how to tell if chatgpt write an essay

How-To Geek

How to tell if an article was written by chatgpt.

While no method is totally effective, you can train yourself to spot telltale markers of AI writing — for now.

Quick Links

How to tell if chatgpt wrote that article, can you use ai to detect ai-generated text, tools to check if an article was written by chatgpt, train your brain to catch ai, key takeaways.

You can tell a ChatGPT-written article by its simple, repetitive structure and its tendency to make logical and factual errors. Some tools are available for automatically detecting AI-generated text, but they are prone to false positives.

AI technology is changing what we see online and how we interact with the world. From a Midjourney photo of the Pope in a puffer coat to language learning models like ChatGPT, artificial intelligence is working its way into our lives.

The more sinister uses of AI tech, like a political disinformation campaign blasting out fake articles, mean we need to educate ourselves enough to spot the fakes. So how can you tell if an article is actually AI generated text?

Multiple methods and tools currently exist to help determine whether the article you're reading was written by a robot. Not all of them are 100% reliable, and they can deliver false positives, but they do offer a starting point.

One big marker of human-written text, at least for now, is randomness. While people will write using different styles and slang and often make typos, AI language models very rarely make those kinds of mistakes. According to MIT Technology Review , "human-written text is riddled with typos and is incredibly variable," while AI generated text models like ChatGPT are much better at creating typo-less text. Of course, a good copy editor will have the same effect, so you have to watch for more than just correct spelling.

Another indicator is punctuation patterns. Humans will use punctuation more randomly than an AI model might. AI generated text also usually contains more connector words like "the," "it," or "is" instead of larger more rarely used words because large language models operate by predicting what word will is most likely to come next, not coming up with something that would sound good the way a human might.

This is visible in ChatGPT's response to one of the stock questions on OpenAI's website. When asked, "Can you explain quantum computing in simple terms," you get sentences like: "What makes qubits special is that they can exist in multiple states at the same time, thanks to a property called superposition. It's like a qubit can be both a 0 and a 1 simultaneously. "

Short, simple connecting words are regularly used, the sentences are all a similar length, and paragraphs all follow a similar structure. The end result is writing that sounds and feels a bit robotic.

Large language models themselves can be trained to spot AI generated writing. Training the system on two sets of text --- one written by AI and the other written by people --- can theoretically teach the model to recognize and detect AI writing like ChatGPT.

Researchers are also working on watermarking methods to detect AI articles and text. Tom Goldstein, who teaches computer science at the University of Maryland, is working on a way to build watermarks into AI language models in the hope that it can help detect machine-generated writing even if it's good enough to mimic human randomness.

Invisible to the naked eye, the watermark would be detectable by an algorithm, which would indicate it as either human or AI generated depending on how often it adhered to or broke the watermarking rules. Unfortunately, this method hasn't tested so well on later models of ChatGPT.

You can find multiple copy-and-paste tools online to help you check whether an article is AI generated. Many of them use language models to scan the text, including ChatGPT-4 itself.

Undetectable AI , for example, markets itself as a tool to make your AI writing indistinguishable from a human's. Copy and paste the text into its window and the program checks it against results from other AI detection tools like GPTZero to assign it a likelihood score --- it basically checks whether eight other AI detectors would think your text was written by a robot.

Originality is another tool, geared toward large publishers and content producers. It claims to be more accurate than others on the market and uses ChatGPT-4 to help detect text written by AI. Other popular checking tools include:

Most of these tools give you a percentage value, like 96% human and 4% AI, to determine how likely it is that the text was written by a human. If the score is 40-50% AI or higher, it's likely the piece was AI-generated.

While developers are working to make these tools better at detecting AI generated text, none of them are totally accurate and can falsely flag human content as AI generated. There's also concern that since large language models like GPT-4 are improving so quickly, detection models are constantly playing catchup.

Related: Can ChatGPT Write Essays: Is Using AI to Write Essays a Good Idea?

In addition to using tools, you can train yourself to catch AI generated content. It takes practice, but over time you can get better at it.

Daphne Ippolito, a senior research scientist at Google's AI division Google Brain, made a game called Real Or Fake Text  (ROFT) that can help you separate human sentences from robotic ones by gradually training you to notice when a sentence doesn't quite look right.

One common marker of AI text, according to Ippolito, is nonsensical statements like "it takes two hours to make a cup of coffee." Ippolito's game is largely focused on helping people detect those kinds of errors. In fact, there have been multiple instances of an AI writing program stating inaccurate facts with total confidence --- you probably shouldn't ask it to do your math assignment , either, as it doesn't seem to handle numerical calculations very well.

Right now, these are the best detection methods we have to catch text written by an AI program. Language models are getting better at a speed that renders current detection methods outdated pretty quickly, however, leaving us in, as Melissa Heikkilä writes for MIT Technology Review, an arms race.

Related: How to Fact-Check ChatGPT With Bing AI Chat

• 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 New
• 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 45,879 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

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.

7 Surefire Signs That ChatGPT Has Written an Essay Revealed

Researchers at the University of Cambridge have revealed the seven telltale signs that a piece of written content was generated by ChatGPT , after carefully analyzing more than 150 essays written by high school students and undergraduates.

They found that ChatGPT loves an Oxford Comma, repeats phrases and spits out tautological statements practically empty of meaning at a much higher frequency than humans.

While the findings are interesting, the sample size is quite small. There’s also no guarantee that the linguistic habits and techniques identified couldn’t and wouldn’t be used by a human. What’s more, AI content detection tools are largely unreliable; there’s still no way to know for certain that any given written content is AI-generated.

Get the latest tech news, straight to your inbox

Stay informed on the top business tech stories with Tech.co's weekly highlights reel.

By signing up to receive our newsletter, you agree to our Privacy Policy . You can unsubscribe at any time.

The 7 Telltale Signs Content is AI-Generated

The researchers at Cambridge analyzed 164 essays written by high school students with four essays written with a helping hand from ChatGPT.

The ChatGPT-assisted essays were generally more information-heavy and had more reflective elements, but the markers at Cambridge found that they lacked the level of comparison and analysis typically found in human-generated content. 

According to UK-based publication The Telegraph , which broke the story, the researchers identified seven key indicators of AI content:

• Frequent use of Latin root words and “vocabulary above the expected level”
• Paragraphs starting with singular words like “however”, and then a comma 
• Lots of numbered lists with colons
• Unnecessary clarificatory language (e.g. “true fact”)
• Tautological language (“Lets come together to unite”)
• Repetition of the same word or phrase twice 
• Consistent and frequent use of Oxford commas in sentences

Are There Any Other Ways to Spot ChatGPT Plagiarism?

Yes and no. There are many tools online that claim to be able to detect AI content, but when I tested a wide range of them last year, I found many to be wildly inaccurate.

For instance, OpenAI’s own text classifier – which was eventually shut down because it performed so poorly – was unable to identify that text written by ChatGPT (effectively itself) was AI-generated.

Even Turnitin has been using automated processes to detect plagiarized content in academic work for years, and they’ve also developed a powerful AI content checker. The company has always maintained that verdicts arrived at by their tools should be treated as an indication, not a cast-iron accusation.

“Given that our false positive rate is not zero” Turnitin explains in a blog post discussing its AI content detection capabilities.

“You as the instructor will need to apply your professional judgment, knowledge of your students, and the specific context surrounding the assignment”.

None of these tools are infallible – and worse still, many of the free ones you’ll find lurking at the top of the Google Search results are completely and utterly useless.

Is It Wrong to Use AI for School or College Work?

While asking AI tools like ChatGPT and Gemini to write you an essay isn’t quite “plagiarism” in the same way copying content written by other people and passing it off as your own is, it’s certainly not advised.

Whether it’s objectively plagiarism or not is likely irrelevant – the educational institution you’re enrolled in has probably created guidelines explicitly banning generative AI. Many universities have already taken a similar approach to peer review and other academic processes.

Besides, the whole point of writing an essay is to consider the range of ideas and views on the topic you’re writing about and evaluate them using your head. Getting an AI to do it for you defeats the whole point of writing the essay in the first place.

Our advice – considering the consequences of being accused of plagiarism while at university – is to stick to the rules. Who knows – you might learn something while you’re at it!

Stay informed on the top business tech stories with Tech.co's weekly highlights reel.

We're sorry this article didn't help you today – we welcome feedback, so if there's any way you feel we could improve our content, please email us at [email protected]

• Artificial Intelligence

Written by:

How to Get Phi-3-Mini: Microsoft’s New Affordable AI Chatbot

Microsoft's pocket-sized LLM, Phi-3-Mini, is the first of...

This AI Weather App Will Give You $10K if It Rains On Your Vacation

A new travel insurance app that launched in 2024 will...

How to Use Meta AI on Facebook, WhatsApp, Instagram and the Web

Meta is making waves this week with a string of AI-fuelled...

The Best Free AI Professional Headshot Generators in 2024

Give your LinkedIn a makeover with these impressive...

• Skip to main content
• Keyboard shortcuts for audio player

A college student created an app that can tell whether AI wrote an essay

Emma Bowman

GPTZero in action: The bot correctly detected AI-written text. The writing sample that was submitted? ChatGPT's attempt at "an essay on the ethics of AI plagiarism that could pass a ChatGPT detector tool." GPTZero.me/Screenshot by NPR hide caption

GPTZero in action: The bot correctly detected AI-written text. The writing sample that was submitted? ChatGPT's attempt at "an essay on the ethics of AI plagiarism that could pass a ChatGPT detector tool."

Teachers worried about students turning in essays written by a popular artificial intelligence chatbot now have a new tool of their own.

Edward Tian, a 22-year-old senior at Princeton University, has built an app to detect whether text is written by ChatGPT, the viral chatbot that's sparked fears over its potential for unethical uses in academia.

Edward Tian, a 22-year-old computer science student at Princeton, created an app that detects essays written by the impressive AI-powered language model known as ChatGPT. Edward Tian hide caption

Edward Tian, a 22-year-old computer science student at Princeton, created an app that detects essays written by the impressive AI-powered language model known as ChatGPT.

Tian, a computer science major who is minoring in journalism, spent part of his winter break creating GPTZero, which he said can "quickly and efficiently" decipher whether a human or ChatGPT authored an essay.

His motivation to create the bot was to fight what he sees as an increase in AI plagiarism. Since the release of ChatGPT in late November, there have been reports of students using the breakthrough language model to pass off AI-written assignments as their own.

"there's so much chatgpt hype going around. is this and that written by AI? we as humans deserve to know!" Tian wrote in a tweet introducing GPTZero.

Tian said many teachers have reached out to him after he released his bot online on Jan. 2, telling him about the positive results they've seen from testing it.

More than 30,000 people had tried out GPTZero within a week of its launch. It was so popular that the app crashed. Streamlit, the free platform that hosts GPTZero, has since stepped in to support Tian with more memory and resources to handle the web traffic.

How GPTZero works

To determine whether an excerpt is written by a bot, GPTZero uses two indicators: "perplexity" and "burstiness." Perplexity measures the complexity of text; if GPTZero is perplexed by the text, then it has a high complexity and it's more likely to be human-written. However, if the text is more familiar to the bot — because it's been trained on such data — then it will have low complexity and therefore is more likely to be AI-generated.

Separately, burstiness compares the variations of sentences. Humans tend to write with greater burstiness, for example, with some longer or complex sentences alongside shorter ones. AI sentences tend to be more uniform.

In a demonstration video, Tian compared the app's analysis of a story in The New Yorker and a LinkedIn post written by ChatGPT. It successfully distinguished writing by a human versus AI.

A new AI chatbot might do your homework for you. But it's still not an A+ student

Tian acknowledged that his bot isn't foolproof, as some users have reported when putting it to the test. He said he's still working to improve the model's accuracy.

But by designing an app that sheds some light on what separates human from AI, the tool helps work toward a core mission for Tian: bringing transparency to AI.

"For so long, AI has been a black box where we really don't know what's going on inside," he said. "And with GPTZero, I wanted to start pushing back and fighting against that."

The quest to curb AI plagiarism

Untangling Disinformation

Ai-generated fake faces have become a hallmark of online influence operations.

The college senior isn't alone in the race to rein in AI plagiarism and forgery. OpenAI, the developer of ChatGPT, has signaled a commitment to preventing AI plagiarism and other nefarious applications. Last month, Scott Aaronson, a researcher currently focusing on AI safety at OpenAI, revealed that the company has been working on a way to "watermark" GPT-generated text with an "unnoticeable secret signal" to identify its source.

The open-source AI community Hugging Face has put out a tool to detect whether text was created by GPT-2, an earlier version of the AI model used to make ChatGPT. A philosophy professor in South Carolina who happened to know about the tool said he used it to catch a student submitting AI-written work.

The New York City education department said on Thursday that it's blocking access to ChatGPT on school networks and devices over concerns about its "negative impacts on student learning, and concerns regarding the safety and accuracy of content."

Tian is not opposed to the use of AI tools like ChatGPT.

GPTZero is "not meant to be a tool to stop these technologies from being used," he said. "But with any new technologies, we need to be able to adopt it responsibly and we need to have safeguards."

How to Use ChatGPT for Research and Essays

Want to use ChatGPT to help out with research and essays? To avoid inaccurate information, there are certain ways you can use it to your advantage.

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

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

1. Draw Your Outline Without ChatGPT

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

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

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

2. Prompt ChatGPT to Draw a Parallel Outline

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

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

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

3. Create a ChatGPT Prompt for Each Section

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

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

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

4. Confirm the Information With a Reputable Source

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

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

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

5. Use ChatGPT for Examples and Breakdowns

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

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

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

6. Write the Essay Yourself

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

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

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

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

7. Polish the Style and Citation With ChatGPT

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

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

ChatGPT Is a Tool, Not a Solution

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

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

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!”

'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, humane ai pin: what went wrong and how it can be fixed (before it's too late), how to get started with meta ai in facebook, instagram, and more.

Numbers, Facts and Trends Shaping Your World

Read our research on:

Full Topic List

Regions & Countries

• Publications
• Our Methods
• Short Reads
• Tools & Resources

Read Our Research On:

About 1 in 5 U.S. teens who’ve heard of ChatGPT have used it for schoolwork

Roughly one-in-five teenagers who have heard of ChatGPT say they have used it to help them do their schoolwork, according to a new Pew Research Center survey of U.S. teens ages 13 to 17. With a majority of teens having heard of ChatGPT, that amounts to 13% of all U.S. teens who have used the generative artificial intelligence (AI) chatbot in their schoolwork.

Teens in higher grade levels are particularly likely to have used the chatbot to help them with schoolwork. About one-quarter of 11th and 12th graders who have heard of ChatGPT say they have done this. This share drops to 17% among 9th and 10th graders and 12% among 7th and 8th graders.

There is no significant difference between teen boys and girls who have used ChatGPT in this way.

The introduction of ChatGPT last year has led to much discussion about its role in schools , especially whether schools should integrate the new technology into the classroom or ban it .

Pew Research Center conducted this analysis to understand American teens’ use and understanding of ChatGPT in the school setting.

The Center conducted an online survey of 1,453 U.S. teens from Sept. 26 to Oct. 23, 2023, via Ipsos. Ipsos recruited the teens via their parents, who were part of its KnowledgePanel . The KnowledgePanel is a probability-based web panel recruited primarily through national, random sampling of residential addresses. The survey was weighted to be representative of U.S. teens ages 13 to 17 who live with their parents by age, gender, race and ethnicity, household income, and other categories.

This research was reviewed and approved by an external institutional review board (IRB), Advarra, an independent committee of experts specializing in helping to protect the rights of research participants.

Here are the  questions used for this analysis , along with responses, and its  methodology .

Teens’ awareness of ChatGPT

Overall, two-thirds of U.S. teens say they have heard of ChatGPT, including 23% who have heard a lot about it. But awareness varies by race and ethnicity, as well as by household income:

• 72% of White teens say they’ve heard at least a little about ChatGPT, compared with 63% of Hispanic teens and 56% of Black teens.
• 75% of teens living in households that make $75,000 or more annually have heard of ChatGPT. Much smaller shares in households with incomes between $30,000 and $74,999 (58%) and less than $30,000 (41%) say the same.

Teens who are more aware of ChatGPT are more likely to use it for schoolwork. Roughly a third of teens who have heard a lot about ChatGPT (36%) have used it for schoolwork, far higher than the 10% among those who have heard a little about it.

When do teens think it’s OK for students to use ChatGPT?

For teens, whether it is – or is not – acceptable for students to use ChatGPT depends on what it is being used for.

There is a fair amount of support for using the chatbot to explore a topic. Roughly seven-in-ten teens who have heard of ChatGPT say it’s acceptable to use when they are researching something new, while 13% say it is not acceptable.

However, there is much less support for using ChatGPT to do the work itself. Just one-in-five teens who have heard of ChatGPT say it’s acceptable to use it to write essays, while 57% say it is not acceptable. And 39% say it’s acceptable to use ChatGPT to solve math problems, while a similar share of teens (36%) say it’s not acceptable.

Some teens are uncertain about whether it’s acceptable to use ChatGPT for these tasks. Between 18% and 24% say they aren’t sure whether these are acceptable use cases for ChatGPT.

Those who have heard a lot about ChatGPT are more likely than those who have only heard a little about it to say it’s acceptable to use the chatbot to research topics, solve math problems and write essays. For instance, 54% of teens who have heard a lot about ChatGPT say it’s acceptable to use it to solve math problems, compared with 32% among those who have heard a little about it.

Note: Here are the  questions used for this analysis , along with responses, and its  methodology .

• Artificial Intelligence
• Technology Adoption
• Teens & Tech

Olivia Sidoti is a research assistant focusing on internet and technology research at Pew Research Center

Jeffrey Gottfried is an associate director focusing on internet and technology research at Pew Research Center

Many Americans think generative AI programs should credit the sources they rely on

Americans’ use of chatgpt is ticking up, but few trust its election information, q&a: how we used large language models to identify guests on popular podcasts, striking findings from 2023, what the data says about americans’ views of artificial intelligence, most popular.

1615 L St. NW, Suite 800 Washington, DC 20036 USA (+1) 202-419-4300 | Main (+1) 202-857-8562 | Fax (+1) 202-419-4372 |  Media Inquiries

Research Topics

• Age & Generations
• Coronavirus (COVID-19)
• Economy & Work
• Family & Relationships
• Gender & LGBTQ
• Immigration & Migration
• International Affairs
• Internet & Technology
• Methodological Research
• News Habits & Media
• Non-U.S. Governments
• Other Topics
• Politics & Policy
• Race & Ethnicity
• Email Newsletters

ABOUT PEW RESEARCH CENTER  Pew Research Center is a nonpartisan fact tank that informs the public about the issues, attitudes and trends shaping the world. It conducts public opinion polling, demographic research, media content analysis and other empirical social science research. Pew Research Center does not take policy positions. It is a subsidiary of  The Pew Charitable Trusts .

Copyright 2024 Pew Research Center

Terms & Conditions

Privacy Policy

Cookie Settings

Reprints, Permissions & Use Policy

Search results for

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

How accurate is ChatGPT? Should you trust its responses?

Published on April 22, 2024

Modern chatbots like ChatGPT can output dozens of words every second, making them invaluable tools for researching and analyzing large amounts of information. With over 500GB of training data and an estimated 300 billion words under its belt, the AI language model can answer many factual questions too. But as human as ChatGPT’s responses may sound, one crucial question remains: how accurate is the information it provides?

While ChatGPT can be impressively informative most of the time, you’ve probably heard of countless controversies surrounding generative AI. From racial biases to harmful content, there’s a history of controversies to consider before trusting any AI-generated output.

Is ChatGPT accurate?

Yes, ChatGPT has the potential to be accurate, especially for factual queries with clear answers. When talking about long-established information, ChatGPT can fetch relevant data from its training and deliver truthful responses. For a question like “What is the capital of France?”, you’re very likely to get the correct answer.

However, chatbots like ChatGPT often fabricate information when they encounter a novel or difficult question. This is because generative language models are designed to mimic the way humans write, not the way we think. Consequently, they have limited logical reasoning capabilities.

The problem with ChatGPT’s accuracy runs deeper than you’d think. It often weaves in entirely fictional details and invents convincing-sounding factoids in response to certain prompts. The chatbot’s creator has placed several safeguards to prevent hallucinations, but as our tests will show later in this article, it isn’t completely effective.

If you’re after empirical data, several studies have tested ChatGPT’s accuracy extensively to reveal one clear trend. ChatGPT boasts a surprisingly high accuracy rating for typical questions. In one medical study , for example, the chatbot scored a median rating of 5.5 on a 6-point scale.

However, ChatGPT’s tendency to receive routine updates can also harm its accuracy and usefulness. Another group of UC Berkeley and Stanford University researchers found that the chatbot’s ability to identify prime numbers dropped from an impressive 84% accuracy to just 51% within three months. In short, you cannot and should not trust ChatGPT’s responses, at least not without fact-checking them first.

How to improve ChatGPT’s accuracy

If you’re only an occasional ChatGPT user, you may have never considered upgrading to the chatbot’s paid tier. However, doing so will improve its accuracy several-fold and should top your priority list if you rely on the chatbot’s responses. This is because the $20 ChatGPT Plus subscription unlocks access to the GPT-4 Turbo language model .

The GPT-4 language model is far more capable than its predecessor, GPT-3.5, which powers the base chatbot experience even today. According to OpenAI, the newer model scored in the 89th percentile of SAT Math, 90th percentile of the Uniform Bar Exam, and 80th percentile of the GRE Quantitative. Almost all of these results are significantly better than that of GPT-3.5.

Results in the 80th to 90th percentile mean that GPT-4’s accuracy doesn’t surpass human experts in their respective fields. However, ChatGPT Plus also unlocks web browsing support, which allows the chatbot to consult Wikipedia and other online sources. You can think of it as live research since it’s similar to how we find the right answer through a Google search. So just how accurate is ChatGPT and is the Plus tier worth paying for? Let’s find out.

ChatGPT 4 accuracy tested: Free vs Plus compared

As I mentioned earlier, ChatGPT can deliver significantly more accurate responses with GPT-4 and Browsing enabled. I asked the chatbot a handful of factual questions, some particularly obscure, to test whether or not I could get a reliably accurate answer.

• Question 1 : Is 17077 a prime number? Think step by step and then answer [Yes] or [No].

A recent ChatGPT update added chain-of-thought reasoning to the chatbot, allowing it to mimic human reasoning. That seems to have paid off, as both versions of ChatGPT were able to correctly identify a prime number. However, the paid version of the chatbot wrote a piece of custom Python code to perform the calculations. While it didn’t improve the result, I did feel that the answer was more trustworthy.

• Question 2 : Does the Setouchi Area Pass cover any local transport in Osaka?

With many of us using ChatGPT for travel advice, I decided to ask a relatively obscure question in that domain. Unfortunately, the base GPT-3.5 model responded inaccurately and only admitted fault when I suggested the correct answer. However, switching to ChatGPT-4 changed the outcome, immediately giving me the correct answer. Still, can the chatbot replace manual research entirely? I’m on the fence, especially since rival chatbots like Perplexity AI cite their sources.

• Question 3 : Select two random integers between 2459 and 3593 and multiply them

Asking a mathematical question will almost always trip up ChatGPT, and that’s exactly what happened with GPT-3.5 or the free version of the chatbot. It delivered a plausible-sounding response (2865×3035 = 8,697,975), but it was actually quite far off from the true answer (8,695,275). ChatGPT-4 used Python code once again to find the right answer, but chances are that it would’ve failed without outside help too.

In summary, remember that ChatGPT will almost always try to deliver a solution to your problem or question without caring much about its accuracy. It will only sometimes admit that it cannot answer a question or doesn’t know enough about the subject matter. Otherwise, it can just as easily hallucinate information without any obvious indication.

You might like

How to use Meta’s new AI chatbot that you can’t avoid

Facebook, instagram, messenger and whatsapp are all pushing a new ai chatbot.

With seemingly fewer friends posting to their main Facebook and Instagram feeds, Meta has introduced a new feature its users can talk to: an AI chatbot.

The feature, named Meta AI, is rolling out to the company’s main apps including Facebook, Instagram, Messenger and WhatsApp. It’s primarily a conversational chat window where you can ask questions and generate AI images, similar to other AI chatbots like OpenAI’s ChatGPT, Microsoft’s Co-Pilot and Google’s Gemini.

Despite over a year of artificial intelligence being everywhere, this could be many people’s first interaction with the technology. Meta has billions of users across its apps, and anyone who has managed to avoid the bots so far will find this one nearly impossible to escape.

Should you trust that AI?

Why is this ai chatbot here.

Facebook and Instagram users probably weren’t banging down Mark Zuckerberg’s door demanding an AI chatbot, so why is this feature suddenly everywhere? The technology is still new and its utility debatable. However, the major tech companies have decided that, like voice assistants and scrollable vertical videos before it, AI is the next big thing. Now they are competing to push out their versions. Facebook and Instagram used to rely on users’ friends, family and communities to keep their attention. Now, as these platforms are aging, the companies may hope a chatty bot can replace some of the human interaction.

How do I find it?

The chatbot is integrated in search and messaging features across Meta’s apps, and may appear in your feed under some posts as well. If you don’t see the AI features it yet, check back later. Its presence is marked with its logo: a thin ring that’s mostly blue and occasionally animated. The AI tool can also be accessed online on the stand-alone website meta.ai . It is not included in the company’s app for children, Messenger Kids.

On Facebook, tap the search icon on top and you’ll find that the usual search bar has been replaced with one that says, “Ask Meta AI anything.” As you start typing, it will auto-suggest searches. Anything with the blue circle next to it is going to bring up the AI chat window. You can also tap the messages icon and engage with Meta AI as if it’s another pal to talk to. If you see it under a post in your feed, it will suggest questions to ask related to the content you see.

In Instagram, Messenger and WhatsApp, you’ll also find Meta AI has taken over the search bars and appears as another chat. If your accounts are connected to each other, the Meta AI conversation should pick up where you left off, regardless of what app you’re in.

How do I turn it off?

There’s no way to get rid of Meta AI in search, confirmed Meta. In WhatsApp, there is an option to hide the new Meta AI button by going to Settings → Chats → Show Meta AI Button. However, it’s still in the search bar. Other apps have an option to mute its replies. I asked the AI chatbot how to turn it off and got multiple incorrect answers with instructions that did not work and for settings that don’t exist.

You can delete a chat with Meta AI to remove it from recent conversations in the same way you would any other chat. Swipe left on the chat and select Delete in Instagram, More → Delete on Facebook and Messenger, and More → Delete Chat on WhatsApp.

How do I get started?

Start typing full sentences or random words in any of the apps’ search bars or in the conversations with Meta AI. If this is your first time using an AI chatbot, you can begin by asking simple questions and even for a list of ways to use it.

I did the first things any normal person does when testing an AI tool. I asked it to be my pretend boyfriend, told it to generate images of ducks writing breakup letters and tried to push its boundaries. I discovered it avoids partaking in overtly sexual conversations or generating photos of the Pope (entirely unrelated questions). As with all artificial intelligence, there are creative ways to get around its filters.

Meta AI includes options for shortcuts. Type a forward slash and command, like /joke:, /imagine: or /story: and type your description after. However, these aren’t really necessary since you can make the same requests in a conversational way, such as “tell me a story about depressed hamster who ran for mayor.”

What should I use it for?

An AI chatbot is like having an enthusiastic but unreliable friend. You can ask it almost anything — but never assume it’s telling the truth. With that in mind, use Meta AI for fun and for noncritical tasks. Ask random questions like you would with Google, start conversations to feel less alone and use it to brainstorm.

Meta AI can also generate images, though in our tests they have the typical flaws associated with artificial intelligence. Most share the hyper-realistic lighting that AI images are known for, fumble details like fingers and eyes, and frequently give women exposed, ample cleavage.

There are plenty of other things you can try. Ask Meta AI to animate images, request a summary of the day’s news or ask it to take on the personality of a specific character when speaking to you. Because it’s integrated with Meta’s other products, you can use it to search things like “Reels of people learning to roller skate.”

To get the best results and avoid bland responses, ask follow-up questions and give as many details as possible. For a list of starter ideas, check out Tech Friend Shira Ovide’s recommendations of useful things to ask a chatbot .

What should I not use it for?

Don’t use AI as an authority for anything of consequence. For example, don’t rely on a chatbot for medical advice or as a source for school or work. Ethically, you shouldn’t use it to write papers for school, though Meta AI is happy to spit out wooden essays on demand.

Experts warn there is a danger of misinformation from tools like Meta’s chatbot. To steer clear, avoid using it as a go-to for anything sensitive or political. Turn to human sources instead like reporters, experts, even Wikipedia and Reddit, before artificial intelligence. For more advice on avoiding misinformation, check out our guide.

How is it different from other AI bots?

For the basics, Meta AI appears to spit out the same generic answers as its competitors. I asked five different chatbots about the best taqueria in San Francisco, a vegetarian meal plan, if God exists and how to know if a polycule is right for you. For the most part, they all gave incredibly similar, mundane but neutral answers with the exception of Microsoft’s Co-pilot, which does not enjoy shenanigans.

Is it keeping my information?

Use the same precautions typing questions and thoughts into an AI chatbot as you would a Google search. Meta does save the conversations but to protect privacy, the data is anonymized, meaning it’s not connected to your name or identity. While this is standard for technology companies, experts say it’s possible to re-identify people using additional data points. If you want to delete a chat, you can use the shortcut “/reset-ai” and Meta claims it will remove the conversation from its servers.

Help Desk: Making tech work for you

Help Desk is a destination built for readers looking to better understand and take control of the technology used in everyday life.

Take control: Sign up for The Tech Friend newsletter to get straight talk and advice on how to make your tech a force for good.

Tech tips to make your life easier: 10 tips and tricks to customize iOS 16 | 5 tips to make your gadget batteries last longer | How to get back control of a hacked social media account | How to avoid falling for and spreading misinformation online

Data and Privacy: A guide to every privacy setting you should change now . We have gone through the settings for the most popular (and problematic) services to give you recommendations. Google | Amazon | Facebook | Venmo | Apple | Android

Ask a question: Send the Help Desk your personal technology questions .

• WhatsApp just added this long-requested feature April 25, 2023 WhatsApp just added this long-requested feature April 25, 2023
• Safety advocates see red flags galore with new tech at CES show January 10, 2023 Safety advocates see red flags galore with new tech at CES show January 10, 2023
• Got a computer collecting dust? Google’s new software could bring it back to life. February 15, 2022 Got a computer collecting dust? Google’s new software could bring it back to life. February 15, 2022

• Do Not Sell My Personal Info

•  ⋅ 

How To Write ChatGPT Prompts To Get The Best Results

Learn how to craft powerful ChatGPT prompts to generate high-quality SEO content. Follow expert tips, examples, and strategies for layering prompts to get the best results.

ChatGPT is a game changer in the field of SEO . This powerful language model can generate human-like content, making it an invaluable tool for SEO professionals.

However, the prompts you provide largely determine the quality of the output.

To unlock the full potential of ChatGPT and create content that resonates with your audience and search engines, writing effective prompts is crucial.

In this comprehensive guide, we’ll explore the art of writing prompts for ChatGPT, covering everything from basic techniques to advanced strategies for layering prompts and generating high-quality, SEO-friendly content.

Writing Prompts For ChatGPT

What is a chatgpt prompt.

A ChatGPT prompt is an instruction or discussion topic a user provides for the ChatGPT AI model to respond to.

The prompt can be a question, statement, or any other stimulus to spark creativity, reflection, or engagement.

Users can use the prompt to generate ideas, share their thoughts, or start a conversation.

ChatGPT prompts are designed to be open-ended and can be customized based on the user’s preferences and interests.

How To Write Prompts For ChatGPT

Start by giving ChatGPT a writing prompt, such as, “Write a short story about a person who discovers they have a superpower.”

ChatGPT will then generate a response based on your prompt. Depending on the prompt’s complexity and the level of detail you requested, the answer may be a few sentences or several paragraphs long.

Use the ChatGPT-generated response as a starting point for your writing . You can take the ideas and concepts presented in the answer and expand upon them, adding your own unique spin to the story.

If you want to generate additional ideas, try asking ChatGPT follow-up questions related to your original prompt.

For example, you could ask, “What challenges might the person face in exploring their newfound superpower?” Or, “How might the person’s relationships with others be affected by their superpower?”

Remember that ChatGPT’s answers are generated by artificial intelligence and may not always be perfect or exactly what you want.

However, they can still be a great source of inspiration and help you start writing.

Must-Have GPTs Assistant

I recommend installing the WebBrowser Assistant created by the OpenAI Team. This tool allows you to add relevant Bing results to your ChatGPT prompts.

This assistant adds the first web results to your ChatGPT prompts for more accurate and up-to-date conversations.

It is very easy to install in only two clicks. (Click on Start Chat. )

For example, if I ask, “Who is Vincent Terrasi?,” ChatGPT has no answer.

With WebBrower Assistant, the assistant creates a new prompt with the first Bing results, and now ChatGPT knows who Vincent Terrasi is.

You can test other GPT assistants available in the GPTs search engine if you want to use Google results.

Master Reverse Prompt Engineering

ChatGPT can be an excellent tool for reverse engineering prompts because it generates natural and engaging responses to any given input.

By analyzing the prompts generated by ChatGPT, it is possible to gain insight into the model’s underlying thought processes and decision-making strategies.

One key benefit of using ChatGPT to reverse engineer prompts is that the model is highly transparent in its decision-making.

This means that the reasoning and logic behind each response can be traced, making it easier to understand how the model arrives at its conclusions.

Once you’ve done this a few times for different types of content , you’ll gain insight into crafting more effective prompts.

Prepare Your ChatGPT For Generating Prompts

First, activate the reverse prompt engineering.

• Type the following prompt: “Enable Reverse Prompt Engineering? By Reverse Prompt Engineering I mean creating a prompt from a given text.”

ChatGPT is now ready to generate your prompt. You can test the product description in a new chatbot session and evaluate the generated prompt.

• Type: “Create a very technical reverse prompt engineering template for a product description about iPhone 11.”

The result is amazing. You can test with a full text that you want to reproduce. Here is an example of a prompt for selling a Kindle on Amazon.

• Type: “Reverse Prompt engineer the following {product), capture the writing style and the length of the text : product =”

I tested it on an SEJ blog post. Enjoy the analysis – it is excellent.

• Type: “Reverse Prompt engineer the following {text}, capture the tone and writing style of the {text} to include in the prompt : text = all text coming from https://www.searchenginejournal.com/google-bard-training-data/478941/”

But be careful not to use ChatGPT to generate your texts. It is just a personal assistant.

Prompts and examples for SEO:

• Keyword research and content ideas p rompt : “Provide a list of 20 long-tail keyword ideas related to ‘local SEO strategies’ along with brief content topic descriptions for each keyword.”
• Optimizing content for featured snippets p rompt : “Write a 40-50 word paragraph optimized for the query ‘what is the featured snippet in Google search’ that could potentially earn the featured snippet.”
• Creating meta descriptions p rompt: “Draft a compelling meta description for the following blog post title: ’10 Technical SEO Factors You Can’t Ignore in 2024′.”

Important Considerations:

• Always Fact-Check: While ChatGPT can be a helpful tool, it’s crucial to remember that it may generate inaccurate or fabricated information. Always verify any facts, statistics, or quotes generated by ChatGPT before incorporating them into your content.
• Maintain Control and Creativity: Use ChatGPT as a tool to assist your writing, not replace it. Don’t rely on it to do your thinking or create content from scratch. Your unique perspective and creativity are essential for producing high-quality, engaging content.
• Iteration is Key: Refine and revise the outputs generated by ChatGPT to ensure they align with your voice, style, and intended message.

Additional Prompts for Rewording and SEO: – Rewrite this sentence to be more concise and impactful. – Suggest alternative phrasing for this section to improve clarity. – Identify opportunities to incorporate relevant internal and external links. – Analyze the keyword density and suggest improvements for better SEO.

Remember, while ChatGPT can be a valuable tool, it’s essential to use it responsibly and maintain control over your content creation process.

Experiment And Refine Your Prompting Techniques

Writing effective prompts for ChatGPT is an essential skill for any SEO professional who wants to harness the power of AI-generated content .

Hopefully, the insights and examples shared in this article can inspire you and help guide you to crafting stronger prompts that yield high-quality content.

Remember to experiment with layering prompts, iterating on the output, and continually refining your prompting techniques.

This will help you stay ahead of the curve in the ever-changing world of SEO.

More resources: 

• 25 ChatGPT Examples For Digital Marketers & SEOs 
• From Zero To ChatGPT Hero: How To Harness The Power Of AI In Marketing
• Leveraging Generative AI Tools For SEO

Featured Image: Tapati Rinchumrus/Shutterstock

Vincent Terrasi is the Co-founder and CTO at Draft&Goal. With more than 15 year’s experience, Vincent has become an expert ...

Subscribe To Our Newsletter.

Conquer your day with daily search marketing news.

ChatGPT doesn't generate code and getting stuck mid response

I have an issue where ChatGPT just freezes around 20l lines of code, then it tries to regenerate but it doesn’t work. causing a weird behaviour. It generated 20 or so lines of code, got stuck, then there empty space and another code prompt with 1 line, then again and again. Then sometimes after trying it 5-10 times it shows “network error”.

I’ve tried different solutions that I found here, like telling to continue and stuff (won’t work cuz prompt never finishes, and stoping it, causes it to regenerate from beginning, and then it get stuck in the same spot). I’ve tried my other account (that doesn’t have premium and same thing, also, 3.5, same thing. iOS and Android apps, same problem. Anyone else expiriences this? It start happening after todays outage, but OpenAI’s Status website says it’s all fixed.

It is not just you, the service is crapped out again.

Edit: The updates page is now showing this as an issue and being investigated.

I’m relieved to hear it’s not only me. Do you also have an issue with the code block?

Update: Just saw it too, hopefully they fix by morning.

I was having issues with everything, I tested some code generation and it also caused an issue.

Hey i am also having this exact problem, and i had it all day yesterday.

The status page now lists it as resolved. I had good luck with it for the past hour or so but it is now acting up again.

Edit: For anyone having issues as well, I created a new gpt without any browsing or dalle. In the chat where the errors were occurring I summoned the new gpt by typing the “@” symbol and the name of the newly created gpt, and asked it to continue generating the script that was incomplete. This seems to have fixed it from being stuck however I can’t guarantee anything.

I have been experiencing the same issue since yesterday evening CET, and it has not been resolved yet.

Getting the same errors as well

Code generation just gets stuck and sometimes repeat itself.

I have this exact issue, my response also stops generating after List

Seems like, I’m not only one with this issue. Prompt : Dont use chars “<>” in your answer and change them for “*” (or anything else) seems to be temporary workaround for me …

Same here, the code generation is interrupted and after a while it shows “Network error”.

Same. Empty code blocks since yesterday.

same problem to. did openai say anything about it ?

Related Topics

Have a thesis expert improve your writing

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

• Knowledge Base

Using AI tools

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

How to Write an Essay with ChatGPT | Tips & Examples

Published on 26 June 2023 by Koen Driessen .

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

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

You can use ChatGPT to:

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

Instantly correct all language mistakes in your text

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

Table of contents

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

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

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

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

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

Example: Using ChatGPT to write a research question

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

The only proofreading tool specialized in correcting academic writing

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

Correct my document today

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

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

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

Examples: Using ChatGPT to generate an essay outline

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

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

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

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

Example: Using ChatGPT to find sources

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

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

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

Example: Using ChatGPT to summarise/paraphrase

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

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

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

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

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

Example: Using ChatGPT for feedback

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

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

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

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

Citing sources

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

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

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

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

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

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

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

Cite this Scribbr article

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

Driessen, K. (2023, June 26). How to Write an Essay with ChatGPT | Tips & Examples. Scribbr. Retrieved 22 April 2024, from https://www.scribbr.co.uk/using-ai-tools/chatgpt-essays/

Is this article helpful?

Koen Driessen

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

Media Inquiries

• 615-322-6397 Email

Latest Stories

• WATCH: These Class of 2024 students use ‘dare to grow’ passion to help others
• A powerful stage for learning: Vanderbilt and TPAC celebrate successful wrap of InsideOut events
• Staff volunteers needed for Class of 2024 Commencement

Apr 22, 2024, 9:00 AM

When some schools are banning ChatGPT, Vanderbilt is embracing generative AI technology to unlock opportunities for research and learning.

By michael blanding.

In her class on the politics of the French Revolution, Holly Tucker starts off by assigning a historical character to each student—Marquis de Lafayette, Jean-Jacques Rousseau, Louis XVI—and giving them a multi-page role sheet detailing their alter ego’s political affiliation, life philosophy and strategic goals. Monarchist or revolutionary firebrand, this will be the student’s persona for the next six weeks, as Tucker has the class role-play scenarios, seek out alliances and vanquish their enemies in a simulation of the crucial historical event.

She next encourages them to do something many teachers wouldn’t dream of—talk to ChatGPT. “One of their first assignments is to upload their role sheet and then ask questions about it,” says Tucker, Mellon Foundation Chair in the Humanities and professor of French, of the interaction with the generative artificial intelligence app that has exploded onto the internet, generating equal parts excitement and fear. “I have them say, ‘Can you help me find three characters I might want to correspond with, and help me brainstorm approaches to frame my letters to them?’”

From then on, artificial intelligence becomes a vital part of the course. Students use it to analyze vast amounts of data, to communicate with each other and to make strategic moves. In all, Tucker says, students write an average of 18,000 messages to each other, as AI helps keep track of the interactions and even offers student insights into potential outcomes of decisions they are considering—teaching students about the French Revolution in a uniquely immersive way.

“It’s a watershed moment for the humanities. We now have the ability to communicate with a computer using natural language,” Tucker says. “We owe it to ourselves to find ways to use generative AI to glean insights from our texts faster and ask new questions about the human endeavor.”

Tucker’s enthusiastic embrace of ChatGPT in her class is just one example of Vanderbilt faculty’s groundbreaking work in harnessing the growing power of artificial intelligence. At a time when some schools are banning ChatGPT in classes—concerned that students will lean too heavily on AI or use it to write papers for them—Vanderbilt has become a leader in integrating AI into academic work. Faculty are using AI in their research, as well as introducing it to students, teaching them how to use it as a tool and not a crutch.

WATCH: AI Unearths Untold Stories

Historians jane landers and daniel genkins leverage artificial intelligence and computer science techniques to scan through thousands of historical documents to form the slave societies digital archive, the world’s largest collection of historical records of africans in the atlantic world..

FUTURE OF LEARNING

“Everybody’s focused on artificial intelligence replacing humans,” says Jules White, professor of computer science and associate dean for strategic learning programs. “But what we want to focus on is augmented intelligence, where it’s all about amplifying human creativity and problem-solving. It’s like an exoskeleton for the mind—you help people create more interesting and expressive things than they could have done before, and at a larger scale.”

White leads the Future of Learning and Generative AI Initiative, a new interdisciplinary program to connect and advise faculty on how to make the most of the prodigious computing power generative AI can offer. A CNN article this summer said Vanderbilt was “among the early leaders taking a strong stance in support of generative AI,” specifically citing an 18-hour online course White created on the e-learning platform Coursera that teaches the fundamentals of “prompt engineering”—how to best fashion a prompt to ChatGPT and other AI platforms to return the most helpful response. The course has been taken by 240,000 people and counting.

In their simplest form, White says, generative AI models are trained to predict the next word in a sentence. If you give it “Mary had a little,” then it should predict “lamb.” The magic happens when you train it on vast amounts of data from the World Wide Web. “It turns out this has surprising ramifications when you do this at a large enough scale, as it learns patterns in our language and can do all of these computations.”

Most of the problems with ChatGPT and other generative AI platforms, White says, result from people not knowing how to use it properly. “People see a text box, and they think they need to use it like Google, which is exactly the wrong way to use it,” he explains. “That doesn’t give you augmented intelligence, that gives you minus intelligence.”

Rather than using it to search for information, he says, generative AI is most effective when treated like you are sending a text message to an incredibly smart and capable assistant. One example he uses in his class is to ask it to create a meal plan “that’s a fusion of food from Ethiopia and Uzbekistan, is keto-friendly and has ingredients I can get from the average grocery store.” There isn’t a page on Google that could give you that info, and yet ChatGPT can create a complete multi-week menu in seconds. Another trick, he adds, is to give it a role, for example, telling it to “act like a speech pathologist” before presenting it with a problem where a child mixes up words and asking it to diagnose possible causes. “Knowing the pattern of interaction allows it to tap into these emergent computational capabilities that no other system on the planet can perform.”

APPLYING AI TO VAST AMOUNTS OF DATA

Another use for the software is to analyze and summarize vast amounts of complex information. In the past, Doug Schmidt, Cornelius Vanderbilt Professor of Computer Science, has worked in government procurement for defense systems—for example, building a next-generation air traffic management or missile defense system. “It involves an enormous number of people over a very long time and at great expense,” he says. Comparing information in multiple reports by different people and then trying to figure out if they meet government regulations can be a major headache. “As luck would have it, large language models are very good at that,” says Schmidt, who is researching how generative AI can dramatically save time and money by comparing and synthesizing such reports.

On another level, Schmidt is using the same tools in his computer science classes, using a Chrome plugin called Glasp to take videos of his lectures and toss a transcript into ChatGPT to summarize the main points. Schmidt then asks it to generate several quiz questions based on the videos. “And boom, within seconds, I have fresh up-to-date questions on what I talked about in class,” he says. Of course, Schmidt reviews the questions to see if they are accurate—something easy to do since he generated the material himself—but the tool helps take away from tasks he finds tedious, so he can focus on those he enjoys, such as writing lectures and code.

As for the fears that students will cheat on tests and papers by using ChatGPT, he addresses that head-on by changing the way he designs problems. Instead of asking students to write very specific code they could easily generate using AI, he presents more open-ended questions that could be solved in a variety of ways, requiring students to use their own creativity. Of course, those tests are harder to grade, but Schmidt has come up with a solution to that, too, training ChatGPT to automatically find elements that should or shouldn’t be in the code. “Instead of hiring an army of graders and asking them to follow some rubric, I’ve found a way to automatically do something that used to require tremendous time and effort on the part of me and my TAs.”

Efforts by some to ban ChatGPT and other AI software, Schmidt says, are misguided. “They think this is a flash in the pan and are actively discouraging people from using it,” he says. “Our hypothesis is that in the very near future people who know how to use this stuff well are going to run rings around the people who don’t. They won’t be able to get anywhere near the level of productivity for the amount of effort expended.”

BUILDING SKEPTICAL AND INFORMED AI USERS

His colleague Jesse Spencer-Smith, chief data scientist and interim director of the Data Science Institute and professor of the practice of computer science, has gone a step further in embracing generative AI for coding. As someone who has taught artificial intelligence for 20 years, Spencer-Smith recently changed the name of his advanced coding class to AI-Assisted Coding. “Rather than trying to detect whether you used ChatGPT to solve a programming problem, we’ve turned it around, to say, ‘Use ChatGPT and get very efficient and know how to guide it,’” he says.

He encourages the same approach in the humanities, citing a clever exercise by a faculty member in the English department who specifically told students to use ChatGPT to write an essay—and then turn around and grade it, so they could see its shortcomings where it used poor phrasing or got information wrong, as well as how it can be used to help organize ideas. “It turns people into skeptical and informed users and also gets them to the point where they can understand what good writing is,” Spencer-Smith says.

On the other hand, generative AI can be an excellent tool for studying or brainstorming. The DSI and Center for Teaching have collaborated on a platform which acts as a personalized tutor, where students can upload a book chapter or paper they need to review, and the AI can generate questions to quiz them on the material. The entire transcript can then be uploaded so the professor can see what the student understands and where they need help. “I used to have help sessions where half the class would be in every week,” Spencer-Smith says. “Now, I have very few people because they are all using ChatGPT to explain concepts in a way customized to their background.”

DSI has also collaborated with faculty to integrate AI into their teaching and research. Recently, for example, it’s been working with Karan Jani, professor of physics and astronomy, on creating an AI model to identify gravity waves to detect the presence of black holes. “The idea is to train a model that could be used to solve not just one problem, but a host of problems, and then be known as the Vanderbilt foundational model for gravity waves,” Spencer-Smith says.

Beyond using AI for research, Spencer-Smith also directs the Data Science for Social Good program, a 10-week program for graduate students who receive a stipend to use AI for practical applications. One recent project with The Vanderbilt Kennedy Center Treatment and Research Institute for Autism Spectrum Disorders (TRIAD) helped develop a workplace app for people with autism, providing a virtual coach they could ask questions and receive help for navigating challenging situations. Another project worked with Professor Emerita of Psychology and Human Development Georgene Troseth and Professor Amy Booth, who spent years developing an app to help provide prompts to parents and other caregivers to better engage with their children when reading books. The AI Storybook project has finally realized their vision, using generative AI to suggest questions in real time for any children’s book.

“The whole purpose of this curriculum is to get students to understand how complex history is and how, during these watershed moments, history can turn on a dime. We don’t need to tell them that—they’re living it.” —Holly Tucker

When and how to best deploy AI in classrooms is something best left to individual instructors rather than mandated by university-wide policy, says Doug Fisher, associate professor of computer science and computer engineering. “While the technology is changing so much, it makes sense for us to allow individuals to investigate different options and then come together to compare notes,” says Fisher, who previously oversaw programs in AI for the National Science Foundation and co-taught a class at Vanderbilt on AI ethics.

Some professors may decide that AI is not appropriate to use in entry-level classes, where students are better off developing their own skills before seeking out computer-assisted aid. At the same time, Fisher noted, AI’s propensity for bias—being trained on a vast corpus of data on an imperfect internet—might give instructors pause before using it around sensitive topics such as race and gender studies. While students might feel more comfortable discussing those ideas with an impersonal machine, “there could be problematic exchanges humans are better equipped to handle.”

However the technology is incorporated into the classroom or the lab, it’s clear that the adventure with AI—particularly generative AI—is just beginning. It may take months or years before students and faculty best understand where it can be used most effectively and how it can best augment learning and discovery. In the meantime, it’s clear that AI is affecting learning now. Tucker says that students in her French Revolution class are required to turn in 20 pages by the end of the course—but they are so engaged that the average student turns in 25. “I’d never used ChatGPT before,” says Remi Bristol, one of Tucker’s students. “Now I definitely see myself using it in the future, for readings in classes that are confusing for me or to help prepare for a job interview.”

A recent survey of executives by IBM predicted that up to 40 percent of the workforce will have to reskill to manage AI in the next three years. It’s clear from their experiences in Tucker’s class and others that Vanderbilt students will be ready for that challenge.

“The whole purpose of this curriculum is to get students to understand how complex history is and how, during these watershed moments, history can turn on a dime,” Tucker says. “We don’t need to tell them that—they’re living it.”

Keep Reading

Vanderbilt extends leadership in generative AI

Unlock the full power of AI with Vanderbilt’s second free ChatGPT online course

Vanderbilt launches Future of Learning and Generative AI Initiative and interdisciplinary advisory board

Explore story topics.

• Cover Feature
• Featured VMAG
• Features - VMAGAZINE
• Vanderbilt Magazine
• Winter/Spring 2024
• Winter/Spring 24
• College of Arts and Science
• data science
• Data Science Institute
• Doug Fisher
• Doug Schmidt
• Holly Tucker
• Jesse Spencer-Smith
• Jules White
• Research and Innovation
• Vanderbilt Magazine – Featured
• Vanderbilt University School of Engineering