writing   
• Predictive Writing 
• Translate   
• Free plagiarism report  
• Free submission readiness report   

You also get to experience the free version of Editage All Access Pack – a subscription-based platform that unifies the best AI tools and services designed to speed up, simplify, and streamline every step of a researcher’s journey.  

Paperpal Prime:   

Paperpal’s Prime plan unlocks unlimited access to all the free features, plus consistency checks and 7,000 words/month of plagiarism checks at just US$19/month, US$39/quarter or US$119 per year.   

Paperpal also offers Teams plans for larger groups with exclusive discounts on annual plans.  

Tired of juggling ChatGPT alternatives? Paperpal is the all-in-one research and writing assistant  

Paperpal vs. ChatGPT: Which is the Best AI Tool for Academic Writing?

Here’s a feature comparison of ChatGPT alternative Paperpal and ChatGPT focused on academic writing and research usage.

ChatGPT excels in generating various text formats, translating languages, and answering queries informatively. However, it has significant limitations when it comes to academic writing and research. The major reasons why academics prefer better ChatGPT alternatives include unintentional plagiarism, lack of academic expertise, source reliability, language precision, and AI hallucination. 

One of the most preferred ChatGPT alternatives, Paperpal, excels in academic writing, with features designed to meet the stringent linguistic and formatting standards required for scholarly publication. Given the comprehensive AI academic writing toolkit’s capabilities, Paperpal’s pricing plans are also a tad bit lower than ChatGPT.   

Who Should Use ChatGPT?

ChatGPT is suitable for users who need a versatile tool for generating creative text formats, translating languages, and engaging in informative conversations. The Plus plan is ideal for those requiring faster response times and access to the latest AI functionalities. 

Who Should Use Paperpal?

• Researchers and PhD Students – Paperpal is a highly recommended free ChatGPT alternative due to its focus on academic writing and robust features designed to aid in research and manuscript preparation. The language checks, paraphrasing, in-built writing prompts, search and cite options, predictive writing capabilities, and plagiarism checker prove especially invaluable. 
• Non-Native English Speakers – Paperpal is the preferred choice for those with English as a second language due to its accurate academic translations, writing support, and extensive language correction, which helps in expressing ideas clearly and concisely in English. 
• Users looking for Comprehensive Academic Writing Support – Paperpal provides a more tailored and advanced set of tools for academic writing compared to other ChatGPT alternatives, including contextual synonyms, academic consistency checks, and AI writing templates, making it the better choice for academics seeking a reliable writing assistant. 
• Users Concerned About Data Privacy –  Paperpal promises to keep your data private and confidential; unlike ChatGPT, it does not train its models with user data. Moreover, the copyright for all text generated or enhanced on Paperpal will always remain with you.  

Try Paperpal, the best ChatGPT alternative for free and get an all-in-one academic writing toolkit to excel in academia. Sign up for free!  

ChatGPT might not be safe for academic writing. Here’s why:  Inaccuracy: ChatGPT excels at generating human-like text, but it can be factually incorrect. Double-checking information and citing credible sources remains crucial.  Lack of Originality: Plagiarism through direct use of ChatGPT outputs is a serious concern. It’s a tool to aid, not replace, your own thinking and analysis.  Academic Integrity: Universities have strict plagiarism policies. Using ChatGPT to generate content you present as your own is a violation.    Instead, try using ChatGPT alternatives like Paperpal, which is tailored to academic writing, to get real-time, subject-specific suggestions and write better, faster.      

Yes, you can use ChatGPT or any other ChatGPT alternative for research, but with caution. Here’s how it can be helpful:  Brainstorming: Stuck on a research topic or thesis statement? ChatGPT can help generate ideas and explore different angles.  Literature Review: It can help you identify relevant keywords and search for existing research on your topic. Remember, you still need to critically evaluate the sources it suggests.  Outlining: Need a structure for your research proposal? ChatGPT can create a basic outline to get you started.   

Here’s how you can use ChatGPT for your research proposal – Provide Context: Clearly explain your research topic and goals to ChatGPT.  Refine Outputs: Don’t accept everything it generates at face value. Fact-check, critically analyze, and edit the information it provides.  Focus on the “Why”: Use ChatGPT to brainstorm ideas but focus on understanding the “why” behind your research question. 

No. While it can be a helpful tool, it shouldn’t be your primary source of information. Always rely on credible academic sources and conduct your own thorough research.    Remember:   Critical thinking is essential   Verification of the scientific accuracy of sources is paramount  Responsible AI use upholds academic integrity    Check with your university’s policies on AI use in academic writing. Consider using ChatGPT alongside other academic writing tools like Paperpal to get the best output.   

• OpenAI. (2023). Introducing ChatGPT. https://openai.com/index/chatgpt/
• OpenAI. (2023). ChatGPT pricing, capabilities, and limitations. https://openai.com/chatgpt/pricing/

Related Reads:

• Why Not to Use ChatGPT for Academic Writing
• How Paperpal’s Built-In Academic Writing Prompts Make It a Better Alternative to ChatGPT
• Grammarly Review – Is Grammarly Worth it? [2024 Update]
• Why Traditional Editorial Process Needs An Upgrade?

How to Write a Good Hook for Essays, with Examples

Leveraging generative ai to enhance student understanding of complex research concepts , you may also like, addressing peer review feedback and mastering manuscript revisions..., introducing paperpal predictive text suggestions: transform ideas into..., what is the importance of a concept paper..., how to write a high-quality conference paper, how paperpal’s research feature helps you develop and..., how paperpal is enhancing academic productivity and accelerating..., how to write a successful book chapter for..., what are scholarly sources and where can you..., how to write a hypothesis types and examples , measuring academic success: definition & strategies for excellence.

• Share on twitter
• Share on facebook

Academics despair as ChatGPT-written essays swamp marking season

‘it’s not a machine for cheating; it’s a machine for producing crap,’ says one professor infuriated by rise of bland scripts.

• Share on linkedin
• Share on mail

The increased prevalence of students using ChatGPT to write essays should prompt a rethink about whether current policies encouraging “ethical” use of artificial intelligence are working, scholars have argued.

With marking season in full flow, lecturers have taken to social media in large numbers to complain about AI-generated content found in submitted work.

Telltale signs of ChatGPT use, according to academics, include little-used words such as “delve” and “multifaceted”, summarising key themes using bullet points and a jarring conversational style using terms such as “let’s explore this theme”.

In a more obvious giveaway, one professor said an advert for an AI essay company was buried in a paper’s introduction ; another academic noted how a student had forgotten to remove a chatbot statement that the content was AI-generated.

“I had no idea how many would resort to it,” admitted one UK law professor .

Des Fitzgerald, professor of medical humanities and social sciences at University College Cork , told Times Higher Education that student use of AI had “gone totally mainstream” this year.

“Across a batch of essays, you do start to notice the tics of ChatGPT essays, which is partly about repetition of certain words or phrases, but is also just a kind of aura of machinic blandness that’s hard to describe to someone who hasn’t encountered it – an essay with no edges, that does nothing technically wrong or bad, but not much right or good, either,” said Professor Fitzgerald.

Since ChatGPT’s emergence in late 2022 , some universities have adopted policies to allow the use of AI as long as it is acknowledged, while others have begun using AI content detectors, although opinion is divided on their effectiveness .

According to the latest Student Academic Experience Survey , for which Advance HE and the Higher Education Policy Institute polled around 10,000 UK undergraduates, 61 per cent use AI at least a little each month, “in a way allowed by their institution”, while 31 per cent do so every week.

Campus resource: Can we spot AI-written content?

Professor Fitzgerald said that although some colleagues “think we just need to live with this, even that we have a duty to teach students to use it well”, he was “totally against” the use of AI tools for essays.

“ChatGPT is completely antithetical to everything I think I’m doing as a teacher – working with students to engage with texts, thinking through ideas, learning to clarify and express complex thoughts, taking some risks with those thoughts, locating some kind of distinctive inner voice. ChatGPT is total poison for all of this, and we need to simply ban it,” he said.

Steve Fuller, professor of sociology at the University of Warwick , agreed that AI use had “become more noticeable” this year despite his students signing contracts saying they would not use it to write essays.

He said he was not opposed to students using it “as long as what they produce sounds smart and on point, and the marker can’t recognise it as simply having been lifted from another source wholesale”.

Those who leaned heavily on the technology should expect a relatively low mark, even though they might pass, said Professor Fuller.

“Students routinely commit errors of fact, reasoning and grammar [without ChatGPT], yet if their text touches enough bases with the assignment they’re likely to get somewhere in the low- to mid-60s. ChatGPT does a credible job at simulating such mediocrity, and that’s good enough for many of its student users,” he said.

Having to mark such mediocre essays partly generated by AI is, however, a growing complaint among academics. Posting on X, Lancaster University economist Renaud Foucart said marking AI-generated essays “takes much more time to assess [because] I need to concentrate much more to cut through the amount of seemingly logical statements that are actually full of emptiness”.

“My biggest issue [with AI] is less the moral issue about cheating but more what ChatGPT offers students,” Professor Fitzgerald added. “All it is capable of is [writing] bad essays made up of non-ideas and empty sentences. It’s not a machine for cheating; it’s a machine for producing crap.”

[email protected]

POSTSCRIPT:

Print headline:  Academics despair over ‘crap’ AI essays

Register to continue

Why register?

• Registration is free and only takes a moment
• Once registered, you can read 3 articles a month
• Sign up for our newsletter

Or subscribe for unlimited access to:

• Unlimited access to news, views, insights & reviews
• Digital editions
• Digital access to THE’s university and college rankings analysis

Already registered or a current subscriber? Login

Related articles

Policing AI use by counting ‘telltale’ words is flawed and damaging

Making people paranoid about employing familiar and useful words is not the way to encourage responsible AI use, say Lilian Schofield and Xue Zhou 

Privileged students ‘more likely to use ChatGPT’ on assessments

Survey finds evidence of ‘emerging digital divide’ as majority of undergraduates say they use generative AI to help with assessments

Less than half of top universities publish AI guidelines

Lack of clear guidelines may put instructors on ‘defensive’ over students’ use of ChatGPT, researchers say

AI text detectors aren’t working. Is regulation the answer?

Tools developed to stamp out misconduct have been shown to be biased and inaccurate. Will AI creators themselves be forced to do it better?

Related universities

University college cork, university of warwick, reader's comments (14), you might also like.

Computer science students must be taught to consider social effects

Departments can no longer be singularly tied to their mathematical and engineering foundations, focused only on what can be built, says Beth Mynatt

What crisis? Students rate UK courses highly despite challenges

More UK undergraduates see courses as value for money in 2024, with international students driving much of the increase

AI or not, students must still learn to think for themselves

Perhaps AI will be a useful tool. But our obsession with every shiny new object regardless of the harm it might do makes me worry, says Melinda Zook

Featured jobs

Don't wait for iOS 18's AI. ChatGPT offers these same 4 features now

After ChatGPT's launch in November 2022, nearly every company joined in on the AI craze -- except Apple. Two years later, at its annual Worldwide Developer Conference (WWDC) , Apple unveiled a collection of AI features known as  Apple Intelligence . While they look impressive (and certainly are), many of the new features have been done before by OpenAI's ChatGPT.

This fall, Apple's software updates will bring  generative AI capabilities to iPhones, iPads, and Macs. However, OpenAI already  unveiled major upgrades to the free version of ChatGPT in May, and the similarities to what Apple Intelligence will do are worth noting. 

Also: Five iOS 18 features that Android users already have

The Apple Intelligence updates will be free, but the full experience  will only be available on iPhones with the A17 Pro chip, which currently only includes iPhone 15 Pro and iPhone 15 Pro Max, and iPads and Macs with the M family of chips. 

Instead of spending thousands of dollars rushing to upgrade to the newest Apple devices, you should check out ChatGPT first. OpenAI's free chatbot has many of the same features coming to Apple Intelligence. 

1. Writing tools 

With Apple Intelligence, users will be able to access a variety of writing tools that can help with rewriting, proofreading, and summarizing text. Apple says the tools will be accessible "everywhere" users write, including in Mail, Keynote, third-party apps, and more. 

ChatGPT's advanced natural language processing (NLP) makes it a great writing tool as well. It can generate new text from scratch, proofread, coedit, rewrite, and more. While the ChatGPT experience may not live natively within Apple devices the way Apple Intelligence will, users can easily copy and paste its output into a tab while accessing ChatGPT in their browser.

Also: How ChatGPT (and other AI chatbots) can help you write an essay

Another option for Apple users is to take advantage of the ChatGPT  app for iPads and iPhones. There's even a ChatGPT app for MacOS , which allows users to access the chatbot quickly via a keyboard shortcut. The Mac app is available now for ChatGPT Plus subscribers, but OpenAI is planning to release access to all users in the coming months.

2. Image generator

Apple also unveiled its first text-to-image generator, Apple's Image Playground . This generator will be built into iOS 18, iPadOS 18, and MacOS Sequoia as part of Apple Intelligence, and will also live as a stand-alone app.

Also: The best AI image generators to try right now

It's unclear without testing it, but Image Playground's functionality will likely be similar to OpenAI's image generator, DALL-E 3, which can be accessed via ChatGPT Plus. Even though it requires a $20 per month subscription, it offers users a wider variety of options, since it can render images in any style. Image Playground is limited to three styles: Animation, illustration, and sketch.

3. On-screen awareness

At Apple's event, the company shared that with Apple Intelligence, Siri will have on-screen awareness, making asking it for help with certain tasks easier. During OpenAI's Spring Launch event, the company also showed a demo indicating that ChatGPT will have on-screen awareness as well, as seen below -- though it didn't clarify when we'll see this feature. 

The value of having an AI voice assistant that can see what you are working on and use it as context for your query is evident, and it will likely be the future of all assistants. 

4. Advanced conversational capabilities 

Another update coming to Siri is better NLP, meaning it will be able to understand you even if you stutter or pause. OpenAI indicated at its Spring Launch that the improved Voice Mode for ChatGPT will have the same capabilities, such as stopping when a user interrupts it, understanding queries better, and more. The improved Voice Mode will be rolling out in alpha in the coming weeks, and ChatGPT Plus users will get early access as the company rolls it out more broadly.

Also: Everything to know about Apple's AI features for iPhones, Macs, and iPads

5. Type and chat

With Apple Intelligence, Siri will be upgraded to accept typed and voice queries -- a significant change considering that it has only ever functioned as a voice assistant. However, as discussed above, ChatGPT can also take text and voice inputs. 

6. And, of course…access to ChatGPT

Apple also announced that Siri will have access to ChatGPT, which you can also access by going directly to the source. 

Here's every iPhone model that will support Apple's latest AI features (for now)

Four ios 18 ai features the iphone needs to catch up with android, every new feature apple unveiled for iphone, ipad, mac, and more this fall (including ai).

Have a language expert improve your writing

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

• Knowledge Base

Using AI tools

Using ChatGPT to Write a College Essay | Tips & Examples

Published on June 26, 2023 by Koen Driessen . Revised on December 8, 2023.

A good college essay helps to distinguish your application from those of other candidates. It conveys your experiences, values, and character traits and indicates why you would make a good addition to the university you’re applying to.

Your college essay should be your own work. However, AI tools like ChatGPT may be helpful during the preparation and revision stages of your writing.

You can also use the essay checker , so you don’t have to revise your writing yourself.

You can use these tools to:

• Brainstorm essay ideas
• Develop an outline
• Generate feedback

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

Brainstorming ideas, developing an outline, generating feedback, limitations of using chatgpt, other interesting articles, frequently asked questions.

Your college essay topic should reveal something distinctive about your personality and have a unique angle.

Brainstorming a range of potential ideas is a good place to start. This can help to stimulate creative thinking and prompt self-reflection. It can also help you draw connections between seemingly unrelated experiences or ideas.

You can use ChatGPT to generate questions to help you brainstorm.

Example: Using ChatGPT to brainstorm ideas

• Generate 10 questions to help me brainstorm topics for my college admission essay.
• How has a particular life experience shaped your perspective on a specific issue or topic?
• What challenges or obstacles have you faced, and how have they influenced your personal growth?
• How has your involvement in extracurricular activities impacted your character development and contributed to your identity?
• In what ways have you demonstrated leadership skills and made a positive impact on your community?
• Describe a significant academic achievement or project that showcases your intellectual curiosity and passion.
• How have your cultural background and family values influenced your aspirations and goals for the future?
• Reflect on a time when you had to step outside of your comfort zone to achieve a meaningful outcome. What did you learn from this experience?
• How do you envision using your education to make a difference in the world or contribute to a specific field or industry?
• What do you believe sets you apart from other applicants, and how would your unique perspective enrich the college community?
• Discuss a book, artwork, or scientific discovery that has profoundly impacted your thinking and helped shape your intellectual interests.

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

College admission essays don’t follow one predefined structure, so you can approach them creatively and incorporate storytelling techniques.

Two common approaches to structuring your essay are the narrative structure (a chronological narrative that shows your character development over time) and the vignette or montage structure (multiple scenes connected by a common topic or theme).

Regardless of the structure you choose, it’s important to establish a coherent narrative and ensure that your essay flows smoothly.

You can use ChatGPT as a source of inspiration and to generate potential ideas on how to structure your college essay . Do this by prompting the tool to create an outline using your chosen topic. You can make the prompt as specific as you like, mentioning any facts or viewpoints that should be incorporated into the output.

Examples: Using ChatGPT to generate an essay outline

• Provide a very short outline for a college admission essay. The essay will be about my experience working at an animal shelter. The essay will be 500 words long.
• Hook: Share a brief and engaging anecdote about your experience at the animal shelter.
• Thesis statement: Working at an animal shelter has been a transformative experience, teaching me valuable lessons about compassion, resilience, and community impact.
• Describe your first impressions and emotions upon starting work at the shelter.
• Discuss the challenges you encountered, such as the condition of the animals or the emotional toll of their situations.
• Highlight the relationships you formed with the animals and their impact on you.
• Discuss specific instances where you witnessed the transformative power of love and care on the animals’ well-being.
• Explore the collaborative efforts within the shelter community.
• Discuss how working with others led to positive outcomes and inspired you to make a difference.
• Reflect on how working at the shelter has shaped your character and values.
• Discuss the skills and lessons learned that are applicable beyond the shelter environment.
• Connect your experiences to your future goals and aspirations.
• Summarize the main points discussed in the essay.
• Reinforce the transformative nature of your experience and your commitment to making a positive impact in the future.

You can use ChatGPT to help revise your essay before submitting it to ensure that it’s of a high quality. However, ChatGPT cannot provide the same kind of informed feedback as a human, and it’s not able to adequately judge qualities such as vulnerability and authenticity. For this reason, it’s important to also ask for feedback from two to three people who have experience with college essays and who know you well.

Nevertheless, you can use ChatGPT to generate feedback on certain aspects, such as consistency of tone, clarity of structure, and grammar and punctuation. You can also use  Scribbr’s free paraphrasing tool to help vary the tone of your writing and Scribbr’s free grammar checker to ensure your text is free of grammar, spelling, and punctuation errors.

Alternatively, you can seek the advice of a human essay coach or editor. We recommend using Scribbr’s essay editing service .

Example: Using ChatGPT to get feedback

• Provide constructive feedback on how to improve the above essay with regard to appropriateness of tone, clarity of structure, and grammar and punctuation.
• The tone of the essay is generally appropriate, conveying a sense of personal growth and passion. However, consider injecting more enthusiasm and emotion into certain parts of the essay to make it more engaging and captivating.
• The overall structure of the essay is clear and follows a logical progression. However, it would benefit from a stronger introduction that hooks the reader and clearly outlines the main points to be discussed.
• Consider using clear topic sentences at the beginning of each paragraph to provide a preview of the main idea or argument that will be presented.
• Pay attention to subject-verb agreement and verb tenses throughout the essay to ensure consistency.
• Proofread the essay to eliminate any repetitive phrases or sentences.
• Check for the correct use of commas and other punctuation marks, ensuring they are used appropriately to enhance clarity and flow.

Additionally, here are a few constructive suggestions for improvement:

• Expand on the ways in which working at the animal shelter influenced your future aspirations and academic/professional pursuits.
• Be mindful of using diverse vocabulary and sentence structures to enhance the overall quality of the essay.

While ChatGPT can help you brainstorm, outline, and revise your essay, having it write your essay for you can negatively impact your application in several ways.

Unoriginal content

ChatGPT responses are based on a wide range of sources and sometimes resemble existing texts. Furthermore, they are not always unique, since other users may receive the same responses to similar prompts.

As the point of a college essay is to showcase your unique experiences and perspective and make you stand out from other candidates, having ChatGPT write your essay is not a good idea.

Formulaic style

ChatGPT outputs don’t reflect your personality, are highly formulaic, and contain many clichés (e.g., outputs often use hackneyed phrases like “burning desire,” “insatiable curiosity,” and “thirst for knowledge”).

Furthermore, ChatGPT outputs often “tell” rather than “show” (i.e., they state a fact instead of illustrating it using examples and vivid imagery).

Lack of personal insight

Human-written text tends to be more unpredictable and contain more creative language choices than AI-generated writing.

While the connections you make in your writing should not be nonsensical, drawing unique and unexpected connections between different experiences can help show character development and display your creativity and critical thinking skills.

ChatGPT can’t do this. Furthermore, it can’t express authentic emotion or vulnerability about specific memories that are, after all, your memories, not ChatGPT’s.

Risk of plagiarism

Passing off AI-generated text as your own work is usually considered plagiarism (or at least academic dishonesty ). AI detectors may be used to detect this offense.

It’s highly unlikely that a university will accept your application if you are caught submitting an AI-generated college essay.

Check for common mistakes

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

Fix mistakes for free

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

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

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

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

Yes, you use ChatGPT to help write your college essay by having it generate feedback on certain aspects of your work (consistency of tone, clarity of structure, etc.).

However, ChatGPT is not able to adequately judge qualities like vulnerability and authenticity. For this reason, it’s important to also ask for feedback from people who have experience with college essays and who know you well. Alternatively, you can get advice using Scribbr’s essay editing service .

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, December 08). Using ChatGPT to Write a College Essay | Tips & Examples. Scribbr. Retrieved June 18, 2024, from https://www.scribbr.com/ai-tools/chatgpt-college-essay/

Is this article helpful?

Koen Driessen

Other students also liked, how to use chatgpt | basics & tips, how to use chatgpt in your studies, using chatgpt for assignments | tips & examples.

Koen Driessen (Scribbr Team)

Thanks for reading! Hope you found this article helpful. If anything is still unclear, or if you didn’t find what you were looking for here, leave a comment and we’ll see if we can help.

Still have questions?

Get unlimited documents corrected.

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

• Services & Software

How to Use ChatGPT to Write a Resume

Already got your AI-assisted cover letter on hand? We walk you through the steps of creating a resume, too.

If you've just graduated college or you're looking for a new job, a solid resume can get your foot in the door. Unlike a cover letter, which has to be tweaked for every new application, your resume only needs to be updated every year or two to showcase your skills, experience, education, honors and references. 

With the state of the job market, mass layoffs, and shift to the gig economy, investing time now to create an epic resume will pay off. Your resume is the first touch point you have with a prospective employer, but if staring at a blank page and trying to write about yourself is discouraging, then let artificial intelligence do the legwork. 

ChatGPT , the breakout generative AI tool, can help you with the best practices of resume writing and speed up the process. If there's one thing AI is good at, it's synthesizing, structuring and summarizing information. And once you have your resume, you can use it to create a custom cover letter . 

You can use a free version of ChatGPT or pay $20 per month for added features like the  most recent models , priority access during peak usage, and image generation. 

If you're struggling to condense career highlights over decades into two pages, read on.

Creating a resume from scratch

Set yourself up for success by doing some preparation. ChatGPT needs context, otherwise it'll spit out generic content that's sometimes even wrong . I started by researching reporter resume templates and jotted down notes about past experience, education and accomplishments. 

Then to find out what ChatGPT needs, just ask. "Can you write me a resume?" was my first prompt, and ChatGPT conveniently told me all the information to input so it could get to work. 

I replied with all my information, outlined like this, and attached my preferred format: 

Here is my professional summary: [paste]  Here is my work experience: [paste]  Here are my major clients: [paste]  Here is my education: [paste]  Please generate a list of skills based on my experience and format my resume like the example below: [paste template]

ChatGPT does a great job of organizing information into a cohesive format, but I wanted to change it so it flowed a little better (it put my education before my experience, making it look at first glance like I didn't have any experience). 

Please reorganize the following sections in this order: 

• Contact Details 
• Summary 
• Experience 
• Major Clients 
• Skills 

Looking good.

Keep your info less sensitive

You'll see that I didn't give the chatbot my contact details to add to the resume. I prefer to keep my sensitive information out of the model to avoid any future data breaches or unnecessary risk, so I'll add my email, phone number and address myself in the final version. 

When reviewing ChatGPT's draft, I noticed two issues: 

• My 10 years as a full-time freelancer needed to be fleshed out, by adding noteworthy projects and long contracts. 
• The skills list was way too long. 

Back in ChatGPT I wrote the following:

Please add two contract roles under Freelance Reporter and Writer in the experience section. 

Freelance Reporter at NerdWallet, August 2022 - present. Tasks: Writing personal finance advice articles, providing insights and strategies to educate and empower everyday consumers in Australia. Topics include credit cards, travel points, frequent flyer programs, BNPL, credit scores, money management, and more.

Freelance Reporter at Decential, September 2022 - present. Tasks: Reporting on the people, projects and protocols in the world of web3. Cover news, interview founders, write deep dive features and commentary, and cover in-person events and conferences.

Then, instead of reducing the skills list, I asked that it be arranged in two columns. The chatbot put the info into a table, which I didn't like, so I asked that it be removed. 

ChatGPT still had a hard time with it. I asked it again to present the info in two columns, with a space in between but without a table or borders. You can highlight a section and reply specifically there. 

But it still didn't work, so I stopped wasting time and did it myself directly in the document. 

Final tweaks

Before I made my final tweaks, I asked ChatGPT to provide a short list of suggestions for how to improve my resume. It gave me some solid advice -- like highlighting achievements, quantifying results, tailoring my resume to a specific job, adding keywords and making my professional summary more concise -- but take it with a grain of salt. 

For example, my professional summary shows my narrative abilities and doesn't take up much real estate. I did, however, add a section for notable projects.  

Though some advice was relevant, like adding metrics to achievements and starting each bullet point with a strong action verb, the others weren't necessary. For instance, I didn't want to make my profile more concise, because that's where I show off my narrative ability for writing jobs. When using artificial intelligence, always trust your human instinct. 

Last, I wanted to get it down from four pages to three, so I arranged my major clients into two columns and reduced the skills list. You can see the final version of my AI-created resume below.

Once ChatGPT is done with the nitty gritty, you can add the finishing touches yourself. I'll drop in my logo and byline hyperlinks, then it's good to go!

For more AI tips, check out  how to use Midjourney to create custom wedding invitations  and how to use AI-powered Grammarly to do all of your editing . For news and hands-on reviews of gen AI tools  ChatGPT ,  Copilot ,  Gemini  and more, check out CNET's  AI Atlas  hub.

ChatGPT's final resume for me:

Editors' note: CNET used an AI engine to help create several dozen stories, which are labeled accordingly. The note you're reading is attached to articles that deal substantively with the topic of AI but are created entirely by our expert editors and writers. For more, see our  AI policy .

ChatGPT is bullshit

• Original Paper
• Open access
• Published: 08 June 2024
• Volume 26 , article number  38 , ( 2024 )

Cite this article

You have full access to this open access article

• Michael Townsen Hicks   ORCID: orcid.org/0000-0002-1304-5668 1 ,
• James Humphries 1 &
• Joe Slater 1  

131k Accesses

1315 Altmetric

13 Mentions

Explore all metrics

Recently, there has been considerable interest in large language models: machine learning systems which produce human-like text and dialogue. Applications of these systems have been plagued by persistent inaccuracies in their output; these are often called “AI hallucinations”. We argue that these falsehoods, and the overall activity of large language models, is better understood as bullshit in the sense explored by Frankfurt (On Bullshit, Princeton, 2005): the models are in an important way indifferent to the truth of their outputs. We distinguish two ways in which the models can be said to be bullshitters, and argue that they clearly meet at least one of these definitions. We further argue that describing AI misrepresentations as bullshit is both a more useful and more accurate way of predicting and discussing the behaviour of these systems.

Similar content being viewed by others

Assessing the Strengths and Weaknesses of Large Language Models

Foundation and large language models: fundamentals, challenges, opportunities, and social impacts

Unraveling the mysteries of AI chatbots

Avoid common mistakes on your manuscript.

Introduction

Large language models (LLMs), programs which use reams of available text and probability calculations in order to create seemingly-human-produced writing, have become increasingly sophisticated and convincing over the last several years, to the point where some commentators suggest that we may now be approaching the creation of artificial general intelligence (see e.g. Knight, 2023 and Sarkar, 2023 ). Alongside worries about the rise of Skynet and the use of LLMs such as ChatGPT to replace work that could and should be done by humans, one line of inquiry concerns what exactly these programs are up to: in particular, there is a question about the nature and meaning of the text produced, and of its connection to truth. In this paper, we argue against the view that when ChatGPT and the like produce false claims they are lying or even hallucinating, and in favour of the position that the activity they are engaged in is bullshitting, in the Frankfurtian sense (Frankfurt, 2002 , 2005 ). Because these programs cannot themselves be concerned with truth, and because they are designed to produce text that looks truth-apt without any actual concern for truth, it seems appropriate to call their outputs bullshit.

We think that this is worth paying attention to. Descriptions of new technology, including metaphorical ones, guide policymakers’ and the public’s understanding of new technology; they also inform applications of the new technology. They tell us what the technology is for and what it can be expected to do. Currently, false statements by ChatGPT and other large language models are described as “hallucinations”, which give policymakers and the public the idea that these systems are misrepresenting the world, and describing what they “see”. We argue that this is an inapt metaphor which will misinform the public, policymakers, and other interested parties.

The structure of the paper is as follows: in the first section, we outline how ChatGPT and similar LLMs operate. Next, we consider the view that when they make factual errors, they are lying or hallucinating: that is, deliberately uttering falsehoods, or blamelessly uttering them on the basis of misleading input information. We argue that neither of these ways of thinking are accurate, insofar as both lying and hallucinating require some concern with the truth of their statements, whereas LLMs are simply not designed to accurately represent the way the world is, but rather to give the impression that this is what they’re doing. This, we suggest, is very close to at least one way that Frankfurt talks about bullshit. We draw a distinction between two sorts of bullshit, which we call ‘hard’ and ‘soft’ bullshit, where the former requires an active attempt to deceive the reader or listener as to the nature of the enterprise, and the latter only requires a lack of concern for truth. We argue that at minimum, the outputs of LLMs like ChatGPT are soft bullshit: bullshit–that is, speech or text produced without concern for its truth–that is produced without any intent to mislead the audience about the utterer’s attitude towards truth. We also suggest, more controversially, that ChatGPT may indeed produce hard bullshit: if we view it as having intentions (for example, in virtue of how it is designed), then the fact that it is designed to give the impression of concern for truth qualifies it as attempting to mislead the audience about its aims, goals, or agenda. So, with the caveat that the particular kind of bullshit ChatGPT outputs is dependent on particular views of mind or meaning, we conclude that it is appropriate to talk about ChatGPT-generated text as bullshit, and flag up why it matters that – rather than thinking of its untrue claims as lies or hallucinations – we call bullshit on ChatGPT.

What is ChatGPT?

Large language models are becoming increasingly good at carrying on convincing conversations. The most prominent large language model is OpenAI’s ChatGPT, so it’s the one we will focus on; however, what we say carries over to other neural network-based AI chatbots, including Google’s Bard chatbot, AnthropicAI’s Claude (claude.ai), and Meta’s LLaMa. Despite being merely complicated bits of software, these models are surprisingly human-like when discussing a wide variety of topics. Test it yourself: anyone can go to the OpenAI web interface and ask for a ream of text; typically, it produces text which is indistinguishable from that of your average English speaker or writer. The variety, length, and similarity to human-generated text that GPT-4 is capable of has convinced many commentators to think that this chatbot has finally cracked it: that this is real (as opposed to merely nominal) artificial intelligence, one step closer to a human-like mind housed in a silicon brain.

However, large language models, and other AI models like ChatGPT, are doing considerably less than what human brains do, and it is not clear whether they do what they do in the same way we do. The most obvious difference between an LLM and a human mind involves the goals of the system. Humans have a variety of goals and behaviours, most of which are extra-linguistic: we have basic physical desires, for things like food and sustenance; we have social goals and relationships; we have projects; and we create physical objects. Large language models simply aim to replicate human speech or writing. This means that their primary goal, insofar as they have one, is to produce human-like text. They do so by estimating the likelihood that a particular word will appear next, given the text that has come before.

The machine does this by constructing a massive statistical model, one which is based on large amounts of text, mostly taken from the internet. This is done with relatively little input from human researchers or the designers of the system; rather, the model is designed by constructing a large number of nodes, which act as probability functions for a word to appear in a text given its context and the text that has come before it. Rather than putting in these probability functions by hand, researchers feed the system large amounts of text and train it by having it make next-word predictions about this training data. They then give it positive or negative feedback depending on whether it predicts correctly. Given enough text, the machine can construct a statistical model giving the likelihood of the next word in a block of text all by itself.

This model associates with each word a vector which locates it in a high-dimensional abstract space, near other words that occur in similar contexts and far from those which don’t. When producing text, it looks at the previous string of words and constructs a different vector, locating the word’s surroundings – its context – near those that occur in the context of similar words. We can think of these heuristically as representing the meaning of the word and the content of its context. But because these spaces are constructed using machine learning by repeated statistical analysis of large amounts of text, we can’t know what sorts of similarity are represented by the dimensions of this high-dimensional vector space. Hence we do not know how similar they are to what we think of as meaning or context. The model then takes these two vectors and produces a set of likelihoods for the next word; it selects and places one of the more likely ones—though not always the most likely. Allowing the model to choose randomly amongst the more likely words produces more creative and human-like text; the parameter which controls this is called the ‘temperature’ of the model and increasing the model’s temperature makes it both seem more creative and more likely to produce falsehoods. The system then repeats the process until it has a recognizable, complete-looking response to whatever prompt it has been given.

Given this process, it’s not surprising that LLMs have a problem with the truth. Their goal is to provide a normal-seeming response to a prompt, not to convey information that is helpful to their interlocutor. Examples of this are already numerous, for instance, a lawyer recently prepared his brief using ChatGPT and discovered to his chagrin that most of the cited cases were not real (Weiser, 2023 ); as Judge P. Kevin Castel put it, ChatGPT produced a text filled with “bogus judicial decisions, with bogus quotes and bogus internal citations”. Similarly, when computer science researchers tested ChatGPT’s ability to assist in academic writing, they found that it was able to produce surprisingly comprehensive and sometimes even accurate text on biological subjects given the right prompts. But when asked to produce evidence for its claims, “it provided five references dating to the early 2000s. None of the provided paper titles existed, and all provided PubMed IDs (PMIDs) were of different unrelated papers” (Alkaissi and McFarland, 2023 ). These errors can “snowball”: when the language model is asked to provide evidence for or a deeper explanation of a false claim, it rarely checks itself; instead it confidently producesmore false but normal-sounding claims (Zhang et al. 2023 ). The accuracy problem for LLMs and other generative Ais is often referred to as the problem of “AI hallucination”: the chatbot seems to be hallucinating sources and facts that don’t exist. These inaccuracies are referred to as “hallucinations” in both technical (OpenAI, 2023 ) and popular contexts (Weise & Metz, 2023 ).

These errors are pretty minor if the only point of a chatbot is to mimic human speech or communication. But the companies designing and using these bots have grander plans: chatbots could replace Google or Bing searches with a more user-friendly conversational interface (Shah & Bender, 2022 ; Zhu et al., 2023 ), or assist doctors or therapists in medical contexts (Lysandrou, 2023 ). In these cases, accuracy is important and the errors represent a serious problem.

One attempted solution is to hook the chatbot up to some sort of database, search engine, or computational program that can answer the questions that the LLM gets wrong (Zhu et al., 2023 ). Unfortunately, this doesn’t work very well either. For example, when ChatGPT is connected to Wolfram Alpha, a powerful piece of mathematical software, it improves moderately in answering simple mathematical questions. But it still regularly gets things wrong, especially for questions which require multi-stage thinking (Davis & Aaronson, 2023 ). And when connected to search engines or other databases, the models are still fairly likely to provide fake information unless they are given very specific instructions–and even then things aren’t perfect (Lysandrou, 2023 ). OpenAI has plans to rectify this by training the model to do step by step reasoning (Lightman et al., 2023 ) but this is quite resource-intensive, and there is reason to be doubtful that it will completely solve the problem—nor is it clear that the result will be a large language model, rather than some broader form of AI.

Solutions such as connecting the LLM to a database don’t work is because, if the models are trained on the database, then the words in the database affect the probability that the chatbot will add one or another word to the line of text it is generating. But this will only make it produce text similar to the text in the database; doing so will make it more likely that it reproduces the information in the database but by no means ensures that it will.

On the other hand, the LLM can also be connected to the database by allowing it to consult the database, in a way similar to the way it consults or talks to its human interlocutors. In this way, it can use the outputs of the database as text which it responds to and builds on. Here’s one way this can work: when a human interlocutor asks the language model a question, it can then translate the question into a query for the database. Then, it takes the response of the database as an input and builds a text from it to provide back to the human questioner. But this can misfire too, as the chatbots might ask the database the wrong question, or misinterpret its answer (Davis & Aaronson, 2023 ). “GPT-4 often struggles to formulate a problem in a way that Wolfram Alpha can accept or that produces useful output.” This is not unrelated to the fact that when the language model generates a query for the database or computational module, it does so in the same way it generates text for humans: by estimating the likelihood that some output “looks like’’ the kind of thing the database will correspond with.

One might worry that these failed methods for improving the accuracy of chatbots are connected to the inapt metaphor of AI hallucinations. If the AI is misperceiving or hallucinating sources, one way to rectify this would be to put it in touch with real rather than hallucinated sources. But attempts to do so have failed.

The problem here isn’t that large language models hallucinate, lie, or misrepresent the world in some way. It’s that they are not designed to represent the world at all; instead, they are designed to convey convincing lines of text. So when they are provided with a database of some sort, they use this, in one way or another, to make their responses more convincing. But they are not in any real way attempting to convey or transmit the information in the database. As Chirag Shah and Emily Bender put it: “Nothing in the design of language models (whose training task is to predict words given context) is actually designed to handle arithmetic, temporal reasoning, etc. To the extent that they sometimes get the right answer to such questions is only because they happened to synthesize relevant strings out of what was in their training data. No reasoning is involved […] Similarly, language models are prone to making stuff up […] because they are not designed to express some underlying set of information in natural language; they are only manipulating the form of language” (Shah & Bender, 2022 ). These models aren’t designed to transmit information, so we shouldn’t be too surprised when their assertions turn out to be false.

Lies, ‘hallucinations’ and bullshit

Frankfurtian bullshit and lying.

Many popular discussions of ChatGPT call its false statements ‘hallucinations’. One also might think of these untruths as lies. However, we argue that this isn’t the right way to think about it. We will argue that these falsehoods aren’t hallucinations later – in Sect. 3.2.3. For now, we’ll discuss why these untruths aren’t lies but instead are bullshit.

The topic of lying has a rich philosophical literature. In ‘Lying’, Saint Augustine distinguished seven types of lies, and his view altered throughout his life. At one point, he defended the position that any instance of knowingly uttering a false utterance counts as a lie, so that even jokes containing false propositions, like –

I entered a pun competition and because I really wanted to win, I submitted ten entries. I was sure one of them would win, but no pun in ten did.

– would be regarded as a lie, as I have never entered such a competition (Proops & Sorensen, 2023 : 3). Later, this view is refined such that the speaker only lies if they intend the hearer to believe the utterance. The suggestion that the speaker must intend to deceive is a common stipulation in literature on lies. According to the “traditional account” of lying:

To lie =  df . to make a believed-false statement to another person with the intention that the other person believe that statement to be true (Mahon, 2015 ).

For our purposes this definition will suffice. Lies are generally frowned upon. But there are acts of misleading testimony which are criticisable, which do not fall under the umbrella of lying. Footnote 1 These include spreading untrue gossip, which one mistakenly, but culpably, believes to be true. Another class of misleading testimony that has received particular attention from philosophers is that of bullshit. This everyday notion was analysed and introduced into the philosophical lexicon by Harry Frankfurt. Footnote 2

Frankfurt understands bullshit to be characterized not by an intent to deceive but instead by a reckless disregard for the truth. A student trying to sound knowledgeable without having done the reading, a political candidate saying things because they sound good to potential voters, and a dilettante trying to spin an interesting story: none of these people are trying to deceive, but they are also not trying to convey facts. To Frankfurt, they are bullshitting.

Like “lie”, “bullshit” is both a noun and a verb: an utterance produced can be a lie or an instance of bullshit, as can the act of producing these utterances. For an utterance to be classed as bullshit, it must not be accompanied by the explicit intentions that one has when lying, i.e., to cause a false belief in the hearer. Of course, it must also not be accompanied by the intentions characterised by an honest utterance. So far this story is entirely negative. Must any positive intentions be manifested in the utterer?

Throughout most of Frankfurt’s discussion, his characterisation of bullshit is negative. He notes that bullshit requires “no conviction” from the speaker about what the truth is ( 2005 : 55), that the bullshitter “pays no attention” to the truth ( 2005 : 61) and that they “may not deceive us, or even intend to do so, either about the facts or what he takes the facts to be” (2005: 54). Later, he describes the “defining feature” of bullshit as “ a lack of concern with truth, or an indifference to how things really are [our emphasis]” (2002: 340). These suggest a negative picture; that for an output to be classed as bullshit, it only needs to lack a certain relationship to the truth.

However, in places, a positive intention is presented. Frankfurt says what a bullshitter ….

“…does necessarily attempt to deceive us about is his enterprise. His only indispensably distinctive characteristic is that in a certain way he misrepresents what he is up to” (2005: 54).

This is somewhat surprising. It restricts what counts as bullshit to utterances accompanied by a higher-order deception. However, some of Frankfurt’s examples seem to lack this feature. When Fania Pascal describes her unwell state as “feeling like a dog that has just been run over” to her friend Wittgenstein, it stretches credulity to suggest that she was intending to deceive him about how much she knew about how run-over dogs felt. And given how the conditions for bullshit are typically described as negative, we might wonder whether the positive condition is really necessary.

Bullshit distinctions

Should utterances without an intention to deceive count as bullshit? One reason in favour of expanding the definition, or embracing a plurality of bullshit, is indicated by Frankfurt’s comments on the dangers of bullshit.

“In contrast [to merely unintelligible discourse], indifference to the truth is extremely dangerous. The conduct of civilized life, and the vitality of the institutions that are indispensable to it, depend very fundamentally on respect for the distinction between the true and the false. Insofar as the authority of this distinction is undermined by the prevalence of bullshit and by the mindlessly frivolous attitude that accepts the proliferation of bullshit as innocuous, an indispensable human treasure is squandered” (2002: 343).

These dangers seem to manifest regardless of whether there is an intention to deceive about the enterprise a speaker is engaged in. Compare the deceptive bullshitter, who does aim to mislead us about being in the truth-business, with someone who harbours no such aim, but just talks for the sake of talking (without care, or indeed any thought, about the truth-values of their utterances).

One of Frankfurt’s examples of bullshit seems better captured by the wider definition. He considers the advertising industry, which is “replete with instances of bullshit so unmitigated that they serve among the most indisputable and classic paradigms of the concept” ( 2005 :22). However, it seems to misconstrue many advertisers to portray their aims as to mislead about their agendas. They are expected to say misleading things. Frankfurt discusses Marlboro adverts with the message that smokers are as brave as cowboys ( 2002 : 341). Is it reasonable to suggest that the advertisers pretended to believe this?

Frankfurt does allow for multiple species of bullshit ( 2002 : 340). Footnote 3 Following this suggestion, we propose to envisage bullshit as a genus, and Frankfurt’s intentional bullshit as one species within this genus. Other species may include that produced by the advertiser, who anticipates that no one will believe their utterances Footnote 4 or someone who has no intention one way or another about whether they mislead their audience. To that end, consider the following distinction:

Bullshit (general)

Any utterance produced where a speaker has indifference towards the truth of the utterance.

Hard bullshit

Bullshit produced with the intention to mislead the audience about the utterer’s agenda.

Soft bullshit

Bullshit produced without the intention to mislead the hearer regarding the utterer’s agenda.

The general notion of bullshit is useful: on some occasions, we might be confident that an utterance was either soft bullshit or hard bullshit, but be unclear which, given our ignorance of the speaker’s higher-order desires. Footnote 5 In such a case, we can still call bullshit.

Frankfurt’s own explicit account, with the positive requirements about producer’s intentions, is hard bullshit, whereas soft bullshit seems to describe some of Frankfurt’s examples, such as that of Pascal’s conversation with Wittgenstein, or the work of advertising agencies. It might be helpful to situate these distinctions in the existing literature. On our view, hard bullshit is most closely aligned with Cassam ( 2019 ), and Frankfurt’s positive account, for the reason that all of these views hold that some intention must be present, rather than merely absent, for the utterance to be bullshit: a kind of “epistemic insouciance” or vicious attitude towards truth on Cassam’s view, and (as we have seen) an intent to mislead the hearer about the utterer’s agenda on Frankfurt’s view. In Sect. 3.2 we consider whether ChatGPT may be a hard bullshitter, but it is important to note that it seems to us that hard bullshit, like the two accounts cited here, requires one to take a stance on whether or not LLMs can be agents, and so comes with additional argumentative burdens.

Soft bullshit, by contrast, captures only Frankfurt’s negative requirement – that is, the indifference towards truth that we have classed as definitional of bullshit (general) – for the reasons given above. As we argue, ChatGPT is at minimum a soft bullshitter or a bullshit machine, because if it is not an agent then it can neither hold any attitudes towards truth nor towards deceiving hearers about its (or, perhaps more properly, its users’) agenda.

It’s important to note that even this more modest kind of bullshitting will have the deleterious effects that concern Frankfurt: as he says, “indifference to the truth is extremely dangerous…by the mindlessly frivolous attitude that accepts the proliferation of bullshit as innocuous, an indispensable human treasure is squandered” (2002, p343). By treating ChatGPT and similar LLMs as being in any way concerned with truth, or by speaking metaphorically as if they make mistakes or suffer “hallucinations” in pursuit of true claims, we risk exactly this acceptance of bullshit, and this squandering of meaning – so, irrespective of whether or not ChatGPT is a hard or a soft bullshitter, it does produce bullshit, and it does matter.

With this distinction in hand, we’re now in a position to consider a worry of the following sort: Is ChatGPT hard bullshitting, soft bullshitting, or neither? We will argue, first, that ChatGPT, and other LLMs, are clearly soft bullshitting. However, the question of whether these chatbots are hard bullshitting is a trickier one, and depends on a number of complex questions concerning whether ChatGPT can be ascribed intentions. We canvas a few ways in which ChatGPT can be understood to have the requisite intentions in Sect. 3.2.

ChatGPT is a soft bullshitter

We are not confident that chatbots can be correctly described as having any intentions at all, and we’ll go into this in more depth in the next Sect. (3.2). But we are quite certain that ChatGPT does not intend to convey truths, and so is a soft bullshitter. We can produce an easy argument by cases for this. Either ChatGPT has intentions or it doesn’t. If ChatGPT has no intentions at all, it trivially doesn’t intend to convey truths. So, it is indifferent to the truth value of its utterances and so is a soft bullshitter.

What if ChatGPT does have intentions? In Sect. 1, we argued that ChatGPT is not designed to produce true utterances; rather, it is designed to produce text which is indistinguishable from the text produced by humans. It is aimed at being convincing rather than accurate. The basic architecture of these models reveals this: they are designed to come up with a likely continuation of a string of text. It’s reasonable to assume that one way of being a likely continuation of a text is by being true; if humans are roughly more accurate than chance, true sentences will be more likely than false ones. This might make the chatbot more accurate than chance, but it does not give the chatbot any intention to convey truths. This is similar to standard cases of human bullshitters, who don’t care whether their utterances are true; good bullshit often contains some degree of truth, that’s part of what makes it convincing. A bullshitter can be more accurate than chance while still being indifferent to the truth of their utterances. We conclude that, even if the chatbot can be described as having intentions, it is indifferent to whether its utterances are true. It does not and cannot care about the truth of its output.

Presumably ChatGPT can’t care about conveying or hiding the truth, since it can’t care about anything. So, just as a matter of conceptual necessity, it meets one of Frankfurt’s criteria for bullshit. However, this only gets us so far – a rock can’t care about anything either, and it would be patently absurd to suggest that this means rocks are bullshitters Footnote 6 . Similarly books can contain bullshit, but they are not themselves bullshitters. Unlike rocks – or even books – ChatGPT itself produces text, and looks like it performs speech acts independently of its users and designers. And while there is considerable disagreement concerning whether ChatGPT has intentions, it’s widely agreed that the sentences it produces are (typically) meaningful (see e.g. Mandelkern and Linzen 2023 ).

ChatGPT functions not to convey truth or falsehood but rather to convince the reader of – to use Colbert’s apt coinage – the truthiness of its statement, and ChatGPT is designed in such a way as to make attempts at bullshit efficacious (in a way that pens, dictionaries, etc., are not). So, it seems that at minimum, ChatGPT is a soft bullshitter: if we take it not to have intentions, there isn’t any attempt to mislead about the attitude towards truth, but it is nonetheless engaged in the business of outputting utterances that look as if they’re truth-apt. We conclude that ChatGPT is a soft bullshitter.

ChatGPT as hard bullshit

But is ChatGPT a hard bullshitter ? A critic might object, it is simply inappropriate to think of programs like ChatGPT as hard bullshitters, because (i) they are not agents, or relatedly, (ii) they do not and cannot intend anything whatsoever.

We think this is too fast. First, whether or not ChatGPT has agency, its creators and users do. And what they produce with it, we will argue, is bullshit. Second, we will argue that, regardless of whether it has agency, it does have a function; this function gives it characteristic goals, and possibly even intentions, which align with our definition of hard bullshit.

Before moving on, we should say what we mean when we ask whether ChatGPT is an agent. For the purposes of this paper, the central question is whether ChatGPT has intentions and or beliefs. Does it intend to deceive? Can it, in any literal sense, be said to have goals or aims? If so, does it intend to deceive us about the content of its utterances, or merely have the goal to appear to be a competent speaker? Does it have beliefs—internal representational states which aim to track the truth? If so, do its utterances match those beliefs (in which case its false statements might be something like hallucinations) or are its utterances not matched to the beliefs—in which case they are likely to be either lies or bullshit? We will consider these questions in more depth in Sect. 3.2.2.

There are other philosophically important aspects of agenthood that we will not be considering. We won’t be considering whether ChatGPT makes decisions, has or lacks autonomy, or is conscious; we also won’t worry whether ChatGPT is morally responsible for its statements or its actions (if it has any of those).

ChatGPT is a bullshit machine

We will argue that even if ChatGPT is not, itself, a hard bullshitter, it is nonetheless a bullshit machine. The bullshitter is the person using it, since they (i) don’t care about the truth of what it says, (ii) want the reader to believe what the application outputs. On Frankfurt’s view, bullshit is bullshit even if uttered with no intent to bullshit: if something is bullshit to start with, then its repetition “is bullshit as he [or it] repeats it, insofar as it was originated by someone who was unconcerned with whether what he was saying is true or false” ( 2022 , p340).

This just pushes the question back to who the originator is, though: take the (increasingly frequent) example of the student essay created by ChatGPT. If the student cared about accuracy and truth, they would not use a program that infamously makes up sources whole-cloth. Equally, though, if they give it a prompt to produce an essay on philosophy of science and it produces a recipe for Bakewell tarts, then it won’t have the desired effect. So the idea of ChatGPT as a bullshit machine seems right, but also as if it’s missing something: someone can produce bullshit using their voice, a pen or a word processor, after all, but we don’t standardly think of these things as being bullshit machines, or of outputting bullshit in any particularly interesting way – conversely, there does seem to be something particular to ChatGPT, to do with the way that it operates, which makes it more than a mere tool, and which suggests that it might appropriately be thought of as an originator of bullshit. In short, it doesn’t seem quite right either to think of ChatGPT as analogous to a pen (can be used for bullshit, but can create nothing without deliberate and wholly agent-directed action) nor as to a bullshitting human (who can intend and produce bullshit on their own initiative).

The idea of ChatGPT as a bullshit machine is a helpful one when combined with the distinction between hard and soft bullshit. Reaching again for the example of the dodgy student paper: we’ve all, I take it, marked papers where it was obvious that a dictionary or thesaurus had been deployed with a crushing lack of subtlety; where fifty-dollar words are used not because they’re the best choice, nor even because they serve to obfuscate the truth, but simply because the author wants to convey an impression of understanding and sophistication. It would be inappropriate to call the dictionary a bullshit artist in this case; but it would not be inappropriate to call the result bullshit. So perhaps we should, strictly, say not that ChatGPT is bullshit but that it outputs bullshit in a way that goes beyond being simply a vector of bullshit: it does not and cannot care about the truth of its output, and the person using it does so not to convey truth or falsehood but rather to convince the hearer that the text was written by a interested and attentive agent.

ChatGPT may be a hard bullshitter

Is ChatGPT itself a hard bullshitter? If so, it must have intentions or goals: it must intend to deceive its listener, not about the content of its statements, but instead about its agenda. Recall that hard bullshitters, like the unprepared student or the incompetent politician, don’t care whether their statements are true or false, but do intend to deceive their audience about what they are doing. If so, it must have intentions or goals: it must intend to deceive its listener, not about the content of its statements, but instead about its agenda. We don’t think that ChatGPT is an agent or has intentions in precisely the same way that humans do (see Levenstein and Herrmann ( forthcoming ) for a discussion of the issues here). But when speaking loosely it is remarkably easy to use intentional language to describe it: what is ChatGPT trying to do? Does it care whether the text it produces is accurate? We will argue that there is a robust, although perhaps not literal, sense in which ChatGPT does intend to deceive us about its agenda: its goal is not to convince us of the content of its utterances, but instead to portray itself as a ‘normal’ interlocutor like ourselves. By contrast, there is no similarly strong sense in which ChatGPT confabulates, lies, or hallucinates.

Our case will be simple: ChatGPT’s primary function is to imitate human speech. If this function is intentional, it is precisely the sort of intention that is required for an agent to be a hard bullshitter: in performing the function, ChatGPT is attempting to deceive the audience about its agenda. Specifically, it’s trying to seem like something that has an agenda, when in many cases it does not. We’ll discuss here whether this function gives rise to, or is best thought of, as an intention. In the next Sect. (3.2.3), we will argue that ChatGPT has no similar function or intention which would justify calling it a confabulator, liar, or hallucinator.

How do we know that ChatGPT functions as a hard bullshitter? Programs like ChatGPT are designed to do a task, and this task is remarkably like what Frankfurt thinks the bullshitter intends, namely to deceive the reader about the nature of the enterprise – in this case, to deceive the reader into thinking that they’re reading something produced by a being with intentions and beliefs.

ChatGPT’s text production algorithm was developed and honed in a process quite similar to artificial selection. Functions and selection processes have the same sort of directedness that human intentions do; naturalistic philosophers of mind have long connected them to the intentionality of human and animal mental states. If ChatGPT is understood as having intentions or intention-like states in this way, its intention is to present itself in a certain way (as a conversational agent or interlocutor) rather than to represent and convey facts. In other words, it has the intentions we associate with hard bullshitting.

One way we can think of ChatGPT as having intentions is by adopting Dennett’s intentional stance towards it. Dennett ( 1987 : 17) describes the intentional stance as a way of predicting the behaviour of systems whose purpose we don’t already know.

“To adopt the intentional stance […] is to decide – tentatively, of course – to attempt to characterize, predict, and explain […] behavior by using intentional idioms, such as ‘believes’ and ‘wants,’ a practice that assumes or presupposes the rationality” of the target system (Dennett, 1983 : 345).

Dennett suggests that if we know why a system was designed, we can make predictions on the basis of its design (1987). While we do know that ChatGPT was designed to chat, its exact algorithm and the way it produces its responses has been developed by machine learning, so we do not know its precise details of how it works and what it does. Under this ignorance it is tempting to bring in intentional descriptions to help us understand and predict what ChatGPT is doing.

When we adopt the intentional stance, we will be making bad predictions if we attribute any desire to convey truth to ChatGPT. Similarly, attributing “hallucinations” to ChatGPT will lead us to predict as if it has perceived things that aren’t there, when what it is doing is much more akin to making something up because it sounds about right. The former intentional attribution will lead us to try to correct its beliefs, and fix its inputs --- a strategy which has had limited if any success. On the other hand, if we attribute to ChatGPT the intentions of a hard bullshitter, we will be better able to diagnose the situations in which it will make mistakes and convey falsehoods. If ChatGPT is trying to do anything, it is trying to portray itself as a person.

Since this reason for thinking ChatGPT is a hard bullshitter involves committing to one or more controversial views on mind and meaning, it is more tendentious than simply thinking of it as a bullshit machine; but regardless of whether or not the program has intentions, there clearly is an attempt to deceive the hearer or reader about the nature of the enterprise somewhere along the line, and in our view that justifies calling the output hard bullshit.

So, though it’s worth making the caveat, it doesn’t seem to us that it significantly affects how we should think of and talk about ChatGPT and bullshit: the person using it to turn out some paper or talk isn’t concerned either with conveying or covering up the truth (since both of those require attention to what the truth actually is ), and neither is the system itself. Minimally, it churns out soft bullshit, and, given certain controversial assumptions about the nature of intentional ascription, it produces hard bullshit; the specific texture of the bullshit is not, for our purposes, important: either way, ChatGPT is a bullshitter.

Bullshit? hallucinations? confabulations? The need for new terminology

We have argued that we should use the terminology of bullshit, rather than “hallucinations” to describe the utterances produced by ChatGPT. The suggestion that “hallucination” terminology is inappropriate has also been noted by Edwards ( 2023 ), who favours the term “confabulation” instead. Why is our proposal better than this or other alternatives?

We object to the term hallucination because it carries certain misleading implications. When someone hallucinates they have a non-standard perceptual experience, but do not actually perceive some feature of the world (Macpherson, 2013 ), where “perceive” is understood as a success term, such that they do not actually perceive the object or property. This term is inappropriate for LLMs for a variety of reasons. First, as Edwards ( 2023 ) points out, the term hallucination anthropomorphises the LLMs. Edwards also notes that attributing resulting problems to “hallucinations” of the models may allow creators to “blame the AI model for faulty outputs instead of taking responsibility for the outputs themselves”, and we may be wary of such abdications of responsibility. LLMs do not perceive, so they surely do not “mis-perceive”. Second, what occurs in the case of an LLM delivering false utterances is not an unusual or deviant form of the process it usually goes through (as some claim is the case in hallucinations, e.g., disjunctivists about perception). The very same process occurs when its outputs happen to be true.

So much for “hallucinations”. What about Edwards’ preferred term, “confabulation”? Edwards ( 2023 ) says:

In human psychology, a “confabulation” occurs when someone’s memory has a gap and the brain convincingly fills in the rest without intending to deceive others. ChatGPT does not work like the human brain, but the term “confabulation” arguably serves as a better metaphor because there’s a creative gap-filling principle at work […].

As Edwards notes, this is imperfect. Once again, the use of a human psychological term risks anthropomorphising the LLMs.

This term also suggests that there is something exceptional occurring when the LLM makes a false utterance, i.e., that in these occasions - and only these occasions - it “fills in” a gap in memory with something false. This too is misleading. Even when the ChatGPT does give us correct answers, its process is one of predicting the next token. In our view, it falsely indicates that ChatGPT is, in general, attempting to convey accurate information in its utterances. But there are strong reasons to think that it does not have beliefs that it is intending to share in general–see, for example, Levenstein and Herrmann ( forthcoming ). In our view, it falsely indicates that ChatGPT is, in general, attempting to convey accurate information in its utterances. Where it does track truth, it does so indirectly, and incidentally.

This is why we favour characterising ChatGPT as a bullshit machine. This terminology avoids the implications that perceiving or remembering is going on in the workings of the LLM. We can also describe it as bullshitting whenever it produces outputs. Like the human bullshitter, some of the outputs will likely be true, while others not. And as with the human bullshitter, we should be wary of relying upon any of these outputs.

Investors, policymakers, and members of the general public make decisions on how to treat these machines and how to react to them based not on a deep technical understanding of how they work, but on the often metaphorical way in which their abilities and function are communicated. Calling their mistakes ‘hallucinations’ isn’t harmless: it lends itself to the confusion that the machines are in some way misperceiving but are nonetheless trying to convey something that they believe or have perceived. This, as we’ve argued, is the wrong metaphor. The machines are not trying to communicate something they believe or perceive. Their inaccuracy is not due to misperception or hallucination. As we have pointed out, they are not trying to convey information at all. They are bullshitting.

Calling chatbot inaccuracies ‘hallucinations’ feeds in to overblown hype about their abilities among technology cheerleaders, and could lead to unnecessary consternation among the general public. It also suggests solutions to the inaccuracy problems which might not work, and could lead to misguided efforts at AI alignment amongst specialists. It can also lead to the wrong attitude towards the machine when it gets things right: the inaccuracies show that it is bullshitting, even when it’s right. Calling these inaccuracies ‘bullshit’ rather than ‘hallucinations’ isn’t just more accurate (as we’ve argued); it’s good science and technology communication in an area that sorely needs it.

A particularly surprising position is espoused by Fichte, who regards as lying not only lies of omission, but knowingly not correcting someone who is operating under a falsehood. For instance, if I was to wear a wig, and someone believed this to be my real hair, Fichte regards this as a lie, for which I am culpable. Bacin ( 2021 ) for further discussion of Fichte’s position.

Originally published in Raritan , VI(2) in 1986. References to that work here are from the 2005 book version.

In making this comment, Frankfurt concedes that what Cohen calls “bullshit” is also worthy of the name. In Cohen’s use ( 2002 ), bullshit is a type of unclarifiable text, which he associates with French Marxists. Several other authors have also explored this area in various ways in recent years, each adding valuable nuggets to the debate. Dennis Whitcomb and Kenny Easwaran expand the domains to which “bullshit” can be applied. Whitcomb argues there can be bullshit questions (as well as propositions), whereas Easwaran argues that we can fruitfully view some activities as bullshit ( 2023 ).

While we accept that these offer valuable streaks of bullshit insight, we will restrict our discussion to the Frankfurtian framework. For those who want to wade further into these distinctions, Neil Levy’s Philosophy, Bullshit, and Peer Review ( 2023 ) offers a taxonomical overview of the bullshit out there.

This need not undermine their goal. The advertiser may intend to impress associations (e.g., positive thoughts like “cowboys” or “brave” with their cigarette brand) upon their audience, or reinforce/instil brand recognition.

Frankfurt describes this kind of scenario as occurring in a “bull session”: “Each of the contributors to a bull session relies…upon a general recognition that what he expresses or says is not to be understood as being what he means wholeheartedly or believes unequivocally to be true” ( 2005 : 37). Yet Frankfurt claims that the contents of bull sessions are distinct from bullshit.

It’s worth noting that something like the distinction between hard and soft bullshitting we draw also occurs in Cohen ( 2002 ): he suggests that we might think of someone as a bullshitter as “a person who aims at bullshit, however frequently or infrequently he hits his target”, or if they are merely “disposed to bullshit: for whatever reason, to produce a lot of unclarifiable stuff” (p334). While we do not adopt Cohen’s account here, the parallels between his characterisation and our own are striking.

Of course, rocks also can’t express propositions – but then, part of the worry here is whether ChatGPT actually is expressing propositions, or is simply a means through which agents express propositions. A further worry is that we shouldn’t even see ChatGPT as expressing propositions - perhaps there are no communicative intentions, and so we should see the outputs as meaningless. Even accepting this, we can still meaningfully talk about them as expressing propositions. This proposal - fictionalism about chatbots - has recently been discussed by Mallory ( 2023 ).

Alkaissi, H., & McFarlane, S. I., (2023, February 19). Artificial hallucinations in ChatGPT: Implications in scientific writing. Cureus, 15 (2), e35179. https://doi.org/10.7759/cureus.35179 .

Bacin, S. (2021). My duties and the morality of others: Lying, truth and the good example in Fichte’s normative perfectionism. In S. Bacin, & O. Ware (Eds.), Fichte’s system of Ethics: A critical guide . Cambridge University Press.

Cassam, Q. (2019). Vices of the mind . Oxford University Press.

Cohen, G. A. (2002). Deeper into bullshit. In S. Buss, & L. Overton (Eds.), The contours of Agency: Essays on themes from Harry Frankfurt . MIT Press.

Davis, E., & Aaronson, S. (2023). Testing GPT-4 with Wolfram alpha and code interpreter plub-ins on math and science problems. Arxiv Preprint: arXiv, 2308 , 05713v2.

Dennett, D. C. (1983). Intentional systems in cognitive ethology: The panglossian paradigm defended. Behavioral and Brain Sciences , 6 , 343–390.

Article   Google Scholar  

Dennett, D. C. (1987). The intentional stance . The MIT.

Dennis Whitcomb (2023). Bullshit questions. Analysis , 83 (2), 299–304.

Easwaran, K. (2023). Bullshit activities. Analytic Philosophy , 00 , 1–23. https://doi.org/10.1111/phib.12328 .

Edwards, B. (2023). Why ChatGPT and bing chat are so good at making things up. Ars Tecnica . https://arstechnica.com/information-technology/2023/04/why-ai-chatbots-are-the-ultimate-bs-machines-and-how-people-hope-to-fix-them/ , accesssed 19th April, 2024.

Frankfurt, H. (2002). Reply to cohen. In S. Buss, & L. Overton (Eds.), The contours of agency: Essays on themes from Harry Frankfurt . MIT Press.

Frankfurt, H. (2005). On Bullshit , Princeton.

Knight, W. (2023). Some glimpse AGI in ChatGPT. others call it a mirage. Wired , August 18 2023, accessed via https://www.wired.com/story/chatgpt-agi-intelligence/ .

Levenstein, B. A., & Herrmann, D. A. (forthcoming). Still no lie detector for language models: Probing empirical and conceptual roadblocks. Philosophical Studies , 1–27.

Levy, N. (2023). Philosophy, Bullshit, and peer review . Camridge University.

Lightman, H., et al. (2023). Let’s verify step by step. Arxiv Preprint: arXiv , 2305 , 20050.

Lysandrou (2023). Comparative analysis of drug-GPT and ChatGPT LLMs for healthcare insights: Evaluating accuracy and relevance in patient and HCP contexts. ArXiv Preprint: arXiv , 2307 , 16850v1.

Macpherson, F. (2013). The philosophy and psychology of hallucination: an introduction, in Hallucination , Macpherson and Platchias (Eds.), London: MIT Press.

Mahon, J. E. (2015). The definition of lying and deception. The Stanford Encyclopedia of Philosophy (Winter 2016 Edition), Edward N. Zalta (Ed.), https://plato.stanford.edu/archives/win2016/entries/lying-definition/ .

Mallory, F. (2023). Fictionalism about chatbots. Ergo , 10 (38), 1082–1100.

Google Scholar  

Mandelkern, M., & Linzen, T. (2023). Do language models’ Words Refer?. ArXiv Preprint: arXiv , 2308 , 05576.

OpenAI (2023). GPT-4 technical report. ArXiv Preprint: arXiv , 2303 , 08774v3.

Proops, I., & Sorensen, R. (2023). Destigmatizing the exegetical attribution of lies: the case of kant. Pacific Philosophical Quarterly . https://doi.org/10.1111/papq.12442 .

Sarkar, A. (2023). ChatGPT 5 is on track to attain artificial general intelligence. The Statesman , April 12, 2023. Accesses via https://www.thestatesman.com/supplements/science_supplements/chatgpt-5-is-on-track-to-attain-artificial-general-intelligence-1503171366.html .

Shah, C., & Bender, E. M. (2022). Situating search. CHIIR ‘22: Proceedings of the 2022 Conference on Human Information Interaction and Retrieval March 2022 Pages 221–232 https://doi.org/10.1145/3498366.3505816 .

Weise, K., & Metz, C. (2023). When AI chatbots hallucinate. New York Times, May 9, 2023. Accessed via https://www.nytimes.com/2023/05/01/business/ai-chatbots-hallucination.html .

Weiser, B. (2023). Here’s what happens when your lawyer uses ChatGPT. New York Times , May 23, 2023. Accessed via https://www.nytimes.com/2023/05/27/nyregion/avianca-airline-lawsuit-chatgpt.html .

Zhang (2023). How language model hallucinations can snowball. ArXiv preprint: arXiv: , 2305 , 13534v1.

Zhu, T., et al. (2023). Large language models for information retrieval: A survey. Arxiv Preprint: arXiv , 2308 , 17107v2.

Download references

Acknowledgements

Thanks to Neil McDonnell, Bryan Pickel, Fenner Tanswell, and the University of Glasgow’s Large Language Model reading group for helpful discussion and comments.

Author information

Authors and affiliations.

University of Glasgow, Glasgow, Scotland

Michael Townsen Hicks, James Humphries & Joe Slater

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Michael Townsen Hicks .

Additional information

Publisher’s note.

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

Rights and permissions

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

Reprints and permissions

About this article

Hicks, M.T., Humphries, J. & Slater, J. ChatGPT is bullshit. Ethics Inf Technol 26 , 38 (2024). https://doi.org/10.1007/s10676-024-09775-5

Download citation

Published : 08 June 2024

DOI : https://doi.org/10.1007/s10676-024-09775-5

Share this article

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

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

Provided by the Springer Nature SharedIt content-sharing initiative

• Artificial intelligence
• Large language models
• Find a journal
• Publish with us
• Track your research

• Artificial intelligence platforms

Getty Images

GPT-4o vs. GPT-4: How do they compare?

Gpt-4o, openai's latest model, promises improved multimodal capabilities and increased efficiency. explore the differences between gpt-4o and its predecessor, gpt-4..

• Lev Craig, Site Editor

OpenAI's latest release, GPT-4o, builds on the foundation set by the company's previous models with significant updates, including enhanced multimodal capabilities and faster performance.

Since OpenAI first launched ChatGPT in late 2022, the chatbot interface and its underlying models have already undergone several major changes. GPT-4o was released in May 2024 and is the successor to GPT-4 , which launched in March 2023.

GPT-4 and GPT-4o (that's the letter "o," for omni ) are advanced generative AI models that OpenAI developed for use within the ChatGPT interface. Both models are trained to generate natural-sounding text in response to users' prompts, and they can engage in interactive, back-and-forth conversations, retaining memory and context to inform future responses.

TechTarget Editorial compared these products by testing the models within ChatGPT; reading informational materials and technical documentation from OpenAI; and analyzing user reviews on Reddit, tech blogs and the OpenAI developer forum.

Differences between GPT-4o and GPT-4

In many ways, GPT-4o and GPT-4 are similar. Both are advanced OpenAI models with vision and audio capabilities and the ability to recall information and analyze uploaded documents. Each has a 128,000-token context window and a knowledge cutoff date in late 2023 (October for GPT-4o, December for GPT-4).

But GPT-4o and GPT-4 also differ significantly in several areas: multimodal capabilities; performance and efficiency; pricing; and language support.

Multimodality

Multimodal AI models are capable of processing multiple data types, such as text, images and audio. In a sense, both GPT-4 and GPT-4o are multimodal: In the ChatGPT interface, users can create and upload images and use voice chat regardless of whether they're using GPT-4 or GPT-4o. However, the way that the two models approach multimodality is very different -- it's one of the biggest differentiators between GPT-4o and GPT-4.

GPT-4 is a large language model ( LLM ) primarily designed for text processing, meaning that it lacks built-in support for handling images, audio and video. Within the ChatGPT web interface, GPT-4 must call on other OpenAI models, such as the image generator Dall-E or the speech recognition model Whisper, to process non-text input.

GPT-4o, in contrast, was designed for multimodality from the ground up, hence the "omni" in its name. "We trained a single new model end-to-end across text, vision, and audio, meaning that all inputs and outputs are processed by the same neural network," OpenAI representatives wrote in a blog post announcing the launch.

This native multimodality makes GPT-4o faster than GPT-4 on tasks involving multiple types of data, such as image analysis. In OpenAI's demo of GPT-4o on May 13, 2024, for example, company leaders ​used GPT-4o to analyze live video of a user solving a math problem and provide real-time voice feedback.

Controversy over GPT-4o's voice capabilities

The demo during OpenAI's livestreamed GPT-4o launch featured a voice called Sky, which listeners and Scarlett Johansson both noted sounded strikingly similar to Johansson's AI assistant character in the film Her . OpenAI CEO Sam Altman himself tweeted the single word "her" during the demo.

Subsequently, Johansson said she had retained legal counsel and revealed that Altman had previously asked to use her voice in ChatGPT, a request she declined. In response, OpenAI paused the use of the Sky voice, although Altman said in a statement that Sky was never intended to resemble Johansson.

The incident highlights growing concerns over the ethical use of voice likenesses and artists' rights in the generative AI era . Rep. Nancy Mace, chairwoman of the House Subcommittee on Cybersecurity, Information Technology and Government Innovation, recently invited Johansson to testify before the committee about the Sky voice and the broader issue of deepfakes.

Performance and efficiency

GPT-4o is also designed to be quicker and more computationally efficient than GPT-4 across the board, not just for multimodal queries. According to OpenAI, GPT-4o is twice as fast as the most recent version of GPT-4.

When TechTarget Editorial timed the two models in testing, GPT-4o's responses were indeed generally quicker than GPT-4's -- although not quite double the speed -- and similar in quality. The following table compares GPT-4o and GPT-4's response times to five sample prompts using the ChatGPT web app.

OpenAI's testing indicates that GPT-4o outperforms GPT-4 on major benchmarks, including simple math, language comprehension and vision understanding. OpenAI has also said that GPT-4o has stronger contextual understanding than GPT-4, enabling it to better grasp idioms, metaphors and cultural references.

What actual users say varies. As of publication time, GPT-4o is the top-rated model on the crowdsourced LLM evaluation platform LMSYS Chatbot Arena, both overall and in specific categories such as coding and responding to difficult queries. But other users call GPT-4o "overhyped," reporting that it performs worse than GPT-4 on tasks such as coding , classification and reasoning.

Unfortunately, each type of evidence -- self-reported benchmarks from model developers, crowdsourced human evaluations and unverified anecdotes -- has its own limitations. For developers building LLM apps and users integrating generative AI into their workflows, deciding which model is the best fit might ultimately require experimenting with both over time and in various contexts. Some developers, for example, say that they switch back and forth between GPT-4 and GPT-4o depending on the task at hand.

One advantage of GPT-4o's improved computational efficiency is its lower pricing. For developers using OpenAI's API, GPT-4o is by far the more cost-effective option. It's available at a rate of $5 per million input tokens and $15 per million output tokens, while GPT-4 costs $30 per million input tokens and $60 per million output tokens. Even GPT-4-Turbo, designed to be faster and cheaper than GPT-4, is more expensive than GPT-4o at $10 per million input tokens and $30 per million output tokens.

For web app users, the difference is even more significant. Moving forward, GPT-4o will power the free version of ChatGPT, replacing GPT-3.5 . This gives free users access to multimodality, higher-quality text responses, voice chat and custom GPTs -- a no-code option for building personalized chatbots -- which were previously only available to paying customers. GPT-4 will remain available only to those on a paid plan, including ChatGPT Plus, Team and Enterprise, which start at $20 per month.

However, this rollout is still in progress, and some users might not yet have access to GPT-4o. As of a test on June 10, 2024, GPT-3.5 was still the default for free users without a ChatGPT account.

Moreover, free and paid users will have different levels of access to each model. Free users will face message limits for GPT-4o, and after hitting those caps, they'll be switched to GPT-3.5. ChatGPT Plus users will have higher message limits than free users, and those on a Team and Enterprise plan will have even fewer restrictions.

Language support

GPT-4o also offers significantly better support for non-English languages compared with GPT-4. In particular, OpenAI has improved tokenization for languages that don't use a Western alphabet, such as Hindi, Chinese and Korean. The new tokenizer more efficiently compresses non-English text, with the aim of handling prompts in those languages in a cheaper, quicker way.

This change addresses a longstanding issue in natural language processing , in which models have historically been optimized for Western languages at the expense of languages spoken in other regions. Handling more languages with greater accuracy and fluency makes GPT-4o more effective for global applications and opens up access to groups that may not have been able to engage with models as fully before.

But the improved language support isn't without challenges. Just days after OpenAI released GPT-4o, researchers noticed that many Chinese tokens included inappropriate phrases related to pornography and gambling. Model developers might have included these problematic tokens due to inadequate data cleaning, potentially degrading the model's comprehension and risking security breaches and hallucinations.

Is GPT-4o better than GPT-4?

In most cases, GPT-4o is indeed better than GPT-4. OpenAI now describes GPT-4o as its flagship model, and its improved speed, lower costs and multimodal capabilities will be appealing to many users.

That said, some users may still prefer GPT-4, especially in business contexts. Because GPT-4 has been available for over a year now, it's well tested and already familiar to many developers and businesses. That kind of stability can be crucial for critical and widely used applications, where reliability might be a higher priority than having the lowest costs or the latest features​.

In addition, although GPT-4o will generally be more cost-effective for new deployments, IT teams looking to manage existing setups might find it more economical to continue using GPT-4. Transitioning to a new model comes with its own costs, particularly for systems tightly integrated with GPT-4 where switching models could involve significant infrastructure or workflow changes.

In addition, GPT-4o's multimodal capabilities might differ for API versus web users, at least for now. In a May 2024 post in the OpenAI Developer Forum, an OpenAI product manager explained that GPT-4o does not yet support image generation or audio through the API. Consequently, enterprises primarily using OpenAI's APIs might not find GPT-4o compelling enough to make the switch until its multimodal capabilities become generally available through the API.

What does the introduction of GPT-4o mean for ChatGPT users?

The introduction of GPT-4o as the new default version of ChatGPT will lead to some major changes for users. One of the most significant updates is the availability of multimodal capabilities, as mentioned previously. Moving forward, all users will be able to interact with ChatGPT using text, images, audio and video and to create custom GPTs -- functionalities that were previously limited or unavailable.

These advancements might make the Plus subscription less appealing to some users, as many formerly premium features are now accessible in the free tier. That said, paid plans still offer benefits such as higher usage caps and faster response times, which could be a deciding factor for heavy users or businesses that need reliability in consistent, high-volume interactions.

Even amid the GPT-4o excitement, many in the AI community are already looking ahead to GPT-5, expected later this summer. Enterprise customers received demos of the new model this spring, sources told Business Insider , and OpenAI has teased forthcoming capabilities such as autonomous AI agents .

Lev Craig covers AI and machine learning as the site editor for TechTarget Editorial's Enterprise AI site. Craig graduated from Harvard University with a bachelor's degree in English and has previously written about enterprise IT, software development and cybersecurity.

Related Resources

• Why Open Source Artificial Intelligence Platforms Help Enterprise Business ... –Red Hat

Dig Deeper on Artificial intelligence platforms

Gemini vs. ChatGPT: What's the difference?

What is Google Gemini (formerly Bard)

Gemini 1.5 Pro explained: Everything you need to know

The longtime BI and data integration vendor's tools enable C40 Cities, a climate leadership consortium of nearly 100 cities, to ...

With trusted data as a foundation, the longtime analytics and data integration vendor has been pragmatic in its creation of an ...

The longtime analytics vendor's latest new features include data integration capabilities targeting data quality and a GenAI ...

The Biden administration's regulatory efforts have defined the U.S. approach to climate over the last four years. That could ...

While there is disagreement in Congress over how to diversify the critical materials supply chain, there is bipartisan agreement ...

As U.S. states like Colorado pass their own AI laws, businesses will need to prepare compliance measures if they do business in ...

The vendor's latest update adds new customer insight capabilities, including an AI assistant, and industry-specific tools all ...

The data quality specialist's capabilities will enable customers to monitor unstructured text to ensure the health of data used ...

Graph databases offer plenty of advantages for enterprises, but relational databases still top the market. Both emphasize ...

Epicor continues its buying spree with PIM vendor Kyklo, enabling manufacturers and distributors to gain visibility into what ...

Supply chains have a range of connection points -- and vulnerabilities. Learn which vulnerabilities hackers look for first and ...

As supplier relationships become increasingly complex and major disruptions continue, it pays to understand the top supply chain ...

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 18 June 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, still have questions.