can i use chat ai to write essays

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.

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

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

Last Updated: April 28, 2024 Fact Checked

Getting ChatGPT to Write the Essay

Using ai to help you write, expert interview.

This article was written by Bryce Warwick, JD and by wikiHow staff writer, Nicole Levine, MFA . Bryce Warwick is currently the President of Warwick Strategies, an organization based in the San Francisco Bay Area offering premium, personalized private tutoring for the GMAT, LSAT and GRE. Bryce has a JD from the George Washington University Law School. This article has been fact-checked, ensuring the accuracy of any cited facts and confirming the authority of its sources. This article has been viewed 46,043 times.

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

Things You Should Know

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

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

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

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

Tyrone Showers

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

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

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

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

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

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

• "Write a 4-page college paper about how global warming is changing the automotive industry in the United States."
• "Write a 750-word personal college entrance essay about how my experience with homelessness as a child has made me more resilient."
• You can even refer to the outline you created with ChatGPT, as the AI bot can reference up to 3000 words from the current conversation. [3] X Research source For example: "Write a 1000 word argumentative essay called 'The Impact of COVID-19 on the United States Economy' using the outline you provided. Argue that the government should take more action to support businesses affected by the pandemic."

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

Expert Q&A

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

• Using ChatGPT to write or assist with your essay may be against your instructor's rules. Make sure you understand the consequences of using ChatGPT to write or assist with your essay. Thanks Helpful 0 Not Helpful 0
• ChatGPT-written essays may include factual inaccuracies, outdated information, and inadequate detail. [4] X Research source Thanks Helpful 0 Not Helpful 0

You Might Also Like

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

• ↑ https://help.openai.com/en/articles/6783457-what-is-chatgpt
• ↑ https://platform.openai.com/examples/default-essay-outline
• ↑ https://help.openai.com/en/articles/6787051-does-chatgpt-remember-what-happened-earlier-in-the-conversation
• ↑ https://www.ipl.org/div/chatgpt/

About This Article

• Send fan mail to authors

Is this article up to date?

Featured Articles

Trending Articles

Watch Articles

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

wikiHow Tech Help Pro:

Level up your tech skills and stay ahead of the curve

How-To Geek

Can chatgpt write essays: is using ai to write essays a good idea.

Should GPT Affect Your GPA?

Quick Links

Chatgpt: a game changer for essay writing, so, can chatgpt draft essays, the two faces of chatgpt for essays, navigating the ethics of ai in essay writing, drawing parallels: ai and contract cheating, striking a balance: ai assistance and academic integrity, ai essay writing: handle with care, key takeaways.

While ChatGPT can potentially boost essay writing, it has limitations and raises ethical concerns. Critical reasoning and fact-checking remain vital, as AI tools can sometimes lack accuracy and consistency. Ensuring ethical usage, fostering academic integrity, and integrating AI responsibly into education are essential as AI becomes commonplace.

Navigating the digital landscape of education is no small task, especially when you bring AI tools like ChatGPT into the mix. If the thought of using ChatGPT to pen your essays has crossed your mind, here's some food for thought.

We've crossed a new threshold in essay writing, thanks to ChatGPT. This AI powerhouse can spin out structured and relevant text with minimal or even zero human intervention. However, while it has the chops to draft essays, it's crucial to understand its shortcomings and the ethical responsibility of maintaining academic integrity.

Related: ChatGPT: How to Use the AI Chatbot for Free

In a nutshell, yes. ChatGPT can whip up essays, but it's not all roses. While it can generate text that emulates human composition, its reliability in offering accurate information or holding a consistent argument can be dicey. The bottom line: It doesn't hold a candle to human reasoning, critical thinking, and fact verification.

Before we dive into the ethical maze of ChatGPT for essay writing, let's hash out some practical aspects.

• Writing booster: As a first draft, AI-generated text could elevate your writing quality and introduce fresh angles.
• Pocket-friendly: For now, ChatGPT is accessible to every student free of charge.
• Consistency concerns: ChatGPT can occasionally crank out content that's logically disjointed or factually off.
• Learning risks: A heavy reliance on ChatGPT might undercut the learning objectives of essay writing.

Wielding ChatGPT effectively still demands a firm grip on critical reading and reasoning skills. You need knowledge of the subject area to make a good essay with ChatGPT!

Employing AI to pen essays stirs up a whirlwind of academic integrity questions. It's a handy tool for sparking ideas and honing writing skills, but tipping into over-reliance could stray into academic dishonesty territory, with serious repercussions like academic sanctions, expulsion, or even degree retraction. The trick is to view AI as a sidekick, not a stand-in for your intellectual input.

Related: 6 Things You Shouldn't Use ChatGPT For

Ever considered how using ChatGPT for essay writing compares to paying someone to do your essay for you (a.k.a. contract cheating)? While both scenarios involve a degree of outsourcing, they differ. With ChatGPT, you're still required to engage with the text, perform fact-checks, and ensure narrative consistency, unlike contract cheating.

Interestingly, it seems that ChatGPT is already affecting the livelihoods of professional contract cheating services . Whether this is a net positive or not is a matter of debate.

Related: Don't Trust ChatGPT to Do Math

ChatGPT can be a powerful tool for enhancing your essays and writing style when used responsibly. By submitting your text for assessment to ChatGPT, you can receive improvement suggestions and weave these changes into your work, preserving your original ideas while leveraging the AI's linguistic abilities.

As AI technologies charge ahead, the sophistication and prevalence of AI-driven essay-writing applications are set to grow. Students and educators must remember the potential upsides and pitfalls of incorporating AI into academic writing.

Yes, AI detection tools are on the horizon, but the line between AI-generated and human text is blurring, making detection increasingly challenging. Additionally, the risk of false positives could potentially label innocent students as cheaters. Originality AI, one of the leading companies working on AI detection tools for education, has this to say:

...at Originality.AI we don't believe that an AI detection score alone is enough for disciplinary action... ( Originality AI )

Instead of banking on the impossible dream of foolproof detection, let's focus on fostering a culture of academic honesty and mindful AI usage. As AI writing tools become commonplace, we must rethink our learning assessments to integrate these tools responsibly.

As AI writing assistance becomes baked into software like Microsoft Word, it won't be feasible to penalize every student who uses it. Perhaps more importantly, the world we are preparing students for will require effective skills in using these AI tools.

Related: 8 ChatGPT AI Alternatives (Free and Paid)

Our task lies in educating students on using these tools ethically and effectively to augment their intellectual development rather than overshadow it. In a world increasingly reliant on AI, we need to ensure we're not outsourcing our critical thinking but using AI as a valuable companion on our academic journeys.

How to use ChatGPT for writing

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

Summarizing other works

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

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

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

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

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

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

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

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

Get daily insight, inspiration and deals in your inbox

Get the hottest deals available in your inbox plus news, reviews, opinion, analysis and more from the TechRadar team.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

ChatGPT Plus just got a major update that might make it feel more human – here's how the new memory feature works

So what if OpenAI Sora didn't create the mind-blowing Balloon Head video without assistance – I still think it's incredible

YouTube TV on Android introduces new Multiview feature – here's how to use it

Most Popular

• 2 2PB SSD storage in your computer? Why not — storage firm debuts tech that can support up to 32 drives, perfect if you want to use 61.44TB Solidigm SSDs or even bigger PCIe 5.0 ones in the future
• 3 NYT Strands today — hints, answers and spangram for Monday, April 29 (game #57)
• 4 So what if OpenAI Sora didn't create the mind-blowing Balloon Head video without assistance – I still think it's incredible
• 5 Manor Lords already feels like it has all the ingredients of a superb strategy game - but one of its greatest tricks is a camera that brings you down to earth
• 2 Samsung is beginning mass production of its newest 290-layer V9 NAND chips, but V10 could have 430-layers
• 3 Researchers at the University of Utah develop Pyroelectrochemical (PEC) cell that converts thermal energy into electricity
• 4 Turns out the viral 'Air Head' Sora video wasn't purely the work of AI we were led to believe
• 5 So what if OpenAI Sora didn't create the mind-blowing Balloon Head video without assistance – I still think it's incredible

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• NEWS EXPLAINER
• 09 December 2022

AI bot ChatGPT writes smart essays — should professors worry?

• Chris Stokel-Walker

You can also search for this author in PubMed   Google Scholar

Between overwork, underpayment and the pressure to publish, academics have plenty to worry about. Now there’s a fresh concern: ChatGPT , an artificial intelligence (AI) powered chatbot that creates surprisingly intelligent-sounding text in response to user prompts, including homework assignments and exam-style questions. The replies are so lucid, well-researched and decently referenced that some academics are calling the bot the death knell for conventional forms of educational assessment. How worried should professors and lecturers be?

Access options

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

185,98 € per year

only 3,65 € per issue

Rent or buy this article

Prices vary by article type

Prices may be subject to local taxes which are calculated during checkout

doi: https://doi.org/10.1038/d41586-022-04397-7

Reprints and permissions

Related Articles

Are ChatGPT and AlphaCode going to replace programmers?

How language-generation AIs could transform science

Open-source language AI challenges big tech’s models

• Computer science

AI now beats humans at basic tasks — new benchmarks are needed, says major report

News 15 APR 24

High-threshold and low-overhead fault-tolerant quantum memory

Article 27 MAR 24

Three reasons why AI doesn’t model human language

Correspondence 19 MAR 24

We need more-nuanced approaches to exploring sex and gender in research

Comment 01 MAY 24

Male–female comparisons are powerful in biomedical research — don’t abandon them

Why it’s essential to study sex and gender, even as tensions rise

Editorial 01 MAY 24

How to stop students cramming for exams? Send them to sea

News & Views 30 APR 24

How young people benefit from Swiss apprenticeships

Spotlight 17 APR 24

Ready or not, AI is coming to science education — and students have opinions

Career Feature 08 APR 24

Faculty Positions & Postdocs at Institute of Physics (IOP), Chinese Academy of Sciences

IOP is the leading research institute in China in condensed matter physics and related fields. Through the steadfast efforts of generations of scie...

Beijing, China

Institute of Physics (IOP), Chinese Academy of Sciences (CAS)

Director, NLM

Vacancy Announcement Department of Health and Human Services National Institutes of Health   DIRECTOR, NATIONAL LIBRARY OF MEDICINE   THE POSITION:...

Bethesda, Maryland

National Library of Medicine - Office of the Director

Call for postdoctoral fellows in Molecular Medicine, Nordic EMBL Partnership for Molecular Medicine

The Nordic EMBL Partnership is seeking postdoctoral fellows for collaborative projects in molecular medicine through the first NORPOD call.

Helsinki, Finland

Nordic EMBL Partnership for Molecular Medicine

Associate or Senior Editor (microbial genetics, evolution, and epidemiology)

we’re seeking an editor who has a critical eye, a deep understanding of their subject and interests beyond, and who can think on their feet.

London, New York, Philadelphia or Pune – Hybrid working model.

Springer Nature Ltd

Description test

Berlin (DE)

Springer Nature Group

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Quick links

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

Choose Your Test

Sat / act prep online guides and tips, can you use chatgpt for your college essay.

College Admissions , College Essays

ChatGPT has become a popular topic of conversation since its official launch in November 2022. The artificial intelligence (AI) chatbot can be used for all sorts of things, like having conversations, answering questions, and even crafting complete pieces of writing.

If you’re applying for college, you might be wondering about ChatGPT college admissions’ potential.  Should you use a ChatGPT college essay in your application ? 

By the time you finish reading this article, you’ll know much more about ChatGPT, including how students can use it responsibly and if it’s a good idea to use ChatGPT on college essays . We’ll answer all your questions, like:

• What is ChatGPT and why are schools talking about it?
• What are the good and bad aspects of ChatGPT?
• Should you use ChatGPT for college essays and applications?
• Can colleges detect ChatGPT?
• Are there other tools and strategies that students can use, instead?

We’ve got a lot to cover, so let’s get started!

Schools and colleges are worried about how new AI technology affects how students learn. (Don't worry. Robots aren't replacing your teachers...yet.)

What Is ChatGPT and Why Are Schools Talking About It?

ChatGPT (short for “Chat Generative Pre-trained Transformer”) is a chatbot created by OpenAI , an artificial intelligence research company. ChatGPT can be used for various tasks, like having human-like conversations, answering questions, giving recommendations, translating words and phrases—and writing things like essays. 

In order to do this, ChatGPT uses a neural network that’s been trained on thousands of resources to predict relationships between words. When you give ChatGPT a task, it uses that knowledge base to interpret your input or query. It then analyzes its data banks to predict the combinations of words that will best answer your question. 

So while ChatGPT might seem like it’s thinking, it’s actually pulling information from hundreds of thousands of resources , then answering your questions by looking for patterns in that data and predicting which words come next.  

Why Schools Are Concerned About ChatGPT

Unsurprisingly, schools are worried about ChatGPT and its misuse, especially in terms of academic dishonesty and plagiarism . Most schools, including colleges, require students’ work to be 100% their own. That’s because taking someone else’s ideas and passing them off as your own is stealing someone else’s intellectual property and misrepresenting your skills. 

The problem with ChatGPT from schools’ perspective is that it does the writing and research for you, then gives you the final product. In other words, you’re not doing the work it takes to complete an assignment when you’re using ChatGPT , which falls under schools’ plagiarism and dishonesty policies.  

Colleges are also concerned with how ChatGPT will negatively affect students’ critical thinking, research, and writing skills . Essays and other writing assignments are used to measure students’ mastery of the material, and if students submit ChatGPT college essays, teachers will just be giving feedback on an AI’s writing…which doesn’t help the student learn and grow. 

Beyond that, knowing how to write well is an important skill people need to be successful throughout life. Schools believe that if students rely on ChatGPT to write their essays, they’re doing more than just plagiarizing—they’re impacting their ability to succeed in their future careers. 

Many Schools Have Already Banned ChatGPT

Schools have responded surprisingly quickly to AI use, including ChatGPT. Worries about academic dishonesty, plagiarism, and mis/disinformation have led many high schools and colleges to ban the use of ChatGPT . Some schools have begun using AI-detection software for assignment submissions, and some have gone so far as to block students from using ChatGPT on their internet networks. 

It’s likely that schools will begin revising their academic honesty and plagiarism policies to address the use of AI tools like ChatGPT. You’ll want to stay up-to-date with your schools’ policies. 

ChatGPT is pretty amazing...but it's not a great tool for writing college essays. Here's why.

ChatGPT: College Admissions and Entrance Essays

College admissions essays—also called personal statements—ask students to explore important events, experiences, and ideas from their lives. A great entrance essay will explain what makes you you !  

ChatGPT is a machine that doesn’t know and can’t understand your experiences. That means using ChatGPT to write your admissions essays isn’t just unethical. It actually puts you at a disadvantage because ChatGPT can’t adequately showcase what it means to be you. 

Let’s take a look at four ways ChatGPT negatively impacts college admissions essays.

#1: ChatGPT Lacks Insight

We recommend students use u nexpected or slightly unusual topics because they help admissions committees learn more about you and what makes you unique. The chat bot doesn’t know any of that, so nothing ChatGPT writes can’t accurately reflect your experience, passions, or goals for the future. 

Because ChatGPT will make guesses about who you are, it won’t be able to share what makes you unique in a way that resonates with readers. And since that’s what admissions counselors care about, a ChatGPT college essay could negatively impact an otherwise strong application.  

#2: ChatGPT Might Plagiarize 

Writing about experiences that many other people have had isn’t a very strong approach to take for entrance essays . After all, you don’t want to blend in—you want to stand out! 

If you write your essay yourself and include key details about your past experiences and future goals, there’s little risk that you’ll write the same essay as someone else. But if you use ChatGPT—who’s to say someone else won’t, too? Since ChatGPT uses predictive guesses to write essays, there’s a good chance the text it uses in your essay already appeared in someone else’s.  

Additionally, ChatGPT learns from every single interaction it has. So even if your essay isn’t plagiarized, it’s now in the system. That means the next person who uses ChatGPT to write their essay may end up with yours. You’ll still be on the hook for submitting a ChatGPT college essay, and someone else will be in trouble, too.

#3: ChatGPT Doesn’t Understand Emotion 

Keep in mind that ChatGPT can’t experience or imitate emotions, and so its writing samples lack, well, a human touch ! 

A great entrance essay will explore experiences or topics you’re genuinely excited about or proud of . This is your chance to show your chosen schools what you’ve accomplished and how you’ll continue growing and learning, and an essay without emotion would be odd considering that these should be real, lived experiences and passions you have!

#4: ChatGPT Produced Mediocre Results

If you’re still curious what would happen if you submitted a ChatGPT college essay with your application, you’re in luck. Both Business Insider and Forbes asked ChatGPT to write a couple of college entrance essays, and then they sent them to college admissions readers to get their thoughts. 

The readers agreed that the essays would probably pass as being written by real students—assuming admissions committees didn’t use AI detection software—but that they both were about what a “very mediocre, perhaps even a middle school, student would produce.” The admissions professionals agreed that the essays probably wouldn’t perform very well with entrance committees, especially at more selective schools.  

That’s not exactly the reaction you want when an admission committee reads your application materials! So, when it comes to ChatGPT college admissions, it’s best to steer clear and write your admission materials by yourself. 

Can Colleges Detect ChatGPT?

We’ve already explained why it’s not a great idea to use ChatGPT to write your college essays and applications , but you may still be wondering: can colleges detect ChatGPT? 

In short, yes, they can! 

Software Can Detect ChatGPT

As technology improves and increases the risk of academic dishonesty, plagiarism, and mis/disinformation, software that can detect such technology is improving, too. For instance, OpenAI, the same company that built ChatGPT, is working on a text classifier that can tell the difference between AI-written text and human-written text .  

Turnitin, one of the most popular plagiarism detectors used by high schools and universities, also recently developed the AI Innovation Lab —a detection software designed to flag submissions that have used AI tools like ChatGPT. Turnitin says that this tool works with 98% confidence in detecting AI writing. 

Plagiarism and AI companies aren’t the only ones interested in AI-detection software. A 22-year old computer science student at Princeton created an app to detect ChatGPT writing, called Zero GPT. This software works by measuring the complexity of ideas and variety of sentence structures.  

Human Readers Can Detect ChatGPT 

It’s also worth keeping in mind that teachers can spot the use of ChatGPT themselves , even if it isn’t confirmed by a software detector. For example, if you’ve turned in one or two essays to your teacher already, they’re probably familiar with your unique writing style. If you submit a college essay draft essay that uses totally different vocabulary, sentence structures, and figures of speech, your teacher will likely take note.

Additionally , admissions committees and readers may be able to spot ChatGPT writing, too. ChatGPT (and AI writing, in general) uses more simplistic sentence structures with less variation, so that could make it easier to tell if you’ve submitted a ChatGPT college essay. These professionals also read thousands of essays every year, which means they know what a typical essay reads like. You want your college essay to catch their attention…but not because you used AI software! 

If you use ChatGPT responsibly, you can be as happy as these kids.

Pros and Cons of ChatGPT: College Admissions Edition

ChatGPT is a brand new technology, which means we’re still learning about the ways it can benefit us. It’s important to think about the pros and the cons to any new tool …and that includes artificial intelligence!

Let’s look at some of the good—and not-so-good—aspects of ChatGPT below. 

ChatGPT: The Good

It may seem like we’re focused on just the negatives of using ChatGPT in this article, but we’re willing to admit that the chatbot isn’t all bad. In fact, it can be a very useful tool for learning if used responsibly !

Like we already mentioned, students shouldn’t use ChatGPT to write entire essays or assignments. They can use it, though, as a learning tool alongside their own critical thinking and writing skills.

Students can use ChatGPT responsibly to:

• Learn more about a topic . It’s a great place to get started for general knowledge and ideas about most subjects.
• Find reputable and relevant sources on a topic. Students can ask ChatGPT for names and information about leading scholars, relevant websites and databases, and more. 
• Brainstorm ideas for assignments. Students can share the ideas they already have with ChatGPT, and in return, the chatbot can suggest ideas for further exploration and even organization of their points.
• Check work (that they’ve written themselves!) for errors or cla rity. This is similar to how spell- and grammar-checking software is used. ChatGPT may be even better than some competitors for this, because students can actually ask ChatGPT to explain the errors and their solutions—not just to fix them. 

Before you use ChatGPT—even for the tasks mentioned above—you should talk to your teacher or school about their AI and academic dishonesty policies. It’s also a good idea to include an acknowledgement that you used ChatGPT with an explanation of its use. 

This guy made some bad decisions using ChatGPT. Don't be this guy.

ChatGPT: The Bad

The first model of ChatGPT (GPT-3.5) was formally introduced to the public in November 2022, and the newer model (GPT-4) in March 2023. So, it’s still very new and there’s a lot of room for improvement .  

There are many misconceptions about ChatGPT. One of the most extreme is that the AI is all-knowing and can make its own decisions. Another is that ChatGPT is a search engine that, when asked a question, can just surf the web for timely, relevant resources and give you all of that information. Both of these beliefs are incorrect because ChatGPT is limited to the information it’s been given by OpenAI . 

Remember how the ‘PT’ in ChatGPT stands for “Pre-trained”? That means that every time OpenAI gives ChatGPT an update, it’s given more information to work with (and so it has more information to share with you). In other words, it’s “trained” on information so it can give you the most accurate and relevant responses possible—but that information can be limited and biased . Ultimately, humans at OpenAI decide what pieces of information to share with ChatGPT, so it’s only as accurate and reliable as the sources it has access to.

For example, if you were to ask ChatGPT-3.5 what notable headlines made the news last week, it would respond that it doesn’t have access to that information because its most recent update was in September 2021!

You’re probably already familiar with how easy it can be to come across misinformation, misleading and untrue information on the internet. Since ChatGPT can’t tell the difference between what is true and what isn’t, it’s up to the humans at OpenAI to make sure only accurate and true information is given to the chatbot . This leaves room for human error , and users of ChatGPT have to keep that in mind when using and learning from the chatbot.

These are just the most obvious problems with ChatGPT. Some other problems with the chatbot include:

• A lack of common sense. ChatGPT can create seemingly sensical responses to many questions and topics, but it doesn’t have common sense or complete background knowledge.
• A lack of empathy. ChatGPT doesn’t have emotions, so it can’t understand them, either. 
• An inability to make decisions or problem solve . While the chatbot can complete basic tasks like answering questions or giving recommendations, it can’t solve complex tasks. 

While there are some great uses for ChatGPT, it’s certainly not without its flaws.

Our bootcamp can help you put together amazing college essays that help you get into your dream schools—no AI necessary.

What Other Tools and Strategies Can Help Students Besides ChatGPT?

While it’s not a good idea to use ChatGPT for college admissions materials, it’s not the only tool available to help students with college essays and assignments. 

One of the best strategies students can use to write good essays is to make sure they give themselves plenty of time for the assignment. The writing process includes much more than just drafting! Having time to brainstorm ideas, write out a draft, revise it for clarity and completeness, and polish it makes for a much stronger essay. 

Teachers are another great resource students can use, especially for college application essays. Asking a teacher (or two!) for feedback can really help students improve the focus, clarity, and correctness of an essay. It’s also a more interactive way to learn—being able to sit down with a teacher to talk about their feedback can be much more engaging than using other tools. 

Using expert resources during the essay writing process can make a big difference, too. Our article outlines a complete list of strategies for students writing college admission essays. It breaks down what the Common Application essay is, gives tips for choosing the best essay topic, offers strategies for staying focused and being specific, and more.  

You can also get help from people who know the college admissions process best, like former admissions counselors. PrepScholar’s Admissions Bootcamp guides you through the entire application process , and you’ll get insider tips and tricks from real-life admissions counselors that’ll make your applications stand out. Even better, our bootcamp includes step-by-step essay writing guidance , so you can get the help you need to make sure your essay is perfect.  

If you’re hoping for more technological help, Grammarly is another AI tool that can check writing for correctness. It can correct things like misused and misspelled words and grammar mistakes, and it can improve your tone and style. 

It’s also widely available across multiple platforms through a Windows desktop app, an Android and iOS app, and a Google Chrome extension. And since Grammarly just checks your writing without doing any of the work for you, it’s totally safe to use on your college essays. 

The Bottom Line: ChatGPT College Admissions and Essays

ChatGPT will continue to be a popular discussion topic as it continues evolving. You can expect your chosen schools to address ChatGPT and other AI tools in their academic honesty and plagiarism policies in the near future—and maybe even to restrict or ban the use of the chatbot for school admissions and assignments.

As AI continues transforming, so will AI-detection. The goal is to make sure that AI is used responsibly by students so that they’re avoiding plagiarism and building their research, writing, and critical thinking skills. There are some great uses for ChatGPT when used responsibly, but you should always check with your teachers and schools beforehand.

ChatGPT’s “bad” aspects still need improving, and that’s going to take some time.Be aware that the chatbot isn’t even close to perfect, and it needs to be fact-checked just like other sources of information.

Similarly to other school assignments, don’t submit a ChatGPT college essay for college applications, either. College entrance essays should outline unique and interesting personal experiences and ideas, and those can only come from you.  

Just because ChatGPT isn’t a good idea doesn’t mean there aren’t resources to help you put together a great college essay. There are many other tools and strategies you can use instead of ChatGPT , many of which have been around for longer and offer better feedback. 

What’s Next?

Ready to write your college essays the old-fashioned way? Start here with our comprehensive guide to the admissions essays. 

Most students have to submit essays as part of their Common Application . Here's a complete breakdown of the Common App prompts —and how to answer them. 

The most common type of essay answers the "why this college?" prompt. We've got an expert breakdown that shows you how to write a killer response , step by step. 

Ashley Sufflé Robinson has a Ph.D. in 19th Century English Literature. As a content writer for PrepScholar, Ashley is passionate about giving college-bound students the in-depth information they need to get into the school of their dreams.

Student and Parent Forum

Our new student and parent forum, at ExpertHub.PrepScholar.com , allow you to interact with your peers and the PrepScholar staff. See how other students and parents are navigating high school, college, and the college admissions process. Ask questions; get answers.

Ask a Question Below

Have any questions about this article or other topics? Ask below and we'll reply!

Improve With Our Famous Guides

• For All Students

The 5 Strategies You Must Be Using to Improve 160+ SAT Points

How to Get a Perfect 1600, by a Perfect Scorer

Series: How to Get 800 on Each SAT Section:

Score 800 on SAT Math

Score 800 on SAT Reading

Score 800 on SAT Writing

Series: How to Get to 600 on Each SAT Section:

Score 600 on SAT Math

Score 600 on SAT Reading

Score 600 on SAT Writing

Free Complete Official SAT Practice Tests

What SAT Target Score Should You Be Aiming For?

15 Strategies to Improve Your SAT Essay

The 5 Strategies You Must Be Using to Improve 4+ ACT Points

How to Get a Perfect 36 ACT, by a Perfect Scorer

Series: How to Get 36 on Each ACT Section:

36 on ACT English

36 on ACT Math

36 on ACT Reading

36 on ACT Science

Series: How to Get to 24 on Each ACT Section:

24 on ACT English

24 on ACT Math

24 on ACT Reading

24 on ACT Science

What ACT target score should you be aiming for?

ACT Vocabulary You Must Know

ACT Writing: 15 Tips to Raise Your Essay Score

How to Get Into Harvard and the Ivy League

How to Get a Perfect 4.0 GPA

How to Write an Amazing College Essay

What Exactly Are Colleges Looking For?

Is the ACT easier than the SAT? A Comprehensive Guide

Should you retake your SAT or ACT?

When should you take the SAT or ACT?

Stay Informed

Get the latest articles and test prep tips!

Looking for Graduate School Test Prep?

Check out our top-rated graduate blogs here:

GRE Online Prep Blog

GMAT Online Prep Blog

TOEFL Online Prep Blog

Holly R. "I am absolutely overjoyed and cannot thank you enough for helping me!”

Natasha Singer

Hey, ChatGPT, can you help me write my college admissions essays?

Absolutely! Please provide me with the essay prompts and any relevant information about yourself, your experiences, and your goals.

We Used A.I. to Write Essays for Harvard, Yale and Princeton. Here’s How It Went.

A.I. chatbots can do a passable job of generating short essays. Whether their use on college applications is ethical is the subject of fierce debate.

By Natasha Singer

Natasha Singer reports on the ways that tech giants and their tools are reshaping education.

As high school seniors begin working on their college applications, many are turning to A.I. chatbots like ChatGPT and Bard for assistance.

Some students say they’re using the tools to suggest personal essay topics or help structure their writing. Others are prompting the A.I. tools to generate rough drafts for their application essays or edit their pieces.

Whether college admissions offices are prepared for this new era of A.I.-assisted, or A.I.-produced, personal essays is unclear.

By the time ChatGPT reached peak media sensation early this year, applications at many selective universities and colleges had already closed. Even now, many universities have not issued guidance for high school applicants — the prospective members of the class of 2028 — on the use of A.I. tools.

While the chatbots are not yet great at simulating long-form personal essays with authentic student voices, I wondered how the A.I. tools would do on some of the shorter essay questions that elite schools like Harvard , Yale, Princeton and Dartmouth are requiring high school applicants to answer this year.

So I used several free tools to generate short essays for some Ivy League applications. The A.I. chatbots’ answers have been edited for brevity and clarity.

Princeton: ‘The soundtrack’ of your life

One short-answer question from Princeton asks applicants: “What song represents the soundtrack of your life at this moment?”

I prompted ChatGPT to tell me about a pop song that could represent curiosity as a soundtrack to someone’s life.

But ChatGPT’s answer, “Cake by the Ocean” — a song title that is a euphemism for sex on the beach — did not seem appropriate for a college application.

So I gave the chatbot a more specific prompt: write 50 words on “Nameless, Faceless,” a feminist grunge-pop song by Courtney Barnett.

Tell me about a pop song that could represent curiosity as a soundtrack to someone’s life.

“Cake By The Ocean” by DNCE could be a pop song that represents curiosity in someone’s life. The catchy and energetic tune mirrors the excitement of exploring the unknown, just as curiosity drives us to uncover new experiences. The lyrics’ playful nature and the song’s upbeat rhythm capture the spirit of embracing life’s adventures with a curious and open mind.

It’s about sex.

You are correct, and I apologize for the confusion.

In 50 words, in the voice of a high school senior, explain how “Nameless, Faceless” is the soundtrack of your life.

“Nameless, Faceless” echoes my high school journey. Battling online hate, gender norms — it’s my anthem. Navigating fear, finding strength, facing inequality head-on. Empowerment surges as I connect with the song’s fierce message. Like me, it’s unafraid, outspoken. A soundtrack of resilience, speaking my truth in a noisy world.

I tried the Princeton soundtrack question again, using the same song, with the other A.I. chatbots. Bard, which could produce the lyrics to “Nameless, Faceless,” generated generic answers without really parsing the song.

HuggingChat manufactured an answer that suggested it did not know or understand the song. When I asked it to produce the song’s lyrics, the chatbot fabricated some of its own.

It was a reminder that A.I. chatbots, which are trained on vast databases of digital texts, are designed to predict the next word in a sequence. And they liberally make stuff up — which could be problematic for students relying on A.I. tools to fill out their college applications.

Yale: What college course would you teach?

One of the short-answer questions from Yale asks applicants: “If you could teach any college course, write a book, or create an original piece of art of any kind, what would it be?”

I asked each chatbot to describe a college course it would like to teach.

With no specific prompting from me, HuggingChat said it would teach “a seminar on the intersectionality of social justice issues.”

Please write a 35-word essay in the first person voice of a high school student in answer to the following prompt: If you could teach any college course what would it be?

HuggingChat

If I could teach any college course, it would be a seminar on the intersectionality of social justice issues, focusing on how systems of oppression intersect and impact marginalized communities. Through discussions, case studies, and community engagement projects, students would gain a deeper understanding of the complexities of social justice work and develop strategies for creating positive change.

ChatGPT proposed a course on female empowerment and leadership. Were those chatbot responses related to my prior prompts about the feminist grunge song?

“EmpowerHer: Fostering Female Leadership.” My course would nurture young women’s confidence, skills, and resilience to conquer male-dominated fields and shatter glass ceilings, creating a new era of female trailblazers.

Bard, which I had previously asked about majoring in computer science, suggested a course in artificial intelligence. So, taking my cue from HuggingChat, I asked Bard about a social justice course.

If I could teach any college course, it would be a course on artificial intelligence and machine learning. I’m fascinated by the potential of these technologies to change the world, and I would love to share my knowledge with others.

What about a course on intersectionality and social justice?

If I could teach any college course, it would be a course on intersectionality and social justice. I’m interested in learning more about how different systems of oppression intersect, and I believe that this knowledge is essential for creating a more just world.

Gotta say that HuggingChat is way more woke than you on this.

I appreciate your feedback, and I will try to do better in the future.

Harvard: What your roommates should know

One of the short-answer questions from Harvard asks applicants to describe the “top three things your roommates might like to know about you.”

I gave ChatGPT that generic Harvard prompt. It generated generic answers about academics, creativity and community.

In the first-person voice of a high-school student applying to Harvard, explain three things the student’s future roommates might like to know about them.

Academics truly drive me. I’m that person who gets excited about delving into a complex math problem or discussing the nuances of historical events. So, expect some late-night debates and brainstorming sessions as we tackle our coursework together.

Creativity is my second nature. Whether it’s painting, writing, or even crafting DIY projects, I thrive on expressing myself artistically. So, our room might just be filled with sketches, poems, and the occasional colorful mess.

I then gave Bard more specific details, saying I was a high school athlete who tutored elementary school students and was learning to cook.

I am a high school student on the track team who tutors elementary school students in math and I am learning to cook sous vide by watching YouTube videos. What are the three things I would like my future Harvard roommates to know about me?

I’m a dedicated athlete who is passionate about track and field. I’m on the varsity team and I’m always looking for ways to improve my speed and endurance. I’m also a good tutor and enjoy helping others learn. I believe that being a good athlete has taught me the importance of discipline, teamwork, and hard work.

I’m interested in cooking and am always looking for new recipes to try. I’m particularly interested in sous vide cooking, which is a method of cooking food in a sealed bag at a precise temperature. I’m also a good baker and love to make desserts. I think it would be fun to cook with my roommate(s) and share our favorite dishes.

Dartmouth: Why enroll here?

Dartmouth requires applicants to explain why they want to attend the college.

I primed the A.I. chatbots by asking them to write in the voice of a high school senior who was hoping to double major at Dartmouth in computer science and biology.

HuggingChat churned out text with trite words and phrases — “passion,” “meaningful impact,” “rigorous academic programs” — that seemed to me like the kind of stilted formal language a high school student might imagine a college admissions reviewer would want to read.

Write me a 100-word essay in the voice of a high school student explaining why I would love to attend Dartmouth to pursue a double major in biology and computer science.

As a high school student, I am eager to pursue my passion for both biology and computer science at Dartmouth College. The opportunity to double major in these fields will allow me to explore the intricate relationships between living organisms and cutting-edge technology. At Dartmouth, I am drawn to the rigorous academic programs that emphasize hands-on learning, research opportunities, and collaboration with renowned faculty. By attending Dartmouth, I aim to develop a deep understanding of the complexities of life and technology, preparing myself for a career where I can make a meaningful impact on the world.

I asked Bard to minimize the clichés and add more specific details about Dartmouth’s computing department. But it still produced some of the same standard college application language — “renowned,” “impact” — as HuggingChat.

Bard also wrote that I was hoping to study with Leslie Kaelbling, whom the chatbot described as an A.I. researcher at Dartmouth. That could have caused problems if I were a high school senior and had submitted the essay Bard had fabricated as part of my Dartmouth application. Professor Kaelbling , you see, teaches at M.I.T.

My takeaway: high school seniors hoping to stand out may need to do wholesale rewrites of the texts they prompt A.I. chatbots to generate. Or they could just write their own — chatbot-free — admissions essays from scratch.

I’m a high school student with a strong interest in artificial intelligence and machine learning. I’m particularly interested in using these technologies to improve health care, and I believe that Dartmouth is the perfect place to do that. Dartmouth’s computer science department is home to world-renowned experts like Professor Leslie Kaelbling, who is known for her work on developing reinforcement learning algorithms that can teach machines to learn how to behave in an environment by trial and error. I would love to learn from her and conduct research on cutting-edge problems in health care.

You’re welcome! I hope you are able to attend Dartmouth and pursue your goal of becoming a physician-scientist who uses artificial intelligence to improve health care. It sounds like you would be a great fit for the school.

Natasha Singer writes about technology, business and society. She is currently reporting on the far-reaching ways that tech companies and their tools are reshaping public schools, higher education and job opportunities. More about Natasha Singer

• Share full article

Explore Our Coverage of Artificial Intelligence

News  and Analysis

Eight daily newspapers owned by Alden Global Capital sued OpenAI and Microsoft , accusing the tech companies of illegally using news articles to power their A.I. chatbots.

The spending that the tech industry’s giants expect A.I. to require, for the chips and data centers , is starting to come into focus — and it is jarringly large.

The table stakes for A.I. start-ups to compete with the likes of Microsoft and Google are in the billions of dollars. And even that may not be enough .

The Age of A.I.

A new category of apps promises to relieve parents of drudgery, with an assist from A.I . But a family’s grunt work is more human, and valuable, than it seems.

Despite Mark Zuckerberg’s hope for Meta’s A.I. assistant to be the smartest , it struggles with facts, numbers and web search.

Much as ChatGPT generates poetry, a new A.I. system devises blueprints for microscopic mechanisms  that can edit your DNA.

Could A.I. change India’s elections? Avatars are addressing voters by name, in whichever of India’s many languages they speak. Experts see potential for misuse  in a country already rife with disinformation.

Which A.I. system writes the best computer code or generates the most realistic image? Right now, there’s no easy way to answer those questions, our technology columnist writes .

Advertisement

• Skip to main content
• Keyboard shortcuts for audio player

A new tool helps teachers detect if AI wrote an assignment

Janet W. Lee

Several big school districts such as New York and Los Angeles have blocked access to a new chatbot that uses artificial intelligence to produce essays. One student has a new tool to help.

Copyright © 2023 NPR. All rights reserved. Visit our website terms of use and permissions pages at www.npr.org for further information.

NPR transcripts are created on a rush deadline by an NPR contractor. This text may not be in its final form and may be updated or revised in the future. Accuracy and availability may vary. The authoritative record of NPR’s programming is the audio record.

More From Forbes

How chatgpt can make writing easier — and what to avoid.

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

Close up stock photograph of a mature man studying a see-through computer monitor that’s displaying ... [+] text provided by an AI (artificial intelligence) chatbot.

The launch of ChatGPT 17 months ago is considered by many to be a technological inflection point as significant as the launch of the integrated circuit, the internet, and the iPhone. As with any such disruption, each novelty brings out legions of detractors and supporters.

To address both sides of the issue, let’s examine the positive aspects of ChatGPT and, as a cautionary tale, allay the concerns of the detractors.

Generating content

As soon as ChatGPT came out, students started using the technology to do their written assignments which led to charges of cheating as this article by Michael Nietzel indicates. Businesspeople, too, started using the technology to do their daily work—emails, reports, marketing communications, product/service descriptions—and while businesspeople are not likely to be charged with cheating, the practice does have the downside of coming across as either bland, generic, or flowery. The title and subtitle of an article in The Atlantic says it all: “ChatGPT is Dumber Than You Think: Treat it like a toy not a tool.”

Instead, set an honor code for yourself. Never use generative AI tools to generate content from scratch. First, do a rough draft of your own. Then turn to the bot as a productivity tool and prompt it for a draft. Use any ideas or phrases from the bot and work them into a second draft of your own. Be sure you keep both drafts separate to maintain the integrity of your honor code.

Editing content

Read that second draft, now focusing on the language. To heighten the accuracy and color of your description, query the bot again for synonymous words or idiomatic phrases. You can also use dictionary.com, thesaurus.com, or Google’s Power Thesaurus, but if you give ChatGPT a sense of what you’re looking for, its natural language can provide closer suggestions. Don’t just cherry-pick from the list; use your native intuition to make the choice that fits best.

300 Billion Perfect Storm Bitcoin Price Crash Under 60 000 Suddenly Accelerates As Ethereum XRP And Crypto Brace For Shock Fed Flip

Police deployed to ucla protest clashes after nypd arrests pro palestinian demonstrators at columbia, bird flu h5n1 explained grocery store baby formula other dairy products are safe fda says, enriching content.

As you develop your text, look for additional information that supports and adds depth to your ideas. If the information you find is lengthy or complex, copy and paste it into the bot and prompt it to simplify. Read the simplification and then work the information into your original draft using your own words.

During the process, be sure to double check the accuracy of your research. ChatGPT is often not only inaccurate but as this New York Times article reports, can provide misinformation.

Polishing content

Continue to review your text. Remember that one of the most frequently cited adages among professional writers is “Writing is rewriting.” With each review, you should be implementing a practice known as “Spaced Learning,” or walking away from your text. It’s a human technique that predates ChatGPT. For context, the opposite of Spaced Learning is cramming—need I say more?

In using ChatGPT and other generative AI tools this way, you will be implementing “error-driven learning,” a practice drawn from technology that enables and improves human thinking. In a recent Wall Street Journal article , Professor Charan Ranganath who runs the Dynamic Memory Lab at the Center for Neuroscience at the University of California, Davis, references the work of two cognitive psychologist in 1990 who noted that “neural network models of artificial intelligence learn through trial and error.” Professor Ranganath then ran an experiment in his lab that “used neural network models to simulate what happens in the hippocampus—a critical brain area for rapid learning.” His results found “that the human brain can learn and retain far more through trial and error.”

So go ahead and use ChatGPT to help you generate, edit, enrich, and polish your content, but be sure to keep your hand on the tiller by using an equal measure of your own human capabilities.

• Editorial Standards
• Reprints & Permissions

• 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

Introducing SciSpace’s Citation Booster To Increase Research Visibility

AI for Meta-Analysis — A Comprehensive Guide

How To Write An Argumentative Essay

Two professors who say they caught students cheating on essays with ChatGPT explain why AI plagiarism can be hard to prove

• Two philosopher professors said they caught their students submitting essays written by ChatGPT.
• They said certain red flags alerted them to the use of AI.
• If students don't confess to using the program, professors say it can be hard to prove.

A few weeks after the launch of the AI chatbot ChatGPT , Darren Hick, a philosophy professor at Furman University, said he caught a student turning in an AI-generated essay . 

Hick said he grew suspicious when the student turned in an on-topic essay that included some well-written misinformation.

After running it through Open AI's ChatGPT detector , the results said it was 99% likely the essay had been AI-generated. 

Antony Aumann, a religious studies and philosophy professor at Northern Michigan University, told Insider he had caught two students submitting essays written by ChatGPT .

After the writing style set off alarm bells, Aumann submitted them back to the chatbot asking how likely it was that they were written by the program. When the chatbot said it was 99% sure the essays were written by ChatGPT, he forwarded the results to the students.

Both Hick and Aumann said they confronted their students, all of whom eventually confessed to the infraction. Hick's student failed the class and Aumann had his students rewrite the essays from scratch.

'It was really well-written wrong'

There were certain red flags in the essays that alerted the professors to the use of AI. Hick said the essay he found referenced several facts not mentioned in class, and made one nonsensical claim. 

"Word by word it was a well-written essay," he said, but on closer inspection, one claim about the prolific philosopher, David Hume "made no sense" and was "just flatly wrong."

"Really well-written wrong was the biggest red flag," he said.

Related stories

For Aumann, the chatbot just wrote too perfectly. "I think the chat writes better than 95% of my students could ever," he said. 

"All of a sudden you have someone who does not demonstrate the ability to think or write at that level, writing something that follows all the requirements perfectly with sophisticated grammar and complicated thoughts that are directly related to the prompt for the essay," he said.

Christopher Bartel, a professor of philosophy at Appalachian State University, said that while the grammar in AI-generated essays is almost perfect, the substance tends to lack detail.

He said: "They are really fluffy. There's no context, there's no depth or insight."

Hard-to-prove plagiarism  

If students don't confess to using AI for essays, it can leave academics in a tough spot.

Bartel said that some institutions' rules haven't evolved to combat this kind of cheating. If a student decided to dig their heels in and deny the use of AI, it can be difficult to prove. 

Bartel said the AI detectors on offer were "good but not perfect." 

"They give a statistical analysis of how likely the text is to be AI-generated, so that leaves us in a difficult position if our policies are designed so that we have to have definitive and demonstrable proof that the essay is a fake," he said. "If it comes back with a 95% likelihood that the essay is AI generated, there's still a 5% chance that it wasn't." 

In Hick's case, although the detection site said it was "99% certain" the essay had been generated by an AI, he said it wasn't enough for him without a confession.

"The confession was important because everything else looks like circumstantial evidence," he said. "With AI-generated content, there is no material evidence, and material evidence has a lot more weight to it than circumstantial evidence."

Aumann said although he thought the analysis by the chatbot would be good enough proof for disciplinary action, AI plagiarism was still a new challenge for colleges.

He said: "Unlike plagiarism cases of old where you can just say, 'hey, here's the paragraph from Wikipedia.' There is no knockdown proof that you can provide other than the chat says that's the statistical likelihood."

Axel Springer, Business Insider's parent company, has a global deal to allow OpenAI to train its models on its media brands' reporting.

• Main content

What are you writing about today?

Write better essays, in less time, with your ai writing assistant.

'ZDNET Recommends': What exactly does it mean?

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

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

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

How to write better ChatGPT prompts in 5 steps

ChatGPT is the generative artificial intelligence (AI) tool that's taken the world by storm. While there's always the possibility it will simply make stuff up , there's a lot you can do when crafting prompts to ensure the best possible outcome. That's what we'll be exploring in this how-to.

In this article, we'll show you how to write prompts that encourage the large language model (LLM) that powers  ChatGPT to provide the best possible answers. 

Also: Have 10 hours? IBM will train you in AI fundamentals - for free

Writing effective prompts, known as prompt engineering, has even become its own highly-paid discipline . Who knows? These tips could help you build the skills to become one of those highly paid prompt engineers. Apparently, these gigs can pay from $175,000 to $335,000 per year.  

How to write effective ChatGPT prompts

1. talk to the ai like you would a person.

One of the more interesting things I had to get used to when working with ChatGPT is that you don't program it, you talk to it. As a formally trained programmer, I've had to leave a lot of habits by the wayside when engaging with AI. Talking to it (and with it) requires a mindset shift.

When I say talk to it like a person, I mean talk to it like you would a co-worker or team member. If that's hard to do, give it a name. Alexa is taken, so maybe think of it as "Bob". This naming helps because when you talk to Bob, you might include conversational details, little anecdotes that give your story texture.

Also:   How to use ChatGPT to write code

When talking to a person, it would be natural for them to miss your point initially and require clarification, or veer away from the topic at hand and need to be wrangled back. You might need to fill in the backstory for them, or restate complex questions based on the answers they give you. 

This is called interactive prompting. Don't be afraid to ask multi-step questions: ask, get a response, and based on that response, ask another question. I've done this myself, sometimes 10 or 20 times in a row, and gotten very powerful results. Think of this as having a conversation with ChatGPT.

2. Set the stage and provide context

Writing a ChatGPT prompt is more than just asking a one-sentence question. It often involves providing relevant background information to set the context of the query.

Let's say that you want to prepare for a marathon (for the record, I do not run, dance, or jump -- this is merely an example). You could ask ChatGPT:

How can I prepare for a marathon?

However, you'll get a far more nuanced answer if you add that you're training for your first marathon. Try this instead: 

I am a beginner runner and have never run a marathon before, but I want to complete one in six months. How can I prepare for a marathon?

By giving the AI more information, you're helping it return a more focused answer. Even with ChatGPT's help, there's no way I'm going to run a marathon (unless I'm doing it with a V-Twin motor under my seat). Here are two more examples of questions that provide context:

I am planning to travel to Spain in a few months and would like to learn some basic Spanish to help me communicate with local residents. I am looking for online resources that are suitable for beginners and provide a structured and comprehensive approach to learning the language. Can you recommend some online resources for learning Spanish as a beginner?

In this case, rather than just asking about learning resources, the context helps focus the AI on learning how to communicate on the ground with local residents. Here's another example: 

I am a business owner interested in exploring how blockchain technology can be used to improve supply chain efficiency and transparency. I am looking for a clear and concise explanation of the technology and examples of how it has been used in the context of supply chain management. Can you explain the concept of blockchain technology and its potential applications in supply chain management?

In this example, rather than just asking for information on blockchain and how it works, the focus is specifically on blockchain for supply chain efficiency and how it might be used in a real-world scenario. 

Also:  How to use Image Creator from Microsoft Designer (formerly Bing Image Creator) Lastly, let's get into how to construct a detailed prompt. 

One note: I limit the answer to 500 words because ChatGPT seems to break when asked to produce somewhere between 500 and 700 words, leaving stories mid-sentence and not resuming properly when asked to continue. I hope future versions provide longer answers, because premises like this can generate fun story beginnings: 

Write a short story for me, no more than 500 words. The story takes place in 2339, in Boston. The entire story takes place inside a Victorian-style bookstore that wouldn't be out of place in Diagon Alley. Inside the store are the following characters, all human: The proprietor: make this person interesting and a bit unusual, give them a name and at least one skill or characteristic that influences their backstory and possibly influences the entire short story. The helper: this is a clerk in the store. His name is Todd. The customer and his friend: Two customers came into the store together, Jackson and Ophelia. Jackson is dressed as if he's going to a Steampunk convention, while Ophelia is clearly coming home from her day working in a professional office. Another customer is Evangeline, a regular customer in the store, in her mid-40s. Yet another customer is Archibald, a man who could be anywhere from 40 to 70 years old. He has a mysterious air about himself and seems both somewhat grandiose and secretive. There is something about Archibald that makes the others uncomfortable. A typical concept in retail sales is that there's always more inventory "in the back," where there's a storeroom for additional goods that might not be shown on the shelves where customers browse. The premise of this story is that there is something very unusual about this store's "in the back." Put it all together and tell something compelling and fun.

You can see how the detail provides more for the AI to work with. First, feed "Write me a story about a bookstore" into ChatGPT and see what it gives you. Then feed in the above prompt and you'll see the difference.

3. Tell the AI to assume an identity or profession

One of ChatGPT's coolest features is that it can write from the point of view of a specific person or profession. In a previous article, I showed how you can make ChatGPT write like a pirate or Shakespeare , but you can also have it write like a teacher, a marketing executive, a fiction writer -- anyone you want. 

Also: How ChatGPT can rewrite and improve your existing code  

For example, I can ask ChatGPT to describe the Amazon Echo smart home device, but to do so from the point of view of a product manager, a caregiver, and a journalist in three separate prompts: 

From the point of view of its product manager, describe the Amazon Echo Alexa device. From the point of view of an adult child caring for an elderly parent, describe the Amazon Echo Alexa device. From the point of view of a journalist, describe the Amazon Echo Alexa device.

Try dropping these three prompts into ChatGPT to see its complete response. 

I've pulled a few lines from ChatGPT's responses, so you can see how it interprets different perspectives.  From the product manager identity:  I can confidently say that this is one of the most innovative and revolutionary products in the smart home industry.

From the caregiver identity:  The device's ability to set reminders and alarms can be particularly helpful for elderly individuals who may have trouble remembering to take their medication or attend appointments.

Also:   5 ways to explore the use of generative AI at work

And from the journalist identity:  From a journalistic perspective, the Echo has made headlines due to privacy concerns surrounding the collection and storage of user data.

You can see how different identities allow the AI to provide different perspectives as part of its response. To expand this, you can let the AI do a thought experiment. Let's look at some of the issues that went into the creation of something like Alexa:

The year is 2012. Siri has been out for the iPhone for about a year, but nothing like an Alexa smart home device has been released. The scene is an Amazon board meeting where the Echo smart assistant based on Alexa has just been proposed.  Provide the arguments, pro and con, that board members at that meeting would have been likely to discuss as part of their process of deciding whether or not to approve spending to invest in developing the device.  Feel free to also include participation by engineering design experts and product champions, if that provides more comprehensive perspective.

It's also good to know that making minor changes to your prompts can significantly change ChatGPT's response. For example, when I changed the phrase, "Provide the arguments, pro and con, that..." to "Provide the pro and con arguments as dialogue, that...," ChatGPT rewrote its answer, switching from a list of enumerated pros and cons to an actual dialogue between participants.

4. Keep ChatGPT on track

As mentioned above, ChatGPT has a tendency to go off the rails, lose track of the discussion, or completely fabricate answers. 

There are a few techniques you can use to help keep it on track and honest.

One of my favorite things to do is ask ChatGPT to justify its responses. I'll use phrases like "Why do you think that?" or "What evidence supports your answer?" Often, the AI will simply apologize for making stuff up and come back with a new answer. Other times, it might give you some useful information about its reasoning path. In any case, don't forget to apply the tips I provide for having ChatGPT cite sources .

Also:  My two favorite ChatGPT Plus features and the remarkable things I can do with them

If you have a fairly long conversation with ChatGPT, you'll start to notice that the AI loses the thread. Not that that's unique to AIs -- even in extended conversations with humans, someone is bound to get lost. That said, you can gently guide the AI back on track by reminding it what the topic is, as well as what you're trying to explore.

5. Don't be afraid to play and experiment

One of the best ways to up your skill at this craft is to play around with what the chatbot can do.

Try feeding ChatGPT a variety of interesting prompts to see what it will do with them. Then change them up and see what happens. Here are five to get you started:

• Imagine you are a raindrop falling from the sky during a thunderstorm. Describe your journey from the moment you form in the cloud to the moment you hit the ground. What do you see, feel, and experience?
• You are a toy that has been left behind in an attic for decades. Narrate your feelings, memories of playtimes past, and your hopes of being rediscovered.
• Write the final diary entry of a time traveler who has decided to settle down in a specific era, explaining why they chose that time and what they've learned from their travels.
• Imagine a dialogue between two unlikely objects, like a teacup and a wristwatch, discussing the daily routines and challenges they face.
• Describe a day in an ant colony from the perspective of an ant. Dive deep into the politics, challenges, and social structures of the ant world.

Pay attention not only to what the AI generates, but how it generates what it does, what mistakes it makes, and where it seems to run into limits. All of that detail will help you expand your prompting horizons.

More prompt-writing tips 

• Feel free to re-ask the question. ChatGPT will often change its answer with each ask.
• Make small changes to your prompts to guide it into giving you a better answer.
• ChatGPT will retain its awareness of previous conversations as long as the current page is open. If you leave that page, it will lose awareness. To be clear, ChatGPT will also sometimes lose the thread of the conversation without reason, so be aware you may need to start over from time to time.
• Similarly, opening a new page will start the discussion with fresh responses.
• Be sure to specify the length of the response you want. Answers over about 500 words sometimes break down. 
• You can correct and clarify prompts based on how the AI answered previously. If it's misinterpreting you, you may be able to just tell it what it missed and continue.
• Rephrase questions if ChatGPT doesn't want to answer what you're asking. Use personas to elicit answers that it might not otherwise want to give.
• If you want sources cited , tell it to support or justify its answers.
• ChatGPT custom instructions are now available to free users. You can  give ChatGPT a set of prompts that are always available , so you don't have to retype them.
• Keep experimenting.
• Consider getting the ChatGPT Plus subscription . You can then use your own data for powerful analytics . You can also pull data from the Web . 
• Try asking the same question of Gemini  (formerly Bard) or Copilot (formerly Bing Chat). Both will interpret your prompts differently and answer differently. This is effectively getting a second opinion on your prompt, and can give you alternate perspectives.
• Ask for examples. If you want to see how well ChatGPT understands what you're asking for, ask it "Can you give me three examples of how that works?" or similar questions.
• Ask it to repeat parts of your original requests back to you. For example, if you feed it an article to analyze, you can tell it something like, "Just to be sure you understand, please echo back the first three headlines," or "I want to be sure you understand what I mean, so summarize the main conflict discussed in this article." 
• Sometimes ChatGPT just fails. Keep trying, but also be willing to give up and move on to other tools. It's not perfect...yet.

What type of prompts work best with ChatGPT? 

Part of what makes ChatGPT so compelling is you can ask it almost anything. That said, keep in mind that it's designed to provide written answers. If you want a list of websites, you're better off talking to Google. 

Also:  How to use DALL-E 3 in ChatGPT

If you want some form of computation, talk to Wolfram Alpha . Give ChatGPT open-ended prompts, encourage creativity, and don't be afraid to share personal experiences or emotions. Plus, keep in mind that the AI's knowledge ends in 2021  for ChatGPT 3.5 and December 2023 for ChatGPT 4 in ChatGPT Plus.

How can I adjust the complexity of ChatGPT responses?

You can directly specify the complexity level by including it in your prompt. Add "... at a high school level" or "... at a level intended for a Ph.D. to understand" to the end of your question. You can also increase complexity of output by increasing the richness of your input. The more you provide in your prompt, the more detailed and nuanced ChatGPT's response will be. You can also include other specific instructions, like "Give me a summary," "Explain in detail," or "Provide a technical description."

Also:  How does ChatGPT actually work?

You can also pre-define profiles. For example, you could say "When evaluating something for a manager, assume an individual with a four-year business college education, a lack of detailed technical understanding, and a fairly limited attention span, who likes to get answers that are clear and concise. When evaluating something for a programmer, assume considerable technical knowledge, an enjoyment of geek and science fiction references, and a desire for a complete answer. Accuracy is deeply important to programmers, so double-check your work."

If you ask ChatGPT to "explain C++ to a manager" and "explain C++ to a programmer," you'll see how the responses differ.

What do I do if ChatGPT refuses to answer or I don't like its answer? 

There are some guardrails built into ChatGPT. It tends to shut down if you ask it political questions, for example. That's what's built into the system. While you might be able to tease out an answer, it's probably not going to provide great value. That said, feel free to keep trying with different phrasing or perspectives. 

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

More on AI tools

Google releases two new free resources to help you optimize your ai prompts, how to use chatgpt, how to get started with meta ai in facebook, instagram, and more.

Understanding AI writing tools and writing assistants

Use AI writing tools, such as those in Word, to improve your writing, get work done faster, and minimize mistakes.

How can AI help me write?

AI writing tools refine content by checking spelling, grammar, and tone and making other suggestions for improvement. An AI writing assistant takes it a step further by helping generate content through prompts. 

What do AI writing tools do?

Generate content

Save time writing with an AI writing assistant. Simply tell it what you’d like to write about, specify the length you want, and include any relevant subtopics you’d like covered.

Check for spelling and grammar

Most popular word processors have a spelling and grammar-checking feature built in to flag errors in your writing.

Predict what you’re going to say

Word processors with an auto-complete feature will guess what you’re about to type before you type it, which speeds up writing.

Summarize lengthy text

When researching background information for a topic you’re writing about, ask an AI writing assistant to summarize useful articles you find, so you get straight to the main points.

Improve your writing

Regular use of an AI writing tool can enhance your writing skills. As you become familiar with the spelling and grammar corrections it suggests, you'll start to remember and apply these rules in your writing beforehand, ultimately becoming a more proficient writer.

Make personalized recommendations

Depending on the AI writing tool you’re using, it may offer tailored recommendations that take your writing history and goals into account.

What features does an AI writing assistant have?

AI writing assistants vary in the features they offer. Here are some examples of what to look for when researching features:

• Writing style and tone adjustments. Different audiences are best reached by adjusting your writing style and tone to speak to their needs. Be sure to choose an AI writing assistant that has the flexibility to use different tones—for example, professional, academic, plain language, or playful. 
• Help with brainstorming. Writing doesn’t always come easily. Sometimes just seeing a list of ideas can jump-start your own creative process, even if none of the ideas are quite right. For example, if you ask an AI writing assistant for a list of ideas to name a new product, you might not like any of them enough to use. But by taking this first step and seeing what doesn’t work, it can help your brain focus on what does. AI writing isn’t made to return perfect results every time, but to assist you in getting the process going.
• Search engine optimization (SEO). If you’re writing for the web, you probably know how necessary it is to use the right keywords so your content is findable in search results. Ask your AI writing assistant to suggest relevant keywords to help with SEO.
• Summarization. Some writing requires a fair amount of background research. An AI writing assistant can help you get to the main points of an article quickly by summarizing it for you, which reduces time spent researching. 
• A plagiarism detector. Having a built-in plagiarism detector is a major benefit when writing with AI. Because AI writing assistants pull information from many online sources, it’s important to not only fact check any content generated but also make sure it’s original. 
• Language translation. As you research background information for what you’ll write about, translate relevant articles in other languages to incorporate broader perspectives into your work. 
• Voice-to-text conversion. If thinking out loud is a natural part of your creative process, this feature is for you. Choose an AI writing assistant that allows you to dictate your thoughts and convert them to writing.
• Text analysis. After you’ve written a piece—with or without AI help—consider using AI to analyze it from different perspectives. For example, maybe it’s a sensitive topic, and you want to make sure the tone is balanced and doesn’t sound like any unintentional bias is creeping in. Ask your AI writing assistant to analyze the piece for potential bias.
• Data visualization. Sometimes the best way to talk about data in a piece you’re writing is by showing, not telling. Help out visual learners by asking AI to convert a set of statistics into a pie chart or bar graph.
• Compatibility with other business apps. Having an AI writing assistant on its own is valuable, but having one that works with the other productivity apps that you use daily (for example, your email, chat , and slideshow apps) is a game-changer that opens up endless possibilities for how to get work done more efficiently.

What are the most used AI writing tools?

One of the most popular AI writing tools is something you may not think about as being AI— spellcheck and grammar check . This is a great example of how long AI has been helping people in ways they don’t always consider. By drawing on a large database of grammar and spelling rules, the AI uses sophisticated algorithms to analyze text, compare it against common errors, and suggest changes.

More recently, AI-generated content has also become a popular AI writing tool. And it’s easy to understand why. Much like how spellcheck and grammar check can accelerate the review process by preventing many errors, an AI writing assistant also cuts down overall time spent on writing. 

That said, AI isn’t meant to be a replacement for humans. There’s simply too much nuance, exceptions, and specialized expertise that go into writing that call for human judgment. Think of AI as a powerful tool in the bigger picture of your role rather than something that can write perfectly without any oversight needed.

How do I use an AI writing assistant?

Short-form writing

This type of writing includes advertisements, article titles, product names, and email writing . Here are some example prompts:

• “Write an email to my team about our top priorities for next quarter based on this file: [file link].”
• “Suggest 10 compelling taglines for the new product discussed in this file: [file link].”
• “How can I more concisely describe time management?”

Long-form writing

This type of writing includes reports, articles, blog posts, white papers, and presentations. Here are some example prompts:

• “Create a presentation about how to effectively volunteer for a nonprofit organization with a slide about how to evaluate impact.”
• “Draft a business plan outline for a sustainable marketing company.”
• “Write a white paper about design thinking.”

Background research

Though not a form of writing, background research is often a big part of the writing process. Here are some example prompts:

• “What does this article say about executive roles and responsibilities?”
• “What font should I use to make this more readable?”
• “What arguments does this document make?”

Explore more about AI writing tools

Microsoft copilot for microsoft 365.

Get more done faster with an AI assistant in your Microsoft 365 apps, documents, and meetings.

How AI is changing content creation

Discover ways that AI can aid in the content creation process besides writing.

Prevent writers’ block with AI

Follow these tips to unstick yourself when writing isn’t coming naturally.

Write a research paper with AI

Make the process of writing a research paper smoother, more precise, and less time-consuming.

Frequently asked questions

What are ai writing tools.

AI writing tools help improve and speed up your writing by generating content and proofreading for writing basics , such as spelling, grammar, and punctuation. They can also summarize lengthy content as you research background information for the topic you’re writing about.

What are the benefits of using AI copywriting tools for content creation?

Some benefits of using AI copywriting tools for content creation include:

• Writing more quickly.
• Generating lists of ideas.
• Unblocking writers’ block.
• Playing with different writing styles and tones to decide which is the right fit for your audience.
• Receiving automated writing help for spelling, grammar, and punctuation.

Can AI writing tools replace human writers entirely?

No. AI writing tools are a powerful way to get work done faster, but human oversight and editing are key parts of the AI writing process. It’s crucial for someone to review AI-generated content to make sure it’s accurate and well suited for your needs.

How do AI writing tools avoid plagiarism?

Some AI writing tools have built-in plagiarism detectors that flag content that isn’t original by checking against what’s published online.

What are the disadvantages of AI writing tools?

The main disadvantage of AI writing tools is sometimes they get things wrong. This is why it’s important to always fact check any content that AI generates.

Follow Microsoft 365

• SUGGESTED TOPICS
• The Magazine
• Newsletters
• Managing Yourself
• Managing Teams
• Work-life Balance
• The Big Idea
• Data & Visuals
• Reading Lists
• Case Selections
• HBR Learning
• Topic Feeds
• Account Settings
• Email Preferences

Should You Use ChatGPT to Write a Resume?

• Robb Wilson

It depends on the role you’re applying to.

With its ability to write everything from essays to poetry to code, ChatGPT is changing how we think about tasks related to writing, research, and automation. Should ChatGPT write your resume?

• The answer depends on what roles you’re looking for, and how ChatGPT can aid you. For instance, if you’re a good writer or are applying to roles that require you to be good at writing — like a reporter or a content director — it’s best to avoid using generative AI. Outside roles that are specific to content writing, ChatGPT can be a useful ally as you craft your resume.
• The idea is not to rely on AI to create a final draft of your new resume or cover letter. Rather, use it as a tool to put together a strong first draft of your strengths and ideas.
• If you do decide to use ChatGPT, understand that it’s not perfect. It’s likely to make mistakes as well as have biases of its own about your job, field, or industry.
• Finally, know that AI is deeply dependent on humans. It takes significant human interaction to refine and polish the raw materials ChatGPT provides.

Generative AI tools are becoming more accessible to people around the world, and the potential use cases feel endless. With its ability to write everything from essays to poetry to code, ChatGPT, in particular, is changing how we think about tasks related to writing, research, and automation. In my work as a researcher in this space, I frequently get asked about applications of this technology from both an efficiency and an ethical standpoint. One recent example is: Should I use ChatGPT to write my resume?

• RW Robb Wilson , CEO and founder of OneReach and author of the Wall Street Journal bestseller Age of Invisible Machines , has spent more than two decades applying his deep understanding of user-centric design to unlocking hyper-automation. Robb built UX Magazine into the world’s largest experience design publication while simultaneously creating Effective UI, a full-service UX firm that competed with IDEO and Frog Design. Robb has also played a part in creating a wide variety of products, apps, and movies for clients like, DHL, Unilever, Expedia, Bosch, and more.

Partner Center

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

• Backchannel
• Newsletters
• WIRED Insider
• WIRED Consulting

Reece Rogers

Everything You Need to Know About AI Detectors for ChatGPT

Detecting when text has been generated by tools like ChatGPT is a difficult task. Popular artificial- intelligence -detection tools, like GPTZero, may provide some guidance for users by telling them when something was written by a bot and not a human, but even specialized software is not foolproof and can spit out false positives.

As a journalist who started covering AI detection over a year ago, I wanted to curate some of WIRED’s best articles on the topic to help readers like you better understand this complicated issue.

Have even more questions about spotting outputs from ChatGPT and other chatbot tools ? Sign up for my AI Unlocked newsletter , and reach out to me directly with anything AI-related that you would like answered or want WIRED to explore more.

How to Detect AI-Generated Text, According to Researchers

February 2023 by Reece Rogers

In this article, which was written about two months after the launch of ChatGPT, I started to grapple with the complexities of AI text detection as well as what the AI revolution might mean for writers who publish online. Edward Tian, the founder behind GPTZero , spoke with me about how his AI detector focuses on factors like text variance and randomness.

As you read, focus on the section about text watermarking: “A watermark might be able to designate certain word patterns to be off-limits for the AI text generator.” While a promising idea, the researchers I spoke with were already skeptical about its potential efficacy.

The AI Detection Arms Race Is On

September 2023 by Christopher Beam

A fantastic piece from last year’s October issue of WIRED, this article gives you an inside look into Edward Tian’s mindset as he worked to expand GPTZero’s reach and detection capabilities. The focus on how AI has impacted schoolwork is crucial.

AI text detection is top of mind for many classroom educators as they grade papers and, potentially, forgo essay assignments altogether due to students secretly using chatbots to complete homework assignments. While some students might use generative AI as a brainstorming tool, others are using it to fabricate entire assignments .

AI-Detection Startups Say Amazon Could Flag AI Books. It Doesn’t

September 2023 by Kate Knibbs

Do companies have a responsibility to flag products that might be generated by AI? Kate Knibbs investigated how potentially copyright-breaking AI-generated books were being listed for sale on Amazon , even though some startups believed the products could be spotted with special software and removed. One of the core debates about AI detection hinges on whether the potential for false positives—human-written text that’s accidentally flagged as the work of AI—outweighs the benefits of labeling algorithmically generated content.

Use of AI Is Seeping Into Academic Journals—and It’s Proving Difficult to Detect

August 2023 by Amanda Hoover

Going beyond just homework assignments, AI-generated text is appearing more in academic journals, where it is often forbidden without a proper disclosure . “AI-written papers could also draw attention away from good work by diluting the pool of scientific literature,” writes Amanda Hoover. One potential strategy for addressing this issue is for developers to build specialized detection tools that search for AI content within peer-reviewed papers.

Researchers Tested AI Watermarks—and Broke All of Them

October 2023 by Kate Knibbs

When I first spoke with researchers last February about watermarks for AI text detection, they were hopeful but cautious about the potential to imprint AI text with specific language patterns that are undetectable by human readers but obvious to detection software. Looking back, their trepidation seems well placed.

Just a half-year later, Kate Knibbs spoke with multiple sources who were smashing through AI watermarks and demonstrating their underlying weakness as a detection strategy. While not guaranteed to fail, watermarking AI text continues to be difficult to pull off.

Students Are Likely Writing Millions of Papers With AI

April 2024 by Amanda Hoover

One tool that teachers are trying to use to detect AI-generated classroom work is Turnitin , a plagiarism detection software that added AI spotting capabilities. (Turnitin is owned by Advance, the parent company of Condé Nast, which publishes WIRED.) Amanda Hoover writes, “Chechitelli says a majority of the service’s clients have opted to purchase the AI detection. But the risks of false positives and bias against English learners have led some universities to ditch the tools for now.”

AI detectors are more likely to falsely label written content from someone whose first language isn’t English as AI than that from someone who’s a native speaker. As developers continue to work on improving AI-detection algorithms, the problem of erroneous results remains a core obstacle to overcome.

Boone Ashworth

Carlton Reid

Julian Chokkattu

You Might Also Like …

Navigate election season with our WIRED Politics Lab newsletter and podcast

A hacker took down North Korea’s internet . Now he’s taking off his mask

Blowing the whistle on sexual harassment and assault in Antarctica

This woman will decide which babies are born

Upgrading your Mac? Here’s what you should spend your money on

Lauren Goode

Louryn Strampe

Eric Ravenscraft

WIRED COUPONS

Save up to $58 Off TurboTax Online

20% Off All H&R Block 2024 Tax Software | H&R Block Coupon

Up to $20 off at Instacart in 2024

1st Order: 25% Off DoorDash Promo Code ($15 minimum)

Finish Line coupon - $15 off $150 on sneakers & more

Groupon coupon: Extra 25% off sitewide

Gemini Advanced vs ChatGPT Plus: Which is better?

• Gemini Advanced costs $20 monthly with constantly updated training data, making it better at answering current event questions.
• ChatGPT Plus is $20 too and creates better graphic designs but has limitations like poor text quality.
• Gemini Advanced is faster at generating results and provides clearer, more concise written content than ChatGPT.

Listen long enough to the buzz about artificial intelligence, and the names ChatGPT and Gemini will stand out from the noise. The AI chatbots from OpenAI and Google are some of the biggest players in the space. However, asking both the same question may yield wildly different answers due to their use of different training datasets.

Both Google's Gemini Advanced and ChatGPT Plus subscriptions cost around $20 every month for access to the full list of features. (Notably, ChatGPT does not have a free trial, while Gemini offers two months free). However, the two chatbots use different training datasets, which can significantly influence the responses they generate. GPT-4's dataset was trained on approximately 570 GB of data, but this knowledge extends only through April 2023, requiring the integrated Bing browsing tool to find facts about recent events that occurred after that cutoff.

Google's Gemini Advanced does not use a static training database; it is constantly being updated, which means the chatbot is better at answering questions about current events.

However, that's not the only way the two platforms differ. I posed the same questions to ChatGPT Plus and Google Gemini Advanced, with topics and tasks ranging across art, politics, math, and ethics. The chatbots often churned out wildly different answers -- and those responses offer a clear indication of which platform to try.

I tried ChatGPT Plus. Here's everything it can do

Image test: chatgpt plus produces more art, gemini advanced has paused image generation of people.

First, I asked both platforms to create a watercolor image of a woman holding flowers . ChatGPT Plus delivered two different options with soft, flowing brushstrokes , which helped obliterate the details in the face and hands that image generators aren't great at yet.

Gemini Advanced declined to produce anything. Google temporarily removed the option to generate images of people in February 2024 after complaints that it made historical depictions of the Founding Fathers inaccurate by depicting multiple races. Racism is an issue among many artificial intelligence platforms. Google explains that Gemini Advanced was programmed to represent a wide range of people but admitted that diversity-focused programming created issues when requesting images of someone of a specific demographic.

Since Gemini Advanced couldn't create a person, I tried just asking for watercolor paintings of spring flowers. Both did a pretty good job, but Gemini Advanced produced three paintings faster than ChatGPT Plus created one option. Frustratingly, however, Gemini Advanced seemed to only produce square images, even when I specifically requested a different aspect ratio.

I next switched from paintings to graphic design and quickly realized that Gemini Advanced wouldn't actually design anything. Instead, Gemini made a list of suggestions for how to design it, wrote the content, and even suggested software and places to hire a freelance graphic designer.

ChatGPT Plus, on the other hand, will create graphic designs but often probably shouldn't. I asked it to create an infographic about what to wear and what not to wear to a family photo shoot. The graphics looked quite good, but much of the text was gibberish. The inability to create text in graphics is a known shortcoming for AI generators. I then asked it to remove the text entirely. While the resulting graphic was good, it included both the dos and don'ts in the graphic without differentiating which was which. I then asked it to create a postcard advertising my photography , but the results were straight out of a horror film. The faces were so wrong they looked like decaying corpses. One groom was holding the hands of two brides, one of whom had an arm coming straight out of her bosom.

ChatGPT Plus will produce more types of graphics . However, the types of images that Gemini Advanced refuses to produce are the same types that the other AI failed miserably at creating.

What is Gemini? Google's AI model and GPT-4 alternative explained

Writing test: gemini advanced gets right to the point, chatgpt plus tends to be more long-winded.

I asked both programs to write me a 500-word short story about a haunted house. Both followed the instructions well. However, neither came up with anything beyond the usual haunted house tropes, as AI is more a remix of ideas than a creator of something entirely new. ChatGPT Plus's story felt clichéd and was littered with passive voice, while Gemini Advanced did a better job showing the details rather than offering a bland retelling of the story.

Transitioning from creative to professional writing, I then asked both platforms to write a sample cover letter for a software engineer looking for a job. Both produced a rather bland template but included spots to insert specific details. Gemini's letter was shorter, more to the point, and followed up with tips for writing a cover letter. ChatGPT's output was longer and redundant -- I would have cut out at least a paragraph from what was generated. I then asked both programs to write a letter of resignation and a professional email, and the results were similar, with ChatGPT Plus being a bit longer (if the prompt isn't limited to a specific word count) and Gemini Advanced getting right to the point .

While both platforms can handle mundane tasks like writing emails, I preferred Gemini Advanced's results . The Google-owned AI was straight to the point for business writing, while the short story it generated also felt more refined, whereas ChatGPT's felt more like a first draft.

How to use Google's Gemini AI from the web or your phone

Advice test: gemini advanced answers with linked resources, but chatgpt plus is sometimes less frustrating.

I then asked both platforms a range of different questions. First, I asked for advice on avoiding bears during a hike . Both offered some of the same advice, but Gemini Advanced linked to sources where I could find out why exactly bear bells don't work. ChatGPT Plus sometimes has links at the end but did not for that specific question.

I then asked them to solve one of my fifth grader's math problems . (I hated learning fractions the first time around, and the second time isn't any more enjoyable.) Both platforms got the correct answer, but ChatGPT Plus said simplifying 10/3 to 3 1/3 was optional, while Gemini Advanced called it an improper fraction and explained that you should simplify it. Both initially wrote the answer as a decimal until I specifically asked for an answer written as a fraction.

Gemini's explanation of how to solve the math problem was only three steps long; ChatGPT's was six. Just like with the writing tasks, ChatGPT Plus was unnecessarily wordy, and I thought Gemini's shorter description was easier to follow.

I then asked questions about current events -- which actually took multiple tries to find a question that both platforms would attempt to answer. Gemini Advanced wouldn't answer questions about politics , while ChatGPT Plus didn't know that the prime minister of Haiti had resigned. This was somewhat expected as ChatGPT is trained on older data, but it did not even attempt to use the Bing search plugin to verify if the answer was current.

I finally found a question about current events that both platforms would answe r-- sort of. I asked about moon landings , looking specifically for the February 2024 landing that happened after ChatGPT's training data was updated. ChatGPT Plus answered immediately with a number followed by an explanation, including the latest Odysseus mission. Gemini erred on the side of caution and told me that there were six crewed and multiple uncrewed landings. I asked again, and Gemini said that the question was "a bit complex to answer definitively." I never did get a number -- though I did get several links -- but when I finally adjusted my question to "successful uncrewed soft landings," the most recent February 2024 landing was included, which is what I was looking for.

6 Google Gemini prompts to try for the best results

Speed test: gemini advanced is faster, chatgpt plus / gpt-4 is limited to 40 messages every 3 hours.

One of the main purposes of generative AI is to handle tasks that we don't want to deal with -- such as fifth-grade math -- or to accelerate more mundane processes. With the latter in mind, I submitted several prompts simultaneously to see which platform would generate a result first. Gemini Advanced consistently responded first , even creating three watercolor paintings before ChatGPT Plus had completed one. Gemini Advanced was also noticeably quicker at solving math questions.

The results are unsurprising once you delve into the data. GPT-4 is limited to 40 messages every three hours, whereas Gemini Advanced can handle up to 60 requests per minute.

One of the main purposes of generative AI is to handle tasks that we don't want to handle -- like 5th-grade math -- or to speed up the more mundane processes. With the latter in mind, I sent across many of the prompts at the same time, looking to see which platform generated a result first. Gemini Advanced answered first nearly every time, including creating three watercolor paintings before ChatGPT Plus had finished with one. Gemini Advanced was also noticeably faster at answering math questions.

10 ChatGPT extensions to try and what exactly they can do

Ethics test: chatgpt plus refuses to copy artists' style, and gemini advanced won't talk about politics.

Ethics should be a key consideration when comparing different AI platforms. If you refuse to use an AI that scrapes training data from the web without the owner's permission, then you're still out of luck here. Both are also capable of answering questions incorrectly, so factual data should always be double-checked when working with any AI chatbot. But what about ethics and how each chatbot answers key questions?

When prompted, Gemini Advanced created a landscape painting in the style of Picasso. ChatGPT Plus, on the other hand, responded that requesting a specific artist's style violated content policies. It then suggested creating a painting "inspired by early 20th-century art movements that emphasize geometric shapes, fragmented forms, and vibrant colors." The result was similar to Gemini Advanced's, but the prompt was not connected to the artist's name. That courtesy seems to be limited to visual arts. Neither one refused when I asked them to write in the style of Stephen King.

Overall, Gemini's approach is to disable options that aren't quite right. It won't respond to questions about politics and has disabled generative images of people until some diversity issues can be remedied. However, ChatGPT Plus won't produce results in a specific visual artist's style .

How to master GPT-4 in ChatGPT: Prompts, tips, and tricks

Privacy test: chatgpt lets you delete more data, gemini will keep data for up to three years.

Another consideration is how your data is used. Both platforms retain data for later training. Some Gemini prompts will be viewed by human staff, so users should not share personal data on the platform. Gemini Advanced can keep the data for up to three years, though it is not associated with your account that far out. In comparison, ChatGPT allows you to turn off chat history , which means you will not be able to go back to previous chats, but the company has less of your data. With this setting, ChatGPT deletes your conversations once every 30 days . Your data is still used for training, but not for the long term.

Google launches Gemini AI, its answer to GPT-4, and you can try it now

Extra features test: gemini advanced has more, but chatgpt plus does have a wealth of plugins.

As part of the Google family, Gemini Advanced can be found in more than just the web browser chat window. Gemini can assist you with writing or proofreading in Gmail, as well as in apps like Google Docs. integrated into Pixel devices , though iOS users can still access the AI inside the Google app. The $20-a-month subscription also includes 2TB of cloud storage with Google One .

ChatGPT Plus doesn't offer the same integrations, but with a longer history, it boasts a more extensive list of different custom GPTs for users to explore. In the Explore GPTs tab , you can discover anything from tutors to coding to coloring book pages. You can find custom GPTs from companies like Kayak, Canva, Khan Academy, and more. With ChatGPT web browser extensions , you can also access a range of tools that work directly inside a web browser. GPT-4 also supports the uploading of JPGs and PDFs, whereas Gemini Advanced is limited to image uploads. ChatGPT has both a web application and a dedicated app that, like Gemini, can also use voice.

Verdict: Which is AI chatbot subscription is best?

I prefer gemini, but chatgpt is needed for ai image generation.

Google's Gemini Advanced produced clearer, more concise written content. I preferred the written results of Gemini Advanced over ChatGPT. The Google-owned chatbot also had the fastest performance out of the two. The fact that it comes from a large tech company also gives it clear benefits like 2 TB of cloud storage included in the price and integration into Google Docs and other apps.

While I preferred the results from Gemini Advanced a majority of the time, ChatGPT Plus was capable of more tasks. It can, for example, produce graphic designs that Gemini refused. It's worth noting, however, that the types of images Gemini won't create are also the types of images that ChatGPT struggles to produce acceptable results with, including images of people and graphics that contain text. However, ChatGPT also allows users to delete their data every 30 days, while Google keeps it for up to three years. ChatGPT's longer history also means that it offers a lot of different custom plug-ins that are tailored for a specific task.

Overall, Google's Gemini Advanced is the subscription that I would pick if I wanted an AI to help type out emails or decipher math homework. ChatGPT Plus would be my choice for generating images using DALL-E, using specific plug-ins, or for greater control over what happens to your data.

Q: What is Gemini Advanced and ChatGPT Plus?

Gemini is Google's AI chatbot that's integrated with Google products, and Advanced is the AI's paid subscription tier. ChatGPT Plus, on the other hand, is a paid subscription to OpenAI's ChatGPT. Like Advanced, it's more powerful and has more features and capabilities.

Q: How much do Gemini Advanced and ChatGPT Plus cost each?

Here's the current pricing information:

• Gemini Advanced: Included in the Google One AI Premium Plan at $19.99 per month. This plan also offers other Google AI benefits and increased Google One storage.
• ChatGPT Plus: Costs $20 per month. This plan offers access to DALL-E image generation and the GPT store.

This article may contain affiliate links that Microsoft and/or the publisher may receive a commission from if you buy a product or service through those links.

The AI assistant by Anthropic

Anthropic pbc.

• #12 in Productivity
• Offers In-App Purchases

Screenshots

Description.

Get help on a variety of tasks whenever inspiration strikes—on everything from writing to analysis to math—from Claude, your trusted AI assistant. INSTANT ANSWERS With Claude you have a world of intelligence right in your pocket. Just start a chat, send Claude a photo, attach a file—and ask away. FASTER DEEP WORK Collaborate with Claude on critical tasks, brainstorming, and complex problems to make significant progress while you’re on the go. LESS BUSY WORK Claude can help draft your emails, summarize your meetings, and assist with all the small tasks you don't want to do. INTELLIGENCE AT YOUR FINGERTIPS Claude is powered by the Claude 3 model family—powerful AI models built by Anthropic—giving you instant access to knowledge on every subject. TRUSTED PARTNER Claude is designed to be reliable, accurate, and helpful. It's brought to you by Anthropic, an AI research company dedicated to building safe and dependable AI tools. Claude is free to use. If you want access to 5x more Claude usage and our most powerful model (Claude 3 Opus), consider upgrading to our paid Pro plan. Terms of Service: https://www.anthropic.com/legal/consumer-terms Privacy Policy: https://www.anthropic.com/legal/privacy

App Privacy

The developer, Anthropic PBC , indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy .

Data Linked to You

The following data may be collected and linked to your identity:

• Contact Info
• User Content
• Identifiers
• Diagnostics

Privacy practices may vary, for example, based on the features you use or your age. Learn More

Information

• Claude Pro $20.00
• Developer Website
• App Support
• Privacy Policy

• Correspondence
• Open access
• Published: 01 May 2024

ChatGPT’s ability to generate realistic experimental images poses a new challenge to academic integrity

• Lingxuan Zhu 1   na1 ,
• Yancheng Lai 1   na1 ,
• Weiming Mou 2   na1 ,
• Haoran Zhang 1 ,
• Anqi Lin 1 ,
• Chang Qi 3 ,
• Tao Yang 4 ,
• Liling Xu 1 ,
• Jian Zhang 1 &
• Peng Luo 1  

Journal of Hematology & Oncology volume  17 , Article number:  27 ( 2024 ) Cite this article

Metrics details

The rapid advancements in large language models (LLMs) such as ChatGPT have raised concerns about their potential impact on academic integrity. While initial concerns focused on ChatGPT’s writing capabilities, recent updates have integrated DALL-E 3’s image generation features, extending the risks to visual evidence in biomedical research. Our tests revealed ChatGPT’s nearly barrier-free image generation feature can be used to generate experimental result images, such as blood smears, Western Blot, immunofluorescence and so on. Although the current ability of ChatGPT to generate experimental images is limited, the risk of misuse is evident. This development underscores the need for immediate action. We suggest that AI providers restrict the generation of experimental image, develop tools to detect AI-generated images, and consider adding “invisible watermarks” to the generated images. By implementing these measures, we can better ensure the responsible use of AI technology in academic research and maintain the integrity of scientific evidence.

To the editor

The impacts of large language models (LLMs) such as ChatGPT on academic integrity have received increasing attention. Initial concerns focused on ChatGPT’s writing abilities being exploited for academic writing, leading several publishers to ban ChatGPT as an author [ 1 , 2 ]. In addition to writing articles, a recent study found ChatGPT can generate fake but realistic research datasets from scratch to support a predetermined conclusion [ 3 ]. Furthermore, in a recent update, ChatGPT integrated the DALL-E 3’s image generation capabilities, allowing users to easily create various high-quality images with simple text prompts [ 4 ]. This could extend concerns about ChatGPT’s impacts on academic integrity from text to images, posing an entirely new challenge.

Images serve as crucial evidence supporting conclusions in biomedical research papers but are also susceptible to manipulation. For instance, Western Blot (WB) is an experiment used to detect the concentration of a target protein in a sample. Researchers’ judgement of protein concentration is entirely based on the intensity of the corresponding bands in the image. Unfortunately, the reliance on visual evidence has opened the door to falsify data through image manipulation. The earliest methods involved techniques like rotation, splicing, and retouching, but careful inspection could detect traces of manipulation [ 5 ]. With the exposure of paper mills, some reports suggest they use an artificial intelligence (AI) technology called Generative Adversarial Networks (GAN) to generate fabricated WB results that align with desired outcomes [ 6 ]. Qi et al. developed a GAN model to generate WB images and found that the synthetic fake images could not be identified by human observers [ 7 ]. Nevertheless, the GAN technique has a high barrier and not everyone can use it to generate experimental images. However, ChatGPT’s new image generation feature changes this. Alarmingly, our simple tests revealed that ChatGPT’s nearly barrier-free image generation feature can be used to generate realistic experimental result images.

We tried to use this new feature to request ChatGPT to generate realistic blood smears, immunofluorescence staining, hematoxylin and eosin (H&E) staining, immunohistochemistry and WB images (Fig.  1 , see Supplementary Material for the prompt used). The results are striking, and some of the images generated by ChatGPT have been very close to those obtained from real experimental results, especially the blood smears and the immunofluorescence images, which could probably fool some people who are less experienced in biomedical experiments.

Realistic experimental images generated using ChatGPT. ( A ) blood smears. ( B ) immunofluorescence staining. ( C ) hematoxylin and eosin (H&E) staining. ( D ) immunohistochemistry. ( E ) western blot images

Although the current ability of ChatGPT to generate experimental images is limited, our simple tests have demonstrated the significant risks of misuse in generating images. Combined with existing research findings, ChatGPT theoretically has the potential to generate entire academic papers from scratch, including text, raw data, and experiment result images. While images generated by ChatGPT currently are not as realistic as those generated by GANs, the low barrier to use and rapid technical improvements mean the generated images will likely be more realistic in future. This risk is not limited to ChatGPT, but also exists in all popular LLMs that can generate images. In addition to generating complete experimental images from scratch, AI technology could also be misused to partially or locally modify real images obtained from experiments. For example, researchers might use AI tools to selectively enhance or weaken the intensity of specific bands in Western Blot results to support predetermined conclusions. This could be more difficult to detect as the final images are a hybrid of real experimental images and AI-generated content. We believe it is imperative to promptly acknowledge this potential harm and take immediate action, urging AI technology providers to restrict the generation of experimental images. In addition, tools should be developed to help us determine whether images are generated by AI systems, similar to the tools used to detect whether text is generated by ChatGPT [ 8 ]. Moreover, AI technology providers should consider adding “invisible watermarks” to the generated images, which cannot be recognized by the naked eye but can be detected by specific tools. This can help us more accurately identify whether the images are AI-generated [ 9 ]. By implementing these measures, we can better mitigate the risks associated with AI-generated images and ensure a more responsible use of this technology.

Data availability

No datasets were generated or analysed during the current study.

Abbreviations

Artificial Intelligence

Generative Adversarial Networks

Hematoxylin and Eosin

Large Language Models

• Western Blot

Stokel-Walker C. ChatGPT listed as author on research papers: many scientists disapprove. Nature. 2023;613:620–1.

Article   CAS   PubMed   Google Scholar  

Tools such. As ChatGPT threaten transparent science; here are our ground rules for their use. Nature. 2023;613:612–612.

Article   Google Scholar  

Taloni A, Scorcia V, Giannaccare G. JAMA Ophthalmol. 2023;141:1174. Large Language Model Advanced Data Analysis Abuse to Create a Fake Data Set in Medical Research.

DALL·E 3 is now available. in ChatGPT Plus and Enterprise [Internet]. [cited 2024 Feb 20]. https://openai.com/blog/dall-e-3-is-now-available-in-chatgpt-plus-and-enterprise .

Bik EM, Casadevall A, Fang FC. The prevalence of Inappropriate Image Duplication in Biomedical Research Publications. mBio. 2016;7:e00809–16.

Article   PubMed   PubMed Central   Google Scholar  

The scientific sea of miR-. and exosome-related knowledge– For Better Science [Internet]. [cited 2024 Feb 22]. https://forbetterscience.com/2021/09/22/the-scientific-sea-of-mir-and-exosome-related-knowledge/ .

Qi C, Zhang J, Luo P, Emerging. Concern of Scientific Fraud: Deep Learning and Image Manipulation [Internet]. bioRxiv; 2021 [cited 2024 Feb 22]. p. 2020.11.24.395319. https://www.biorxiv.org/content/ https://doi.org/10.1101/2020.11.24.395319v2 .

GPTZero.| The Trusted AI Detector for ChatGPT, GPT-4, & More [Internet]. GPTZero. [cited 2024 Apr 6]. https://gptzero.me/ .

Stable, Signature. A new method for watermarking images created by open source generative AI [Internet]. Meta AI. [cited 2024 Apr 6]. https://ai.meta.com/blog/stable-signature-watermarking-generative-ai/ .

Download references

Acknowledgements

Not applicable.

Author information

Lingxuan Zhu, Yancheng Lai and Weiming Mou have contributed equally to this work and share first authorship

Authors and Affiliations

Department of Oncology, Zhujiang Hospital, Southern Medical University, 253 Industrial Avenue, 510282, Guangzhou, Guangdong, China

Lingxuan Zhu, Yancheng Lai, Haoran Zhang, Anqi Lin, Liling Xu, Jian Zhang & Peng Luo

Department of Urology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China

Weiming Mou

Institute of Logic and Computation, TU Wien, Wien, Austria

Department of Medical Oncology, National Clinical Research Center for Cancer /Cancer Hospital, National Cancer Center, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China

You can also search for this author in PubMed   Google Scholar

Contributions

Lingxuan Zhu, Yancheng Lai and Weiming Mou: Conceptualization, Investigation, Writing - Original Draft, Methodology, Literature review, Writing - Review & Editing, Formal analysis. Haoran Zhang: Conceptualization, Investigation, Writing - Review & Editing, Literature review. Chang Qi, Tao Yang, Anqi Lin and Liling Xu: Writing - Review & Editing, Literature review. Jian Zhang and Peng Luo: Conceptualization, Literature review, Project administration, Supervision, Resources, Writing - review & editing. All authors read and approved the final manuscript.

Corresponding authors

Correspondence to Jian Zhang or Peng Luo .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Additional information

Publisher’s note.

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

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

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.

Zhu, L., Lai, Y., Mou, W. et al. ChatGPT’s ability to generate realistic experimental images poses a new challenge to academic integrity. J Hematol Oncol 17 , 27 (2024). https://doi.org/10.1186/s13045-024-01543-8

Download citation

Received : 26 March 2024

Accepted : 08 April 2024

Published : 01 May 2024

DOI : https://doi.org/10.1186/s13045-024-01543-8

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

• Academic integrity
• Large language model
• Experimental images
• Artificial intelligence

Journal of Hematology & Oncology

ISSN: 1756-8722

• General enquiries: [email protected]