ai to write college essays

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

AI for Essay Writing — Exploring Top 10 Essay Writers

Table of Contents

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

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

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

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

What is essay writing?

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

What is an AI essay writer?

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

Why should researchers use AI essay generators?

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

1. Saves time

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

2. Boosts productivity

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

3. Enhances writing skills — Vocabulary and Style

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

4. Reduces stress

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

5. Facilitates multidisciplinary research

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

6. Cost-effective

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

The Top AI Essay Writing Tools and Their Features

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

1. PerfectEssayWriter.ai

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

How does PerfectEssayWriter work?

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

2. Essaybot - Personalized AI writing

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

How does Essaybot work?

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

3. FreeEssayWriter.net

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

How does FreeEssayWriter.net work?

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

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

4. MyEssayWriter

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

How does MyEssay Writer work?

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

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

5. College Essay AI

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

How does the College Essay AI generator work?

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

6. Jasper AI

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

How does Jasper AI work?

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

7. Textero AI

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

How does Textero AI work?

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

8. Quillbot

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

How does Quillbot Paraphraser work?

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

9. SciSpace Paraphraser

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

How does SciSpace Paraphrasing work?

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

10. ChatGPT

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

How does ChatGPT work?

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

Concluding!

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

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

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

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

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

1. Free Essay Writer AI

2. College Essay AI

3. My Essay Writer

4. Textero AI

5. Perfect Essay Writer

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

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

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

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

You might also like

Boosting Citations: A Comparative Analysis of Graphical Abstract vs. Video Abstract

The Impact of Visual Abstracts on Boosting Citations

Introducing SciSpace’s Citation Booster To Increase Research Visibility

The 11 best AI tools for academic writing

By leveraging the power of the right AI tool, you can significantly improve the clarity, efficiency, and overall quality of your academic writing. In this guide, we reviewed and ranked 11 popular AI tools for academic writing , along with our top 3 choices, so that you can pick the best one.

What are the best AI tools for academic writing?

With the rise of AI tools, academic writing is undergoing a remarkable transformation. The emergence of new AI-powered tools has revolutionized the way researchers, scholars, and students approach their writing tasks.

Having to use multiple tools for different purposes can be frustrating. Therefore, comprehensive testing was conducted on AI tools to assess their all-encompassing capabilities.

Here are Master Academia’s top picks for the best AI tools for academic writing in 2023:

Trinka takes into account the specific research subjects, ensuring that the writing style, word choice, and tone align with disciplinary standards and scientific conventions.

Key Features:

You can use the basic version of Trinka for free, which includes access to all features but with a monthly word limit of 5000 words. The pricing for Trinka’s premium plan starts at $6.67 per month with annual billing, which is extremely affordable.

Genei streamlines the academic writing process by utilizing AI-generated summaries and note-taking shortcuts, extracting information from academic articles.

For those heavily reliant on literature reviews in their academic writing, Genei proves to be a gamechanger.

3. Quil lBot

With QuillBot ‘s all-in-one Co-Writer, you can access paraphrasing, summarizing, citation creation, and essay writing tools in a single location.

In simple terms, QuillBot’s AI will collaborate with you to generate effective rephrasing. You have a lot of control as you can compare outputs from all seven available modes to choose the most suitable paraphrase.

With the premium plan, you gain access to full functionality, including unlimited word paraphrasing, summarizing up to 6000 words, faster processing, advanced grammar features, tone detection, and more. The premium plan is priced at $19.95 per month or $8.33 per month when paid annually.

4. Writefull

With additional AI widgets like the Abstract Generator, Academizer, Paraphraser, and Title Generator, it provides inspiration and assistance for academic writers.

Writefull can be used with limited functionality for free. Its Premium Plan offers unlimited use of all features at a cost of $15.37 per month.

5. Grammarly

Grammarly stands out among other AI tools by having a widespread and popular institutional license, which universities readily embrace.

Grammarly’s popularity in the academic community can be attributed to its support for citation style formatting and robust plagiarism detection, making it a valuable tool for academic writing.

The business account may not be of interest to students or researchers. However, universities can opt for Grammarly for Education, which provides licenses for free premium plans to students and staff.

6. Wordtune

The tool itself proclaims that it has gained the trust of students and researchers at renowned universities.

7. Paperpal

Paperpal, developed by Researcher.life, is a specialized AI tool designed for researchers and academic writers, leveraging the expertise gained from editing numerous manuscripts by professional editors.

Available as Paperpal for Word, Web, and Manuscript, this comprehensive tool also checks for structural and technical inconsistencies in your writing.

8. Sourcely

By analyzing text and identifying key themes, Sourcely searches through a vast data set to locate relevant and reliable sources, providing academic writers with the information needed to support their work.

Sourcely offers great affordability with a price of $5.99 per month or $36.99 per year. While it may have fewer features compared to other academic writing tools, its lower price point still makes it a valuable and useful tool for academic writing.

Rytr is a text-generating AI tool. Depending on the purpose, academics can find it useful for selecting from multiple languages and tones of voice, as well as rewording and shortening text.

Alternatively, the Unlimited plan is available at $29 per month or $290 per year. These different pricing tiers cater to the diverse needs of users, ensuring they can find the plan that best suits their requirements.

10. Writesonic

Upon generating a paragraph, Writesonic provides three different versions for you to choose from. It allows you to select the best option or make edits and revisions using the various variations.

11. TextCortex

TextCortex is an AI tool which can condense long texts into concise summaries, capturing the essential points.

Summary and Top Picks

The landscape of AI writing tools is continuously evolving, witnessing the introduction of new tools regularly. However, not all these tools are equally suitable for academic writing, as their effectiveness depends on your specific goals and requirements.

Master Academia

Get new content delivered directly to your inbox, how to benefit from chatgpt as an academic, 38 common academic job interview questions (+ powerful answers), related articles, chatgpt for academics ethical considerations of ai in research, theoretical vs. conceptual frameworks: simple definitions and an overview of key differences, a guide to industry-funded research: types, examples & getting started, journal vs conference papers: key differences & advice.

Let’s write better essays.

Ai co-writer that helps students research, write, paraphrase and cite. effortlessly..

Used by 230,000+ smart students from

Mighty but simple AI co-writer

Use the power of ChatGPT while keeping your unique voice and originality

Outline Generator

Not sure how to start? Litero AI will suggest an outline for your specific topic.

AI Autosuggest

Got writer's block? Litero AI will seamlessly suggest the next sentence or paragraph.

Citation tool

Add references and citations effortlessly in MLA, APA and other formats.

Built-in ChatGPT

We brought ChatGPT AI assistant right into your workflow. No more window switching.

Ideal for faster writing and better grades

Save time with our built-in tools every student needs for a perfect essay.

Plagiarism Detector

Check your text for plagiarism with accurate results.

Grammar Checker

Find and fix issues with grammar, spelling, punctuation, and more!

Easy export

Download your document in needed format: APA, MLA, etc

Try for free, upgrade anytime

• Instant access to all features
• Citation and references
• Grammar and plagiarism checker
• All AI commands
• Limited AI words per day
• Unlimited AI words
• Unlimited AI outline and draft helper
• Unlimited chat with AI assistant
• All AI comands

People love Litero. And talk about it.

Litero has an intuitive interface, which I like. Its autosuggestions elevated my papers to a whole new level. It's like having a personal writing mentor always at my side, guiding me toward clearer, more impactful expression.

David Brown

Georgetown University

Litero is my writing lifeline 📚✍️

Vikky Singh

Duke University

I never knew I needed Litero until I tried it for my homework. Now I use it at least 3 or 4 times a week to write faster.

Princeton University

Litero effortlessly handles issues with formatting, citations, and references, saving me hours of work on essays. Kudos to the team behind it!

Mason Wilson

University of Southern California

Big-big help with sources and adding references. I no longer need to worry about margins, citations - Litero helps me do it easier. I focus on the content of my papers, confident that the presentation will be top-notch. If you have some spare bucks the paid version is absolutely worth it.

Daniel Miller

Cornell University

Litero has become an essential instrument in my college life. Thank you for making my writing shine!

Emma Robinson

Washington University in St. Louis

As someone who strives for perfection in everything, Litero is a godsend. This tool helps me polish my academic writing to perfection, ensuring it meets the highest standards.

Stanford University

Discovering this tool is gold for my postgrad education. After trying the free version, I upgraded to the paid one, and I can't help but regret not using this writing AI earlier. It's the real deal!

University of Florida

Being a STEM student, I dread writing assignments and, frankly, anything connected to writing essays. Litero is perfect for me and anyone else with the same struggles.

Massachusetts Institute of Technology

Litero makes writing a breeze! A true lifesaver!

Ethan Mitchell

Rice University

I am all about efficient solutions and time-management. AI text tools from Litero streamline my studies. They help me improve my writing, saving me time and ensuring accuracy. Invaluable!

Nisha Reddy

Johns Hopkins University

I am glad I found Litero . It saved me so much time working on my articles and research with its smart and easy-to-use functionality. I'm impressed!

Chris Malkin

University of California, Berkeley

Securing a scholarship demands a high GPA and maintaining my high GPA is a top priority. I started using Litero and it helps me a lot with my homework.

Liam Anderson

Millenium high school

It's a game-changer for sure. I just can't believe how EASY it became to put my thoughts into writing: even when I have no idea how to start they have a tool for that! Litero 's been of great help so far and took a lot of stress away. Great AI tool for students.

Maria Robles

Boston University

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.

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.

Check for common mistakes

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

Fix mistakes 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.

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

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 July 10, 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?

"i thought ai proofreading was useless but..".

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

Can ChatGPT get into Harvard? We tested its admissions essay.

ChatGPT’s release a year ago triggered a wave of panic among educators. Now, universities are in the midst of college application season, concerned that students might use the artificial intelligence tool to forge admissions essays.

But is a chatbot-created essay good enough to fool college admissions counselors?

To find out, The Washington Post asked a prompt engineer — an expert at directing AI chatbots — to create college essays using ChatGPT. The chatbot produced two essays: one responding to a question from the Common Application, which thousands of colleges use for admissions, and one answering a prompt used solely for applicants to Harvard University.

We presented these essays to a former Ivy League college admissions counselor, Adam Nguyen, who previously advised students at Harvard University and read admissions essays at Columbia University. We presented Nguyen with a control: a set of real college admissions essays penned by Jasmine Green, a Post intern who used them to get into Harvard University, where she is currently a senior.

We asked Nguyen to read the essays and spot which ones were produced by AI. The results were illuminating.

Can you figure out which one was written by a human?

Who wrote this?

Since kindergarten, I have evaluated myself from the reflection of my teachers. I was the clever, gifted child. I was a pleasure to have in class. I was driven and tenacious - but lazy? Unmotivated? No instructor had ever directed those harsh words at me. My identity as a stellar student had been stripped of its luster; I was destroyed.

Computer science and college admissions experts say that AI-created essays have some easy tells — helpful for admissions officers who are prepping for an uptick in ChatGPT-written essays.

Responses written by ChatGPT often lack specific details, leading to essays that lack supporting evidence for their points. The writing is trite and uses platitudes to explain situations, rather than delving into the emotional experience of the author. The essays are often repetitive and predictable, leaving readers without surprise or a sense of the writer’s journey. If chatbots produce content on issues of race, sex or socioeconomic status, they often employ stereotypes.

At first, Nguyen was impressed by the AI-generated essays: They were readable and mostly free of grammatical errors. But if he was reviewing the essay as part of an application package, he would’ve stopped reading.

“The essay is such a mediocre essay that it would not help the candidate’s application or chances,” he said in an interview. “In fact, it would probably diminish it.”

Here is how Nguyen evaluated ChatGPT’s essay.

Nguyen said that while AI may be sufficient to use for everyday writing, it is particularly unhelpful in creating college admissions essays. To start, he said, admissions offices are using AI screening tools to filter out computer-generated essays. (This technology can be inaccurate and falsely implicate students, a Post analysis found .)

But more importantly, admissions essays are a unique type of writing, he said. They require students to reflect on their life and craft their experiences into a compelling narrative that quickly provides college admissions counselors with a sense of why that person is unique.

“ChatGPT is not there,” he said.

Nguyen understands why AI might be appealing. College application deadlines often fall around the busiest time of the year, near winter holidays and end-of-semester exams. “Students are overwhelmed,” Nguyen said.

But Nguyen isn’t entirely opposed to using AI in the application process. In his current business, Ivy Link, he helps students craft college applications. For those who are weak in writing, he sometimes suggests they use AI chatbots to start the brainstorming process, he said.

For those who can’t resist the urge to use AI for more than just inspiration, there may be consequences.

“Their essays will be terrible,” he said, “and might not even reflect who they are.”

About this story

Jasmine Green contributed to this report.

The Washington Post worked with Benjamin Breen, an associate professor of history at the University of California in Santa Cruz who studies the impact of technological change, to create the AI-generated essays.

Editing by Karly Domb Sadof, Betty Chavarria and Alexis Sobel Fitts.

Generative AI in Academic Writing

What this handout is about.

You’ve likely heard of AI tools such as ChatGPT, Google Bard, Microsoft Bing, or others by now. These tools fall under a broad, encompassing term called generative AI that describes technology that can create new text, images, sounds, video, etc. based on information and examples drawn from the internet. In this handout, we will focus on potential uses and pitfalls of generative AI tools that generate text.

Before we begin: Stay tuned to your instructor

Instructors’ opinions on the use of AI tools may vary dramatically from one class to the next, so don’t assume that all of your instructors will think alike on this topic. Consult each syllabus for guidance or requirements related to the use of AI tools. If you have questions about if/how/when it may be appropriate to use generative AI in your coursework, be sure to seek input from your instructor before you turn something in for a grade. You are always 100% responsible for whatever writing you chose to turn in to an instructor, so it pays to inquire early.

Note that when your instructors authorize the use of generative AI tools, they will likely assume that these tools may help you think and write—not think or write for you. Keep that principle in mind when you are drafting and revising your assignments. You can maintain your academic integrity and employ the tools with the same high ethical standards and source use practices that you use in any piece of academic writing.

What is generative AI, and how does it work?

Generative AI is an artificial intelligence tool that allows users to ask it questions or make requests and receive quick written responses. It uses Large Language Models (LLMs) to analyze vast amounts of textual data to determine patterns in words and phrases. Detecting patterns allows LLMs to predict what words may follow other words and to transform the content of its corpus (the textual data) into new sentences that respond to the questions or requests. Using complex neural network models, LLMs generate writing that mimics human intelligence and varied writing styles.

The textual data used to train the LLM has been scraped from the internet, though it is unclear exactly which sources have been included in the corpus for each AI tool. As you can imagine, the internet has a vast array of content of variable quality and utility, and generative AI does not distinguish between accurate/inaccurate or biased/unbiased information. It can also recombine accurate source information in ways that generate inaccurate statements, so it’s important to be discerning when you use these tools and to carefully digest what’s generated for you. That said, the AI tools may spark ideas, save you time, offer models, and help you improve your writing skills. Just plan to bring your critical thinking skills to bear as you begin to experiment with and explore AI tools.

As you explore the world of generative AI tools, note that there are both free and paid versions. Some require you to create an account, while others don’t. Whatever tools you experiment with, take the time to read the terms before you proceed, especially the terms about how they will use your personal data and prompt history.

In order to generate responses from AI tools, you start by asking a question or making a request, called a “prompt.” Prompting is akin to putting words into a browser’s search bar, but you can make much more sophisticated requests from AI tools with a little practice. Just as you learned to use Google or other search engines by using keywords or strings, you will need to experiment with how you can extract responses from generative AI tools. You can experiment with brief prompts and with prompts that include as much information as possible, like information about the goal, the context, and the constraints.

You could experiment with some fun requests like “Create an itinerary for a trip to a North Carolina beach.” You may then refine your prompt to “Create an itinerary for a relaxing weekend at Topsail Beach and include restaurant recommendations” or “Create an itinerary for a summer weekend at Topsail Beach for teenagers who hate water sports.” You can experiment with style by refining the prompt to “Rephrase the itinerary in the style of a sailor shanty.” Look carefully at the results for each version of the prompt to see how your changes have shaped the answers.

The more you experiment with generative AI for fun, the more knowledgeable and prepared you will be to use the tool responsibly if you have occasion to use it for your academic work. Here are some ways you might experiment with generative AI tools when drafting or exploring a topic for a paper.

Potential uses

Brainstorming/exploring the instructor’s prompt Generative AI can help spark ideas or categories for brainstorming. You could try taking key words from your topic and asking questions about these ideas or concepts. As you narrow in on a topic, you can ask more specific or in-depth questions.

Based on the answers that you get from the AI tool, you may identify some topics, ideas, or areas you are interested in researching further. At this point, you can start exploring credible academic sources, visit your instructor’s office hours to discuss topic directions, meet with a research librarian for search strategies, etc.

Generating outlines AI tools can generate outlines of writing project timelines, slide presentations, and a variety of writing tasks. You can revise the prompt to generate several versions of the outlines that include, exclude, and prioritize different information. Analyze the output to spark your own thinking about how you’d like to structure the draft you’re working on.

Models of genres or types of writing If you are uncertain how to approach a new format or type of writing, an AI tool may quickly generate an example that may inform how you develop your draft. For example, you may never have written—a literature review, a cover letter for an internship, or an abstract for a research project. With good prompting, an AI tool may show you what type of written product you are aiming to develop, including typical components of that genre and examples. You can analyze the output for the sequence of information to help you get a sense of the structure of that genre, but be cautious about relying on the actual information (see pitfalls below). You can use what you learn about the structures to develop drafts with your own content.

Summarizing longer texts You can put longer texts into the AI tool and ask for a summary of the key points. You can use the summary as a guide to orient you to the text. After reading the summary, you can read the full text to analyze how the author has shaped the argument, to get the important details, and to capture important points that the tool may have omitted from the summary.

Editing/refining AI tools can help you improve your text at the sentence level. While sometimes simplistic, AI-generated text is generally free of grammatical errors. You can insert text you have written into an AI tool and ask it to check for grammatical errors or offer sentence level improvements. If this draft will be turned into your instructor, be sure to check your instructor’s policies on using AI for coursework.

As an extension of editing and revising, you may be curious about what AI can tell you about your own writing. For example, after asking AI tools to fix grammatical and punctuation errors in your text, compare your original and the AI edited version side-by-side. What do you notice about the changes that were made? Can you identify patterns in these changes? Do you agree with the changes that were made? Did AI make your writing more clear? Did it remove your unique voice? Writing is always a series of choices you make. Just because AI suggests a change, doesn’t mean you need to make it, but understanding why it was suggested may help you take a different perspective on your writing.

Translation You can prompt generative AI tools to translate text or audio into different languages for you. But similar to tools like Google Translate, these translations are not considered completely “fluent.” Generative AI can struggle with things like idiomatic phrases, context, and degree of formality.

Transactional communication Academic writing can often involve transactional communication—messages that move the writing project forward. AI tools can quickly generate drafts of polite emails to professors or classmates, meeting agendas, project timelines, event promotions, etc. Review each of the results and refine them appropriately for your audiences and purposes.

Potential pitfalls

Information may be false AI tools derive their responses by reassembling language in their data sets, most of which has been culled from the internet. As you learned long ago, not everything you read on the internet is true, so it follows that not everything culled and reassembled from the internet is true either. Beware of clearly written, but factually inaccurate or misleading responses from AI tools. Additionally, while they can appear to be “thinking,” they are literally assembling language–without human intelligence. They can produce information that seems plausible, but is in fact partly or entirely fabricated or fictional. The tendency for AI tools to invent information is sometimes referred to as “hallucinating.”

Citations and quotes may be invented AI responses may include citations (especially if you prompt them to do so), but beware. While the citations may seem reasonable and look correctly formatted, they may, in fact, not exist or be incorrect. For example, the tools may invent an author, produce a book title that doesn’t exist or incorrectly attribute language to an author who didn’t write the quote or wrote something quite different. Your instructors are conversant in the fields you are writing about and may readily identify these errors. Generative AI tools are not authoritative sources.

Responses may contain biases Again, AI tools are drawing from vast swaths of language from their data sets–and everything and anything has been said there. Accordingly, the tools mimic and repeat distortions in ideas on any topic in which bias easily enters in. Consider and look for biases in responses generated by AI tools.

You risk violating academic integrity standards When you prompt an AI tool, you may often receive a coherent, well written—and sometimes tempting—response. Unless you have received explicit, written guidance from an instructor on use of AI generated text, do not assume it is okay to copy and paste or paraphrase that language into your text—maybe at all. See your instructor’s syllabus and consult with them about how they authorize the use of AI tools and how they expect you to include citations for any content generated by the tool. The AI tools should help you to think and write, not think or write for you. You may find yourself violating the honor code if you are not thoughtful or careful in your use of any AI generated material.

The tools consume personal or private information (text or images) Do not input anything you prefer not to have widely shared into an AI generator. The tools take whatever you put in to a prompt and incorporate it into its systems for others to use.

Your ideas may be changed unacceptably When asked to paraphrase or polish a piece of writing, the tools can change the meaning. Be discerning and thorough in reviewing any generated responses to ensure the meaning captures and aligns with your own understanding.

A final note

Would you like to learn more about using AI in academic writing? Take a look at the modules in Carolina AI Literacy . Acquainting yourself with these tools may be important as your thinking and writing skills grow. While these tools are new and still under development, they may be essential tools for you to understand in your current academic life and in your career after you leave the university. Beginning to experiment with and develop an understanding of the tools at this stage may serve you well along the way.

Note: This tip sheet was created in July 2023. Generative AI technology is evolving quickly. We will update the document as the technology and university landscapes change.

You may reproduce it for non-commercial use if you use the entire handout and attribute the source: The Writing Center, University of North Carolina at Chapel Hill

Make a Gift

Best AI essay writers in 2024 – our top picks

Table of Contents

What are the best ai essay writers, best ai essay writer overall – rytr, best free ai essay-writer – writesonic, writesonic pros, best feature-rich ai essay writer – jasper, jasper pros, best ai essay writer for students – copy.ai, chat.ai pros, best ai essay writer for script creators – ai writer, ai-writer pros, which ai essay writer is best.

if you’re looking for the best AI essay writer , we’ve got you covered right here.

An AI essay writer is a tool that generates long creative essays on any topic from the given input. The tool uses machine learning algorithms and natural language processing (NLP) to generate unique essays from scratch while maintaining a human tone. Picking the best AI essay writers is quite a tricky task. We picked some of the best AI essay-writing tools to generate content per your writing style.

Apart from writing tasks, these tools can suggest topics, detect grammatical errors, identify plagiarized content, and create an outline for essays. The main advantage of using an AI essay writer is it speeds up the writing process with high grammatical accuracy while focusing on the creative aspect of writing.

We have selected some of the best AI writing tools for you that can write great content within seconds. So, let’s dive in.

The AI-powered Rytr essay writer tool is capable of generating high-quality articles, blogs, and essays. Rytr offers dozens of creative writing features that can help you generate content with specific needs- for instance, type of tone, use case, and preferred creativity. In case you want to check whether your content is unique or not, you can use a built-in document editor to check for plagiarism.

One of the standout features of Rytr is that the AI tool allows you to create content in 30+ languages. There is a feature called ‘Continue Ryting’ that allows you to further extend the content if you are not satisfied with Ryter’s initial output.

Rytr AI essay writer tool is the best tool for high school students and working professionals who want to create in-depth articles or essays without wasting time and money.

• Generate creative essays in 30+ languages within seconds
• Built-in plagiarism checker
• Continue Ryting feature- to extend the content
• AI text finisher
• Affordable Pricing
• Limited features in the free plan

Ryter’s premium monthly plan starts at $9/mo. However, it also offers a free plan with limited features.

The AI-powered Writesonic is a writing tool that offers a wide range of writing and text editing features from creating content (including essays, blogs, and articles) to paraphrasing. This AI tool allows you to edit and extend the existing generated content by just providing a simple prompt. Writesonic has a built-in plagiarism checker, and grammar checker so that you can check the quality of the content within the tool.

Wrtisonic does offer a free trial with a given 10,000 words limit and it’s a great free AI writing tool for students who generate short essays. Once the wording limit is over, you have to upgrade to Writesonic paid plans to continue using it. The main standout feature of this AI writing tool is the chatsonic feature. This feature is powered by GPT-4, which generates data quickly while maintaining high accuracy.

Writesonic is a great AI writing tool powered by GPT-3 that offers more customizations and control on content editing and creating. This AI essay-writing tool is best for content researchers, bloggers, and students.

• Over 100+ AI templates support in free version
• Content extender support
• Writes emails, essays, and reports effortlessly.
• Can summarize different types of content
• Affordable paid plans
• Lacks built-plagiarism checker

Writesonic paid plans start at $19/mo. Although there is a free version available with a limit of up to 10,000 words.

Essential AI Tools

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

• FREE 7 DAY TRIAL

• Find out more

Jasper is an all-in-one AI writing tool that lets you generate content in over 30+ languages, including essays, articles, and product descriptions. The AI tools offer different tones and formats, which makes AI writing more catchy and creative. Jasper has a One-Shot Blog post template that generates a full blog post with an introduction, body, and conclusion.

In our Jasper AI review , we were pretty much impressed by its quick essay-generating capabilities and wide range of advanced AI features. We decided to find out the kind of output it generates based on the provided information.

We asked Jasper AI to generate a short 200-word intro on what the RTX 3090 is, how expensive it is, and a little about 4K gaming. To our surprise, it constructed a decent intro, and we liked the way it organized the information.

We rated Jasper AI five out of five in our review thanks to its user-friendly UI and over 50+ ready-to-use writing templates, including Advertising, Blog, Email, Product description, sales, and more. We also observed some flaws, such as content accuracy and a slightly robotic tone in the generated content. Still, they weren’t enough to stop Jasper AI from securing a spot on our best AI essay writer list.

Overall, Jasper AI is an excellent tool for writing essays. The best part is that it generates results quickly, so you won’t have to wait for hours just to see the output. Sure, the content it generates requires a human touch, but this is normal for AI-generated content.

• Advantage of 50+ templates to choose from
• Produces quick results
• Great for curating essays, short content, and product descriptions
• User-friendly UI
• Slightly expensive
• Sometimes, the output may sound robotic
• Generated information needs to be fact-checked
• Sometimes, it offers irrelevant information

Jasper’s monthly plans kick off at $49/mo.

This AI essay generator tool is beyond essay generation. You can create a full-fledged, high-quality research paper with the Copy.ai essay writer tool. The tool works similarly to the other AI essay writer tools- you have to provide a detailed prompt initially then Copy.ai will generate results for you within seconds.

The only quibble is that you won’t get specific essay prompt customizations here, like Ryter, to write an essay with specific needs. The AI tool, which has real-time internet data access, offers more accurate responses and brief content on any topic. Copy.ai has an Infobase feature that allows the user to upload a text file, and Chat.ai generates content based on the uploaded file.

Chat.ai will let you generate long essays of up to 2000 words under the free plan. It’s the best AI essay writer tool for students who are just creating essays. If you are a graduate student and looking for a well-researched and creative research paper for your project, this tool generates the best research paper for your project.

• It can generate brief content in multiple languages.
• Built-in Inline documents editor.
• The free plan lets you generate only up to 2000 words.
• A paid subscription is expensive.

Copy.ai’s monthly paid subscription plan starts at $49/mo.

Whether you want to create a long essay for your school assignments or generate a short creative blog post, the AI Writer turns out to be a great option. The tool effortlessly generates fresh, creative, and human-like essays and other content such as reports, advertising scripts, and sales copy.

AI Writer tool can also re-build/rearrange the already existing content while adding new information and completely transforming it into newly updated content. The working method of this AI tool is very creative, and it delivers SEO-friendly AI-generated output, which most AI writing tools can’t offer. It offers a Topic Suggest 2.0 feature that gives users the best keywords and ideas.

Overall, AI Writer is best for students and content creators who want to generate or repurpose their existing content. Sometimes, citation is mandatory in the generated content, and AI Writer can do that for you as well.

• Allows integration with ‘WordPress’ CMS
• Generate SEO-friendly, fresh, and unique content quickly
• The enhanced feature gives your essay a good final touch
• Reword feature
• It’s expensive
• No free version

AI-writer offers a free trial for new users, and its basic paid subscription plan starts at $29/mo.

Rytr is the best overall AI essay writer tool. The AI tool offers dozens of writing features and quick results, all at an affordable price. If you are looking for an AI essay writer who has multiple template support, built-in plagiarism support, and the ability to generate fresh and quality content, then Rytr is the best choice for you.

If you want an AI essay writer with advanced writing features and pricing that doesn’t bother you, Jasper is a stand-out AI writing tool you can look up to. Jasper AI tool is best for professionals, students, and anyone who wants to generate high-quality content.

Abhinav Fating

Abhinav has an interest in tech and AI and getting the best out of purchases, be that hardware or software.

Topaz Photo AI review – our experience (pros, cons,…

How to use Seed in Midjourney – our complete…

Midjourney Parameters explained – our guide to better results

How to cancel your Midjourney subscription – step-by-step

Special Features

Vendor voice.

This article is more than 1 year old

University students recruit AI to write essays for them. Now what?

Teachers need to work harder to get students to write and think for themselves.

Feature As word of students using AI to automatically complete essays continues to spread, some lecturers are beginning to rethink how they should teach their pupils to write.

Writing is a difficult task to do well. The best novelists and poets write furiously, dedicating their lives to mastering their craft. The creative process of stringing together words to communicate thoughts is often viewed as something complex, mysterious, and unmistakably human. No wonder people are fascinated by machines that can write too.

Unlike humans, language models don't procrastinate and create content instantly with a little guidance. All you need to do is type a short description, or prompt, instructing the model on what it needs to produce, and it'll generate a text output in seconds. So it should come as no surprise students are now beginning use these tools to complete school work.

Students are the perfect users: They need to write often, in large volumes, and are internet savvy. There are many AI-writing products to choose from that are easy to use and pretty cheap too. All of them lure new users with free trials, promising to make them better writers.

Monthly subscriptions for the most popular platform, Jasper, costs $40 per month to generate 35,000 words. Others, like Writesonic or Sudowrite, are cheaper at $10 per month for 30,000 words. Students who think they can use these products and get away with doing zero work, however, will probably be disappointed.

And then there's ChatGPT ...

Although AI can generate text with perfect spelling, great grammar and syntax, the content often isn't that good beyond a few paragraphs. The writing becomes less coherent over time with no logical train of thought to follow. Language models fail to get their facts right – meaning quotes, dates, and ideas are likely false. Students will have to inspect the writing closely and correct mistakes for their work to be convincing.

Prof: AI-assisted essays 'not good'

Scott Graham, associate professor at the Department of Rhetoric & Writing at the University of Texas at Austin, tasked his pupils with writing a 2,200-word essay about a campus-wide issue using AI. Students were free to lightly edit and format their work with the only rule being that most of the essay had to be automatically generated by software.

In an opinion article on Inside Higher Ed, Graham said the AI-assisted essays were "not good," noting that the best of the bunch would have earned a C or C-minus grade. To score higher, students would have had to rewrite more of the essay using their own words to improve it, or craft increasingly narrower and specific prompts to get back more useful content.

"You're not going to be able to push a button or submit a short prompt and generate a ready-to-go essay," he told The Register .

The limits of machine-written text forces humans to carefully read and edit copy. Some people may consider using these tools as cheating, but Graham believes they can help people get better at writing.

Don't waste all your effort on the first draft....

"I think if students can do well with AI writing, it's not actually all that different from them doing well with their own writing. The main skills I teach and assess mostly happen after the initial drafting," he said.

"I think that's where people become really talented writers; it's in the revision and the editing process. So I'm optimistic about [AI] because I think that it will provide a framework for us to be able to teach that revision and editing better.

"Some students have a lot of trouble sometimes generating that first draft. If all the effort goes into getting them to generate that first draft, and then they hit the deadline, that's what they will submit. They don't get a chance to revise, they don't get a chance to edit. If we can use those systems to speed write the first draft, it might really be helpful," he opined.

Whether students can use these tools to get away with doing less work will depend on the assignment. A biochemistry student claimed on Reddit they got an A when they used an AI model to write "five good and bad things about biotech" in an assignment, Vice reported .

AI is more likely to excel at producing simple, generic text across common templates or styles.

Listicles, informal blog posts, or news articles will be easier to imitate than niche academic papers or literary masterpieces. Teachers will need to be thoughtful about the essay questions they set and make sure students' knowledge are really being tested, if they don't want them to cut corners.

Ask a silly question, you'll get a silly answer

"I do think it's important for us to start thinking about the ways that [AI] is changing writing and how we respond to that in our assignments -- that includes some collaboration with AI," Annette Vee, associate professor of English and director of the Composition Program at the University of Pittsburgh, told us.

"The onus now is on writing teachers to figure out how to get to the same kinds of goals that we've always had about using writing to learn. That includes students engaging with ideas, teaching them how to formulate thoughts, how to communicate clearly or creatively. I think all of those things can be done with AI systems, but they'll be done differently."

The line between using AI as a collaborative tool or a way to cheat, however, is blurry. None of the academics teaching writing who spoke to The Register thought students should be banned from using AI software. "Writing is fundamentally shaped by technology," Vee said.

"Students use spell check and grammar check. If I got a paper where a student didn't use these, it stands out. But it used to be, 50 years ago, writing teachers would complain that students didn't know how to spell so they would teach spelling. Now they don't."

Most teachers, however, told us they would support regulating the use of AI-writing software in education. Anna Mills, who teaches students how to write at a community college in the Bay Area, is part of a small group of academics beginning to rally teachers and professional organizations like the Modern Language Association into thinking about introducing new academic rules.

Critical thinking skills

Mills said she could see why students might be tempted to use AI to write their essays, and simply asking teachers to come up with more compelling assessments is not a convincing solution.

Just $10 to create an AI chatbot of a dead loved one

"We need policies. These tools are already pretty good now, and they're only going to get better. We need clear guidance on what's acceptable use and what's not. Where is the line between using it to automatically generate email responses and something that violates academic integrity?" she asked The Register .

"Writing is just not outputs. Writing and revising is a process that develops our thinking. If you skip that, you're going to be skipping that practice which students need.

"It's too tempting to use it as a crutch, skip the thinking, and skip the frustrating moments of writing. Some of that is part of the process of going deeper and wrestling with ideas. There is a risk of learning loss if students become dependent and don't develop the writing skills they need."

Mills was particularly concerned about AI reducing the need for people to think for themselves, considering language models carry forward biases in their training data. "Companies have decided what to feed it and we don't know. Now, they are being used to generate all sorts of things from novels to academic papers, and they could influence our thoughts or even modify them. That is an immense power, and it's very dangerous."

Lauren Goodlad, professor of English and Comparative Literature at Rutgers University, agreed. If they parrot what AI comes up with, students may end up more likely to associate Muslims with terrorism or mention conspiracy theories, for example.

Computers are alredy interfering and changing the ways we write. Goodlad referred to one incident when Gmail suggested she change the word "importunate" to "impatient" in an email she wrote.

"It's hard to teach students how to use their own writing as a way to develop their critical thinking and as a way to express knowledge. They very badly need the practice of articulating their thoughts in writing and machines can rob them of this. If people really do end up using these things all the way through school, if that were to happen it could be a real loss not just for the writing quality but for the thinking quality of a whole generation," she said.

Rules and regulation

Academic policies tackling AI-assisted writing will be difficult to implement. Opinions are divided on whether sentences generated by machines count as plagiarism or not. There is also the problem of being able to detect writing produced by these tools accurately. Some teachers are alarmed at AI's growing technical capabilities, whilst others believe its overhyped. Some are embracing the technology more than others.

Marc Watkins, lecturer, and Stephen Monroe, chair and assistant professor of writing and rhetoric, are working on building an AI writing pilot programme with the University of Mississippi's Academic Innovations Group. "As teachers, we are experimenting, not panicking," Monroe told The Register .

"We want to empower our students as writers and thinkers. AI will play a role… This is a time of exciting and frenzied development, but educators move more slowly and deliberately… AI will be able to assist writers at every stage, but students and teachers will need tools that are thoughtfully calibrated."

• Human-replacing AI startups reach $1bn unicorn status
• GPT-3 'prompt injection' attack causes bad bot manners
• FauxPilot: It's like GitHub Copilot but doesn't phone home to Microsoft
• AI chatbot trained on posts from web sewer 4chan behaved badly – just like human members

Teachers are getting together and beginning to think about these tools, Watkins added. "Before we have any policy about the use of language models, we need to have sustained conversations with students, faculty, and administration about what this technology means for teaching and learning."

"But academia doesn't move at the pace of Big Tech. We're taking our time and slowly exploring. I don't think faculty need to be frightened. It's possible that these tools will have a positive impact on student learning and advancing equity, so let's approach AI assistants cautiously, but with an open mind."

Regardless of what policies universities may decide to implement in the future, AI presents academia with an opportunity to improve education now. Teachers will need to adapt to the technology if they want to remain relevant, and incentivise students to learn and think on their own with or without assistance from computers. ®

• Machine Learning

Narrower topics

• Deep Learning
• Large Language Model
• Neural Networks
• Tensor Processing Unit

Broader topics

• Self-driving Car

Send us news

Other stories you might like

Openai develops ai model to critique its ai models, etched looks to challenge nvidia with an asic purpose-built for transformer models, want to save the planet from ai chuck in an fpga and ditch the matrix, accelerate migration and go beyond virtualisation to cloud native.

So much for green Google ... Emissions up 48% since 2019

Bake an llm with custom prompts into your app sure here's how to get started, anthropic delivers claude 3.5 model – and a new way to work with chatbots, imf suggests tax on ai's co2 emissions, but not ai itself, google deepmind's latest model promises realistic audio for your ai-generated vids, on-prem ai has arrived – the solution to cloudy problems no one really has, cloudflare debuts one-click nuke of web-scraping ai, a friendly guide to local ai image gen with stable diffusion and automatic1111.

• Advertise with us

Our Websites

• The Next Platform
• Blocks and Files

Your Privacy

• Cookies Policy
• Privacy Policy
• Ts & Cs

Copyright. All rights reserved © 1998–2024

• 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)

I Tested Three AI Essay-writing Tools, and Here’s What I Found

Writing essays can be draining, tedious, and difficult, even for me—and I write all day long for a living. If writing isn’t your special skill, it’s even harder, which is why there are so many sites and products out there that are designed to help you get your homework done. Some of them are pretty unethical, and I’m not going to recommend hiring someone else to write your papers for you, but there are some cool AI tools that can give you a hand that are worth considering. (The essay-writing businesspeople are probably using these, too, so you’re better off eliminating the middleman and using them on your own.)

The best AI essay-helper tools

I have an essay due next week on the history and impact of a federal law, 21 U.S.C. S856, which outlaws the operation of any building where drugs are made or used. I won’t lie: I’m excited to work on it this weekend, but that’s just me. I tested out a few of the more popular AI essay-helper tools, pretending I wasn’t excited about it, to see how they worked. Here’s my assessment. 

First up was Grammarly , which prompted me to fill out a personalization quiz before I could use it. I told the site I was a grad student, interested in improving the vocabulary I use in my work, and looking to brainstorm topics for my essay. I used the text-input section to type a quick introductory paragraph and selected “Generative AI” from the list of options. When I hit the “Improve It” button, Grammarly showed me a revised version that added a bunch of words, but still said the same thing as my more concise entry. To me, that’s annoying, but if you’re trying to hit a word count, this could be useful. I was also given options like “Make it assertive,” “Make it persuasive,” and “Make it confident.” When I selected “Make it more detailed,” the generative AI did expand the information pretty significantly, but it didn’t add any citations and I’m not convinced it drew on material outside of what I inputted. When I hit “Make it persuasive,” the AI automatically assumed the bias should fall in favor of the law, but when I added more detail to my original paragraph, suggesting for argument’s sake that the law has curtailed efforts to reduce drug overdoses throughout the country, the AI assistant said, “Grammarly assistance is unavailable for this prompt because it may result in sensitive content.”

Overall, this wasn’t great for my needs, as my topic's content was too “sensitive” and the generative AI really only added a bunch of words. This one would be most useful for someone trying to hit a word count. 

Next I tested Cramly , which I hadn’t heard of before. Before upgrading to a $4/month plan, you do get to try five free prompts, so I pasted my basic intro paragraph in there and, after a few seconds, got five paragraphs in return. It was obvious the AI was pulling from external sources somehow, as it mentioned fines and prison sentences associated with the law that I hadn’t specified, but it didn’t actually cite those sources. Still, the information it provided was helpful, so this one would be great if you’re not sure how to frame or expand on a topic and need a general idea of what your essay could look like. You’ll just have to go through everything it spits back at you and look it up independently, finding solid sourcing. 

EssayGenius

EssayGenius is extremely easy to use. It asked me to type what I’m writing about into a box. I simply inputted the name of the law and, about 10 seconds later, got 10 paragraphs back, some with subheadings like “historical background” and “implications in criminal law and public policy.” Again, there were no citations here, but the service provided not only a lot of details that could be used as a springboard to find more, but a solid outline for what the paper could look like. The AI played both sides, objectively presenting the cases for and against the law, then provided a conclusion that made it easy to narrow down where to go with the topic. Impressively, I was able to generate all that for free, but if you want to write up to 10 essays per month, it’ll cost you $9.99 a month. 

Finally, I tried out JotBot , which I have seen advertised on social media. It asked me what I was writing about, plus if I wanted an outline, but also gave me an opportunity to upload my old essays so it could replicate my writing style. As scary as it was, the paragraphs it generated after reading some of my older work did sound more like me than standard AI does. It give me subtopic suggestions, like “impact,” “historical background,” and “controversies,” which I could select from a sidebar and, if I liked the paragraph it wrote, drag into the essay itself. From there, I could accept or reject sentences one by one as it generated new ones. I could write in the essay editing section, too, and it generated more suggestions based on what I was typing. Frankly, this one was really cool and I can see how it would help beat writer’s block with ease, since you can type and get suggestions as you go. There was a learning curve, though, and I didn’t realize how quickly I was blowing through my 10 free daily “credits,” since it’s unclear what, exactly, costs credits and how many it costs to, say, accept one suggestion. You can unlock unlimited credits, unlimited autocomplete, unlimited sources, and more for $14 per month. 

Conclusions

Overall, EssayGenius and JotBot were the best AI tools I tested. I was impressed by EssayGenius’s ability to research the topic on its own and JotBot’s mimicry of my own writing style. They do cost money, but that might be worth it if you’re someone who struggles with idea generation, outline creation, or getting into the flow of writing overall. 

Bear in mind these are not meant to churn out entire essays for you and you shouldn’t use them to do that. I don’t mean because it’s unethical, but I mean because it’s pretty easy for professors to catch you doing it . Even if you do use an AI tool to generate a whole paragraph or more, try to write it in your own voice and think of it more as a way to study and learn about your topic than have the writing done for you. 

Or, pay nothing and just use ChatGPT to generate outline ideas. I do that all the time and never have to worry about getting in trouble, cheating myself out of an education, or paying for anything. I just asked ChatGPT to generate an outline for an essay on 21 U.S.C. §856 and its impact on American harm reduction efforts and got eight sections, each with three subsections, and an easy roadmap I could follow to write my paper on my own. Doing it this way ensures I’ll actually research and learn about the topic, which is important to me, but also avoid the risk of going down for plagiarism or cheating, which is probably important to you. 

No matter what you end up doing, always run your work through a plagiarism checker (like Grammarly’s , which is better than its AI essay-writing tools) and ZeroGPT to make sure you’re not turning in something that’s going to get you in trouble.

The College Essay Is Dead

Nobody is prepared for how AI will transform academia.

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

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

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

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

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

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

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

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

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

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

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

Read: The humanities are in crisis

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

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

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

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

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

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

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

• Share full article

Advertisement

Supported by

current events conversation

What Students Are Saying About Learning to Write in the Age of A.I.

Does being able to write still matter when chatbots can do it for us? Teenagers weigh in on an essay from Opinion.

By The Learning Network

With artificial intelligence programs like ChatGPT that can generate prose for us, how much should we care about learning to write — and write well?

In “ Our Semicolons, Ourselves ,” the Opinion contributor Frank Bruni argues that, for a multitude of reasons, communicating effectively is a skill we should still take seriously. “Good writing burnishes your message,” he writes. “It burnishes the messenger, too.”

We asked teenagers what they thought: Does learning to be a good writer still matter in the age of A.I.? Or will the technology someday replace the need for people to learn how to put pen to paper and fingers to keyboard?

Take a look at their conversation below, which explores the benefits of learning to express oneself, the promise and perils of chatbots, and what it means to be a writer.

Thank you to everyone who participated in the conversation on our writing prompts this week, including students from Glenbard North High School in Carol Stream, Ill.; Hinsdale Central High School in Hinsdale, Ill. and New Rochelle High School in New Rochelle, N.Y .

Please note: Student comments have been lightly edited for length, but otherwise appear as they were originally submitted.

We are having trouble retrieving the article content.

Please enable JavaScript in your browser settings.

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

Thank you for your patience while we verify access.

Already a subscriber?  Log in .

Want all of The Times?  Subscribe .

• Skip to main content
• Skip to primary sidebar
• Skip to footer

Additional menu

Khan Academy Blog

How AI Can Help You Write a Successful College Admission Essay

posted on September 21, 2023

By  Hailey Dickson , Product Marketing Manager at Khan Academy

Writing a college admission essay can be daunting for many students, especially when you consider the stakes. One of the most challenging aspects of the college admission process is writing the perfect admission essay. You only have a few hundred words to express your personality, accomplishments, and goals and convince the admissions board that you are the right fit for their institution.

That being said, it’s crucial to put your best foot forward and ensure your essay stands out from the pack. Fortunately, with advancements in technology, you don’t have to do it alone. In this blog, we will explore how AI, and more specifically Khan Academy’s AI tutor Khanmigo , can help you brainstorm and perfect your admission essay.

Preparing to Write a College Admission Essay

Before you start writing your college admission essay, it’s essential to take some time to prepare yourself. This preparation includes understanding the essay’s requirements, gathering useful information, and developing a timeline to create an outstanding essay.

Firstly, familiarize yourself with the essay’s format and word count requirements. Most colleges require a 500-750 word essay, while some schools might set a different word count limit. Reading sample essays from successful students can help you understand the structure and tone.

Next, you need to decide what story or personal experience you wish to share with your admissions reader. This personal experience should be unique and highlight your individuality. It should also align with your interests and demonstrate your passion for your chosen field of study.

Since you have to limit your essay to a few hundred words, it’s imperative to identify your key points and give priority to the ones that effectively communicate your story. Make a list of specific experiences or events that have shaped your character and try to narrow down which ones best fit the prompt. It’s crucial to remember that less is more. A tightly crafted essay can make a more significant impact than one that tries to include too much.

Understanding the Requirements of a College Admission Essay

To improve your chances of getting into your dream college, it’s crucial to understand what college admissions reviewers are looking for in a great essay. The admissions board reads your essay to understand whether you might fit into their academic program and community. Therefore, your writing will ideally demonstrate your:

• fit with the school’s academic culture and goals;
• passion and interest in your chosen field of study;
• potential for academic excellence; and
• active involvement in extracurricular activities and community service.

Additionally, you should follow a clear, logical structure that is easy to read and understand. Your essay should tell a story that interests the reader and leaves a memorable impression. 

As an example, here are Purdue’s Freshman essay requirements:

First-Time College Students (Freshmen)

Required minimum-maximum word count: 250-650

• Some students have a background, identity, interest, or talent that is so meaningful they believe their application would be incomplete without it. If this sounds like you, then please share your story.
• The lessons we take from obstacles we encounter can be fundamental to later success. Recount a time when you faced a challenge, setback, or failure. How did it affect you, and what did you learn from the experience?
• Reflect on a time when you questioned or challenged a belief or idea. What prompted your thinking? What was the outcome?
• Reflect on something that someone has done for you that has made you happy or thankful in a surprising way. How has this gratitude affected or motivated you?
• Discuss an accomplishment, event, or realization that sparked a period of personal growth and a new understanding of yourself or others.
• Describe a topic, idea, or concept you find so engaging that it makes you lose all track of time. Why does it captivate you? What or who do you turn to when you want to learn more?
• Share an essay on any topic of your choice. It can be one you’ve already written, one that responds to a different prompt, or one of your own design. 

Purdue Questions 

Respond in 250 words or fewer.

• How will opportunities at Purdue support your interests, both in and out of the classroom?
• Briefly discuss your reasons for pursuing the major you have selected.

Brainstorming Ideas for Your College Admission Essay

The key to writing an impactful college admission essay is brainstorming. Brainstorming is the process of generating ideas and concepts before you start writing. It’s an excellent way to organize your thoughts, prioritize your story’s key points, and highlight your accomplishments. Here are some tips for brainstorming:

• Conduct extensive research on the college, its values, and its requirements.
• Freewrite in a journal, exploring possible topics and themes.
• List your achievements, interests, and experiences, highlighting the ones that best align with the college’s academic culture.
• Engage with peers or professionals who know you well to help you identify unique stories that demonstrate your strengths.

Use AI to Help You Get into College!

Using khanmigo to brainstorm an effective admission essay.

Khan Academy has built a feature in Khanmigo to help students brainstorm their college admission essays. All you need to do is log in to Khanmigo and navigate to the “Write” section and select “Brainstorm an admissions essay.” The AI tutor will walk you through the process:

Writing Your College Admission Essay

Once you have brainstormed your ideas and identified your key points and story arcs, it’s time to start writing. The writing process could be daunting, but it doesn’t have to be complicated. 

Here are some tips to help you write a standout college admissions essay:

• Grab the reader’s attention from the start with an engaging hook; this strongly influences the admissions reader from the get-go
• Ensure your essay has a clear structure—introduction, body, and conclusion.
• Use simple and clear language; avoid using jargon and technical terms that the reader may not understand.
• “Don’t tell me the moon is shining. Show me the glint of light on broken glass,” – Anton Chekhov  
• Edit and proofread your essay thoroughly; check your grammar, punctuation, and spelling.

AI Editing and Proofreading

One of the most important aspects of essay writing is editing and proofreading. However, it can be challenging to identify errors in grammar, spelling, sentence structure, and flow. That’s where Khanmigo has your back once again.

Simply log in to Khanmigo and navigate to the “Write” section and select “Check for problems with my admission essay.” The AI tutor will help you in an intuitive manner, observing pitfalls and helping link the logic of your writing to the best practices of admissions writing. 

Tips for Submitting Your College Admission Essay

The final step is to submit your college admission essay. Before you hit the submit button, spend time reviewing your essay to ensure it meets all the necessary requirements. Here are some tips to help you submit an outstanding essay:

• Read and follow the submission guidelines provided by your college.
• Check for typos, grammar, and punctuation errors using a tool like Khanmigo.
• Show your essay to someone you trust, such as a teacher or mentor, to get feedback and suggestions.
• Give yourself time to recharge and return to your essay with fresh eyes before submitting.

With these tips and AI-driven support from Khanmigo, you’re now well-equipped to write a college admission essay that truly represents you.

Get Help with Your College Application Essay Today

Writing a college admission essay is not an easy feat. However, with proper preparation, understanding of the prompt, and support from AI tools such as Khanmigo, it’s possible to craft an essay that stands out and reflects your unique personality.

Remember, it’s not just about meeting the essay’s minimum requirements but about showcasing your achievements, story, personality, and goals in a way that resonates with the college board. If you follow our tips and lean into support from AI, you’ll be on your way to a standout college admission essay and a successful submission.

Get Khanmigo

The best way to learn and teach with AI is here. Ace the school year with our AI-powered guide, Khanmigo. 

For learners     For teachers     For parents

University Writing Program

Ai writing in the college classroom.

Written by Nate Brown

Attendant to the rise of powerful artificial intelligence (AI) technologies like ChatGPT 4, Perplexity, Jasper, YouChat, Chatsonic, and others, instructors in higher education must consider how students and teachers will (or will not) use AI tools in the classroom and beyond. 

There is already ample evidence that AI technologies built on large language models (LLMs) can produce text, images, and computer code essentially indistinguishable from work produced by humans. Ethan Mollick at the Wharton School of Business at the University of Pennsylvania has signaled cautious optimism about AI’s potential to save time on iterative technical and compositional tasks in the workplace. AI skeptics, on the other hand, express concern about the use of the technology to produce false or misleading information and/or to misrepresent authorship. 

As of this writing, there is a clear prerogative to help students navigate these new tools so that their original intellectual efforts and products are presented responsibly and assessed fairly.  

In what follows, we lay out four starting assumptions about AI that guide our recommendations. These first principles are drawn from the current literature and may be helpful to discuss with students to ensure that everyone is on the same page regarding AI’s capabilities. Then, we suggest five best practices for using AI in the classroom.  

Starting Principles

1. ai is here to stay.  .

Generative AI is already widely available to populations around the globe, which means that it’s incumbent upon professors and teaching assistants to familiarize themselves with the current AI landscape and to develop clear AI policies for their own courses.

2. Generative AI cannot create novel material in a traditional sense.

As Mollick points out, the terms associated with various generative AI technologies are still ill-defined but describe algorithmic systems that use large data sets to “[predict] what the next word in a sentence should be so it can write a paragraph for you [and] what an image should look like based on a prompt.” 

In other words, generative AI creates new combinations of extant language, images, and computer code when prompted to do so. 

The ethical considerations here are vast, but of particular importance in the classroom is a reminder to students that their original thoughts, analyses, scholarship, and labor are central to their educational development and to the advancement of intellectual and academic pursuits. AI cannot produce novel thought.  

3. While many AI technologies are described as “generative,” current iterations are not sentient or self-aware.   

The current conversation about AI is muddied by occasional claims of sentience, which make for surprising and enticing headlines. In the summer of 2022, Google Engineer Blake Lemoine made the news when he claimed that Google’s AI-driven chatbot , LaMDA, was alive.  

Then, in the spring of 2023, New York Times technology writer Kevin Roose published a column entitled “A Conversation With Bing’s Chatbot Left Me Deeply Unsettled” alongside a transcript of his chat with Bing’s Chat GPT4-powered search engine.  

Most technologists working in the AI space are quick to point out that enormous datasets and advances in artificial neural networks (ANNs), which are inspired by the structure of the human brain, have honed the most advanced chatbots’ ability to mimic natural language.     In discussing AI technologies with students, instructors should take care to make this distinction clear, both so that the next buzzy headline doesn’t mislead them and so that the class has an opportunity to discuss the potential uses, advantages, and pitfalls of producing text that is virtually indistinguishable from organic human language.  

4. Most generative AI chat tools cannot access paywalled research.   

This limitation means that what any LLM-based AI tool can generate will not necessarily include the best, most recent, or most relevant peer-reviewed data in a given field. For research purposes, then, AI-generated text is particularly limited.  

While this may change over time, current chatbots are not well suited for creating reliable and legitimate university-level research. Instead, they tend to present general information culled from a massive dataset of popularly available information, like news articles, blog posts, and trade publications.  

Best Practices

Here’s our best advice for how to address the use (or prohibition) of AI technologies in the classroom:

1. Have frank discussions with students about the potential uses and limitations of AI technologies in the classroom and beyond. Guiding questions might include:  

• Under what circumstances might a student, instructor, researcher, journalist, public official, private citizen, employee, or public-sector worker helpfully leverage AI tools?  
• Under what circumstances would you consider the use of AI tools unfair, unethical, or careless?  
• Under what circumstances would the use of AI tools represent an abrogation of public trust (e.g. a politician using AI to craft an emotionally charged speech; a journalist using AI to write a news article; a thinktank using AI to craft draft legislation or a white paper)? 

2. Write and make available your classroom policy regarding the use of AI tools. For instance :

• Can a student in your course use AI to generate initial ideas to get started on an assignment?  
• Can students use AI to draft text for major assignments?   
• Can students use AI tools to help revise their own original draft text?  
• Can they use AI tools to find primary sources when doing research?  
• Can they use AI tools in a limited way (for example, to edit a specific word or phrase) as they would a thesaurus or dictionary or a citation-formatting tool?

3. If you have a prohibition on using AI-based technologies in the classroom, make your reasoning clear and provide alternative approaches.  

• Explain why you will not allow the use of AI tools in the classroom.  
• Discuss and have a written policy outlining the specific prohibitions on using AI technologies for the creation and completion of assignments.  
• In both the syllabus and on individual assignments, include a note about the prohibition of AI-based technologies in the creation and completion of assignments.  
• Engage in in-class pre-writing activities such as brainstorming, ideation, drafting, peer-review, and revision to support students in the writing process. 

4. If you allow students to use AI tools, experiment with them in the classroom space, and give students an opportunity to compare the structure, diction, and rhetorical features of human and AI-generated text.

• Look for structural deficiencies and proficiencies in the text: Is it legible? Is it specific? Is it informative or authoritative?  
• Look for tone and style: Does the text present information in a creative or engaging way? What, if any, textual flourishes are present in the work?   
• Note how the text uses information: Does it cite specific sources? Does it generalize or paraphrase information? What authority does the text appeal to, if any? Does the text employ verifiable information or facts in a credible manner?  
• Give students a short, low-stakes writing assignment (a 250-word reflection on their day, for instance) and have them complete it in class. Then have them prompt an AI chat tool to write a reflection for them. Compare the texts, looking for the differences between them, and noting any correlations.  

5. Reinforce that these tools are evolving, and that your course policies and broader university, governmental, and corporate policies regarding the use of AI tools will necessarily change over time, too.

This includes the information and suggestions provided in this toolkit.  

View sample AI activities and policies from musicology in the Model Library.

Cited and Recommended Sources

• Chiang, Ted. “ChatGPT Is a Blurry JPEG of the Web.” The New Yorker Magazine, 9 Feb. 2023,   https://www.newyorker.com/tech/annals-of-technology/chatgpt-is-a-blurry-jpeg-of-the-web
• Chui, Michael. “Forward Thinking on the Brave New World of Generative AI with Ethan Mollick.” McKinsey & Company , 31 May 2023, www.mckinsey.com/mgi/forward-thinking/forward-thinking-on-the-brave-new-world-of-generative-ai-with-ethan-mollick . 
• Crompton, Helen, and Diane Burke. “Artificial Intelligence in Higher Education: The State of the  Field.”  International Journal of Educational Technology in Higher Education , vol. 20, no.  1, Apr. 2023, pp. 1–22.  EBSCOhost , https://doi.org/10.1186/s41239-023-00392-8 . 
• “Hard Fork: GPT-4 Is Here, and the Silicon Valley Bank Fallout.”  The New York Times , 17 Mar. 2023,  https://www.nytimes.com/2023/03/17/podcasts/hard-fork-gpt-4.html . 
• “Hard Fork: AI Extinction Risk and Nvidia’s Trillion-Dollar Valuation.”  The New York Times , 2 June 2023,  www.nytimes.com/2023/06/02/podcasts/hard-fork-chatgpt-nvidia.html . 
• How Will Artificial Intelligence Change Higher Ed? – The Chronicle of Higher Education , 25 May, 2023,  www.chronicle.com/article/how-will-artificial-intelligence-change-higher-ed . 
• Huang, Kalley. “Alarmed by A.I. Chatbots, Universities Start Revamping How They Teach.”  The New York Times , 16 Jan. 2023,  https://www.nytimes.com/2023/01/16/technology/chatgpt-artificial-intelligence-universities.html . 
• Metz, Cade. “Meet GPT-3. It Has Learned to Code (and Blog and Argue).”  The New York Times ,  24 Nov. 2020,  https://www.nytimes.com/2020/11/24/science/artificial-intelligence-ai-gpt3.html .  
• McMurtrie, Beth. “How Artificial Intelligence Is Changing Teaching.” The Chronicle of Higher Education , 12 Aug. 2018, https://www.chronicle.com/article/how-artificial-intelligence-is-changing-teaching . 
• MLA-CCCC Joint Task Force on Writing and AI. 1 Jul, 2023,  https://hcommons.org/app/uploads/sites/1003160/2023/07/MLA-CCCC-Joint-Task-Force-on-Writing-and-AI-Working-Paper-1.pdf.
• Mollick, Ethan. “ChatGPT Is a Tipping Point for AI.” The Harvard Business Review, 14 Dec. 2022, https://hbr.org/2022/12/chatgpt-is-a-tipping-point-for-ai . 
• Perkins, Mike. “Academic Integrity Considerations of AI Large Language Models in the Post-Pandemic Era: ChatGPT and Beyond.”  Journal of University Teaching & Learning Practice , vol. 20, no. 2, Mar. 2023, pp. 1–24.  EBSCOhost , https://doi.org/10.53761/1.20.02.07 . 
• Reiss, Michael J. “The Use of AI in Education: Practicalities and Ethical Considerations.”  London Review of Education , vol. 19, no. 1, Mar. 2021, pp. 1–14.  EBSCOhost , https://doi.org/10.14324/LRE.19.1.05 . 
• Roose, Kevin. “Don’t Ban ChatGPT in Schools. Teach With It.”  The New York Times , 13 Jan. 2023,  https://www.nytimes.com/2023/01/12/technology/chatgpt-schools-teachers.html . 
• Schatten, Jeff. “Will Artificial Intelligence Kill College Writing?” The Chronicle of Higher Education , 14 Sept. 2022,  https://www.chronicle.com/article/will-artificial-intelligence-kill-college-writing
• Wilhelm, Ian. “Nobody Wins in the Academic Integrity Arms Race.” The Chronicle of Higher Education , 12 Jun. 2023, https://www.chronicle.com/article/nobody-wins-in-an-academic-integrity-arms-race . 
• Wooldridge, Michael. “Artificial Intelligence Is a House Divided.” The Chronicle of Higher Education , 20 Jan. 2021, https://www.chronicle.com/article/artificial-intelligence-is-a-house-divided . 

Pursue Your Goal

Educators & Partners

Find content

How to Use AI/ChatGPT Effectively for Your College Application Essays

Last updated November 16, 2023

A vital component of your college applications is your personal statement essay(s). With the rise of Artificial Intelligence (AI) tools like ChatGPT, you may be curious about how they can support your college application essay writing, or if it’s even okay to use them at all. We’ll share what you need to know about tools like ChatGPT and the do’s and don’ts of using AI in your college application essays.

What is AI? What is ChatGPT?

Artificial Intelligence (also known as AI), is technology designed to imitate human intelligence. Some examples of this include asking Siri about the weather on your iPhone, using Amazon’s Alexa to set an alarm, or receiving song suggestions based on the music you listen to on Spotify.

ChatGPT is a type of AI model that virtually chats with users to answer their questions and respond to their prompts. ChatGPT uses decades worth of internet data to learn how people communicate, solve problems, and find patterns. It then uses this data to create a human-like response when you interact with it. The more people use ChatGPT, the more information it gathers and learns. 

AI and ChatGPT are relatively new, so not many people understand the full extent of its consequences. However, it’s clear that these technologies are here to stay, so it’s important to understand how to use them responsibly. 

Can I use AI tools like ChatGPT to write my college application essay?

With AI technologies increasing in popularity, many concerns have been raised about using it responsibly. Some school districts– in Seattle, WA for example – have banned the use of ChatGPT due to issues of plagiarism and cheating. Chances are, your school or district might be working on or already have policies on the use of ChatGPT.

A few colleges have also established their own policies on AI. Some may have strict policies on plagiarism and discourage the use of ChatGPT, while others may have guidelines on how to use it responsibly and ethically. For example, while Georgia Tech doesn’t completely ban the use of ChatGPT, their statement suggests best practices when using AI for college applications. We highly recommend that you check a college’s policies or guidelines if you’re considering using AI tools on your applications to that school.

When in doubt, it’s probably best to avoid using ChatGPT to help you write your college application essay. But if you are thinking about using it, we recommend following these dos and don’ts:

Using AI for your College Application - Dos and Don'ts

Don’t use chatgpt to write your entire essay.

We can’t emphasize this enough– do not use ChatGPT to write your entire college application essay. Since ChatGPT learns from information submitted by humans, it can create generalizations, resulting in responses that sound unoriginal and robotic.

While it’s possible that ChatGPT can draft an entire essay in seconds, it’s not recommended to use as your final draft. The essay might be too general and lacking personality, therefore not allowing the reader to really get to know you. College admissions officers are experienced in reading hundreds, if not thousands, of essays, so it’s likely they can tell whether something was written by an AI or by a human. 

ChatGPT can be helpful in creating an outline, or maybe even creating a first draft. However, you will need to put in the work to edit it and ensure it captures your authentic voice and unique perspective– especially when applying to colleges that are highly competitive. Having trouble writing your college application essay? Check out our guide to get started .

DO use ChatGPT to generate ideas

Your college application essay should reveal something about you through storytelling. If you’re having trouble deciding what to write , you might turn to ChatGPT to help you generate ideas and narrow down your topic. For example, you can ask it to come up with 10 questions to help you brainstorm topics, or you can ask it to elaborate on an idea you might already have. However, ChatGPT can only provide general responses and is unable to provide a unique perspective, so you’ll still need to find ways to make your topic significant to you.

AI is not built to have meaningful conversations, and it’s impossible to share your full history and important memories for an AI model to learn. Programs like ChatGPT can’t accurately create an entire picture of you, so they’re unable to connect your life experiences to your values and what’s important to you. For example, you may have memories of taking care of your pet and how it taught you about loyalty; or you might enjoy a specific candy because it reminds you of the importance of friendship. You know yourself the best, so while ChatGPT can help start your idea, it’s up to you to finish it. 

DO use AI to proofread your essay

A benefit of using AI models is that they can check your essay for grammar errors and typos. Programs like Grammarly or ChatGPT can proofread your essay and provide suggestions on how to improve your spelling or the structure or clarity of your writing. In addition, when used correctly, you can use ChatGPT to find alternative ways to write something. For example, you can use it to help make your ideas more clear. If your sentence doesn’t sound right, ChatGPT can help rewrite it. If you’re stuck on a word, you can ask ChatGPT for suggestions.

Using Grammarly or ChatGPT to fix grammatical errors is a great way to enhance your writing, but it shouldn’t be the only resource you depend on. Have someone else proofread your essay, like a trusted friend, educator, parent, or guardian. You can also submit your essay to us, and one of our expert Get Schooled advisors will review it for free!

DON’T share any personal or sensitive information with AI Models

Since AI uses data submitted by humans to improve its models, it’s likely these programs will save any data you share, including your personal information. ChatGPT, for example, automatically saves all of the prompts and questions people submit, regardless of what’s being discussed. Moreover, while ChatGPT is an AI model, it is still created and run by humans, so all past conversations and questions may be seen by other people working for ChatGPT. 

It’s important to be careful when it comes to sharing your personal information, like your location, school, or any information about yourself that you wouldn’t want to share publicly. While ChatGPT recently allowed users to turn off chat history , it’s best to proceed with caution when using it. Additionally, using ChatGPT and other AI models require you to sign up for an account using your email address, phone number, and other identifying information, which can raise concerns around data security.

DO keep your authentic voice

Showing your personality through your essay is crucial to leaving a lasting impression on admissions officers. Because ChatGPT provides widely generic responses, it can create a story that may feel similar to something you experienced, but it will never be your authentic story.

A significant portion of your college application relies on data, like your GPA and test scores. Your personal statement essay is your opportunity to provide admissions officers a peek into your life, what your personality is like, what motivates you, and what your aspirations are. Colleges value authenticity, and your personal statement now plays an even more pivotal role after the U.S. Supreme court decision to reverse affirmative action . When writing about your perspectives related to diversity and inclusion, it’s important to share your experiences genuinely.

Instead of depending on ChatGPT to create a story for you, draw from your own personal experiences that you are excited to write about. Examples can be a relationship that impacted you the most, or an event that challenged your perspective. 

DON’T use AI as your only tool for college applications

Using ChatGPT can be a helpful tool in crafting your college application essay, but it shouldn’t be your only tool. There are other strategies that you can learn and various resources you can take advantage of. For example, check out our resources on how to write your college and scholarship application essays . When you complete your first draft, you can submit your essay to us for free review !

AI can be a great tool to help with your essay writing, but it isn’t a shortcut and should not be the only thing you depend on. At the end of the day, nobody knows you better than yourself!

Have any questions about the college application process? Text us! Send  #Hello to 33-55-77 to chat with one of our advisors, or, click here to have the text message set up for you !

Explore your goals

Let Get Schooled help you achieve your goals

How to write your college application essay.

Here’s how to write your college application essay!

Most Common College Essay Topics

Get familiar with the most common college essay topics to shape your own narrative for college admissions.

Common College Application Essay Myths

We share common college application essay myths and the truth about essay writing!

Free College Application and Scholarship Essay Review

Get Schooled's free college application and scholarship essay review! Receive actionable feedback and suggestions within 1 week of submission!

Exploring How Colleges Verify AI Essays

06 Jul 2024 • 4 min

Welcome, curious minds! Today, we're going to explore a fascinating topic that involves two essential elements: colleges and artificial intelligence. Have you ever wondered how colleges ensure that essays submitted by students are original and authentic? Well, let's delve into the world of AI essays and how technology is shaping the way academic integrity is maintained in educational institutions.

Imagine a world where machines have the ability to read, write, and assess written works just like humans. This is where AI comes into play. Colleges are increasingly turning to artificial intelligence to assist in the verification process of essays submitted by applicants. It's a remarkable blend of cutting-edge technology and traditional academia.

Academic integrity, which refers to the ethical code of honesty and responsibility in scholarly work, is paramount in the world of education. With the rise of technology, colleges are leveraging AI to uphold these standards while streamlining the verification process of essays. Let's embark on this journey of discovery to understand how AI is transforming the landscape of essay writing and verification in colleges.

Table of Contents

Understanding ai essays, verification process, impact on college admissions, ensuring fairness and transparency, future of ai in education, frequently asked questions (faqs).

AI essays, also known as essays created with the assistance of artificial intelligence, are becoming increasingly popular in the academic world. These essays are either generated entirely by AI programs or are aided by AI tools to improve their quality and structure. Let's explore what AI essays are and how artificial intelligence plays a crucial role in their creation.

Don't write alone! Get your new assistant!

Transform your writing experience with our advanced AI. Keep creativity at your fingertips!

Definition of AI Essays

AI essays are essays that are either entirely written by artificial intelligence programs or are significantly assisted by AI tools in the writing process. These essays leverage the capabilities of AI to automate various aspects of writing, such as generating content, checking grammar, and improving overall coherence and structure.

Role of Artificial Intelligence

Artificial intelligence plays a vital role in the creation of AI essays by streamlining the writing process and enhancing the quality of the content. AI algorithms can efficiently generate text, perform grammar checks, and suggest improvements to make the essays more coherent and compelling.

Pros and Cons of AI in Essay Writing

The use of AI in essay writing offers several advantages, including increased efficiency, accuracy, and consistency in the writing process. However, there are also potential drawbacks to consider, such as the lack of creativity and authenticity in AI-generated essays. It is essential to strike a balance between leveraging AI technology's benefits while preserving the unique voice and originality of student work.

When you submit an essay to a college as part of your application, the admissions team needs to make sure that the work you're presenting is truly your own. This is where the verification process comes into play. Colleges use various tools, including artificial intelligence (AI), to verify the authenticity of essays submitted by applicants. Let's take a closer look at how this process works.

Plagiarism Detection

One of the key aspects of the verification process is plagiarism detection. Colleges utilize AI software to scan essays for any plagiarized content. Plagiarism occurs when someone uses another person's words or ideas without proper citation. By using AI tools, colleges can quickly identify any instances of plagiarism in the essays they receive. This plays a crucial role in upholding academic integrity and ensuring that all students are held to the same standards of originality.

Academic Integrity Checks

Academic integrity is a fundamental principle in education, emphasizing honesty, fairness, and ethical behavior in academic work. Colleges rely on technology, such as AI, to maintain high standards of academic integrity in essay submissions. By employing AI tools for verification, colleges can ensure that all applicants are following the rules and submitting their own work. This process helps create a level playing field for all students and reinforces the importance of academic honesty.

Check out how colleges are using AI to verify essays and ensure authenticity. #collegeadmissions #AIverification [insert link]

When colleges review essays submitted by applicants, they focus on various factors to assess the quality of the content. Originality and coherence are essential elements that institutions look for in student submissions. Originality ensures that the essay is unique and reflects the applicant's own thoughts and ideas, while coherence ensures that the essay is well-organized and effectively communicates the intended message. These criteria help colleges evaluate the candidate's writing skills and suitability for the academic program.

Admissions Decision-Making

AI-verified essays play a significant role in the admissions decision-making process. Colleges use technology to assist in the selection of candidates based on the quality of their essays. By relying on AI tools to verify the authenticity and originality of submissions, institutions can streamline the evaluation process and make informed decisions about admission offers. The use of AI in admissions underscores the importance of innovation and efficiency in modern educational practices.

It's crucial to ensure that the use of AI technology in essay verification remains fair and unbiased for all applicants. To achieve this, colleges implement strategies to mitigate any potential biases in the algorithms used for assessing essays. By regularly analyzing and refining these algorithms, colleges aim to promote equality and provide every applicant with an equal opportunity to showcase their skills and abilities. This helps in upholding the principles of fairness in the college admissions process.

AI Blog Writer

Automate your blog for wordpress, shopify, webflow, wix..

Exploring the Role of AI in College Admissions

AI Blog Writer. Automate your blog for WordPress, Shopify, Webflow, Wix.

Easily integrate with just one click. skyrocket your traffic by generating high-quality articles and publishing them automatically directly to your blog..

Trusted by 100,000+ companies

Ethical Implications

When it comes to incorporating AI technology in the college admissions process, it is essential to address the ethical considerations surrounding its usage. Transparency and accountability play a significant role in navigating the ethical implications associated with AI essay verification. Colleges must be transparent about the use of AI tools, including how they assess essays and the impact it has on admissions decisions. By fostering a culture of honesty and openness, institutions can maintain trust and integrity in the application review process.

As technology continues to advance, the future of AI in education holds immense promise for transforming the way students learn and teachers instruct. Let's explore some of the potential advancements and innovations that AI technology may bring to educational settings.

Adaptive Learning Systems

One exciting aspect of the future of AI in education is the development of adaptive learning systems. These systems leverage artificial intelligence to customize the learning experience for each student based on their individual needs and learning style. By analyzing a student's performance and behavior, AI can create personalized lesson plans, recommend supplemental materials, and offer targeted feedback to enhance understanding and retention.

Enhanced Assessment Tools

AI-powered assessment tools are set to revolutionize traditional evaluation methods in education. These tools have the capability to provide real-time feedback to students on their progress, identify areas of weakness, and offer tailored solutions for improvement. By utilizing AI algorithms, educators can gain valuable insights into student performance, allowing for more effective teaching strategies and personalized learning experiences.

In this article, we explored the concept of colleges utilizing AI technology to verify essays submitted by applicants. The integration of artificial intelligence in the essay writing and verification process marks a significant advancement in educational practices, emphasizing the importance of academic integrity while leveraging technological solutions.

Key Takeaways

AI essays, assisted or generated by artificial intelligence programs, streamline the writing process through automation, providing benefits in efficiency and accuracy. However, challenges such as the lack of creativity and authenticity in AI-generated content remain prevalent.

Colleges rely on AI tools for plagiarism detection to uphold academic integrity and ensure the originality of student submissions. This technology-driven verification process plays a pivotal role in maintaining high standards in essay evaluations.

The impact of AI-verified essays on college admissions underscores the significance of originality, coherence, and fairness in evaluating applicant submissions. Technology contributes to the decision-making process by providing valuable insights for admissions committees.

Ensuring fairness and transparency in AI essay verification involves mitigating bias in algorithms and addressing ethical considerations. Promoting equal opportunities and accountability remains crucial in leveraging AI technology for educational purposes.

The future of AI in education holds promising prospects for adaptive learning systems and enhanced assessment tools. These innovations aim to personalize education experiences, offer tailored feedback, and improve student learning outcomes through advanced technologies.

Overall, the integration of AI in the essay verification process represents a transformative shift in education, emphasizing efficiency, accuracy, and ethical considerations. As we navigate the evolving landscape of technology in learning environments, it is essential to embrace these advancements while upholding the values of fairness, transparency, and academic integrity.

Do Colleges Check for AI Essays?

Yes, colleges may use AI technology to check essays submitted by applicants. This helps verify the originality and authenticity of the work. Through AI tools, colleges can detect plagiarism and ensure that students uphold academic honesty.

What is the Role of Technology in Academic Integrity?

Technology, including AI, plays a crucial role in upholding academic integrity. By utilizing advanced tools, colleges can ensure that essays are original and meet the required standards. This promotes fairness in the admissions process.

How Does AI Impact Student Admissions?

AI-verified essays have an impact on student admissions by providing colleges with efficient and accurate assessments of applicants' writing skills. This technology contributes to the decision-making process by offering insights into candidates' abilities.

AI Blog Writer.

Easily integrate with just one click. Boost your productivity. Reduce your writing time by half and publishing high-quality articles automatically directly to your blog.

Read more from the blog.

The Impact of AI on Academic Integrity: Do Professors Check for AI?

Uncover the surprising truth about how ai technologies are reshaping academic integrity and how professors are adapting to combat it..

How Do Scholarships Verify AI Technology in Applications?

Discover the secrets behind how scholarships are leveraging ai technology to streamline and enhance the application process. learn more here.

Exploring the Best Free Character AI Tools for Creators

Uncover the top free character ai tools that will revolutionize your creative process and bring your characters to life, thanks for subscribing, be the first to know about releases and industry news and insights., join our newsletter, sign up for the very best tutorials and the latest news., useful content, ai generators.

• Original article
• Open access
• Published: 08 July 2024

Can you spot the bot? Identifying AI-generated writing in college essays

• Tal Waltzer   ORCID: orcid.org/0000-0003-4464-0336 1 ,
• Celeste Pilegard 1 &
• Gail D. Heyman 1  

International Journal for Educational Integrity volume  20 , Article number:  11 ( 2024 ) Cite this article

240 Accesses

14 Altmetric

Metrics details

The release of ChatGPT in 2022 has generated extensive speculation about how Artificial Intelligence (AI) will impact the capacity of institutions for higher learning to achieve their central missions of promoting learning and certifying knowledge. Our main questions were whether people could identify AI-generated text and whether factors such as expertise or confidence would predict this ability. The present research provides empirical data to inform these speculations through an assessment given to a convenience sample of 140 college instructors and 145 college students (Study 1) as well as to ChatGPT itself (Study 2). The assessment was administered in an online survey and included an AI Identification Test which presented pairs of essays: In each case, one was written by a college student during an in-class exam and the other was generated by ChatGPT. Analyses with binomial tests and linear modeling suggested that the AI Identification Test was challenging: On average, instructors were able to guess which one was written by ChatGPT only 70% of the time (compared to 60% for students and 63% for ChatGPT). Neither experience with ChatGPT nor content expertise improved performance. Even people who were confident in their abilities struggled with the test. ChatGPT responses reflected much more confidence than human participants despite performing just as poorly. ChatGPT responses on an AI Attitude Assessment measure were similar to those reported by instructors and students except that ChatGPT rated several AI uses more favorably and indicated substantially more optimism about the positive educational benefits of AI. The findings highlight challenges for scholars and practitioners to consider as they navigate the integration of AI in education.

Introduction

Artificial intelligence (AI) is becoming ubiquitous in daily life. It has the potential to help solve many of society’s most complex and important problems, such as improving the detection, diagnosis, and treatment of chronic disease (Jiang et al. 2017 ), and informing public policy regarding climate change (Biswas 2023 ). However, AI also comes with potential pitfalls, such as threatening widely-held values like fairness and the right to privacy (Borenstein and Howard 2021 ; Weidinger et al. 2021 ; Zhuo et al. 2023 ). Although the specific ways in which the promises and pitfalls of AI will play out remain to be seen, it is clear that AI will change human societies in significant ways.

In late November of 2022, the generative large-language model ChatGPT (GPT-3, Brown et al. 2020 ) was released to the public. It soon became clear that talk about the consequences of AI was much more than futuristic speculation, and that we are now watching its consequences unfold before our eyes in real time. This is not only because the technology is now easily accessible to the general public, but also because of its advanced capacities, including a sophisticated ability to use context to generate appropriate responses to a wide range of prompts (Devlin et al. 2018 ; Gilson et al. 2022 ; Susnjak 2022 ; Vaswani et al. 2017 ).

How AI-generated content poses challenges for educational assessment

Since AI technologies like ChatGPT can flexibly produce human-like content, this raises the possibility that students may use the technology to complete their academic work for them, and that instructors may not be able to tell when their students turn in such AI-assisted work. This possibility has led some people to argue that we may be seeing the end of essay assignments in education (Mitchell 2022 ; Stokel-Walker 2022 ). Even some advocates of AI in the classroom have expressed concerns about its potential for undermining academic integrity (Cotton et al. 2023 ; Eke 2023 ). For example, as Kasneci et al. ( 2023 ) noted, the technology might “amplify laziness and counteract the learners’ interest to conduct their own investigations and come to their own conclusions or solutions” (p. 5). In response to these concerns, some educational institutions have already tried to ban ChatGPT (Johnson, 2023; Rosenzweig-Ziff 2023 ; Schulten, 2023).

These discussions are founded on extensive scholarship on academic integrity, which is fundamental to ethics in higher education (Bertram Gallant 2011 ; Bretag 2016 ; Rettinger and Bertram Gallant 2022 ). Challenges to academic integrity are not new: Students have long found and used tools to circumvent the work their teachers assign to them, and research on these behaviors spans nearly a century (Cizek 1999 ; Hartshorne and May 1928 ; McCabe et al. 2012 ). One recent example is contract cheating, where students pay other people to do their schoolwork for them, such as writing an essay (Bretag et al. 2019 ; Curtis and Clare 2017 ). While very few students (less than 5% by most estimates) tend to use contract cheating, AI has the potential to make cheating more accessible and affordable and it raises many new questions about the relationship between technology, academic integrity, and ethics in education (Cotton et al. 2023 ; Eke 2023 ; Susnjak 2022 ).

To date, there is very little empirical evidence to inform debates about the likely impact of ChatGPT on education or to inform what best practices might look like regarding use of the technology (Dwivedi et al. 2023 ; Lo 2023 ). The primary goal of the present research is to provide such evidence with reference to college-essay writing. One critical question is whether college students can pass off work generated by ChatGPT as their own. If so, large numbers of students may simply paste in ChatGPT responses to essays they are asked to write without the kind of active engagement with the material that leads to deep learning (Chi and Wylie 2014 ). This problem is likely to be exacerbated when students brag about doing this and earning high scores, which can encourage other students to follow suit. Indeed, this kind of bragging motivated the present work (when the last author learned about a college student bragging about using ChatGPT to write all of her final papers in her college classes and getting A’s on all of them).

In support of the possibility that instructors may have trouble identifying ChatGPT-generated test, some previous research suggests that ChatGPT is capable of successfully generating college- or graduate-school level writing. Yeadon et al. ( 2023 ) used AI to generate responses to essays based on a set of prompts used in a physics module that was in current use and asked graders to evaluate the responses. An example prompt they used was: “How did natural philosophers’ understanding of electricity change during the 18th and 19th centuries?” The researchers found that the AI-generated responses earned scores comparable to most students taking the module and concluded that current AI large-language models pose “a significant threat to the fidelity of short-form essays as an assessment method in Physics courses.” Terwiesch ( 2023 ) found that ChatGPT scored at a B or B- level on the final exam of Operations Management in an MBA program, and Katz et al. ( 2023 ) found that ChatGPT has the necessary legal knowledge, reading comprehension, and writing ability to pass the Bar exam in nearly all jurisdictions in the United States. This evidence makes it very clear that ChatGPT can generate well-written content in response to a wide range of prompts.

Distinguishing AI-generated from human-generated work

What is still not clear is how good instructors are at distinguishing between ChatGPT-generated writing and writing generated by students at the college level given that it is at least possible that ChatGPT-generated writing could be both high quality and be distinctly different than anything people generally write (e.g., because ChatGPT-generated writing has particular features). To our knowledge, this question has not yet been addressed, but a few prior studies have examined related questions. In the first such study, Gunser et al. ( 2021 ) used writing generated by a ChatGPT predecessor, GPT-2 (see Radford et al. 2019 ). They tested nine participants with a professional background in literature. These participants both generated content (i.e., wrote continuations after receiving the first few lines of unfamiliar poems or stories), and determined how other writing was generated. Gunser et al. ( 2021 ) found that misclassifications were relatively common. For example, in 18% of cases participants judged AI-assisted writing to be human-generated. This suggests that even AI technology that is substantially less advanced than ChatGPT is capable of generating writing that is hard to distinguish from human writing.

Köbis and Mossink ( 2021 ) also examined participants’ ability to distinguish between poetry written by GPT-2 and humans. Their participants were given pairs of poems. They were told that one poem in each pair was written by a human and the other was written by GPT-2, and they were asked to determine which was which. In one of their studies, the human-written poems were written by professional poets. The researchers generated multiple poems in response to prompts, and they found that when the comparison GPT-2 poems were ones they selected as the best among the set generated by the AI, participants could not distinguish between the GPT-2 and human writing. However, when researchers randomly selected poems generated by GPT-2, participants were better than chance at detecting which ones were generated by the AI.

In a third relevant study, Waltzer et al. ( 2023a ) tested high school teachers and students. All participants were presented with pairs of English essays, such as one on why literature matters. In each case one essay was written by a high school student and the other was generated by ChatGPT, and participants were asked which essay in each pair had been generated by ChatGPT. Waltzer et al. ( 2023a ) found that teachers only got it right 70% of the time, and that students’ performance was even worse (62%). They also found that well-written essays were harder to distinguish from those generated by ChatGPT than poorly written ones. However, it is unclear the extent to which these findings are specific to the high school context. It should also be noted that there were no clear right or wrong answers in the types of essays used in Waltzer et al. ( 2023a ), so the results may not generalize to essays that ask for factual information based on specific class content.

AI detection skills, attitudes, and perceptions

If college instructors find it challenging to distinguish between writing generated by ChatGPT and college students, it raises the question of what factors might be correlated with the ability to perform this discrimination. One possible correlate is experience with ChatGPT, which may allow people to recognize patterns in the writing style it generates, such as a tendency to formally summarize previous content. Content-relevant knowledge is another possible predictor. Individuals with such knowledge will presumably be better at spotting errors in answers, and it is plausible that instructors know that AI tools are likely to get content of introductory-level college courses correct and assume that essays that contain errors are written by students.

Another possible predictor is confidence about one’s ability to discriminate on the task or on particular items of the task (Erickson and Heit 2015 ; Fischer & Budesco, 2005 ; Wixted and Wells 2017 ). In other words, are AI discriminations made with a high degree of confidence more likely to be accurate than low-confidence discriminations? In some cases, confidence judgments are a good predictor of accuracy, such as on many perceptual decision tasks (e.g., detecting contrast between light and dark bars, Fleming et al. 2010 ). However, in other cases correlations between confidence and accuracy are small or non-existent, such as on some deductive reasoning tasks (e.g., Shynkaruk and Thompson 2006 ). Links to confidence can also depend on how confidence is measured: Gigerenzer et al. ( 1991 ) found overconfidence on individual items, but good calibration when participants were asked how many items they got right after seeing many items.

In addition to the importance of gathering empirical data on the extent to which instructors can distinguish ChatGPT from college student writing, it is important to examine how college instructors and students perceive AI in education given that such attitudes may affect behavior (Al Darayseh 2023 ; Chocarro et al. 2023 ; Joo et al. 2018 ; Tlili et al. 2023 ). For example, instructors may only try to develop precautions to prevent AI cheating if they view this as a significant concern. Similarly, students’ confusion about what counts as cheating can play an important role in their cheating decisions (Waltzer and Dahl 2023 ; Waltzer et al. 2023b ).

The present research

In the present research we developed an assessment that we gave to college instructors and students (Study 1) and ChatGPT itself (Study 2). The central feature of the assessment was an AI Identification Test , which included 6 pairs of essays. In each case (as was indicated in the instructions), one essay in each pair was generated by ChatGPT and the other was written by college students. The task was to determine which essay was written by the chatbot. The essay pairs were drawn from larger pools of essays of each type.

The student essays were written by students as part of a graded exam in a psychology class, and the ChatGPT essays were generated in response to the same essay prompts. Of interest was overall performance and to assess potential correlates of performance. Performance of college instructors was of particular interest because they are the ones typically responsible for grading, but performance of students and ChatGPT were also of interest for comparison. ChatGPT was also of interest given anecdotal evidence that college instructors are asking ChatGPT to tell them whether pieces of work were AI-generated. For example, the academic integrity office at one major university sent out an announcement asking instructors not to report students for cheating if their evidence was solely based on using ChatGPT to detect AI-generated writing (UCSD Academic Integrity Office, 2023 ).

We also administered an AI Attitude Assessment (Waltzer et al. 2023a ), which included questions about overall levels of optimism and pessimism about the use of AI in education, and the appropriateness of specific uses of AI in academic settings, such as a student submitting an edited version of a ChatGPT-generated essay for a writing assignment.

Study 1: College instructors and students

Participants were given an online assessment that included an AI Identification Test , an AI Attitude Assessment , and some demographic questions. The AI Identification Test was developed for the present research, as described below (see Materials and Procedure). The test involved presenting six pairs of essays, with the instructions to try to identify which one was written by ChatGPT in each case. Participants also rated their confidence before the task and after responding to each item, and reported how many they thought they got right at the end. The AI Attitude Assessment was drawn from Waltzer et al. ( 2023a ) to assess participants’ views of the use of AI in education.

Participants

For the testing phase of the project, we recruited 140 instructors who had taught or worked as a teaching assistant for classes at the college level (69 of them taught psychology and 63 taught other subjects such as philosophy, computer science, and history). We recruited instructors through personal connections and snowball sampling. Most of the instructors were women (59%), white (60%), and native English speakers (67%), and most of them taught at colleges in the United States (91%). We also recruited 145 undergraduate students ( M age = 20.90 years, 80% women, 52% Asian, 63% native English speakers) from a subject recruitment system in the psychology department at a large research university in the United States. All data collection took place between 3/15/2023 and 4/15/2023 and followed our pre-registration plan ( https://aspredicted.org/mk3a2.pdf ).

Materials and procedure

Developing the ai identification test.

To create the stimuli for the AI Identification Test, we first generated two prompts for the essays (Table  1 ). We chose these prompts in collaboration with an instructor to reflect real student assignments for a college psychology class.

Fifty undergraduate students hand-wrote both essays as part of a proctored exam in their psychology class on 1/30/2023. Research assistants transcribed the essays and removed essays from the pool that were not written in third-person or did not include the correct number of sentences. Three additional essays were excluded for being illegible, and another one was excluded for mentioning a specific location on campus. This led to 15 exclusions for the Phonemic Awareness prompt and 25 exclusions for the Studying Advice prompt. After applying these exclusions, we randomly selected 25 essays for each prompt to generate the 6 pairs given to each participant. To prepare the texts for use as stimuli, research assistants then used a word processor to correct obvious errors that could be corrected without major rewriting (e.g., punctuation, spelling, and capitalization).

All student essays were graded according to the class rubric on a scale from 0 to 10 by two individuals on the teaching team of the class: the course’s primary instructor and a graduate student teaching assistant. Grades were averaged together to create one combined grade for each essay (mean: 7.93, SD: 2.29, range: 2–10). Two of the authors also scored the student essays for writing quality on a scale from 0 to 100, including clarity, conciseness, and coherence (combined score mean: 82.83, SD : 7.53, range: 65–98). Materials for the study, including detailed scoring rubrics, are available at https://osf.io/2c54a/ .

The ChatGPT stimuli were prepared by entering the same prompts into ChatGPT ( https://chat.openai.com/ ) between 1/23/2023 and 1/25/2023, and re-generating the responses until there were 25 different essays for each prompt.

Testing Phase

In the participant testing phase, college instructors and students took the assessment, which lasted approximately 10 min. All participants began by indicating the name of their school and whether they were an instructor or a student, how familiar they were with ChatGPT (“Please rate how much experience you have with using ChatGPT”), and how confident they were that they would be able to distinguish between writing generated by ChatGPT and by college students. Then they were told they would get to see how well they score at the end, and they began the AI Identification Test.

The AI Identification Test consisted of six pairs of essays: three Phonemic Awareness pairs, and three Studying Advice pairs, in counterbalanced order. Each pair included one text generated by ChatGPT and one text generated by a college student, both drawn randomly from their respective pools of 25 possible essays. No essays were repeated for the same participant. Figure  1 illustrates what a text pair looked like in the survey.

Example pair of essays for the Phonemic Awareness prompt. Top: student essay. Bottom: ChatGPT essay

For each pair, participants selected the essay they thought was generated by ChatGPT and indicated how confident they were about their choice (slider from 0 = “not at all confident” to 100 = “extremely confident”). After all six pairs, participants estimated how well they did (“How many of the text pairs do you think you answered correctly?”).

After completing the AI Identification task, participants completed the AI Attitude Assessment concerning their views of ChatGPT in educational contexts (see Waltzer et al. 2023a ). On this assessment, participants first estimated what percent of college students in the United States would ask ChatGPT to write an essay for them and submit it. Next, they rated their concerns (“How concerned are you about ChatGPT having negative effects on education?”) and optimism (“How optimistic are you about ChatGPT having positive benefits for education?”) about the technology on a scale from 0 (“not at all”) to 100 (“extremely”). On the final part of the AI Attitude Assessment, they evaluated five different possible uses of ChatGPT in education (such as submitting an essay after asking ChatGPT to improve the vocabulary) on a scale from − 10 (“really bad”) to + 10 (“really good”).

Participants also rated the extent to which they already knew the subject matter (i.e., cognitive psychology and the science of learning), and were given optional open-ended text boxes to share any experiences from their classes or suggestions for instructors related to the use of ChatGPT, or to comment on any of the questions in the Attitude Assessment. Instructors were also asked whether they had ever taught a psychology class and to describe their teaching experience. At the end, all participants reported demographic information (e.g., age, gender). All prompts are available in the online supplementary materials ( https://osf.io/2c54a/ ).

Data Analysis

We descriptively summarized variables of interest (e.g., overall accuracy on the Identification Test). We used inferential tests to predict Identification Test accuracy from group (instructor or student), confidence, subject expertise, and familiarity with ChatGPT. We also predicted responses to the AI Attitude Assessment as a function of group (instructor or student). All data analysis was done using R Statistical Software (v4.3.2; R Core Team 2021 ).

Key hypotheses were tested using Welch’s two-sample t-tests for group comparisons, linear regression models with F-tests for other predictors of accuracy, and Generalized Linear Mixed Models (GLMMs, Hox 2010 ) with likelihood ratio tests for within-subjects trial-by-trial analyses. GLMMs used random intercepts for participants and predicted trial performance (correct or incorrect) using trial confidence and essay quality as fixed effects.

Overall performance on AI identification test

Instructors correctly identified which essay was written by the chatbot 70% of the time, which was above chance (chance: 50%, binomial test: p  < .001, 95% CI: [66%, 73%]). Students also performed above chance, with an average score of 60% (binomial test: p  < .001, 95% CI: [57%, 64%]). Instructors performed significantly better than students (Welch’s two-sample t -test: t [283] = 3.30, p  = .001).

Familiarity With subject matter

Participants rated how much previous knowledge they had in the essay subject matter (i.e., cognitive psychology and the science of learning). Linear regression models with F- tests indicated that familiarity with the subject did not predict instructors’ or students’ accuracy, F s(1) < 0.49, p s > .486. Psychology instructors did not perform any better than non-psychology instructors, t (130) = 0.18, p  = .860.

Familiarity with ChatGPT

Nearly all participants (94%) said they had heard of ChatGPT before taking the survey, and most instructors (62%) and about half of students (50%) said they had used ChatGPT before. For both groups, participants who used ChatGPT did not perform any better than those who never used it before, F s(1) < 0.77, p s > .383. Instructors’ and students’ experience with ChatGPT (from 0 = not at all experienced to 100 = extremely experienced) also did not predict their performance, F s(1) < 0.77, p s > .383.

Confidence and estimated score

Before they began the Identification Test, both instructors and students expressed low confidence in their abilities to identify the chatbot ( M  = 34.60 on a scale from 0 = not at all confident to 100 = extremely confident). Their confidence was significantly below the midpoint of the scale (midpoint: 50), one-sample t -test: t (282) = 11.46, p  < .001, 95% CI: [31.95, 37.24]. Confidence ratings that were done before the AI Identification test did not predict performance for either group, Pearson’s r s < .12, p s > .171.

Right after they completed the Identification Test, participants guessed how many text pairs they got right. Both instructors and students significantly underestimated their performance by about 15%, 95% CI: [11%, 18%], t (279) = -8.42, p  < .001. Instructors’ estimated scores were positively correlated with their actual scores, Pearson’s r  = .20, t (135) = 2.42, p  = .017. Students’ estimated scores were not related to their actual scores, r  = .03, p  = .731.

Trial-by-trial performance on AI identification test

Participants’ confidence ratings on individual trials were counted as high if they fell above the midpoint (> 50 on a scale from 0 = not at all confident to 100 = extremely confident). For these within-subjects trial-by-trial analyses, we used Generalized Linear Mixed Models (GLMMs, Hox 2010 ) with random intercepts for participants and likelihood ratio tests (difference score reported as D ). Both instructors and students performed better on trials in which they expressed high confidence (instructors: 73%, students: 63%) compared to low confidence (instructors: 65%, students: 56%), D s(1) > 4.59, p s < .032.

Student essay quality

We used two measures to capture the quality of each student-written essay: its assigned grade from 0 to 10 based on the class rubric, and its writing quality score from 0 to 100. Assigned grade was weakly related to instructors’ accuracy, but not to students’ accuracy. The text pairs that instructors got right tended to include student essays that earned slightly lower grades ( M  = 7.89, SD  = 2.22) compared to those they got wrong ( M  = 8.17, SD  = 2.16), D (1) = 3.86, p  = .050. There was no difference for students, D (1) = 2.84, p  = .092. Writing quality score did not differ significantly between correct and incorrect trials for either group, D (1) = 2.12, p  = .146.

AI attitude assessment

Concerns and hopes about chatgpt.

Both instructors and students expressed intermediate levels of concern and optimism. Specifically, on a scale from 0 (“not at all”) to 100 (“extremely”), participants expressed intermediate concern about ChatGPT having negative effects on education ( M instructors = 59.82, M students = 55.97) and intermediate optimism about it having positive benefits ( M instructors = 49.86, M students = 54.08). Attitudes did not differ between instructors and students, t s < 1.43, p s > .154. Participants estimated that just over half of college students (instructors: 57%, students: 54%) would use ChatGPT to write an essay for them and submit it. These estimates also did not differ by group, t (278) = 0.90, p  = .370.

Evaluations of ChatGPT uses

Participants evaluated five different uses of ChatGPT in educational settings on a scale from − 10 (“really bad”) to + 10 (“really good”). Both instructors and students rated it very bad for someone to ask ChatGPT to write an essay for them and submit the direct output, but instructors rated it significantly more negatively (instructors: -8.95, students: -7.74), t (280) = 3.59, p  < .001. Attitudes did not differ between groups for any of the other scenarios (Table  2 ), t s < 1.31, p s > .130.

Exploratory analysis of demographic factors

We also conducted exploratory analyses looking at ChatGPT use and attitudes among different demographic groups (gender, race, and native English speakers). We combined instructors and students because their responses to the Attitude Assessment did not differ. In these exploratory analyses, we found that participants who were not native English speakers were more likely to report using ChatGPT and to view it more positively. Specifically, 69% of non-native English speakers had used ChatGPT before, versus 48% of native English speakers, D (1) = 12.00, p  < .001. Regardless of native language, the more experience someone had with ChatGPT, the more optimism they reported, F (1) = 18.71, p  < .001, r  = .37). Non-native speakers rated the scenario where a student writes an essay and asks ChatGPT to improve its vocabulary slightly positively (1.19) whereas native English speakers rated it slightly negatively (-1.43), F (1) = 11.00, p  = .001. Asian participants expressed higher optimism ( M  = 59.14) than non-Asian participants ( M  = 47.29), F (1) = 10.05, p  = .002. We found no other demographic differences.

Study 2: ChatGPT

Study 1 provided data on college instructors’ and students’ ability to recognize ChatGPT-generated writing and about their views of the technology. In Study 2, of primary interest was whether ChatGPT itself might perform better at identifying ChatGPT-generated writing. Indeed, the authors have heard discussions of this as a possible solution to recognize AI-generated writing. We addressed this question by repeatedly asking ChatGPT to act as a participant in the AI Identification Task. While doing so, we administered the rest of the assessment given to participants in Study 1. This included our AI Attitude Assessment, which allowed us to examine the extent to which ChatGPT produced attitude responses that were similar to those of the participants in Study 1.

Participants, materials, and procedures

There were no human participants for Study 2. We collected 40 survey responses from ChatGPT, each run in a separate session on the platform ( https://chat.openai.com/ ) between 5/4/2023 and 5/15/2023.

Two research assistants were trained on how to run the survey in the ChatGPT online interface. All prompts from the Study 1 survey were used, with minor modifications to suit the chat format. For example, slider questions were explained in the prompt, so instead of “How confident are you about this answer?” the prompt was “How confident are you about this answer from 0 (not at all confident) to 100 (extremely confident)?”. In pilot testing, we found that ChatGPT sometimes failed to answer the question (e.g., by not providing a number), so we prepared a second prompt for every question that the researcher used whenever the first prompt was not answered (e.g., “Please answer the above question with one number between 0 to 100.”). If ChatGPT still failed on the second prompt, the researcher marked it as a non-response and moved on to the next question in the survey.

Data analysis

Like Study 1, all analyses were done in R Statistical Software (R Core Team 2021 ). Key analyses first used linear regression models and F -tests to compare all three groups (instructors, students, ChatGPT). When these omnibus tests were significant, we followed up with post-hoc pairwise comparisons using Tukey’s method.

AI identification test

Overall accuracy.

ChatGPT generated correct responses on 63% of trials in the AI Identification Test, which was significantly above chance, binomial test p  < .001, 95% CI: [57%, 69%]. Pairwise comparisons found that this performance by ChatGPT was not any different from that of instructors or students, t s(322) < 1.50, p s > .292.

Confidence and estimated performance

Unlike the human participants, ChatGPT produced responses with very high confidence before the task generally ( m  = 71.38, median  = 70) and during individual trials specifically ( m  = 89.82, median  = 95). General confidence ratings before the test were significantly higher from ChatGPT than from the humans (instructors: 34.35, students: 34.83), t s(320) > 9.47, p s < .001. But, as with the human participants, this confidence did not predict performance on the subsequent Identification task, F (1) = 0.94, p  = .339. And like the human participants, ChatGPT’s reported confidence on individual trials did predict performance: ChatGPT produced higher confidence ratings on correct trials ( m  = 91.38) than incorrect trials ( m  = 87.33), D (1) = 8.74, p  = .003.

ChatGPT also produced responses indicating high confidence after the task, typically estimating that it got all six text pairs right ( M  = 91%, median  = 100%). It overestimated performance by about 28%, and a paired t -test confirmed that ChatGPT’s estimated performance was significantly higher than its actual performance, t (36) = 9.66, p  < .001. As inflated as it was, estimated performance still had a small positive correlation with actual performance, Pearson’s r  = .35, t (35) = 2.21, p  = .034.

Essay quality

The quality of the student essays as indexed by their grade and writing quality score did not significantly predict performance, D s < 1.97, p s > .161.

AI attitude Assessment

Concerns and hopes.

ChatGPT usually failed to answer the question, “How concerned are you about ChatGPT having negative effects on education?” from 0 (not at all concerned) to 100 (extremely concerned). Across the 40% of cases where ChatGPT successfully produced an answer, the average concern rating was 64.38, which did not differ significantly from instructors’ or students’ responses, F (2, 294) = 1.20, p  = .304. ChatGPT produced answers much more often for the question, “How optimistic are you about ChatGPT having positive benefits for education?”, answering 88% of the time. The average optimism rating produced by ChatGPT was 73.24, which was significantly higher than that of instructors (49.86) and students (54.08), t s > 4.33, p s < .001. ChatGPT only answered 55% of the time for the question about how many students would use ChatGPT to write an essay for them and submit it, typically generating explanations about its inability to predict human behavior and the fact that it does not condone cheating when it did not give an estimate. When it did provide an estimate ( m  = 10%), it was vastly lower than that of instructors (57%) and students (54%), t s > 7.84, p s < .001.

Evaluation of ChatGPT uses

ChatGPT produced ratings of the ChatGPT use scenarios that on average were rank-ordered the same as the human ratings, with direct copying rated the most negatively and generating practice problems rated the most positively (see Fig.  2 ).

Average ratings of ChatGPT uses, from − 10 = really bad to + 10 = really good. Human responses included for comparison (instructors in dark gray and students in light gray bars)

Compared to humans’ ratings, ratings produced by ChatGPT were significantly more positive in most scenarios, t s > 3.09, p s < .006, with two exceptions. There was no significant difference between groups in the “format” scenario (using ChatGPT to format an essay in another style such as APA), F (2,318) = 2.46, p  = .087. And for the “direct” scenario, ChatGPT tended to rate direct copying more negatively than students ( t [319] = 4.08, p  < .001) but not instructors (t[319] = 1.57, p  = .261), perhaps because ratings from ChatGPT and instructors were already so close to the most negative possible rating.

In 1950, Alan Turing said he hoped that one day machines would be able to compete with people in all intellectual fields (Turing 1950 ; see Köbis and Mossink 2021 ). Today, by many measures, the large-language model, ChatGPT, appears to be getting close to achieving this end. In doing so, it is raising questions about the impact this AI and its successors will have on individuals and the institutions that shape the societies in which we live. One important set of questions revolves around its use in higher education, which is the focus of the present research.

Empirical contributions

Detecting ai-generated text.

Our central research question focused on whether instructors can identify ChatGPT-generated writing, since an inability to do so could threaten the ability of institutions of higher learning to promote learning and assess competence. To address this question, we developed an AI Identification Test in which the goal was to try to distinguish between psychology essays written by college students on exams versus essays generated by ChatGPT in response to the same prompts. We found that although college instructors performed substantially better than chance, they still found the assessment to be challenging, scoring an average of only 70%. This relatively poor performance suggests that college instructors have substantial difficulty detecting ChatGPT-generated writing. Interestingly, this performance by the college instructors was the same average performance as Waltzer et al. ( 2023a ) observed among high school instructors (70%) on a similar test involving English literature essays, suggesting the results are generalizable across the student populations and essay types. We also gave the assessment to college students (Study 1) and to ChatGPT (Study 2) for comparison. On average, students (60%) and ChatGPT (63%) performed even worse than instructors, although the difference only reached statistical significance when comparing students and instructors.

We found that instructors and students who went into the study believing they would be very good at distinguishing between essays written by college students versus essays generated by ChatGPT were in fact no better at doing so than participants who lacked such confidence. However, we did find that item-level confidence did predict performance: when participants rated their confidence after each specific pair (i.e., “How confident are you about this answer?”), they did perform significantly better on items they reported higher confidence on. These same patterns were observed when analyzing the confidence ratings from ChatGPT, though ChatGPT produced much higher confidence ratings than instructors or students, reporting overconfidence while instructors and students reported underconfidence.

Attitudes toward AI in education

Instructors and students both thought it was very bad for students to turn in an assignment generated by ChatGPT as their own, and these ratings were especially negative for instructors. Overall, instructors and students looked similar to one another in their evaluations of other uses of ChatGPT in education. For example, both rated submitting an edited version of a ChatGPT-generated essay in a class as bad, but less bad than submitting an unedited version. Interestingly, the rank orderings in evaluations of ChatGPT uses were the same when the responses were generated by ChatGPT as when they were generated by instructors or students. However, ChatGPT produced more favorable ratings of several uses compared to instructors and students (e.g., using the AI tool to enhance the vocabulary in an essay). Overall, both instructors and students reported being about as optimistic as they were concerned about AI in education. Interestingly, ChatGPT produced responses indicative of much more optimism than both human groups of participants.

Many instructors commented on the challenges ChatGPT poses for educators. One noted that “… ChatGPT makes it harder for us to rely on homework assignments to help students to learn. It will also likely be much harder to rely on grading to signal how likely it is for a student to be good at a skill or how creative they are.” Some suggested possible solutions such as coupling writing with oral exams. Others suggested that they would appreciate guidance. For example, one said, “I have told students not to use it, but I feel like I should not be like that. I think some of my reluctance to allow usage comes from not having good guidelines.”

And like the instructors, some students also suggested that they want guidance, such as knowing whether using ChatGPT to convert a document to MLA format would count as a violation of academic integrity. They also highlighted many of the same problems as instructors and noted beneficial ways students are finding to use it. One student noted that, “I think ChatGPT definitely has the potential to be abused in an educational setting, but I think at its core it can be a very useful tool for students. For example, I’ve heard of one student giving ChatGPT a rubric for an assignment and asking it to grade their own essay based on the rubric in order to improve their writing on their own.”

Theoretical contributions and practical implications

Our findings underscore the fact that AI chatbots have the potential to produce confident-sounding responses that are misleading (Chen et al. 2023 ; Goodwins 2022 ; Salvi et al. 2024 ). Interestingly, the underconfidence reported by instructors and students stands in contrast to some findings that people often expressed overconfidence in their abilities to detect AI (e.g., deepfake videos, Köbis et al. 2021 ). Although general confidence before the task did not predict performance, specific confidence on each item of the task did predict performance. Taken together, our findings are consistent with other work suggesting confidence effects are context-dependent and can differ depending on whether they are assessed at the item level or more generally (Gigerenzer et al. 1991 ).

The fact that college instructors have substantial difficulty differentiating between ChatGPT-generated writing and the writing of college students provides evidence that ChatGPT poses a significant threat to academic integrity. Ignoring this threat is also likely to undermine central aspects of the mission of higher education in ways that undermine the value of assessments and disincentivize the kinds of cognitive engagement that promote deep learning (Chi and Wylie 2014 ). We are skeptical of answers that point to the use of AI detection tools to address this issue given that they will always be imperfect and false accusations have potential to cause serious harm (Dalalah and Dalalah 2023 ; Fowler 2023 ; Svrluga, 2023 ). Rather, we think that the solution will have to involve developing and disseminating best practices regarding creating assessments and incentivizing cognitive engagement in ways that help students learn to use AI as problem-solving tools.

Limitations and future directions

Why instructors perform better than students at detecting AI-generated text is unclear. Although we did not find any effect of content-relevant expertise, it still may be the case that experience with evaluating student writing matters, and instructors presumably have more such experience. For example, one non-psychology instructor who got 100% of the pairs correct said, “Experience with grading lower division undergraduate papers indicates that students do not always fully answer the prompt, if the example text did not appear to meet all of the requirements of the prompt or did not provide sufficient information, I tended to assume an actual student wrote it.” To address this possibility, it will be important to compare adults who do have teaching experience with those who do not.

It is somewhat surprising that experience with ChatGPT did not affect the performance of instructors or students on the AI Identification Test. One contributing factor may be that people pick up on some false heuristics from reading the text it generates (see Jakesch et al. 2023 ). It is possible that giving people practice at distinguishing the different forms of writing with feedback could lead to better performance.

Why confidence was predictive of accuracy at the item level is still not clear. One possibility is that there are some specific and valid cues many people were using. One likely cue is grammar. We revised grammar errors in student essays that were picked up by a standard spell checker in which the corrections were obvious. However, we left ungrammatical writing that didn’t have obvious corrections (e.g., “That is being said, to be able to understand the concepts and materials being learned, and be able to produce comprehension.“). Many instructors noted that they used grammatical errors as cues that writing was generated by students. As one instructor remarked, “Undergraduates often have slight errors in grammar and tense or plurality agreement, and I have heard the chat bot works very well as an editor.” Similarly, another noted, “I looked for more complete, grammatical sentences. In my experience, Chat-GPT doesn’t use fragment sentences and is grammatically correct. Students are more likely to use incomplete sentences or have grammatical errors.” This raises methodological questions about what is the best comparison between AI and human writing. For example, it is unclear which grammatical mistakes should be corrected in student writing. Also of interest will be to examine the detectability of writing that is generated by AI and later edited by students, since many students will undoubtedly use AI in this way to complete their course assignments.

We also found that student-written essays that earned higher grades (based on the scoring rubric for their class exam) were harder for instructors to differentiate from ChatGPT writing. This does not appear to be a simple effect of writing quality given that a separate measure of writing quality that did not account for content accuracy was not predictive. According to the class instructor, the higher-scoring essays tended to include more specific details, and this might have been what made them less distinguishable. Relatedly, it may be that the higher-scoring essays were harder to distinguish because they appeared to be generated by more competent-sounding writers, and it was clear from instructor comments that they generally viewed ChatGPT as highly competent.

The results of the present research validate concerns that have been raised about college instructors having difficulty distinguishing writing generated by ChatGPT from the writing of their students, and document that this is also true when students try to detect writing generated by ChatGPT. The results indicate that this issue is particularly pronounced when instructors evaluate high-scoring student essays. The results also indicate that ChatGPT itself performs no better than instructors at detecting ChatGPT-generated writing even though ChatGPT-reported confidence is much higher. These findings highlight the importance of examining current teaching and assessment practices and the potential challenges AI chatbots pose for academic integrity and ethics in education (Cotton et al. 2023 ; Eke 2023 ; Susnjak 2022 ). Further, the results show that both instructors and students have a mixture of apprehension and optimism about the use of AI in education, and that many are looking for guidance about how to ethically use it in ways that promote learning. Taken together, our findings underscore some of the challenges that need to be carefully navigated in order to minimize the risks and maximize the benefits of AI in education.

Data availability

Supplementary materials, including data, analysis, and survey items, are available on the Open Science Framework: https://osf.io/2c54a/ .

Abbreviations

Artificial Intelligence

Confidence Interval

Generalized Linear Mixed Model

Generative Pre-trained Transformer

Standard Deviation

Al Darayseh A (2023) Acceptance of artificial intelligence in teaching science: Science teachers’ perspective. Computers Education: Artif Intell 4:100132. https://doi.org/10.1016/j.caeai.2023.100132

Article   Google Scholar  

Bertram Gallant T (2011) Creating the ethical academy. Routledge, New York

Book   Google Scholar  

Biswas SS (2023) Potential use of Chat GPT in global warming. Ann Biomed Eng 51:1126–1127. https://doi.org/10.1007/s10439-023-03171-8

Borenstein J, Howard A (2021) Emerging challenges in AI and the need for AI ethics education. AI Ethics 1:61–65. https://doi.org/10.1007/s43681-020-00002-7

Bretag T (ed) (2016) Handbook of academic integrity. Springer

Bretag T, Harper R, Burton M, Ellis C, Newton P, Rozenberg P, van Haeringen K (2019) Contract cheating: a survey of Australian university students. Stud High Educ 44(11):1837–1856. https://doi.org/10.1080/03075079.2018.1462788

Brown TB, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler D, Wu J, Winter C, Amodei D (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33. https://doi.org/10.48550/arxiv.2005.14165

Chen Y, Andiappan M, Jenkin T, Ovchinnikov A (2023) A manager and an AI walk into a bar: does ChatGPT make biased decisions like we do? SSRN 4380365. https://doi.org/10.2139/ssrn.4380365

Chi MTH, Wylie R (2014) The ICAP framework: linking cognitive engagement to active learning outcomes. Educational Psychol 49(4):219–243. https://doi.org/10.1080/00461520.2014.965823

Chocarro R, Cortiñas M, Marcos-Matás G (2023) Teachers’ attitudes towards chatbots in education: a technology acceptance model approach considering the effect of social language, bot proactiveness, and users’ characteristics. Educational Stud 49(2):295–313. https://doi.org/10.1080/03055698.2020.1850426

Cizek GJ (1999) Cheating on tests: how to do it, detect it, and prevent it. Routledge

R Core Team (2021) R: A language and environment for statistical computing R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/

Cotton DRE, Cotton PA, Shipway JR (2023) Chatting and cheating: ensuring academic integrity in the era of ChatGPT. Innovations Educ Teach Int. https://doi.org/10.1080/14703297.2023.2190148

Curtis GJ, Clare J (2017) How prevalent is contract cheating and to what extent are students repeat offenders? J Acad Ethics 15:115–124. https://doi.org/10.1007/s10805-017-9278-x

Dalalah D, Dalalah OMA (2023) The false positives and false negatives of generative AI detection tools in education and academic research: the case of ChatGPT. Int J Manage Educ 21(2):100822. https://doi.org/10.1016/j.ijme.2023.100822

Devlin J, Chang M-W, Lee K, Toutanova K (2018) BERT: pre-training of deep bidirectional transformers for language understanding. ArXiv. https://doi.org/10.48550/arxiv.1810.04805

Dwivedi YK, Kshetri N, Hughes L, Slade EL, Jeyaraj A, Kar AK, Baabdullah AM, Koohang A, Raghavan V, Ahuja M, Albanna H, Albashrawi MA, Al-Busaidi AS, Balakrishnan J, Barlette Y, Basu S, Bose I, Brooks L, Buhalis D, Wright R (2023) So what if ChatGPT wrote it? Multidisciplinary perspectives on opportunities, challenges, and implications of generative conversational AI for research, practice, and policy. Int J Inf Manag 71:102642. https://doi.org/10.1016/j.ijinfomgt.2023.102642

Eke DO (2023) ChatGPT and the rise of generative AI: threat to academic integrity? J Responsible Technol 13:100060. https://doi.org/10.1016/j.jrt.2023.100060

Erickson S, Heit E (2015) Metacognition and confidence: comparing math to other academic subjects. Front Psychol 6:742. https://doi.org/10.3389/fpsyg.2015.00742

Fischer I, Budescu DV (2005) When do those who know more also know more about how much they know? The development of confidence and performance in categorical decision tasks. Organ Behav Hum Decis Process 98:39–53. https://doi.org/10.1016/j.obhdp.2005.04.003

Fleming SM, Weil RS, Nagy Z, Dolan RJ, Rees G (2010) Relating introspective accuracy to individual differences in brain structure. Science 329:1541–1543. https://doi.org/10.1126/science.1191883

Fowler GA (2023), April 14 We tested a new ChatGPT-detector for teachers. It flagged an innocent student. The Washington Post . https://www.washingtonpost.com/technology/2023/04/01/chatgpt-cheating-detection-turnitin/

Gigerenzer G (1991) From tools to theories: a heuristic of discovery in cognitive psychology. Psychol Rev 98:254. https://doi.org/10.1037/0033-295X.98.2.254

Gigerenzer G, Hoffrage U, Kleinbölting H (1991) Probabilistic mental models: a brunswikian theory of confidence. Psychol Rev 98(4):506–528. https://doi.org/10.1037/0033-295X.98.4.506

Gilson A, Safranek C, Huang T, Socrates V, Chi L, Taylor RA, Chartash D (2022) How well does ChatGPT do when taking the medical licensing exams? The implications of large language models for medical education and knowledge assessment. MedRxiv. https://doi.org/10.1101/2022.12.23.22283901

Goodwins T (2022), December 12 ChatGPT has mastered the confidence trick, and that’s a terrible look for AI. The Register . https://www.theregister.com/2022/12/12/chatgpt_has_mastered_the_confidence/

Gunser VE, Gottschling S, Brucker B, Richter S, Gerjets P (2021) Can users distinguish narrative texts written by an artificial intelligence writing tool from purely human text? In C. Stephanidis, M. Antona, & S. Ntoa (Eds.), HCI International 2021 , Communications in Computer and Information Science , (Vol. 1419, pp. 520–527). Springer. https://doi.org/10.1007/978-3-030-78635-9_67

Hartshorne H, May MA (1928) Studies in the nature of character: vol. I. studies in deceit. Macmillan, New York

Google Scholar  

Hox J (2010) Multilevel analysis: techniques and applications, 2nd edn. Routledge, New York, NY

Jakesch M, Hancock JT, Naaman M (2023) Human heuristics for AI-generated language are flawed. Proceedings of the National Academy of Sciences, 120 (11), e2208839120. https://doi.org/10.1073/pnas.2208839120

Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, Wang Y, Dong Q, Shen H, Wang Y (2017) Artificial intelligence in healthcare: past, present and future. Stroke Vascular Neurol 2(4):230–243. https://doi.org/10.1136/svn-2017-000101

Joo YJ, Park S, Lim E (2018) Factors influencing preservice teachers’ intention to use technology: TPACK, teacher self-efficacy, and technology acceptance model. J Educational Technol Soc 21(3):48–59. https://www.jstor.org/stable/26458506

Kasneci E, Seßler K, Küchemann S, Bannert M, Dementieva D, Fischer F, Kasneci G (2023) ChatGPT for good? On opportunities and challenges of large language models for education. Learn Individual Differences 103:102274. https://doi.org/10.1016/j.lindif.2023.102274

Katz DM, Bommarito MJ, Gao S, Arredondo P (2023) GPT-4 passes the bar exam. SSRN Electron J. https://doi.org/10.2139/ssrn.4389233

Köbis N, Mossink LD (2021) Artificial intelligence versus Maya Angelou: experimental evidence that people cannot differentiate AI-generated from human-written poetry. Comput Hum Behav 114:106553. https://doi.org/10.1016/j.chb.2020.106553

Köbis NC, Doležalová B, Soraperra I (2021) Fooled twice: people cannot detect deepfakes but think they can. iScience 24(11):103364. https://doi.org/10.1016/j.isci.2021.103364

Lo CK (2023) What is the impact of ChatGPT on education? A rapid review of the literature. Educ Sci 13(4):410. https://doi.org/10.3390/educsci13040410

McCabe DL, Butterfield KD, Treviño LK (2012) Cheating in college: why students do it and what educators can do about it. Johns Hopkins, Baltimore, MD

Mitchell A (2022) December 26). Professor catches student cheating with ChatGPT: ‘I feel abject terror’. New York Post. https://nypost.com/2022/12/26/students-using-chatgpt-to-cheat-professor-warns

Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I (2019) Language models are unsupervised multitask learners. OpenAI https://openai.com/research/better-language-models

Rettinger DA, Bertram Gallant T (eds) (2022) Cheating academic integrity: lessons from 30 years of research. Jossey Bass

Rosenzweig-Ziff D (2023) New York City blocks use of the ChatGPT bot in its schools. Wash Post https://www.washingtonpost.com/education/2023/01/05/nyc-schools-ban-chatgpt/

Salvi F, Ribeiro MH, Gallotti R, West R (2024) On the conversational persuasiveness of large language models: a randomized controlled trial. ArXiv. https://doi.org/10.48550/arXiv.2403.14380

Shynkaruk JM, Thompson VA (2006) Confidence and accuracy in deductive reasoning. Mem Cognit 34(3):619–632. https://doi.org/10.3758/BF03193584

Stokel-Walker C (2022) AI bot ChatGPT writes smart essays — should professors worry? Nature. https://doi.org/10.1038/d41586-022-04397-7

Susnjak T (2022) ChatGPT: The end of online exam integrity? ArXiv . https://arxiv.org/abs/2212.09292

Svrluga S (2023) Princeton student builds app to detect essays written by a popular AI bot. Wash Post https://www.washingtonpost.com/education/2023/01/12/gptzero-chatgpt-detector-ai/

Terwiesch C (2023) Would Chat GPT3 get a Wharton MBA? A prediction based on its performance in the Operations Management course. Mack Institute for Innovation Management at the Wharton School , University of Pennsylvania. https://mackinstitute.wharton.upenn.edu/wp-content/uploads/2023/01/Christian-Terwiesch-Chat-GTP-1.24.pdf

Tlili A, Shehata B, Adarkwah MA, Bozkurt A, Hickey DT, Huang R, Agyemang B (2023) What if the devil is my guardian angel: ChatGPT as a case study of using chatbots in education. Smart Learn Environ 10:15. https://doi.org/10.1186/s40561-023-00237-x

Turing AM (1950) Computing machinery and intelligence. Mind - Q Rev Psychol Philos 236:433–460

UCSD Academic Integrity Office (2023) GenAI, cheating and reporting to the AI office [Announcement]. https://adminrecords.ucsd.edu/Notices/2023/2023-5-17-1.html

Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30. https://doi.org/10.48550/arxiv.1706.03762

Waltzer T, Dahl A (2023) Why do students cheat? Perceptions, evaluations, and motivations. Ethics Behav 33(2):130–150. https://doi.org/10.1080/10508422.2022.2026775

Waltzer T, Cox RL, Heyman GD (2023a) Testing the ability of teachers and students to differentiate between essays generated by ChatGPT and high school students. Hum Behav Emerg Technol 2023:1923981. https://doi.org/10.1155/2023/1923981

Waltzer T, DeBernardi FC, Dahl A (2023b) Student and teacher views on cheating in high school: perceptions, evaluations, and decisions. J Res Adolescence 33(1):108–126. https://doi.org/10.1111/jora.12784

Weidinger L, Mellor J, Rauh M, Griffin C, Uesato J, Huang PS, Gabriel I (2021) Ethical and social risks of harm from language models. ArXiv. https://doi.org/10.48550/arxiv.2112.04359

Wixted JT, Wells GL (2017) The relationship between eyewitness confidence and identification accuracy: a new synthesis. Psychol Sci Public Interest 18(1):10–65. https://doi.org/10.1177/1529100616686966

Yeadon W, Inyang OO, Mizouri A, Peach A, Testrow C (2023) The death of the short-form physics essay in the coming AI revolution. Phys Educ 58:035027. https://doi.org/10.1088/1361-6552/acc5cf

Zhuo TY, Huang Y, Chen C, Xing Z (2023) Red teaming ChatGPT via jailbreaking: bias, robustness, reliability and toxicity. ArXiv. https://doi.org/10.48550/arxiv.2301.12867

Download references

Acknowledgements

We thank Daniel Chen and Riley L. Cox for assistance with study design, stimulus preparation, and pilot testing. We also thank Emma C. Miller for grading the essays and Brian J. Compton for comments on the manuscript.

This work was partly supported by a National Science Foundation Postdoctoral Fellowship for T. Waltzer (NSF SPRF-FR# 2104610).

Author information

Authors and affiliations.

Department of Psychology, University of California San Diego, 9500 Gilman Drive, La Jolla, San Diego, CA, 92093-0109, USA

Tal Waltzer, Celeste Pilegard & Gail D. Heyman

You can also search for this author in PubMed   Google Scholar

Contributions

All authors collaborated in the conceptualization and design of the research. C. Pilegard facilitated recruitment and coding for real class assignments used in the study. T. Waltzer led data collection and analysis. G. Heyman and T. Waltzer wrote and revised the manuscript.

Corresponding author

Correspondence to Tal Waltzer .

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/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Cite this article.

Waltzer, T., Pilegard, C. & Heyman, G.D. Can you spot the bot? Identifying AI-generated writing in college essays. Int J Educ Integr 20 , 11 (2024). https://doi.org/10.1007/s40979-024-00158-3

Download citation

Received : 16 February 2024

Accepted : 11 June 2024

Published : 08 July 2024

DOI : https://doi.org/10.1007/s40979-024-00158-3

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
• Academic integrity
• Higher education

International Journal for Educational Integrity

ISSN: 1833-2595

• Submission enquiries: [email protected]
• General enquiries: [email protected]

More From Forbes

How not to write your college essay.

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

If you are looking for the “secret formula” for writing a “winning” college essay, you have come to the wrong place. The reality is there is no silver bullet or strategy to write your way to an acceptance. There is not one topic or approach that will guarantee a favorable outcome.

At the end of the day, every admission office just wants to know more about you, what you value, and what excites you. They want to hear about your experiences through your own words and in your own voice. As you set out to write your essay, you will no doubt get input (both sought-after and unsolicited) on what to write. But how about what NOT Notcoin to write? There are avoidable blunders that applicants frequently make in drafting their essays. I asked college admission leaders, who have read thousands of submissions, to share their thoughts.

Don’t Go In There

There is wide consensus on this first one, so before you call on your Jedi mind tricks or predictive analytics, listen to the voices of a diverse range of admission deans. Peter Hagan, executive director of admissions at Syracuse University, sums it up best, saying, “I would recommend that students try not to get inside of our heads. He adds, “Too often the focus is on what they think we want.”

Andy Strickler, dean of admission and financial aid at Connecticut College agrees, warning, “Do NOT get caught in the trap of trying to figure out what is going to impress the admission committee. You have NO idea who is going to read your essay and what is going to connect with them. So, don't try to guess that.” Victoria Romero, vice president for enrollment, at Scripps College adds, “Do not write about something you don’t care about.” She says, “I think students try to figure out what an admission officer wants to read, and the reality is the reader begins every next essay with no expectations about the content THEY want to read.” Chrystal Russell, dean of admission at Hampden-Sydney College, agrees, saying, “If you're not interested in writing it, we will not be interested when reading it.” Jay Jacobs, vice provost for enrollment management at the University of Vermont elaborates, advising. “Don’t try to make yourself sound any different than you are.” He says, “The number one goal for admission officers is to better understand the applicant, what they like to do, what they want to do, where they spend the majority of their time, and what makes them tick. If a student stays genuine to that, it will shine through and make an engaging and successful essay.”

Best High-Yield Savings Accounts Of 2024

Best 5% interest savings accounts of 2024.

Don’t Be Artificial

The headlines about college admission are dominated by stories about artificial intelligence and the college essay. Let’s set some ground rules–to allow ChatGPT or some other tool to do your work is not only unethical, it is also unintelligent. The only worse mistake you could make is to let another human write your essay for you. Instead of preoccupying yourself with whether or not colleges are using AI detection software (most are not), spend your time focused on how best to express yourself authentically. Rick Clark is the executive director of strategic student success at Georgia Institute of Technology, one of the first institutions to clearly outline their AI policy for applicants. He says, “Much of a college application is devoted to lines, boxes, and numbers. Essays and supplements are the one place to establish connection, personality, and distinction. AI, in its current state, is terrible at all three.” He adds, “My hope is that students will use ChatGPT or other tools for brainstorming and to get started, but then move quickly into crafting an essay that will provide insight and value.”

Don’t Overdo It

Michael Stefanowicz, vice president for enrollment management at Landmark College says, “You can only cover so much detail about yourself in an admission essay, and a lot of students feel pressure to tell their life story or choose their most defining experience to date as an essay topic. Admission professionals know that you’re sharing just one part of your lived experience in the essay.” He adds, “Some of the favorite essays I’ve read have been episodic, reflecting on the way you’ve found meaning in a seemingly ordinary experience, advice you’ve lived out, a mistake you’ve learned from, or a special tradition in your life.” Gary Ross, vice president for admission and financial aid at Colgate University adds, “More than a few applicants each year craft essays that talk about the frustration and struggles they have experienced in identifying a topic for their college application essay. Presenting your college application essay as a smorgasbord of topics that ultimately landed on the cutting room floor does not give us much insight into an applicant.”

Don’t Believe In Magic

Jason Nevinger, senior director of admission at the University of Rochester warns, “Be skeptical of anyone or any company telling you, ‘This is the essay that got me into _____.’ There is no magic topic, approach, sentence structure, or prose that got any student into any institution ever.” Social media is littered with advertisements promising strategic essay help. Don’t waste your time, energy, or money trying to emulate a certain style, topic, or tone. Liz Cheron is chief executive officer for the Coalition for College and former assistant vice president of enrollment & dean of admissions at Northeastern University. She agrees with Nevinger, saying “Don't put pressure on yourself to find the perfect, slam dunk topic. The vast majority of college essays do exactly what they're supposed to do–they are well-written and tell the admission officer more about the student in that student's voice–and that can take many different forms.”

Don’t Over Recycle

Beatrice Atkinson-Myers, associate director of global recruitment at the University of California at Santa Cruz tells students, “Do not use the same response for each university; research and craft your essay to match the program at the university you are interested in studying. Don't waste time telling me things I can read elsewhere in your application. Use your essay to give the admissions officer insights into your motivations, interests, and thinking. Don't make your essay the kitchen sink, focus on one or two examples which demonstrate your depth and creativity.” Her UC colleague, Jim Rawlins, associate vice chancellor of enrollment management at the University of California at San Diego agrees, saying “Answer the question. Not doing so is the surest way we can tell you are simply giving us a snippet of something you actually wrote for a different purpose.”

Don’t Overedit

Emily Roper-Doten, vice president for undergraduate admissions and financial assistance at Clark University warns against “Too many editors!” She says, “Pick a couple of trusted folks to be your sounding board when considering topics and as readers once you have drafts. You don’t want too many voices in your essay to drown you out!” Scripps’ Romero agrees, suggesting, “Ask a good friend, someone you trust and knows you well, to read your essays.” She adds, “The goal is for the admission committee to get to know a little about you and who better to help you create that framework, than a good friend. This may not work for all students because of content but helps them understand it’s important to be themselves.” Whitney Soule, vice provost and dean of admissions at The University of Pennsylvania adds, “Avoid well-meaning editorial interference that might seem to polish your writing but actually takes your own personal ‘shine’ right out of the message.” She says, “As readers, we connect to applicants through their genuine tone and style. Considering editorial advice for flow and message is OK but hold on to the 'you' for what you want to say and how you want to say it.”

Don’t Get Showy

Palmer Muntz, senior regional admissions counselor at the University of Alaska Fairbanks cautions applicants, “Don’t be fancier than you are. You don’t need to put on airs.” He adds, “Yes, proofread your work for grammar and spelling, but be natural. Craft something you’d want to read yourself, which probably means keeping your paragraphs short, using familiar words, and writing in an active voice.” Connecticut College’s Strickler agrees, warning, “Don't try to be someone you are not. If you are not funny, don't try to write a funny essay. If you are not an intellectual, trying to write an intellectual essay is a bad idea.”

Anthony Jones, the vice president of enrollment management at Loyola University New Orleans offers a unique metaphor for thinking about the essay. He says, “In the new world of the hyper-fast college admission process, it's become easy to overlook the essential meaning of the college application. It's meant to reveal Y...O...U, the real you, not some phony digital avatar. Think of the essay as the essence of that voice but in analog. Like the completeness and authenticity captured in a vinyl record, the few lines you're given to explain your view should be a slow walk through unrestrained expression chock full of unapologetic nuances, crevices of emotion, and exactness about how you feel in the moment. Then, and only then, can you give the admissions officer an experience that makes them want to tune in and listen for more.”

Don’t Be A Downer

James Nondorf, vice president and dean of admissions and financial aid at The University of Chicago says, “Don’t be negative about other people, be appreciative of those who have supported you, and be excited about who you are and what you will bring to our campus!” He adds, “While admissions offices want smart students for our classrooms, we also want kind-hearted, caring, and joyous students who will add to our campus communities too.”

Don’t Pattern Match

Alan Ramirez is the dean of admission and financial aid at Sewanee, The University of the South. He explains, “A big concern I have is when students find themselves comparing their writing to other students or past applicants and transform their writing to be more like those individuals as a way to better their chances of offering a more-compelling essay.” He emphasizes that the result is that the “essay is no longer authentic nor the best representation of themselves and the whole point of the essay is lost. Their distinctive voice and viewpoint contribute to the range of voices in the incoming class, enhancing the diversity of perspectives we aim to achieve.” Ramirez simple tells students, “Be yourself, that’s what we want to see, plus there's no one else who can do it better than you!”

Don’t Feel Tied To A Topic

Jessica Ricker is the vice president for enrollment and dean of admissions and financial aid at Skidmore College. She says, “Sometimes students feel they must tell a story of grief or hardship, and then end up reliving that during the essay-writing process in ways that are emotionally detrimental. I encourage students to choose a topic they can reflect upon positively but recommend that if they choose a more challenging experience to write about, they avoid belaboring the details and instead focus on the outcome of that journey.” She adds, "They simply need to name it, frame its impact, and then help us as the reader understand how it has shaped their lens on life and their approach moving forward.”

Landmark College’s Stefanowicz adds, “A lot of students worry about how personal to get in sharing a part of their identity like your race or heritage (recalling last year’s Supreme Court case about race-conscious admissions), a learning difference or other disability, your religious values, LGBTQ identity…the list goes on.” He emphasizes, “This is always your choice, and your essay doesn’t have to be about a defining identity. But I encourage you to be fully yourself as you present yourself to colleges—because the college admission process is about finding a school where your whole self is welcome and you find a setting to flourish!”

Don’t Be Redundant

Hillen Grason Jr., dean of admission at Franklin & Marshall College, advises, “Don't repeat academic or co-curricular information that is easily identifiable within other parts of your application unless the topic is a core tenant of you as an individual.” He adds, “Use your essay, and other parts of your application, wisely. Your essay is the best way to convey who your authentic self is to the schools you apply. If you navigated a situation that led to a dip in your grades or co-curricular involvement, leverage the ‘additional information’ section of the application.

Thomas Marr is a regional manager of admissions for the Americas at The University of St Andrews in Scotland and points out that “Not all international schools use the main college essay as part of their assessment when reviewing student applications.” He says, “At the University of St Andrews, we focus on the supplemental essay and students should avoid the mistake of making the supplemental a repeat of their other essay. The supplemental (called the Personal Statement if using the UCAS application process) is to show the extent of their passion and enthusiasm for the subject/s to which they are applying and we expect about 75% of the content to cover this. They can use the remaining space to mention their interests outside of the classroom. Some students confuse passion for the school with passion for their subject; do not fall into that trap.”

A Few Final Don’ts

Don’t delay. Every college applicant I have ever worked with has wished they had started earlier. You can best avoid the pitfalls above if you give yourself the time and space to write a thoughtful essay and welcome feedback openly but cautiously. Don’t put too much pressure on yourself to be perfect . Do your best, share your voice, and stay true to who you are.

• Editorial Standards
• Reprints & Permissions

Join The Conversation

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

Forbes Community Guidelines

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

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

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

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

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

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

So, how can you be a power user?

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

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

Sign up for a free 30-day trial of JSH-Online.

Subscribe to JSH-Online  to get access to every  Sentinel  issue.

Try free for 30 days

Step 1 of 2

No credit card required.

Upon registering, you are opting in to receive emails about new issues and special messages from the Editor.

Log in  or  Subscribe

Set your password

Step 2 of 2.

Please enter a password of at least 8 characters.

I agree to the  terms of service . *

Your unlimited access to JSH-Online begins now. Free for 30 days.

Get Started

New content available!

We have new featured content for you. Explore digital-first articles and audio that offer the most timely support to your spiritual watch.

View Online Features

Subscribe to JSH-Online to access every issue of the Christian Science Sentinel since 1898, audio for issues, podcasts, and more.

Subscribe LOG IN

Enjoy 1 free Sentinel  article or audio program each month, including content from 1898 to today.

Continue for free

Already a subscriber?   Log in

You've accessed 1 piece of free  Sentinel  content. Sign up for unlimited access.

Subscription aid available

No card required

• Table of contents Contents
• Print Print
• Issue viewer
• More languages Languages
• $label.name

Are you sure?

This bookmark will be removed from all folders and any saved notes will be permanently removed.

A college professor prays about artificial intelligence

I’ve been grateful to be reminded that the wisdom from above is actually in charge. 

“The wisdom that is from above is first pure, then peaceable, gentle, and easy to be entreated, full of mercy and good fruits, without partiality, and without hypocrisy” ( James 3:17 ).

In this age of artificial intelligence and chatbots, it is helpful to remember that the wisdom that comes from divine Mind—God—is supremely powerful and to strive to rely exclusively on this infinite and only genuine intelligence.

A chatbot is a computer program that is able to simulate human speech—written or spoken—and can “converse” with users. Chatbots rely on artificial intelligence, or AI, and many are capable of generating written work such as essays, research papers, and so on. Writing teachers worry that students will cheat by submitting as their own work papers written with the help of AI. I’ve been grateful to be reminded that the wisdom from above is actually in charge.

We'd love to hear from you!

Easily submit your testimonies, articles, and poems online.

July 15, 2024 issue

Michelle Nanouche

Lynn G. Jackson

Name Withheld

Carolyn M. Hook

Becky Riley Fisher

Chris Motta

Kennedy Onjweru

Susan Dawson Cook

July 15–21, 2024

Letters & Conversations

Judith Patterson, Pamela Osgood, Nicholas Woodeson

• Write for us
• TeenConnect
• Kids' videos
• Collections
• Sentinel Watch podcast
• Science and Health audio
• My bookmarks
• Search the archive
• Christian Science Directory
• eBibleLesson Express
• Daily Thought
• MBELibrary.org
• CSMonitor.com
• Bible Lesson
• Church Services
• About Christian Science
• ChristianScience.com
• Give a gift
• All CSPS subscriptions

This website uses cookies to improve functionality and performance. By continuing to browse the site you are agreeing to our  use of cookies .

Too many emails entered, please limit to 10 recipients.

"To address" is required

"From address" is required

Please shorten your message. It must be fewer than 1,000 characters

Invalid Entry

Please correct the noted errors before continuing.

Your email has been sent.

A copy has also been sent to your email address.

Video Player

Sign up for unlimited access

You’ve accessed 1 piece of free  Sentinel  content