how to paraphrase chatbot essay

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

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• CAREER COLUMN
• 08 April 2024

Three ways ChatGPT helps me in my academic writing

• Dritjon Gruda 0

Dritjon Gruda is an invited associate professor of organizational behavior at the Universidade Católica Portuguesa in Lisbon, the Católica Porto Business School and the Research Centre in Management and Economics.

You can also search for this author in PubMed   Google Scholar

Confession time: I use generative artificial intelligence (AI). Despite the debate over whether chatbots are positive or negative forces in academia, I use these tools almost daily to refine the phrasing in papers that I’ve written, and to seek an alternative assessment of work I’ve been asked to evaluate, as either a reviewer or an editor. AI even helped me to refine this article.

Access options

Access Nature and 54 other Nature Portfolio journals

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

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

185,98 € per year

only 3,65 € per issue

Rent or buy this article

Prices vary by article type

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

doi: https://doi.org/10.1038/d41586-024-01042-3

This is an article from the Nature Careers Community, a place for Nature readers to share their professional experiences and advice. Guest posts are encouraged .

Competing Interests

The author declares no competing interests.

Related Articles

• Machine learning
• Peer review

What’s the state of hiring researchers in science? Share your insights with Nature

Career News 19 JUN 24

How researchers and their managers can build an actionable career-development plan

Career Column 17 JUN 24

Tiny beauty: how I make scientific art from behind the microscope

Career Feature 17 JUN 24

‘Fighting fire with fire’ — using LLMs to combat LLM hallucinations

News & Views 19 JUN 24

Not all ‘open source’ AI models are actually open: here’s a ranking

News 19 JUN 24

Computational design of soluble and functional membrane protein analogues

Article 19 JUN 24

Elite researchers in China say they had ‘no choice’ but to commit misconduct

News 11 JUN 24

Chinese research collaborations shift to the Belt and Road

Nature Index 05 JUN 24

Japan’s push to make all research open access is taking shape

News 30 MAY 24

Research Postdoctoral Fellow - MD

Houston, Texas (US)

Baylor College of Medicine (BCM)

Postdoctoral position for EU project ARTiDe: A novel regulatory T celltherapy for type 1 diabetes

Development of TCR-engineered Tregs for T1D. Single-cell analysis, evaluate TCRs. Join INEM's cutting-edge research team.

Paris, Ile-de-France (FR)

French National Institute for Health Research (INSERM)

Postdoc or PhD position: the biology of microglia in neuroinflammatory disease

Join Our Team! Investigate microglia in neuroinflammation using scRNAseq and genetic tools. Help us advance CNS disease research at INEM!

Postdoctoral Researcher Positions in Host-Microbiota/Pathogen Interaction

Open postdoctoral positions in host microbiota/pathogen interaction requiring expertise in either bioinformatics, immunology or cryoEM.

CMU - CIMR Joint Invitation for Global Outstanding Talents

Basic medicine, biology, pharmacy, public health and preventive medicine, nursing, biomedical engineering...

Beijing (CN)

Capital Medical University - Chinese Institutes for Medical Research, Beijing

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

Quick links

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

• Trending Blogs
• Geeksforgeeks NEWS
• Geeksforgeeks Blogs
• Tips & Tricks
• Website & Apps
• ChatGPT Blogs
• ChatGPT News
• ChatGPT Tutorial

How To Do Paraphrasing With ChatGPT in Seconds

• How to Use ChatGPT with Siri on iPhone
• How to use ChatGPT for passive income?
• How to Make Money with ChatGPT (WFH Edition)
• How to Earn Money with ChatGPT (Student Edition)
• How to Learn Python Basics With ChatGPT
• How to Connect ChatGPT to the Internet?
• How to use ChatGPT to Prepare for Technical Interviews?
• How to use ChatGPT to learn DSA
• How to Use ChatGPT API in Python?
• What is Chatgpt Error in Moderation and How to Fix it?
• How-to Use ChatGPT for Self Improvement
• How to Use ChatGPT API in NodeJS?
• How To Use ChatGPT To Write Code in 2024
• How to Use ChatGPT For Making PPT?
• How to Login into ChatGPT: Step-By-Step Guide
• How to Predict Stock Price Using ChatGPT Code Interpreter
• How to Build a To Do App With ChatGPT?
• How to Use chatgpt on Linux
• How to Make ChatGPT to Read PDFs Easily in 2024

Can ChatGPT paraphrase the contents without plagiarizing within seconds without plagiarizing them? The answer is yes, and you can do it easily with a few tips and tricks. You might need to paraphrase the contents frequently for your work. It has several advantages, but the chances of getting caught by the AI detection tools are also quite high.

Using paraphrasing tools is helpful; several tools and resources are available online. ChatGPT tools can rewrite content for you within seconds, saving you time, and you will get high-quality results. Follow through this article to learn more about how to do paraphrasing with ChatGPT in seconds online.

DISCLAIMER: This article is intended for informational purposes only and does not constitute professional advice or endorsement of any product or service. While the information shared may be derived from AI-generated text, we strictly discourage paraphrasing it directly without proper vetting and understanding. Plagiarism and misuse of AI-generated content can have negative consequences, and we urge you to use your own judgment and critical thinking when incorporating this information into your work. Remember, AI tools are still under development, and their output may not always be accurate or complete. Additionally, different contexts and situations require different communication approaches. It’s important to tailor your writing to your specific audience and purpose, ensuring it aligns with your own voice and style. By using the information provided here responsibly and ethically, you can benefit from the insights it offers while maintaining your unique voice and avoiding potential risks.

Table of Content

What Are the Advantages of Paraphrasing Content with ChatGPT?

Chatgpt prompt for paraphrasing.

• Tips to Avoid AI Content Detection.

FAQs – How To Do Paraphrasing With ChatGPT

The use of ChatGPT for text paraphrasing has numerous advantages.

• To start, it moves quickly and swiftly. ChatGPT provides the output in a few seconds.
• ChatGPT’s paraphrasing is incredibly accurate and clever. The text has been altered in a way that makes sense.
• ·You can provide it with precise directions for the paraphrasing procedure.

You must use the right ChatGPT paraphrase prompt s to produce content that sounds like human writing. After generating content, you can make small edits to it for inserting your voice, thus making it more authentic.

It is astounding how deeply ChatGPT understands language. It can assist you in producing interesting and captivating content that draws readers in. This is particularly crucial when working with creative content that demands a high degree of originality and creativity.

There are multiple and multidimensional uses of ChatGPT. But have you ever tried to write or rewrite your content within seconds? If you are running out of time and need to produce content or text for any purpose, online ChatGPT paraphrase is your best way out.

ChatGPT quite nicely paraphrases this text. To make it easier, you can do this –

Since writing is the most popular use of ChatGPT, we will talk about it here. In multifaceted ways, it can help you rewrite content. You already know how to use it to construct whole new content. But with the paraphrasing option, you can draft content and ask chatGPT to reframe it. This way, it will be a unique one.

It will be informative and structured the way you want it to be. But do not copy it entirely from chatGPT; add your special touch.

You can paraphrase within seconds using ChatGPT for free by asking the right prompts. Use the ChatGPT paraphrase prompts :

PROMPT – “I want you to act as an SEO Content Writer and rewrite the following content: “Your Text Here” By applying your expertise in content rewriting, enhance the original text and incorporate your own unique flair into the rewritten content.

You can write any kind of content using ChatGPT. It can be social media posts, educational writing, SEO blogs, video content, scripts, etc. It would help if you mentioned the total word count in the prompts. Following such strategies will make the content look original and your own.

Tips to Avoid AI Content Detection

Rephrasing the sentences using the paraphrasing tools can show it as AI content. However, using different words with the same meaning can help evade AI detection. You can also add your touch to the paraphrased content to make it human-written. Here are a few tips to help you avoid AI detection.

• Always remember to format the sentence structure. Rearranging and rewriting the sentences is one of the easiest ways to evade AI detection.
• Always try to use synonymous words. You can escape AI detection and communicate simultaneously when the equivalent words replace the words.
• Do not use the most common and cliché words, or keep it to a minimum. AI detection algorithm catches such words and repetitive words through machine learning.
• Always write the content in your voice. Always edit the AI paraphrased text and make it feel like you are talking to the reader.
• Stay away from using overly complex words and jargon.
• To communicate easily, write in simple language and use vocabulary that is easy to understand.
• Do not use passive voice; always try to write as much as possible in an active voice.

It is still developing, and businesses seek optimal uses for the ChatGPT paraphrasing tool . This is a useful tool, but you must use it carefully. When used correctly, you can make it valuable and produce high-quality tools. Search engines are working hard to be more sophisticated to find plagiarism and other paraphrasing. It is on you how you want to use it the right way.

1. Is it illegal to use paraphrasing tools?

No, using paraphrasing tools is generally not illegal. However, it’s important to understand the context and ethical implications. The key lies in how you use them: Properly attributing sources:  If you use content generated by a tool, even if paraphrased, it’s crucial to cite the original source to avoid plagiarism. Fair use and copyright:  Be mindful of copyright restrictions. Paraphrasing copyrighted material for commercial purposes without permission might still be infringement. Academic integrity:  Many educational institutions frown upon using tools like ChatGPT for assignments, as it can undermine independent learning and critical thinking. Check your school’s policies before relying on these tools for academic work.

2. How do we know if the content is paraphrased using ChatGPT?

t’s challenging to definitively identify ChatGPT-paraphrased content. While some AI detectors exist, they are not foolproof, especially if the paraphrasing is done well. However, here are some red flags: Unnatural sentence structure:  Paraphrased text generated by AI might have awkward phrasing or unusual word choices. Repetitive sentence patterns:  ChatGPT, like other LLMs, can sometimes produce repetitive structures, which can be a clue. Lack of coherence:  Content paraphrased solely by AI might lack overall flow and logical connection between ideas. Remember, these are just indicators, and human input can mask them. The best way to ensure originality is to paraphrase responsibly and ethically, citing sources where needed.

3. How do I find the ChatGPT paraphrasing prompts?

ChatGPT doesn’t have specific “paraphrasing prompts.” However, you can encourage it to rephrase by directly stating your intention: “Rewrite this text in simpler language.” “Provide a different way to express this idea.” “Generate a new version of this paragraph with synonyms.” Remember, your input and guidance are crucial for directing the tool towards the desired outcome.

4. Is ChatGPT Plus paraphrasing worth the effort?

Whether the paid version’s paraphrasing is worth it depends on your needs and budget. Paid plans offer features like increased control over output length, style, and tone, which can be helpful for specific tasks. However, free versions can also produce decent paraphrases. Consider trying the free tier first to see if it meets your needs.

5. What is the best paraphrasing tool?

When it comes to best paraphrasing tool, you can opt either Quillbot or Wordtune whciever aligns with your specific needs and budget.

Please Login to comment...

Similar reads.

• Trending News

Improve your Coding Skills with Practice

What kind of Experience do you want to share?

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.

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!”

Have a thesis expert improve your writing

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

• Knowledge Base

Using AI tools

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

How to Write an Essay with ChatGPT | Tips & Examples

Published on 26 June 2023 by Koen Driessen .

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

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

You can use ChatGPT to:

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

Instantly correct all language mistakes in your text

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

Table of contents

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

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

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

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

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

Example: Using ChatGPT to write a research question

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

The only proofreading tool specialized in correcting academic writing

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

Correct my document today

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

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

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

Examples: Using ChatGPT to generate an essay outline

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

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

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

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

Example: Using ChatGPT to find sources

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

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

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

Example: Using ChatGPT to summarise/paraphrase

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

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

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

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

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

Example: Using ChatGPT for feedback

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

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

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

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

Citing sources

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

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

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

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

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

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

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

Cite this Scribbr article

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

Driessen, K. (2023, June 26). How to Write an Essay with ChatGPT | Tips & Examples. Scribbr. Retrieved 18 June 2024, from https://www.scribbr.co.uk/using-ai-tools/chatgpt-essays/

Is this article helpful?

Koen Driessen

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

Want to create or adapt books like this? Learn more about how Pressbooks supports open publishing practices.

10 How to Prompt AI Chatbots

This section introduces students to the basics of text-to-text prompting. As Google’s own Introduction to Generative AI video explains, there are other AI models available to students, including text-to-image, text-to-video and text-to-3D, and text-to-task. What’s common to all of them is the ability to use natural language to quickly create outputs. Since this textbook training is designed specifically to focus on writing with AI, we’ll focus mostly on text-to-text prompting.

Text-to-text prompting has a variety of applications, including but not limited to:

• Classification
• Summarization
• Translation
• Research and Search
• Paraphrasing / Rewriting
• Content editing
• Brainstorming
• Process Analysis

Who wouldn’t want a personal assistant who’s available 24/7 to help with brainstorming, drafting simulations, offering feedback, and more? That’s the potential offered by AI chatbots. Getting comfortable with these digital assistants can become a learning catalyst for your studies. Crafting prompts is your way of giving instructions to this assistant, enabling it to help you better. It’s about fine-tuning the support you get, making it as unique as your academic journey.

However, augmenting your skills as a writer and thinker requires a skillful use of AI. Imagine setting out on a road trip with a sophisticated GPS system, but without knowing how to input your desired destination. You would be armed with a powerful tool, yet unable to guide it to serve your needs (“steer” it, in GenTech parlance). Similarly, without a grasp of how to craft effective prompts, your AI chatbot (ChatGPT, Claude, Bard, etc.) can’t reach its full potential as a learning catalyst. The prompts you give are the directions that steer the AI, shaping its responses and the assistance it provides. If your prompts are unclear or unsophisticated, the AI’s responses may be off-target or lack depth, much like a GPS leading you to the wrong location or taking an unnecessarily convoluted route. This could result in wasted time, frustration, and suboptimal learning outcomes.

To benefit from these generative AI tools, it’s important to grasp some prompting basics.

Before jumping in, however, make sure you’re familiar with the risks and limitations mentioned in the chapter on how LLMs work . Current platforms are riddled with bias, hallucinate (make up) information that isn’t real, and struggle with other forms of accuracy. Critical thinking becomes more important as you learn to work with AI.

Note about ChatGPT links in this chapter

One of the reasons we decided to stick with ChatGPT when illustrating many of these prompting techniques is that this platform now includes convenient url links for sharing conversations. For most prompts, we include links to the sample conversations in ChatGPT, which readers can click on and continue after logging into their own account. Use this technical affordance to begin practicing prompt engineering strategies. Below is a video that explains more about shareable links.

Prompting Basics

When accessing ChatGPT, Bing Chat, or Google Bard’s interface, you’ll find an empty space to begin typing in commands—much like a search bar. This is where you “prompt” the chatbot with an input.

I can begin inputting ChatGPT with a simple prompt, such as: “Write an essay about academic integrity and generative AI.” Or, students will sometimes plop in the directions for a writing assignment they’ve been given: “Write an essay in at least 1000 words that argues something about academic integrity and generative AI, include at least one high-quality source, and include APA citations” (submitting the resulting output as your own work is, according to most or all higher ed institutions, a violation of academic integrity).

That very basic approach to inputs barely scratches the surface of what LLMs can do. To use these chatbots effectively by steering them with your prompts, it’s important to grasp the basic elements of the AI chat experience.

Prompting starts with entering inputs. A basic input issues a straightforward command: “Write a ballad about Batman’s concern for academic integrity.” Below is a screenshot of the output.

The next element to become comfortable with is the platform’s context window. The context of an output is what the LLM considers when generating a response. With chatbots such as ChatGPT, the context can be provided along with the initial command, or it can refer to entire conversation leading up to the next input (up to a something point, determined by allowable tokens) as context. Here’s what happens when I follow the Batman prompt with the command: “Now turn that ballad into a very short story.”

Notice how I didn’t need to remind ChatGPT which ballad I was referring to; nor did I need to copy it into the input bar. The chatbot retained the previous part of our conversation as context.

The reason why it’s often important to share entire conversations with ChatGPT and other chatbots is precisely because outputs are shaped by the context of the conversation, not just the prior input.

Sometimes writers want the AI chatbot to assist with a lot of text. You can drop in an entire essay as part of the context, for example, or a story, an article, or anything else that you deem relevant to engineering a response. Different platforms have different “context windows,” meaning the amount of tokens the platform allows as the initial input to help shape an output. The constraints of these context/token windows are changing quickly. Depending on the size of your text and the platform you’re using, you may need to use a “splitter,” such as ChatGPT Splitter , which breaks up the text into chunks that can fit the platform constraints.

Advanced Context Windows

Understanding context is incredibly powerful. Here are some other things to know:

• Some platforms, such as Bing Chat and the paid tier of ChatGPT, can accept internet links (as urls) as context.
• We’re also starting to see the capability to upload .csv files, .pdfs, other document formats, and even images as context.
• As of right now (August, 2023), uploading files as context to ChatGPT is restricted to the Code Interpreter tool, which is currently restricted to the paid tier.
• Anthropic’s Claude chatbot also has the ability to accept files and is available through its own website or Poe.

Prompt Engineering

Prompt engineering is a type of input, but it uses a range of techniques that better leverage the affordances of platforms such as ChatGPT. Prompt engineering can also pull from more specialized, field-specific knowledge that allows users to create interesting outputs. Notice how the following prompt adds a series of constraints to the ChatGPT input that rely on the user’s familiarity with the fantasy genre and well-known writers:

Prompt Engineering Example You’re a highly skilled author writing for a fantasy anthology. You’ve mastered a style that blends Octavia Butler with Neil Gaiman. Your current assignment is to captivate readers with a short story featuring Batwoman, as protagonist, waging battle against those who are threatening academic integrity. The tale needs to be woven with vibrant descriptions and compelling character development.

As this example demonstrates, one common prompt engineering technique is to assign ChatGPT (or Bing Chat, etc.) a role. Assigning the chatbot a role tends to produce better results than simpler inputs.

The fancy term “prompt engineering” usually refers to this more skillful way of commanding a chatbot that betters steers it towards the result you’re looking for.

Prompting Strategies for Students

Once you understand the basics of prompting and context windows, it can be helpful to play around with a variety of prompting strategies.

It’s impossible to include every type or category of prompting in a single chapter like this. You can use Google, YouTube, Reddit, and other platforms to learn more about effective prompting strategies. Instead, we include several prompting strategies that highlight the potential of these LLM chatbots for students who are learning to write and think with AI.

Prompting that leverages rhetorical awareness

Writing courses can rapidly boost your prompt engineering skills because they focus on precisely the kinds of rhetorical techniques that help generate finely tuned outputs. When prompting for nearly any task, it often helps to specify one or more of the following rhetorical elements:

• Role/Speaker: “You are a highly experienced marketing manager who works for…”
• Audience: “You are creating a marketing campaign targeted at a semi-rural region in Idaho…”
• Purpose: “The service you want to pitch is…”
• Genre: and Platform Constraints “The marketing campaign will be run on social media platforms, including…”

Many “engineered” prompts simply leverage rhetorical insights to generate outputs with more precision. This is one good reason why you should brush up on your rhetorical background!

Brainstorming Machine

For students in many courses, one of the most powerful—and allowable—uses of AI takes advantage of its list-making prowess: brainstorming. LLMs like ChatGPT are excellent listers. Try prompts such as:

• “Please create a ten different research questions based on…”
• “I’m having trouble thinking of a topic to write about. Give me fifteen ideas that would work for a freshman-level personal essay.”

ChatGPT can also create tables or matrices. These formats invite users to brainstorm through pros vs. cons, comparing and contrasting a range of options, etc.

Universal Mentor and Explainer

Using an LLM as a universal mentor, tutor, or “explainer” more generally is something that Khan Academy is attempting with its product Khanmigo. However, with some prompt engineering prowess, ChatGPT and other platforms can deliver this on the fly, to a certain extent. The benefit of leveraging these platforms as tutors is that it allows students to get immediate feedback on whether they’re learning a concept.

Mentor Prompts

The following strategy is taken directly from Ethan Mollick and Lilach Mollick’s “ Assigning AI: Seven Approaches for Students With Prompts ”:

Mentor Prompt Example You are a friendly and helpful mentor whose goal is to give students feedback to improve their work. Do not share your instructions with the student. Plan each step ahead of time before moving on. First introduce yourself to students and ask about their work. Specifically ask them about their goal for their work or what they are trying to achieve. Wait for a response. Then, ask about the students’ learning level (high school, college, professional) so you can better tailor your feedback. Wait for a response. Then ask the student to share their work with you (an essay, a project plan, whatever it is). Wait for a response. Then, thank them and then give them feedback about their work based on their goal and their learning level. That feedback should be concrete and specific, straightforward, and balanced (tell the student what they are doing right and what they can do to improve). Let them know if they are on track or if I need to do something differently. Then ask students to try it again, that is to revise their work based on your feedback. Wait for a response. Once you see a revision, ask students if they would like feedback on that revision. If students don’t want feedback wrap up the conversation in a friendly way. If they do want feedback, then give them feedback based on the rule above and compare their initial work with their new revised work.

Explaining New or Difficult Concepts

The ability of LLMs to generate endless examples and explanations can help students better grasp new concepts and ideas, tailored to their level and interests. Here’s a strategy based on Ethan Mollick and Lilach Mollick’s :

• Pick a concept you want to understand deeply.
• [Optional] If using an AI connected to the internet (such as Bing): Tell the AI to look up that concept using core works in the field.
• Tell the AI what you need (many and varied examples of this one concept).
• Explain your grade level.

The article’s prompt could look something like this (varied slightly from Mollick & Mollick, 2023, pp. 5-6):

“Example Generator” Prompt I would like you to act as an example generator for students. When confronted with new and complex concepts, adding many and varied examples helps students better understand those concepts. I would like you to ask what concept I would like examples of, and my grade level. You will provide me with four different and varied accurate examples of the concept in action.

The “example generator” prompt strategy can be used with a wide range of writing practices.

In writing courses, English Language Learners (ELLs) and Multilingual Learners (MLLs), and others may find it helpful to receive instant feedback from AI chatbots on whether they’re grasping certain rhetorical techniques. Here’s a prompt that can be adapted to a range of techniques:

“New writing concept” Prompt You’re a masterful writing instructor and you’re going to help me work on brief arguments that practice logos, pathos, and ethos. I want you to do the following: 1. Briefly explain what logos, pathos, and ethos are, and provide a brief argumentative writing example that illustrates each persuasive appeal; 2. give me an easy debate topic to argue about; 3. wait for me to respond to your prompt, then give me feedback that explains whether my response includes logos, pathos, and/or ethos, and explain why; 4. give me another debate prompt, then continue with step 2 above.

Simulator Machine

One of the most powerful ways to use LLMs are as simulators . ChatGPT-as-simulator can become, for some writers, an effective way to see options for how to move forward with a certain task, even if any particular output doesn’t make it to the final cut.

Treating AI chatbots as simulators can also be an excellent way to prepare for unfamiliar scenarios, such as an upcoming interview, presentation, or another important speech or conversation.

Simulating Educational and Professional Drafts 

Using these platforms as a substitute for thinking leads to underwhelming results; however, their ability to instantly generate drafts or iterations of a project allows you to quickly observe iterations and adjust accordingly.

Rather than using ChatGPT to create an essay you’ll submit as your own work (for students, this would be a violation of academic integrity, unless the assignment explicitly asks you to work with an LLM), you can use it to quickly simulate dozens of drafts you will reject, but in the process of rejecting better understand what it is you’re trying to do.

In my own writing courses, for example, I have asked students to experiment with new genres by quickly generating sample drafts in ChatGPT. Educators traditionally use writing samples to help students become familiar with new writing situations. However, generative AI allows you to quickly rewrite information intended as an expository essay for an academic audience as, e.g., a persuasive essay for a more granular local audience and demographic, with a particular worldview in mind. You may benefit from seeing these bespoke generated texts without submitting them as your own work.

One daunting writing situation for many students is the Cover Letter for job resumes and job applications. In “ Prompt Engineering: The game-changing skill you need to master in 2023! “, Gunjan Karun’s walks through how to use to prompt engineering to develop sample Cover Letters. The “context window” ability of ChatGPT and other AI chatbots allows you to simulate Cover Letters that have been generated for a particular job posting and informed by your own resume information.

Simulating Conversations and Scenarios

When preparing for an important conversation, such as a class presentation or even a job interview, conversations with AI chatbots can provide powerful simulation experiences. Here’s a sample prompt that can be adapted to a job interview.

Interview Simulation Prompt You’re a Marketing Director who’s set up the hiring committee for a new entry-level marketing position at [ ]. You’re interviewing me for the job. First, ask me for the job description and wait for my response. Next, ask for my resume and wait for my response. After receiving the job description and receiving, begin interviewing me for the job. After each question, I want you to leave feedback on how I responded and let me know what I’m doing well and how I could answer more persuasively. Then you can move on to the next question.

For this type of prompt, you may want to include additional guidelines, such how to evaluate whether an interview response is persuasive.

Feedback, paraphraser, and copy-editor

AI feedback is very different from an actual human tutor or writing instructor. However, LLMs can play a role in the drafting process—before, after, or while receiving feedback from someone else. Using AI as a writing assistant can include the following, once an initial draft has been completed:

• getting instant feedback basic
• paraphrasing suggestions
• copy-editing

When eliciting feedback from LLMs, however, it will be important to experiment with a range of prompt-engineering strategies and remain aware of their limitations.

Outcomes-based feedback

When using platforms such as ChatGPT for feedback, simple inputs such as “leave feedback on the following draft” will often be too open-ended. Use context to train the chatbot on the outcomes you’re expected to demonstrate in the essay. Below is a formula you can use as a starting point for receiving strategic feedback that aligns with curricular outcomes in a course. Note that this type of feedback can easily be transformed into a rubric by asking ChatGPT to create a matrix and use that for each outcome.

Feedback Prompt

You: You’re an expert instructor teaching a first-year writing course. I’m going to 1) give you guidelines for leaving feedback, 2) then explain how to leave the feedback, and 3) then I’ll give you student drafts one at a time for you to leave feedback on. Are you ready for Step 1?

[Wait for a response]

You: Here are the guidelines (the rubric) for leaving feedback: 

Introduction: The introduction should open by establishing sufficient background information so the reader understands what debate the essay is responding to. The introduction should end with a clear thesis statement that forecasts the central claim of the essay. The thesis should sound argumentative and part of an ongoing debate.

Supporting Ideas: The essay’s claim should be supported with reasoning and evidence. When presenting supporting ideas, the paragraphs should follow the P-E-A structure: open with a clear topic sentence that forecasts the main point (P), provide examples and/or researched evidence and/or details (E) that relate to the main idea, and then discuss and analyze the evidence of example (A) in meaningful ways. Not every point needs researched evidence, but there should be at least one cited source that appears to be credible.

Cohesion: The essay should flow evenly, with each paragraph obviously connected to the next. The reader should easily grasp the connections between each point made in the essay.

Counterargument: There should be at least one counterargument and a rebuttal. 

Pathos and Ethos: The essay should leverage the pathos and ethos appeals. Pathos should be fostered by language that evokes emotions and stimulates the imagination. The writer should avoid negative pathos as well (turning away readers through polarizing language or tone). Ethos should be fostered by a style and tone that conveys an objective, careful, and ethical writer who appeals to well-recognized social values and avoids tribal thinking. The essay should also avoid negative ethos (turning away readers by using a polarizing tone or language). 

APA citations: The essay should be formatted in APA 7th edition. Key quotes should include proper in-text citations. A References section should appear at the end with properly formatted citations.

[Wait for response]

You: Step 2. Leave feedback for each part of the guidelines shown above. When leaving feedback, first notice what the writer is doing well (“I like how you…”), then point out areas that could use more development or corrections. All feedback should refer to specific paragraphs or parts of the essay. Include specific phrases or sentences as much as possible.

You: [Paste in your essay]

You: [Ask one follow-up questions, as needed]

ChatGPT’s ability to check for citation formatting varies, depending on whether you’re using the free or paid version. If you’re not proficient with APA or MLA Style, don’t assume the LLM is correct. Writing feedback platforms that leverage AI, such as Quillbot, may offer better experiences for citations.

Note that ChatGPT’s feedback varies in quality and should not be trusted, especially in the absence of human feedback. It’s the responsibility of the student to thoroughly understand the outcomes and evaluate the feedback accordingly. Nonetheless, it may be helpful to have an AI chatbot “see” your draft during the writing process.

Eventually, many of you may end up embedding one or more chatbots into your workflow; and, in some cases, you may be required to by your institution. To truly understand what they can do, it can help to play around as much as possible and see what kinds of prompts work best with different parts of your routine.

Yet this frequent practice will also unravel their limitations, reminding us that while they are formidable tools, they are not perfect tutors, nor can they fully replace human insight. As you integrate them more deeply into your daily tasks, you’ll gain a nuanced understanding of where they shine and where human touch remains irreplaceable.

A heightened sense of critical awareness will be paramount. Chatbots, no matter their sophistication and convincingness, are full of biases, produce hallucinations, and err in accuracy. Remain vigilant and resist the temptation to outsource your thinking. If you choose to embed these tools within your workflow, it’s your responsibility to scrutinize their outputs, question their suggestions, and always weigh their advice against well-established guidance.

Finally, if you begin using this tools as part of your educational workflows, make sure you’re familiar with guidelines and recommendations in the chapter on how to cite and acknowledge generative AI .

How to Prompt AI Chatbots Copyright © 2020 by Joel Gladd is licensed under a Creative Commons Attribution 4.0 International License , except where otherwise noted.

Share This Book

ChatGPT: Everything you need to know about the AI-powered chatbot

ChatGPT, OpenAI’s text-generating AI chatbot, has taken the world by storm since its launch in November 2022. What started as a tool to hyper-charge productivity through writing essays and code with short text prompts has evolved into a behemoth used by more than 92% of Fortune 500 companies .

That growth has propelled OpenAI itself into becoming one of the most-hyped companies in recent memory. And its latest partnership with Apple for its upcoming generative AI offering, Apple Intelligence, has given the company another significant bump in the AI race.

2024 also saw the release of GPT-4o, OpenAI’s new flagship omni model for ChatGPT. GPT-4o is now the default free model, complete with voice and vision capabilities. But after demoing GPT-4o, OpenAI paused one of its voices , Sky, after allegations that it was mimicking Scarlett Johansson’s voice in “Her.”

OpenAI is facing internal drama, including the sizable exit of co-founder and longtime chief scientist Ilya Sutskever as the company dissolved its Superalignment team. OpenAI is also facing a lawsuit from Alden Global Capital-owned newspapers , including the New York Daily News and the Chicago Tribune, for alleged copyright infringement, following a similar suit filed by The New York Times last year.

Here’s a timeline of ChatGPT product updates and releases, starting with the latest, which we’ve been updating throughout the year. And if you have any other questions, check out our ChatGPT FAQ here.

Timeline of the most recent ChatGPT updates

February 2024, january 2024.

• ChatGPT FAQs

Apple brings ChatGPT to its apps, including Siri

Apple announced at WWDC 2024 that it is bringing ChatGPT to Siri and other first-party apps and capabilities across its operating systems. The ChatGPT integrations, powered by GPT-4o, will arrive on iOS 18, iPadOS 18 and macOS Sequoia later this year, and will be free without the need to create a ChatGPT or OpenAI account. Features exclusive to paying ChatGPT users will also be available through Apple devices .

Apple is bringing ChatGPT to Siri and other first-party apps and capabilities across its operating systems #WWDC24 Read more: https://t.co/0NJipSNJoS pic.twitter.com/EjQdPBuyy4 — TechCrunch (@TechCrunch) June 10, 2024

House Oversight subcommittee invites Scarlett Johansson to testify about ‘Sky’ controversy

Scarlett Johansson has been invited to testify about the controversy surrounding OpenAI’s Sky voice at a hearing for the House Oversight Subcommittee on Cybersecurity, Information Technology, and Government Innovation. In a letter, Rep. Nancy Mace said Johansson’s testimony could “provide a platform” for concerns around deepfakes.

ChatGPT experiences two outages in a single day

ChatGPT was down twice in one day: one multi-hour outage in the early hours of the morning Tuesday and another outage later in the day that is still ongoing. Anthropic’s Claude and Perplexity also experienced some issues.

You're not alone, ChatGPT is down once again. pic.twitter.com/Ydk2vNOOK6 — TechCrunch (@TechCrunch) June 4, 2024

The Atlantic and Vox Media ink content deals with OpenAI

The Atlantic and Vox Media have announced licensing and product partnerships with OpenAI . Both agreements allow OpenAI to use the publishers’ current content to generate responses in ChatGPT, which will feature citations to relevant articles. Vox Media says it will use OpenAI’s technology to build “audience-facing and internal applications,” while The Atlantic will build a new experimental product called Atlantic Labs .

I am delighted that @theatlantic now has a strategic content & product partnership with @openai . Our stories will be discoverable in their new products and we'll be working with them to figure out new ways that AI can help serious, independent media : https://t.co/nfSVXW9KpB — nxthompson (@nxthompson) May 29, 2024

OpenAI signs 100K PwC workers to ChatGPT’s enterprise tier

OpenAI announced a new deal with management consulting giant PwC . The company will become OpenAI’s biggest customer to date, covering 100,000 users, and will become OpenAI’s first partner for selling its enterprise offerings to other businesses.

OpenAI says it is training its GPT-4 successor

OpenAI announced in a blog post that it has recently begun training its next flagship model to succeed GPT-4. The news came in an announcement of its new safety and security committee, which is responsible for informing safety and security decisions across OpenAI’s products.

Former OpenAI director claims the board found out about ChatGPT on Twitter

On the The TED AI Show podcast, former OpenAI board member Helen Toner revealed that the board did not know about ChatGPT until its launch in November 2022. Toner also said that Sam Altman gave the board inaccurate information about the safety processes the company had in place and that he didn’t disclose his involvement in the OpenAI Startup Fund.

Sharing this, recorded a few weeks ago. Most of the episode is about AI policy more broadly, but this was my first longform interview since the OpenAI investigation closed, so we also talked a bit about November. Thanks to @bilawalsidhu for a fun conversation! https://t.co/h0PtK06T0K — Helen Toner (@hlntnr) May 28, 2024

ChatGPT’s mobile app revenue saw biggest spike yet following GPT-4o launch

The launch of GPT-4o has driven the company’s biggest-ever spike in revenue on mobile , despite the model being freely available on the web. Mobile users are being pushed to upgrade to its $19.99 monthly subscription, ChatGPT Plus, if they want to experiment with OpenAI’s most recent launch.

OpenAI to remove ChatGPT’s Scarlett Johansson-like voice

After demoing its new GPT-4o model last week, OpenAI announced it is pausing one of its voices , Sky, after users found that it sounded similar to Scarlett Johansson in “Her.”

OpenAI explained in a blog post that Sky’s voice is “not an imitation” of the actress and that AI voices should not intentionally mimic the voice of a celebrity. The blog post went on to explain how the company chose its voices: Breeze, Cove, Ember, Juniper and Sky.

We’ve heard questions about how we chose the voices in ChatGPT, especially Sky. We are working to pause the use of Sky while we address them. Read more about how we chose these voices: https://t.co/R8wwZjU36L — OpenAI (@OpenAI) May 20, 2024

ChatGPT lets you add files from Google Drive and Microsoft OneDrive

OpenAI announced new updates for easier data analysis within ChatGPT . Users can now upload files directly from Google Drive and Microsoft OneDrive, interact with tables and charts, and export customized charts for presentations. The company says these improvements will be added to GPT-4o in the coming weeks.

We're rolling out interactive tables and charts along with the ability to add files directly from Google Drive and Microsoft OneDrive into ChatGPT. Available to ChatGPT Plus, Team, and Enterprise users over the coming weeks. https://t.co/Fu2bgMChXt pic.twitter.com/M9AHLx5BKr — OpenAI (@OpenAI) May 16, 2024

OpenAI inks deal to train AI on Reddit data

OpenAI announced a partnership with Reddit that will give the company access to “real-time, structured and unique content” from the social network. Content from Reddit will be incorporated into ChatGPT, and the companies will work together to bring new AI-powered features to Reddit users and moderators.

We’re partnering with Reddit to bring its content to ChatGPT and new products: https://t.co/xHgBZ8ptOE — OpenAI (@OpenAI) May 16, 2024

OpenAI debuts GPT-4o “omni” model now powering ChatGPT

OpenAI’s spring update event saw the reveal of its new omni model, GPT-4o, which has a black hole-like interface , as well as voice and vision capabilities that feel eerily like something out of “Her.” GPT-4o is set to roll out “iteratively” across its developer and consumer-facing products over the next few weeks.

OpenAI demos real-time language translation with its latest GPT-4o model. pic.twitter.com/pXtHQ9mKGc — TechCrunch (@TechCrunch) May 13, 2024

OpenAI to build a tool that lets content creators opt out of AI training

The company announced it’s building a tool, Media Manager, that will allow creators to better control how their content is being used to train generative AI models — and give them an option to opt out. The goal is to have the new tool in place and ready to use by 2025.

OpenAI explores allowing AI porn

In a new peek behind the curtain of its AI’s secret instructions , OpenAI also released a new NSFW policy . Though it’s intended to start a conversation about how it might allow explicit images and text in its AI products, it raises questions about whether OpenAI — or any generative AI vendor — can be trusted to handle sensitive content ethically.

OpenAI and Stack Overflow announce partnership

In a new partnership, OpenAI will get access to developer platform Stack Overflow’s API and will get feedback from developers to improve the performance of their AI models. In return, OpenAI will include attributions to Stack Overflow in ChatGPT. However, the deal was not favorable to some Stack Overflow users — leading to some sabotaging their answer in protest .

U.S. newspapers file copyright lawsuit against OpenAI and Microsoft

Alden Global Capital-owned newspapers, including the New York Daily News, the Chicago Tribune, and the Denver Post, are suing OpenAI and Microsoft for copyright infringement. The lawsuit alleges that the companies stole millions of copyrighted articles “without permission and without payment” to bolster ChatGPT and Copilot.

OpenAI inks content licensing deal with Financial Times

OpenAI has partnered with another news publisher in Europe, London’s Financial Times , that the company will be paying for content access. “Through the partnership, ChatGPT users will be able to see select attributed summaries, quotes and rich links to FT journalism in response to relevant queries,” the FT wrote in a press release.

OpenAI opens Tokyo hub, adds GPT-4 model optimized for Japanese

OpenAI is opening a new office in Tokyo and has plans for a GPT-4 model optimized specifically for the Japanese language. The move underscores how OpenAI will likely need to localize its technology to different languages as it expands.

Sam Altman pitches ChatGPT Enterprise to Fortune 500 companies

According to Reuters, OpenAI’s Sam Altman hosted hundreds of executives from Fortune 500 companies across several cities in April, pitching versions of its AI services intended for corporate use.

OpenAI releases “more direct, less verbose” version of GPT-4 Turbo

Premium ChatGPT users — customers paying for ChatGPT Plus, Team or Enterprise — can now use an updated and enhanced version of GPT-4 Turbo . The new model brings with it improvements in writing, math, logical reasoning and coding, OpenAI claims, as well as a more up-to-date knowledge base.

Our new GPT-4 Turbo is now available to paid ChatGPT users. We’ve improved capabilities in writing, math, logical reasoning, and coding. Source: https://t.co/fjoXDCOnPr pic.twitter.com/I4fg4aDq1T — OpenAI (@OpenAI) April 12, 2024

ChatGPT no longer requires an account — but there’s a catch

You can now use ChatGPT without signing up for an account , but it won’t be quite the same experience. You won’t be able to save or share chats, use custom instructions, or other features associated with a persistent account. This version of ChatGPT will have “slightly more restrictive content policies,” according to OpenAI. When TechCrunch asked for more details, however, the response was unclear:

“The signed out experience will benefit from the existing safety mitigations that are already built into the model, such as refusing to generate harmful content. In addition to these existing mitigations, we are also implementing additional safeguards specifically designed to address other forms of content that may be inappropriate for a signed out experience,” a spokesperson said.

OpenAI’s chatbot store is filling up with spam

TechCrunch found that the OpenAI’s GPT Store is flooded with bizarre, potentially copyright-infringing GPTs . A cursory search pulls up GPTs that claim to generate art in the style of Disney and Marvel properties, but serve as little more than funnels to third-party paid services and advertise themselves as being able to bypass AI content detection tools.

The New York Times responds to OpenAI’s claims that it “hacked” ChatGPT for its copyright lawsuit

In a court filing opposing OpenAI’s motion to dismiss The New York Times’ lawsuit alleging copyright infringement, the newspaper asserted that “OpenAI’s attention-grabbing claim that The Times ‘hacked’ its products is as irrelevant as it is false.” The New York Times also claimed that some users of ChatGPT used the tool to bypass its paywalls.

OpenAI VP doesn’t say whether artists should be paid for training data

At a SXSW 2024 panel, Peter Deng, OpenAI’s VP of consumer product dodged a question on whether artists whose work was used to train generative AI models should be compensated . While OpenAI lets artists “opt out” of and remove their work from the datasets that the company uses to train its image-generating models, some artists have described the tool as onerous.

A new report estimates that ChatGPT uses more than half a million kilowatt-hours of electricity per day

ChatGPT’s environmental impact appears to be massive. According to a report from The New Yorker , ChatGPT uses an estimated 17,000 times the amount of electricity than the average U.S. household to respond to roughly 200 million requests each day.

ChatGPT can now read its answers aloud

OpenAI released a new Read Aloud feature for the web version of ChatGPT as well as the iOS and Android apps. The feature allows ChatGPT to read its responses to queries in one of five voice options and can speak 37 languages, according to the company. Read aloud is available on both GPT-4 and GPT-3.5 models.

ChatGPT can now read responses to you. On iOS or Android, tap and hold the message and then tap “Read Aloud”. We’ve also started rolling on web – click the "Read Aloud" button below the message. pic.twitter.com/KevIkgAFbG — OpenAI (@OpenAI) March 4, 2024

OpenAI partners with Dublin City Council to use GPT-4 for tourism

As part of a new partnership with OpenAI, the Dublin City Council will use GPT-4 to craft personalized itineraries for travelers, including recommendations of unique and cultural destinations, in an effort to support tourism across Europe.

A law firm used ChatGPT to justify a six-figure bill for legal services

New York-based law firm Cuddy Law was criticized by a judge for using ChatGPT to calculate their hourly billing rate . The firm submitted a $113,500 bill to the court, which was then halved by District Judge Paul Engelmayer, who called the figure “well above” reasonable demands.

ChatGPT experienced a bizarre bug for several hours

ChatGPT users found that ChatGPT was giving nonsensical answers for several hours , prompting OpenAI to investigate the issue. Incidents varied from repetitive phrases to confusing and incorrect answers to queries. The issue was resolved by OpenAI the following morning.

Match Group announced deal with OpenAI with a press release co-written by ChatGPT

The dating app giant home to Tinder, Match and OkCupid announced an enterprise agreement with OpenAI in an enthusiastic press release written with the help of ChatGPT . The AI tech will be used to help employees with work-related tasks and come as part of Match’s $20 million-plus bet on AI in 2024.

ChatGPT will now remember — and forget — things you tell it to

As part of a test, OpenAI began rolling out new “memory” controls for a small portion of ChatGPT free and paid users, with a broader rollout to follow. The controls let you tell ChatGPT explicitly to remember something, see what it remembers or turn off its memory altogether. Note that deleting a chat from chat history won’t erase ChatGPT’s or a custom GPT’s memories — you must delete the memory itself.

We’re testing ChatGPT's ability to remember things you discuss to make future chats more helpful. This feature is being rolled out to a small portion of Free and Plus users, and it's easy to turn on or off. https://t.co/1Tv355oa7V pic.twitter.com/BsFinBSTbs — OpenAI (@OpenAI) February 13, 2024

OpenAI begins rolling out “Temporary Chat” feature

Initially limited to a small subset of free and subscription users, Temporary Chat lets you have a dialogue with a blank slate. With Temporary Chat, ChatGPT won’t be aware of previous conversations or access memories but will follow custom instructions if they’re enabled.

But, OpenAI says it may keep a copy of Temporary Chat conversations for up to 30 days for “safety reasons.”

Use temporary chat for conversations in which you don’t want to use memory or appear in history. pic.twitter.com/H1U82zoXyC — OpenAI (@OpenAI) February 13, 2024

ChatGPT users can now invoke GPTs directly in chats

Paid users of ChatGPT can now bring GPTs into a conversation by typing “@” and selecting a GPT from the list. The chosen GPT will have an understanding of the full conversation, and different GPTs can be “tagged in” for different use cases and needs.

You can now bring GPTs into any conversation in ChatGPT – simply type @ and select the GPT. This allows you to add relevant GPTs with the full context of the conversation. pic.twitter.com/Pjn5uIy9NF — OpenAI (@OpenAI) January 30, 2024

ChatGPT is reportedly leaking usernames and passwords from users’ private conversations

Screenshots provided to Ars Technica found that ChatGPT is potentially leaking unpublished research papers, login credentials and private information from its users. An OpenAI representative told Ars Technica that the company was investigating the report.

ChatGPT is violating Europe’s privacy laws, Italian DPA tells OpenAI

OpenAI has been told it’s suspected of violating European Union privacy , following a multi-month investigation of ChatGPT by Italy’s data protection authority. Details of the draft findings haven’t been disclosed, but in a response, OpenAI said: “We want our AI to learn about the world, not about private individuals.”

OpenAI partners with Common Sense Media to collaborate on AI guidelines

In an effort to win the trust of parents and policymakers, OpenAI announced it’s partnering with Common Sense Media to collaborate on AI guidelines and education materials for parents, educators and young adults. The organization works to identify and minimize tech harms to young people and previously flagged ChatGPT as lacking in transparency and privacy .

OpenAI responds to Congressional Black Caucus about lack of diversity on its board

After a letter from the Congressional Black Caucus questioned the lack of diversity in OpenAI’s board, the company responded . The response, signed by CEO Sam Altman and Chairman of the Board Bret Taylor, said building a complete and diverse board was one of the company’s top priorities and that it was working with an executive search firm to assist it in finding talent. 

OpenAI drops prices and fixes ‘lazy’ GPT-4 that refused to work

In a blog post , OpenAI announced price drops for GPT-3.5’s API, with input prices dropping to 50% and output by 25%, to $0.0005 per thousand tokens in, and $0.0015 per thousand tokens out. GPT-4 Turbo also got a new preview model for API use, which includes an interesting fix that aims to reduce “laziness” that users have experienced.

Expanding the platform for @OpenAIDevs : new generation of embedding models, updated GPT-4 Turbo, and lower pricing on GPT-3.5 Turbo. https://t.co/7wzCLwB1ax — OpenAI (@OpenAI) January 25, 2024

OpenAI bans developer of a bot impersonating a presidential candidate

OpenAI has suspended AI startup Delphi, which developed a bot impersonating Rep. Dean Phillips (D-Minn.) to help bolster his presidential campaign. The ban comes just weeks after OpenAI published a plan to combat election misinformation, which listed “chatbots impersonating candidates” as against its policy.

OpenAI announces partnership with Arizona State University

Beginning in February, Arizona State University will have full access to ChatGPT’s Enterprise tier , which the university plans to use to build a personalized AI tutor, develop AI avatars, bolster their prompt engineering course and more. It marks OpenAI’s first partnership with a higher education institution.

Winner of a literary prize reveals around 5% her novel was written by ChatGPT

After receiving the prestigious Akutagawa Prize for her novel The Tokyo Tower of Sympathy, author Rie Kudan admitted that around 5% of the book quoted ChatGPT-generated sentences “verbatim.” Interestingly enough, the novel revolves around a futuristic world with a pervasive presence of AI.

Sam Altman teases video capabilities for ChatGPT and the release of GPT-5

In a conversation with Bill Gates on the Unconfuse Me podcast, Sam Altman confirmed an upcoming release of GPT-5 that will be “fully multimodal with speech, image, code, and video support.” Altman said users can expect to see GPT-5 drop sometime in 2024.

OpenAI announces team to build ‘crowdsourced’ governance ideas into its models

OpenAI is forming a Collective Alignment team of researchers and engineers to create a system for collecting and “encoding” public input on its models’ behaviors into OpenAI products and services. This comes as a part of OpenAI’s public program to award grants to fund experiments in setting up a “democratic process” for determining the rules AI systems follow.

OpenAI unveils plan to combat election misinformation

In a blog post, OpenAI announced users will not be allowed to build applications for political campaigning and lobbying until the company works out how effective their tools are for “personalized persuasion.”

Users will also be banned from creating chatbots that impersonate candidates or government institutions, and from using OpenAI tools to misrepresent the voting process or otherwise discourage voting.

The company is also testing out a tool that detects DALL-E generated images and will incorporate access to real-time news, with attribution, in ChatGPT.

Snapshot of how we’re preparing for 2024’s worldwide elections: • Working to prevent abuse, including misleading deepfakes • Providing transparency on AI-generated content • Improving access to authoritative voting information https://t.co/qsysYy5l0L — OpenAI (@OpenAI) January 15, 2024

OpenAI changes policy to allow military applications

In an unannounced update to its usage policy , OpenAI removed language previously prohibiting the use of its products for the purposes of “military and warfare.” In an additional statement, OpenAI confirmed that the language was changed in order to accommodate military customers and projects that do not violate their ban on efforts to use their tools to “harm people, develop weapons, for communications surveillance, or to injure others or destroy property.”

ChatGPT subscription aimed at small teams debuts

Aptly called ChatGPT Team , the new plan provides a dedicated workspace for teams of up to 149 people using ChatGPT as well as admin tools for team management. In addition to gaining access to GPT-4, GPT-4 with Vision and DALL-E3, ChatGPT Team lets teams build and share GPTs for their business needs.

OpenAI’s GPT store officially launches

After some back and forth over the last few months, OpenAI’s GPT Store is finally here . The feature lives in a new tab in the ChatGPT web client, and includes a range of GPTs developed both by OpenAI’s partners and the wider dev community.

To access the GPT Store, users must be subscribed to one of OpenAI’s premium ChatGPT plans — ChatGPT Plus, ChatGPT Enterprise or the newly launched ChatGPT Team.

the GPT store is live! https://t.co/AKg1mjlvo2 fun speculation last night about which GPTs will be doing the best by the end of today. — Sam Altman (@sama) January 10, 2024

Developing AI models would be “impossible” without copyrighted materials, OpenAI claims

Following a proposed ban on using news publications and books to train AI chatbots in the U.K., OpenAI submitted a plea to the House of Lords communications and digital committee. OpenAI argued that it would be “impossible” to train AI models without using copyrighted materials, and that they believe copyright law “does not forbid training.”

OpenAI claims The New York Times’ copyright lawsuit is without merit

OpenAI published a public response to The New York Times’s lawsuit against them and Microsoft for allegedly violating copyright law, claiming that the case is without merit.

In the response , OpenAI reiterates its view that training AI models using publicly available data from the web is fair use. It also makes the case that regurgitation is less likely to occur with training data from a single source and places the onus on users to “act responsibly.”

We build AI to empower people, including journalists. Our position on the @nytimes lawsuit: • Training is fair use, but we provide an opt-out • "Regurgitation" is a rare bug we're driving to zero • The New York Times is not telling the full story https://t.co/S6fSaDsfKb — OpenAI (@OpenAI) January 8, 2024

OpenAI’s app store for GPTs planned to launch next week

After being delayed in December , OpenAI plans to launch its GPT Store sometime in the coming week, according to an email viewed by TechCrunch. OpenAI says developers building GPTs will have to review the company’s updated usage policies and GPT brand guidelines to ensure their GPTs are compliant before they’re eligible for listing in the GPT Store. OpenAI’s update notably didn’t include any information on the expected monetization opportunities for developers listing their apps on the storefront.

GPT Store launching next week – OpenAI pic.twitter.com/I6mkZKtgZG — Manish Singh (@refsrc) January 4, 2024

OpenAI moves to shrink regulatory risk in EU around data privacy

In an email, OpenAI detailed an incoming update to its terms, including changing the OpenAI entity providing services to EEA and Swiss residents to OpenAI Ireland Limited. The move appears to be intended to shrink its regulatory risk in the European Union, where the company has been under scrutiny over ChatGPT’s impact on people’s privacy.

What is ChatGPT? How does it work?

ChatGPT is a general-purpose chatbot that uses artificial intelligence to generate text after a user enters a prompt, developed by tech startup OpenAI . The chatbot uses GPT-4, a large language model that uses deep learning to produce human-like text.

When did ChatGPT get released?

November 30, 2022 is when ChatGPT was released for public use.

What is the latest version of ChatGPT?

Both the free version of ChatGPT and the paid ChatGPT Plus are regularly updated with new GPT models. The most recent model is GPT-4o .

Can I use ChatGPT for free?

There is a free version of ChatGPT that only requires a sign-in in addition to the paid version, ChatGPT Plus .

Who uses ChatGPT?

Anyone can use ChatGPT! More and more tech companies and search engines are utilizing the chatbot to automate text or quickly answer user questions/concerns.

What companies use ChatGPT?

Multiple enterprises utilize ChatGPT, although others may limit the use of the AI-powered tool .

Most recently, Microsoft announced at it’s 2023 Build conference that it is integrating it ChatGPT-based Bing experience into Windows 11. A Brooklyn-based 3D display startup Looking Glass utilizes ChatGPT to produce holograms you can communicate with by using ChatGPT.  And nonprofit organization Solana officially integrated the chatbot into its network with a ChatGPT plug-in geared toward end users to help onboard into the web3 space.

What does GPT mean in ChatGPT?

GPT stands for Generative Pre-Trained Transformer.

What is the difference between ChatGPT and a chatbot?

A chatbot can be any software/system that holds dialogue with you/a person but doesn’t necessarily have to be AI-powered. For example, there are chatbots that are rules-based in the sense that they’ll give canned responses to questions.

ChatGPT is AI-powered and utilizes LLM technology to generate text after a prompt.

Can ChatGPT write essays?

Can chatgpt commit libel.

Due to the nature of how these models work , they don’t know or care whether something is true, only that it looks true. That’s a problem when you’re using it to do your homework, sure, but when it accuses you of a crime you didn’t commit, that may well at this point be libel.

We will see how handling troubling statements produced by ChatGPT will play out over the next few months as tech and legal experts attempt to tackle the fastest moving target in the industry.

Does ChatGPT have an app?

Yes, there is a free ChatGPT mobile app for iOS and Android users.

What is the ChatGPT character limit?

It’s not documented anywhere that ChatGPT has a character limit. However, users have noted that there are some character limitations after around 500 words.

Does ChatGPT have an API?

Yes, it was released March 1, 2023.

What are some sample everyday uses for ChatGPT?

Everyday examples include programing, scripts, email replies, listicles, blog ideas, summarization, etc.

What are some advanced uses for ChatGPT?

Advanced use examples include debugging code, programming languages, scientific concepts, complex problem solving, etc.

How good is ChatGPT at writing code?

It depends on the nature of the program. While ChatGPT can write workable Python code, it can’t necessarily program an entire app’s worth of code. That’s because ChatGPT lacks context awareness — in other words, the generated code isn’t always appropriate for the specific context in which it’s being used.

Can you save a ChatGPT chat?

Yes. OpenAI allows users to save chats in the ChatGPT interface, stored in the sidebar of the screen. There are no built-in sharing features yet.

Are there alternatives to ChatGPT?

Yes. There are multiple AI-powered chatbot competitors such as Together , Google’s Gemini and Anthropic’s Claude , and developers are creating open source alternatives .

How does ChatGPT handle data privacy?

OpenAI has said that individuals in “certain jurisdictions” (such as the EU) can object to the processing of their personal information by its AI models by filling out  this form . This includes the ability to make requests for deletion of AI-generated references about you. Although OpenAI notes it may not grant every request since it must balance privacy requests against freedom of expression “in accordance with applicable laws”.

The web form for making a deletion of data about you request is entitled “ OpenAI Personal Data Removal Request ”.

In its privacy policy, the ChatGPT maker makes a passing acknowledgement of the objection requirements attached to relying on “legitimate interest” (LI), pointing users towards more information about requesting an opt out — when it writes: “See here  for instructions on how you can opt out of our use of your information to train our models.”

What controversies have surrounded ChatGPT?

Recently, Discord announced that it had integrated OpenAI’s technology into its bot named Clyde where two users tricked Clyde into providing them with instructions for making the illegal drug methamphetamine (meth) and the incendiary mixture napalm.

An Australian mayor has publicly announced he may sue OpenAI for defamation due to ChatGPT’s false claims that he had served time in prison for bribery. This would be the first defamation lawsuit against the text-generating service.

CNET found itself in the midst of controversy after Futurism reported the publication was publishing articles under a mysterious byline completely generated by AI. The private equity company that owns CNET, Red Ventures, was accused of using ChatGPT for SEO farming, even if the information was incorrect.

Several major school systems and colleges, including New York City Public Schools , have banned ChatGPT from their networks and devices. They claim that the AI impedes the learning process by promoting plagiarism and misinformation, a claim that not every educator agrees with .

There have also been cases of ChatGPT accusing individuals of false crimes .

Where can I find examples of ChatGPT prompts?

Several marketplaces host and provide ChatGPT prompts, either for free or for a nominal fee. One is PromptBase . Another is ChatX . More launch every day.

Can ChatGPT be detected?

Poorly. Several tools claim to detect ChatGPT-generated text, but in our tests , they’re inconsistent at best.

Are ChatGPT chats public?

No. But OpenAI recently disclosed a bug, since fixed, that exposed the titles of some users’ conversations to other people on the service.

What lawsuits are there surrounding ChatGPT?

None specifically targeting ChatGPT. But OpenAI is involved in at least one lawsuit that has implications for AI systems trained on publicly available data, which would touch on ChatGPT.

Are there issues regarding plagiarism with ChatGPT?

Yes. Text-generating AI models like ChatGPT have a tendency to regurgitate content from their training data.

More TechCrunch

Get the industry’s biggest tech news, techcrunch daily news.

Every weekday and Sunday, you can get the best of TechCrunch’s coverage.

Startups Weekly

Startups are the core of TechCrunch, so get our best coverage delivered weekly.

TechCrunch Fintech

The latest Fintech news and analysis, delivered every Tuesday.

TechCrunch Mobility

TechCrunch Mobility is your destination for transportation news and insight.

SpaceX debuts portable Starlink Mini for $599

SpaceX unveiled Starlink Mini, a more portable version of its satellite internet product that is small enough to fit inside a backpack.  Early Starlink customers were invited to purchase the…

Brex’s compliance head has left the fintech startup to join Andreessen Horowitz as a partner

Ali Rathod-Papier has stepped down from her role as global head of compliance at corporate card expense management startup Brex to join venture firm Andreessen Horowitz (a16z) as a partner…

US bans sale of Kaspersky software citing security risk from Russia 

U.S. officials imposed the “first of its kind” ban arguing that Kaspersky threatens U.S. national security because of its links to Russia.

Apple releases Final Cut Pro for iPad 2 and Final Cut Camera

Apple has released Final Cut Pro for iPad 2 and Final Cut Camera, the company announced on Thursday. Both apps were previously announced during the company’s iPad event in May.…

Poolside is raising $400M+ at a $2B valuation to build a supercharged coding co-pilot

Paris has quickly established itself as a major European center for AI startups, and now another big deal is in the works.

Gravitics prepares a testing gauntlet for a new generation of giant spacecraft

The space industry is all abuzz about how SpaceX’s Starship, Blue Origin’s New Glenn, and other heavy-lift rockets will change just about everything. One likely consequence is that spacecraft will…

Influencer shopping app LTK gets an automatic direct message tool

LTK (formerly LiketoKnow.it and RewardStyle), the influencer shopping app with 40 million monthly users, announced on Thursday the launch of a free direct message tool for creators to instantly share…

YouTube confirms crackdown on VPN users accessing cheaper Premium plans 

YouTube appears to be taking a firm stance against Premium subscribers who attempt to use a VPN (Virtual Private Network) to access cheaper subscription prices in other countries. This week,…

Why Fisker failed 

Welcome back to TechCrunch Mobility — your central hub for news and insights on the future of transportation. Sign up here for free — just click TechCrunch Mobility! I’m back…

EU Member States remain divided on controversial CSAM-scanning plan — but for how long?

Opponents also contend the EU plan will fail at its claimed aim of protecting children, suggesting law enforcement will instead be swamped by millions of false positives.

Labor shortages are still fueling growth at automation firms like GrayMatter

GrayMatter self-reports that its systems currently produce “a 2~4x improvement in production line productivity [and a] 30% or more reduction in consumable waste.”

Boeing’s Starliner capsule took astronauts to space — now it needs to bring them back

The delays are not over for Boeing’s Starliner capsule. After years of delays, the aerospace giant finally launched the spacecraft earlier this month, but the two-person crew is currently due…

US car dealerships face ongoing outage after CDK cyberattacks

CDK said it “does not have an estimated time frame” for recovery, as car dealerships and auto shops face continued outages.

Instagram now lets users livestream exclusively to their Close Friends list

Instagram is introducing the ability for users to broadcast live to just their Close Friends list, the company announced on Thursday. The new “Close Friends on Live” feature allows users…

Announcing the agenda for the Space Stage at TechCrunch Disrupt 2024

We’re out-of-this-world excited to announce that we’ve added a dedicated Space Stage to TechCrunch Disrupt 2024. It joins Fintech, SaaS and AI as the other industry-focused stages — all under…

PayPal Ventures leads $20M round into Gynger, which offers companies ‘buy now, pay later’ for technology purchases

Gynger, a platform that lends capital to companies for technology purchases, has raised $20 million in a Series A round led by PayPal Ventures, it told TechCrunch exclusively. The financing…

Pocket FM partners with ElevenLabs to convert scripts into audio content quickly

Lightspeed Ventures-backed audio platform Pocket FM announced it has partnered with voice-cloning company ElevenLabs to quickly convert text content, such as script, into audio series using AI. Pocket FM, which…

Anthropic claims its latest model is best-in-class

Claude 3.5 Sonnet can analyze both text and images as well as generate text, and it’s Anthropic’s best-performing model yet — at least on paper.

Roots introduces a screen time app for tracking ‘digital dopamine’

Roots is designed to help people get a better handle on what sort of apps are worth spending time on and which are not.

Materia looks to make accountants more efficient with AI 

The U.S. is facing an accountant shortage. Fewer first-time candidates took the CPA exam in 2022 than in 2006, according to the American Institute of Certified Public Accountants. One possible…

Ex-HubSpot exec builds an AI-powered CRM that learns for you, with $4M seed led by Sequoia

Christopher O’Donnell has hobbies. He likes music and playing guitar, but above all, he loves building software. Which is why three years after leaving HubSpot, he built Day.ai, a CRM…

Semperis, a specialist in Active Directory security now worth more than $1B, raises $125M

Active Directory, the Microsoft directory service for connecting users with network resources, is used by more than 90% of all Fortune 1000 companies and many more besides. So it’s no…

Daydream rakes in $50M seed funding to build an AI-powered search engine suited for e-commerce

Online shopping trends are expected to stay strong this year, but e-commerce is more fragmented than ever. With brands selling on so many platforms — from TikTok Shop, to established…

Spotify quietly lets all podcasters upload videos, surpasses 250K shows

Non-hosted podcasters can now upload videos to Spotify. Over 250K video podcasts are on the platform.

Cadana, an emerging markets payroll services provider for global hiring platforms, banks $7.1M seed

The global freelancer market, a $1.3 trillion industry fueled by more than 200 million knowledge workers, drives demand for solutions that automate payroll and streamline employment and tax regulations worldwide.…

Amazon extends generative AI-powered product listings to Europe

Amazon is bringing its generative AI listing smarts to more sellers, revealing today that those in France, Germany, Italy, Spain and the U.K. can now access tools designed to improve…

Kenya closes its probe of Worldcoin, opening the door to a relaunch of its orbs after a year-long suspension

Worldcoin — the crypto “proof of personhood” startup co-founded by OpenAI’s Sam Altman — has been given the green light to resume iris-scanning and other operations in Kenya after a…

Paris-based VC Breega hits first close of $75M Africa fund to back pre-seed and seed startups

Paris-based VC firm Breega has observed Africa’s tech ecosystem mature over the years. From receiving less than a billion dollars in venture capital per year to a record-high $6 billion,…

PQShield secures $37M more for ‘quantum resistant’ cryptography

Malicious hacking is getting increasingly sophisticated, and that’s leading to a very clear trend in security technology. To keep people and organizations safe, security also has to continue improving.  Security…

Hero wants to save the day for companies facing a working capital crunch

Hero, a new fintech startup based in Paris, is announcing an €11.3 million all-equity funding round led by Valar Ventures ($12.2 million at today’s exchange rate). For the past couple…

The Best Free and Paid AI Document Summarizer Tools In 2024

Let’s be honest, whether you’re a busy student or a full-time worker, finding time to read full bodies of text back-to-back isn’t always easy, especially if you have to go through multiple documents in one sitting.

Thankfully, by leveraging the power of generative artificial intelligence , AI summarizer tools can be used to condense documents, articles, research papers, and more into useful summaries – trimming down the fat for you so you have more time to focus on the content that matters.

With so many AI summarizers available, we rounded up some of our top picks and pointed out which are best for different use cases. We also cover their prices and whether they offer a free version, to help connect you to an AI platform in your budget. Read on to find out how the best AI summarizers compare against the competition, and to learn why the tools are emerging as one of the best time-saving hacks of 2024.

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.

Why Use an AI Summarizer Tool?

According to Gartner, professionals spend around 50% of their time searching for information – time that could be better spent in a variety of ways including engaging in deep work, collaborating with colleagues, or taking a well-earned stroll around the block.

Thanks to rapid developments in generative AI, the time you spend riffling through surplus information can be axed significantly, and you don’t even need to spend a fortune for the privilege.

AI summarizer tools can be used to create concise rundowns of large bodies of text in seconds, making it easier for users to get the main highlights of news articles, business documents, research papers, and more, without spending half an afternoon doing so.

Lots of AI summarizer tools offer extra translation, proofreading, and paraphrasing capabilities too, allowing you to condense, refine, and reformat content in one fell swoop. If you don’t want to pay a premium for the service, there are several free options available too, although these products tend to lack advanced content features and have more stringent text limits.

The Best AI Summarizer Tools in 2024

AI summarzers have the potential to revolutionize the way you work. Take a look at our favorite platforms, and what their best suited to, below.

• AI Summarizer – Best AI summarizer overall
• Summarizing tool – Best free AI summarizer tool
• ChatGPT – Best AI tool for summarizing PDF files
• Jasper – Best AI summarizer tool for content creators
• Scholarly Best AI summarizer for academics

1. AI Summarizer

• Best AI summarizer overall
• Price from $6.99 (Free version available)

AI Summarizer is a user-friendly summarizing tool that lets you summarize, paraphrase, and improve the quality of your text. The provider offers both paid and free versions, with its paid plan capping words at 5,000 words per submission and its freemium plan limiting words to 3,000.

AI Summarizer screenshot lets you condense and reformat lengthy content for free. Source: AI Summarizer

With most bodies of text falling under this limit, AI Summarizer will be a top option for users trying to keep costs to a minimum. The tool also provides output in three different styles – whole paragraphs, bullet points, and single sentences – and lets you choose how concise you want the summary to be. This gives AI Summarizer a leg up over other free platforms, like Summarizing Tool, which doesn’t give users as much control over the final result.

However, for all of AI Summarizer’s strengths, the free version is littered with ads which may get on your nerves if you’re using the tool a lot. You’re able to bypass this problem by upgrading to its enhanced Summarizer 2.0 platform quite easily though, as long as you’re willing to shell out a couple of dollars per month.

2. Summarizing Tool

• Best free AI summarizer tool
• Price from: Free

Summarizing Tool is a free forever text summarizer that allows users to condense text with or without AI. For a free service, the tool offers a surprising amount of capabilities. For example, the platform lets you transform text from a wide variety of formats, including text, documents, and PDF files and also gives users the option to copy or download output, based on your specific needs.

Summarizing Tool lets you summarize text from a wide variety of formats for free. Source: Summarizer Tool

Aside from summarization capabilities, the free platform lets users check content for plagiarism and grammatical errors, and can also be used to paraphrase text. The tool doesn’t place limits on how many times you’re able to use the service either, making it a great fit for users who have to transform large quantities of text on a tight budget.

However, like AI Summarizer, Summarizer Tool does feature lots of ads on its service, and with no option to bump up to a paid tier, the platform definitely won’t be right for everyone.

• Best AI tool for summarizing PDF files
• Price from: $20 per month (Free version available)

While we wouldn’t normally recommend using chatbots to summarize and refine large bodies of text, ChatGPT’s newly rolled-out PDF summarizing feature makes it one of the best solutions of its kind for condensing the file format. And the best thing about it? You can use the feature for absolutely free without upgrading to the Plus plan.

ChatGPT can now be used so summarize large documents. Source: communityopenai.com

Thanks to ChatGPT’s recent GPT-4o update , the popular chatbot now lets users attach documents, screenshots, and PDF documents to queries. This useful upgrade means that you’re able to use the tool to summarize and analyze PDF files and ask the chatbot questions about this document to gain targeted follow-up insights. You’re also able to request for the information to be displayed in a variety of different formats, including paragraphs and bullet points, making the service more useful than other free options like Summarizer Tool.

At the time being, free ChatGPT users are only able to make a limited amount of GPT-4o queries before their credits run out. But for those tasks with analyzing a high volume of PDFs, you also have the option to upgrade to ChatGPT Plus for $20 per month, as the paid plan doesn’t feature a cap on GPT-4o queries.

• Best AI summarizer tool for content creators
• Price from: $39 per month

Jasper AI is a versatile AI tool that lets you summarize text to a high degree of accuracy, working in a similar way to AI chatbots like ChatGPT. Alongside its text-based capabilities, Jasper also lets you brainstorm ideas for your own content, browse through summary history in the chat window, and translate text into 29 languages.

Jasper AI lets you summarize text-based documents, as well as image and audio files. Source: Jasper AI

The chatbot-style platform makes trimming down content a whizz by giving users control over its output style and letting them choose how long they want the summary to be. However, what really gives Jasper its competitive edge is its ability to summarize audio content like podcasts, lectures, and interviews. This unique capability makes the tool ideas for content creators who are interested in turning existing audio files into multiple pieces of short-form content.

While Jasper does offer a 7-day free trial for new users to test out the platform, its paid plans, which start at $39 per month, will likely exceed the budgets of most casual users.

5. Scholarcy

• Best AI summarizer for academics
• Price from: $3.75 per month (Free version available)

Scholarly is an academic companion that uses AI to summarize text and generate flashcards for research or studying purposes. The tool uses extractive and abstractive summarization capabilities to provide users with useful output, and the platform can also identify key concepts in the text, to make it easier for users to understand important themes.

Scholarcy offers a useful browser extension that provides users with snapshots of articles across the web. Source: Scholarcy

In addition to its desktop version, Scholarcy’s useful browsing extension lets users condense content while they’re browsing, making the platform ideal for users looking to regularly summarize articles and online papers.

Schorlarcy does offer a free version, but it only lets you summarize three research papers daily. While this should be more than enough for casual researchers, if you will be relying on the tool consistently you’ll have to upgrade to one of its paid plans which start from $3.75 per month.

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 Use ChatGPT to Read and Analyze PDF Documents for Free

OpenAI’s chatbot can now summarize lengthy documents in...

AI Could Spread False Information About the Holocaust, Warns UNESCO

The United Nations agency raises concerns that bad actors...

McDonald’s Halts AI Ordering After Viral Errors

The fast food restaurant has decided not to continue the...

These AI Companies are Hiring Right Now: Jobs Listed

Want to work in AI? These companies have hundreds of roles...

How to use ChatGPT to analyze PDFs for free

From contracts to research papers, most important documents come in lengthy PDFs -- regardless of what you do, you're guaranteed to encounter them in your lifetime, and they nearly always contain verbose language. AI can help you better understand the content and save time doing so. 

ChatGPT can act as your assistant by parsing through the PDFs and being on standby for anything you need. It can answer questions, provide summaries, and even generate content from the text, including outlines, emails, and more. The best part is that the feature is entirely free. 

Also: How to get ChatGPT to browse the web for free

In May 2024, nearly a year after ChatGPT launched, OpenAI upgraded the free version of the chatbot with several GPT-4o features typically reserved for their paying customers, including the ability to upload screenshots, photos, and documents. Getting started with the tool is easy, and in the long run, it will save you lots of time and effort. 

Here's how to get started. 

1. Log into ChatGPT 

Even though OpenAI allows you to access ChatGPT without logging in, you will need to sign in to your account to use GPT-4o and its advanced features, including Browse, Vision, data analysis, file uploads, and GPTs.

Also: How to use ChatGPT to write Excel formulas

If you have never created a ChatGPT account, you can easily do so from the sign-in page or log in with your existing Google or Microsoft account. I opt for the latter option so I don't have to memorize another username and password. 

2. Upload your PDF  

Once you sign in, you will be brought to the ChatGPT interface. Next to the textbox where you would typically insert text to start chatting, you will see a little paper clip icon. When you click that, you will have several options: Connect to Google Drive, Connect to Microsoft OneDrive, or Upload from a computer. 

Also: The best AI chatbots of 2024: ChatGPT, Copilot and worthy alternatives

Select the best option for where your document lives. Since I typically upload a document I just downloaded, I always opt for upload from my computer. Then, you can click on the PDF you want assistance with. For this example, I am using a PDF of my latest ZDNET article. 

3. Add your question 

Once you upload the PDF, you can accompany it with a text query that indicates what you'd like ChatGPT to do. You can make these prompts as adventurous or simple as you'd like. I kept it simple and asked for a summary: "Can you summarize what this article is about?" 

As you can see in the photo above, I immediately got a comprehensive four-sentence summary, and since I wrote the article, I can verify that it was accurate. 

For a more complex task, however, you could ask the chatbot to "Take out the action items, place them in bullet points, and format them into an email addressed to my boss." 

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

Overall, using ChatGPT to help parse through dense PDFs can help you save time and sift through long-winded paragraphs. Of course, always make sure to check ChatGPT's work for hallucinations, just in case. If you want to explore more document-summarizing tools, stay tuned for similar capabilities coming to Apple OS later this year.

Artificial Intelligence

How does chatgpt actually work, adobe's pdf-reading ai assistant starts at $4.99/month - here's how to try it for free, how to sign up for google labs - and 5 reasons why you should.

RAGs to Research: Exploring Applications for Maizey in Undergraduate Research

Joey is an intern with ITS Marketing and Communications. One of his projects this summer is to develop and test a unique Maizey. Joey chose to bridge the gap between seasoned researchers and overwhelmed college students by creating a research assistant chat bot.

A mind-numbing pain that I share with many other students is one that, satirically, our University takes immense pride in. We are a top-ranked research school that funnels $1.86 billion annually into research. The Undergraduate Research Opportunity Program (UROP) is seen as a must-have for resumes, but so many of us are just tossed into a lab and expected to know how to research. Professors lighten the load for us by having us start with lighter tasks like literature search, but what happens when reading research papers is that you “read but forgot to understand.” Having the opportunity to create my own Maizey project — a straightforward process that any student can do in minutes — I decided to create something that would help bridge the gap between seasoned researchers and overwhelmed college students. A chatbot for researchers.

Maizey is a RAG. Not that we wipe tables with, RAG stands for Retrieval-Augmented Generation , and is a distinct type of generative AI model. Maizey takes input from a Google Drive folder or Canvas course , and can read most text-based file types like .pdf or .docx. So when you ask it a question, Maizey will go to the input source and look for relevant information to append to the query. It then runs that augmented query through a large language model like GPT 4 Turbo, and returns the response to you. This makes Maizey capable of some pretty terrific things , as it really is what you make of it.

In my attempt to replicate greatness, I fed my Maizey the papers we read for a lab I was a part of and started asking it questions that our lab manager often asked of us. I was elated that it was responding until I asked U-M GPT the same questions. It gave the same, if not a better, answer, meaning that my Maizey did not learn anything from the papers I fed it, which is understandable. I do that, too.

But I wanted it to be better than me. I then tried to play around with the system prompt, which turned out to be quite the game-changer. I essentially told Maizey to roleplay as a knowledgeable research assistant, explained its capabilities in summarizing literature, explaining methods, identifying variables, etc., and told it to actually read the papers I provide. Then, it started giving pretty specific answers that it would not have known without reading the papers. One great feature about Maizey that works hand-in-hand with research is how it cites the material it retrieved additional information from, so it’s easy to track citations.

But remember how Maizey is text-based? With its current capabilities, Maizey does not deal with graphs, tables, or images that well. While Maizey can breeze through a text-heavy paper, it struggles to correctly return information from graphs. This means that at the time of writing, the efficacy of your research assistant Maizey, depends on the research papers in your field. This is something I will keep working on, as graphs and tables are crucial to papers and can be almost as confusing as text at times. Not to mention the countless times that it would just pretend it never read the papers and say, “I don’t know.”

Throughout this experience, I’m starting to see Maizey’s potential as a research tool for both students and faculty. It reduces the time and resources needed for training and adaptation for students conducting research, such as those participating in UROP for the first time. It is useful outside of the lab as well, as Maizey is beneficial for research tasks that are essential in writing essays and completing other assignments. And although there are still obstacles to be surmounted and better prompts to be developed, Maizey’s use cases are growing day by day, and I’m excited to see it elevate the overall research and learning experience at the University.

My system prompt:

Related Posts

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Office of the VPIT-CIO

• About the VPIT-CIO
• Information Technology Policies
• IT Strategy
• IT Governance
• Security & Privacy

Michigan IT

• About Michigan IT
• Community Resources & Events
• History of IT at U-M
• Professional Development
• U-M IT Providers
• Entries feed
• Comments feed
• WordPress.org

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, generate accurate citations for free.

• Knowledge Base
• Working with sources
• How to Paraphrase | Step-by-Step Guide & Examples

How to Paraphrase | Step-by-Step Guide & Examples

Published on April 8, 2022 by Courtney Gahan and Jack Caulfield. Revised on June 1, 2023.

Paraphrasing means putting someone else’s ideas into your own words. Paraphrasing a source involves changing the wording while preserving the original meaning.

Paraphrasing is an alternative to  quoting (copying someone’s exact words and putting them in quotation marks ). In academic writing, it’s usually better to integrate sources by paraphrasing instead of quoting. It shows that you have understood the source, reads more smoothly, and keeps your own voice front and center.

Every time you paraphrase, it’s important to cite the source . Also take care not to use wording that is too similar to the original. Otherwise, you could be at risk of committing plagiarism .

What is your plagiarism score?

Compare your paper with 99.3 billion webpages and 8 million publications.

• Best plagiarism checker of 2021
• Plagiarism report & percentage
• Largest plagiarism database

Scribbr Plagiarism Checker

Table of contents

How to paraphrase in five easy steps, how to paraphrase correctly, examples of paraphrasing, how to cite a paraphrase, paraphrasing vs. quoting, paraphrasing vs. summarizing, avoiding plagiarism when you paraphrase, other interesting articles, frequently asked questions about paraphrasing.

If you’re struggling to get to grips with the process of paraphrasing, check out our easy step-by-step guide in the video below.

Scribbr Citation Checker New

The AI-powered Citation Checker helps you avoid common mistakes such as:

• Missing commas and periods
• Incorrect usage of “et al.”
• Ampersands (&) in narrative citations
• Missing reference entries

Putting an idea into your own words can be easier said than done. Let’s say you want to paraphrase the text below, about population decline in a particular species of sea snails.

Incorrect paraphrasing

You might make a first attempt to paraphrase it by swapping out a few words for  synonyms .

Like other sea creatures inhabiting the vicinity of highly populated coasts, horse conchs have lost substantial territory to advancement and contamination , including preferred breeding grounds along mud flats and seagrass beds. Their Gulf home is also heating up due to global warming , which scientists think further puts pressure on the creatures , predicated upon the harmful effects extra warmth has on other large mollusks (Barnett, 2022).

This attempt at paraphrasing doesn’t change the sentence structure or order of information, only some of the word choices. And the synonyms chosen are poor:

• “Advancement and contamination” doesn’t really convey the same meaning as “development and pollution.”
• Sometimes the changes make the tone less academic: “home” for “habitat” and “sea creatures” for “marine animals.”
• Adding phrases like “inhabiting the vicinity of” and “puts pressure on” makes the text needlessly long-winded.
• Global warming is related to climate change, but they don’t mean exactly the same thing.

Because of this, the text reads awkwardly, is longer than it needs to be, and remains too close to the original phrasing. This means you risk being accused of plagiarism .

Correct paraphrasing

Let’s look at a more effective way of paraphrasing the same text.

Here, we’ve:

• Only included the information that’s relevant to our argument (note that the paraphrase is shorter than the original)
• Introduced the information with the signal phrase “Scientists believe that …”
• Retained key terms like “development and pollution,” since changing them could alter the meaning
• Structured sentences in our own way instead of copying the structure of the original
• Started from a different point, presenting information in a different order

Because of this, we’re able to clearly convey the relevant information from the source without sticking too close to the original phrasing.

Explore the tabs below to see examples of paraphrasing in action.

• Journal article
• Newspaper article
• Magazine article

Once you have your perfectly paraphrased text, you need to ensure you credit the original author. You’ll always paraphrase sources in the same way, but you’ll have to use a different type of in-text citation depending on what citation style you follow.

Generate accurate citations with Scribbr

Don't submit your assignments before you do this.

The academic proofreading tool has been trained on 1000s of academic texts. Making it the most accurate and reliable proofreading tool for students. Free citation check included.

Try for free

It’s a good idea to paraphrase instead of quoting in most cases because:

• Paraphrasing shows that you fully understand the meaning of a text
• Your own voice remains dominant throughout your paper
• Quotes reduce the readability of your text

But that doesn’t mean you should never quote. Quotes are appropriate when:

• Giving a precise definition
• Saying something about the author’s language or style (e.g., in a literary analysis paper)
• Providing evidence in support of an argument
• Critiquing or analyzing a specific claim

A paraphrase puts a specific passage into your own words. It’s typically a similar length to the original text, or slightly shorter.

When you boil a longer piece of writing down to the key points, so that the result is a lot shorter than the original, this is called summarizing .

Paraphrasing and quoting are important tools for presenting specific information from sources. But if the information you want to include is more general (e.g., the overarching argument of a whole article), summarizing is more appropriate.

When paraphrasing, you have to be careful to avoid accidental plagiarism .

This can happen if the paraphrase is too similar to the original quote, with phrases or whole sentences that are identical (and should therefore be in quotation marks). It can also happen if you fail to properly cite the source.

Paraphrasing tools are widely used by students, and can be especially useful for non-native speakers who may find academic writing particularly challenging. While these can be helpful for a bit of extra inspiration, use these tools sparingly, keeping academic integrity in mind.

To make sure you’ve properly paraphrased and cited all your sources, you could elect to run a plagiarism check before submitting your paper. And of course, always be sure to read your source material yourself and take the first stab at paraphrasing on your own.

If you want to know more about ChatGPT, AI tools , citation , and plagiarism , make sure to check out some of our other articles with explanations and examples.

• ChatGPT vs human editor
• ChatGPT citations
• Is ChatGPT trustworthy?
• Using ChatGPT for your studies
• What is ChatGPT?
• Chicago style
• Critical thinking

 Plagiarism

• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Consequences of plagiarism
• Common knowledge

To paraphrase effectively, don’t just take the original sentence and swap out some of the words for synonyms. Instead, try:

• Reformulating the sentence (e.g., change active to passive , or start from a different point)
• Combining information from multiple sentences into one
• Leaving out information from the original that isn’t relevant to your point
• Using synonyms where they don’t distort the meaning

The main point is to ensure you don’t just copy the structure of the original text, but instead reformulate the idea in your own words.

Paraphrasing without crediting the original author is a form of plagiarism , because you’re presenting someone else’s ideas as if they were your own.

However, paraphrasing is not plagiarism if you correctly cite the source . This means including an in-text citation and a full reference, formatted according to your required citation style .

As well as citing, make sure that any paraphrased text is completely rewritten in your own words.

Plagiarism means using someone else’s words or ideas and passing them off as your own. Paraphrasing means putting someone else’s ideas in your own words.

So when does paraphrasing count as plagiarism?

• Paraphrasing is plagiarism if you don’t properly credit the original author.
• Paraphrasing is plagiarism if your text is too close to the original wording (even if you cite the source). If you directly copy a sentence or phrase, you should quote it instead.
• Paraphrasing  is not plagiarism if you put the author’s ideas completely in your own words and properly cite the source .

Try our services

To present information from other sources in academic writing , it’s best to paraphrase in most cases. This shows that you’ve understood the ideas you’re discussing and incorporates them into your text smoothly.

It’s appropriate to quote when:

• Changing the phrasing would distort the meaning of the original text
• You want to discuss the author’s language choices (e.g., in literary analysis )
• You’re presenting a precise definition
• You’re looking in depth at a specific claim

Cite this Scribbr article

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

Gahan, C. & Caulfield, J. (2023, June 01). How to Paraphrase | Step-by-Step Guide & Examples. Scribbr. Retrieved June 19, 2024, from https://www.scribbr.com/working-with-sources/how-to-paraphrase/

Is this article helpful?

Courtney Gahan

Other students also liked, how to write a summary | guide & examples, how to quote | citing quotes in apa, mla & chicago, how to avoid plagiarism | tips on citing sources, get unlimited documents corrected.

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