how to check if essay is chatgpt

GPT Essay Checker for Students

How to Interpret the Result of AI Detection

To use our GPT checker, you won’t need to do any preparation work!

Take the 3 steps:

Copy and paste the text you want to be analyzed,
Click the button,
Follow the prompts to interpret the result.

Our AI detector doesn’t give a definitive answer. It’s only a free beta test that will be improved later. For now, it provides a preliminary conclusion and analyzes the provided text, implementing the color-coding system that you can see above the analysis.

It is you who decides whether the text is written by a human or AI:

Your text was likely generated by an AI if it is mostly red with some orange words. This means that the word choice of the whole document is nowhere near unique or unpredictable.
Your text looks unique and human-made if our GPT essay checker adds plenty of orange, green, and blue to the color palette.
🔮 The Tool’s Benefits

🤖 Will AI Replace Human Writers?

✅ ai in essay writing.

🕵 How do GPT checkers work?

Chat GPT in Essay Writing – the Shortcomings

The tool doesn’t know anything about what happened after 2021. Novel history is not its strong side. Sometimes it needs to be corrected about earlier events. For instance, request information about Heathrow Terminal 1 . The program will tell you it is functioning, although it has been closed since 2015.
The reliability of answers is questionable. AI takes information from the web which abounds in fake news, bias, and conspiracy theories.
References also need to be checked. The links that the tool generates are sometimes incorrect, and sometimes even fake.
Two AI generated essays on the same topic can be very similar. Although a plagiarism checker will likely consider the texts original, your teacher will easily see the same structure and arguments.
Chat GPT essay detectors are being actively developed now. Traditional plagiarism checkers are not good at finding texts made by ChatGPT. But this does not mean that an AI-generated piece cannot be detected at all.

🕵 How Do GPT Checkers Work?

An AI-generated text is too predictable. Its creation is based on the word frequency in each particular case.

Thus, its strong side (being life-like) makes it easily discernible for ChatGPT detectors.

Once again, conventional anti-plagiarism essay checkers won’t work there merely because this writing features originality. Meanwhile, it will be too similar to hundreds of other texts covering the same topic.

Here’s an everyday example. Two people give birth to a baby. When kids become adults, they are very much like their parents. But can we tell this particular human is a child of the other two humans? No, if we cannot make a genetic test. This GPT essay checker is a paternity test for written content.

❓ GPT Essay Checker FAQ

Updated: Oct 25th, 2023

Abstracts written by ChatGPT fool scientists - Nature
How to... use ChatGPT to boost your writing
Will ChatGPT Kill the Student Essay? - The Atlantic
ChatGPT: how to use the AI chatbot taking over the world
Overview of ChatGPT - Technology Hits - Medium
Free Essays
Writing Tools
Lit. Guides
Donate a Paper
Referencing Guides
Free Textbooks
Tongue Twisters
Job Openings
Expert Application
Video Contest
Writing Scholarship
Discount Codes
IvyPanda Shop
Terms and Conditions
Privacy Policy
Cookies Policy
Copyright Principles
DMCA Request
Service Notice

This page contains a free online GPT checker for essays and other academic writing projects. Being based on the brand-new technology, this AI essay detector is much more effective than traditional plagiarism checkers. With this AI checker, you’ll easily find out if an academic writing piece was written by a human or a chatbot. We provide a comprehensive guide on how to interpret the results of analysis. It is up to you to draw your own conclusions.

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

Check if Something Was Written by ChatGPT: AI Detection Guide

Last Updated: May 14, 2024 Fact Checked

How AI Detection Tools Work

Using ai detection tools, signs of chatgpt use.

This article was written by Stan Kats and by wikiHow staff writer, Nicole Levine, MFA . Stan Kats is the COO and Chief Technologist for The STG IT Consulting Group in West Hollywood, California. Stan provides comprehensive technology & cybersecurity solutions to businesses through managed IT services, and for individuals through his consumer service business, Stan's Tech Garage. Stan has over 7 years of cybersecurity experience, holding senior positions in information security at General Motors, AIG, and Aramark over his career. Stan received a BA in International Relations from The University of Southern California. There are 11 references cited in this article, which can be found at the bottom of the page. This article has been fact-checked, ensuring the accuracy of any cited facts and confirming the authority of its sources. This article has been viewed 46,968 times.

With the rising popularity of ChatGPT, Bard, and other AI chatbots, it can be hard to tell whether a piece of writing was created by a human or AI. There are many AI detection tools available, but the truth is, many of these tools can produce both false-positive and false-negative results in essays, articles, cover letters, and other content. Fortunately, there are still reliable ways to tell whether a piece of writing was generated by ChatGPT or written by a human. This wikiHow article will cover the best AI detection tools for teachers, students, and other curious users, and provide helpful tricks for spotting AI-written content by sight.

Things You Should Know

Tools like OpenAI's Text Classifier, GPTZero, and Copyleaks can check writing for ChatGPT, LLaMA, and other AI language model use.
ChatGPT often produces writing that looks "perfect" on the surface but contains false information.
Some signs that ChatGPT did the writing: A lack of descriptive language, words like "firstly" and "secondly," and sentences that look right but don't make sense.

Step 1 AI detection tools evaluate how predictable the text is.

The detection tool compares a piece of writing to similar content, decides how predictable the text is, and labels the text as either human or AI-generated.
These tools also look for other indicators, or "signatures" that are associated with AI-generated text, such as word choice and patterns. [1] X Research source

Step 2 AI detectors often make mistakes.

If an AI detection tool reports that a piece of writing was mostly AI-generated, don't rely on that report alone. It's best to only use AI detection tools if you've already found other signs that the writing was written by ChatGPT. [3] X Research source
Running a piece of writing through multiple AI detection tools can help you get an idea of how different tools work. It can also help you narrow down false-negatives and false-positives.

If you're evaluating a piece of writing for potential AI use, try searching the web for a few facts from the text. Try to search for facts that are easy to verify—e.g., dates and specific events.

Step 2 Some sentences look right, but don't actually make sense.

Tyrone Showers

Spotting AI-written text on your own can be a real challenge. Look for grammatically correct but robotic language lacking humor and personal touches. A writer's sudden shift towards perfect language can also indicate AI involvement. Remember, human writing can share these traits, so considering the context is crucial.

Step 6 No grammatical or spelling errors.

For example, if you're evaluating a cover letter for AI use, you might tell ChatGPT, "Write me a cover letter for a junior developer position at Company X. Explain that I graduated from Rutgers with a Computer Science degree, love JavaScript and Ruby, and have been working as a barista for the past year."
Because ChatGPT is conversational, you can continue providing more context. For example, "add something to the cover letter about not jumping right into the industry after college because of the pandemic."

Expert Q&A

Cornell researchers determined that humans incorrectly found AI-generated news articles credible more than 60% of the time. [12] X Research source Thanks Helpful 0 Not Helpful 0
If you're using a ChatGPT detection tool that identified writing as AI-written, consider that it may be a false positive before approaching the situation with the writer. Thanks Helpful 0 Not Helpful 0
If you suspect ChatGPT wrote something but can't tell for sure, have a conversation with the writer. Don't accuse them of using ChatGPT—instead, ask them more questions about the writing or content to make their knowledge lines up with the content. You may also want to ask them about their writing process to see if they admit to using ChatGPT or other AI writing tools. Thanks Helpful 0 Not Helpful 0

↑ https://www.turnitin.com/blog/ai-writing-the-challenge-and-opportunity-in-front-of-education-now
↑ https://www.turnitin.com/blog/understanding-false-positives-within-our-ai-writing-detection-capabilities
↑ https://help.openai.com/en/collections/5929286-educator-faq
↑ https://www.npr.org/2023/01/09/1147549845/gptzero-ai-chatgpt-edward-tian-plagiarism
↑ https://app.gptzero.me/app/subscription-plans
↑ https://contentatscale.ai/ai-content-detector/
↑ https://copyleaks.com/api-pricing
↑ https://research.google/pubs/pub51844/
↑ https://help.openai.com/en/articles/6783457-what-is-chatgpt
↑ https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9939079/
↑ https://www.technologyreview.com/2022/12/19/1065596/how-to-spot-ai-generated-text/

About This Article

Send fan mail to authors

Is this article up to date?

Featured Articles

The Best Ways to Speed Read & Become a Faster Reader

Watch Articles

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

Keep up with tech in just 5 minutes a week!

Can AI detectors save us from ChatGPT? I tried 5 online tools to find out

When I first looked at the question of whether it's possible to fight back against AI-generated plagiarism, and how that might work, it was January 2023, just a few months into the world's exploding awareness of generative AI . Now, almost a year later, it feels like we've been exploring generative AI for years and years, but we've really been looking at the issue for a matter of months.

In any case, this is an updated version of that original January article. When I first tested GPT detectors, I used three: the GPT-2 Output Detector (this is a different URL than we published before), Writer.com AI Content Detector , and Content at Scale AI Content Detection . The best result was 66% correct, from the GPT-2 Output Detector. This time, I'm adding three more: GPTZero , ZeroGPT (yes, they're different), and Writefull's GPT Detector .

Also: How to use ChatGPT: Everything you need to know

Unfortunately, I'm removing the Writer.com AI Content Detector from our test suite because it failed back in January, it failed again in October, and it failed now. See below for a comment from the company, which their team sent me after the original article was published in January.

Before I go on, though, we need to talk about the concept of plagiarism and how it relates to our problem. Merriam-Webster defines " plagiarize " as "to steal and pass off (the ideas or words of another) as one's own; use (another's production) without crediting the source."

This definition fits AI-created content. While someone using an AI tool like Notion AI or ChatGPT isn't stealing content, if that person doesn't credit the words as coming from an AI and claims them as their own, it still meets the dictionary definition of plagiarism.

Also: The best AI image generators to try

In this experimental article, I've asked ChatGPT to help out. My words are in normal and bold text. The AI's words are italicized. After each AI-generated section, I'll show the results of the detectors. At the end of the article, we'll look at how well the detectors performed overall.

Here's the result for the above text, which I wrote myself:

GPT-2 Output Detector: 99.98% real
Content at Scale AI Content Detection: 100% Highly likely to be human!
GPTZero: Your text is likely to be written entirely by a human
ZeroGPT: 28.9% AI GPT Your Text is Most Likely Human written
Writefull GPT Detector: 1% likely this comes from GPT-3, GPT-4 or ChatGPT

Human-written content: 4-of-5 correct

With that, let's dig in some more.

Explain why ChatGPT can be a real problem for teachers and editors when it comes to plagiarism

ChatGPT is a variant of the GPT (Generative Pre-trained Transformer) language model developed by OpenAI. It is designed to generate human-like text by predicting the next word or phrase in a given input sequence. While ChatGPT can be a useful tool for generating text and responding to prompts, it can also be a problem for teachers and editors when it comes to plagiarism.

One of the main reasons why ChatGPT can be a problem for teachers and editors is that it can generate text that is very similar to that of real human writers. This means that students or other individuals could potentially use ChatGPT to generate text that they could then submit as their own work, thereby committing plagiarism.

Also: 4 ways to overcome your biggest worries about generative AI

For teachers and editors, detecting whether a given piece of text was generated by ChatGPT or written by a human can be very difficult, as the generated text may not contain any obvious errors or discrepancies that would reveal its artificial origin. This can make it difficult for teachers and editors to identify and prevent plagiarism, as they may not be able to tell whether a given piece of text is original or copied from another source.

Overall, ChatGPT and other similar language models can be a problem for teachers and editors when it comes to plagiarism because they can generate text that is difficult to distinguish from that written by humans, making it easier for students and other individuals to commit plagiarism without being detected.

GPT-2 Output Detector: 99.69% real
Content at Scale AI Content Detection: 3% Highly likely to be AI-generated!
GPTZero: We suggest entering a longer text for more precise prediction
ZeroGPT: 51.22% AI GPT Your Text is AI/GPT Generated
Writefull GPT Detector: 12% likely this comes from GPT-3, GPT-4 or ChatGPT

AI-written content: 1-of-5 correct (barely)

Remember, text shown in italics was generated by the AI.

Show me at least three ways that I can detect ChatGPT was used to produce a piece of text

There are several ways that you can potentially detect whether ChatGPT or another language model was used to produce a piece of text. Here are three potential approaches you could use:

Look for repetitive or unusual patterns in the text: One way to detect whether a language model was used to generate a piece of text is to look for repetitive or unusual patterns in the writing. For example, language models may repeat certain phrases or word combinations, or use unusual or inconsistent sentence structures.
Check for lack of originality: Another way to detect whether a language model was used to generate a piece of text is to check for a lack of originality in the writing. If a piece of text appears to be copied from another source, or if it contains information that is widely available on the internet or in other sources, it could be a sign that it was generated by a language model.
Use a plagiarism checker: Finally, you can use a plagiarism checker to check whether a piece of text appears to be copied from another source. While a plagiarism checker may not be able to definitively determine whether a language model was used to generate a piece of text, it can help you identify instances of copying or paraphrasing from other sources.
Note when the answer is obviously wrong: I talked about this in my Notion AI review , where I spotlighted some text the AI wrote with seeming authority, but which was blatantly wrong. If a student or writer doesn't have full command of the topic being discussed, they may not spot the inaccuracies and simply leave them in the AI-generated response. Of course, incorrect statements aren't just the purview of an AI writing tool. Many bloggers and commenters, for example, simply repeat statements made by other bloggers, creating an echo chamber of completely "false facts", showing that while intelligence may be artificial, stupidity is a universal trait.

Keep in mind that it can be difficult to definitively determine whether a language model was used to generate a piece of text, and these methods may not always be effective. However, they can be useful tools to help you identify potential instances of language model-generated text.

In this set of tests, only the italicized content above was run through the checker suite.

GPT-2 Output Detector: 99.98% fake
Content at Scale AI Content Detection: 99% Highly likely to be Human!
GPTZero: Your text may include parts written by AI
ZeroGPT: 91.35% AI GPT Your Text is AI/GPT Generated
Writefull GPT Detector: 77% likely this comes from GPT-3, GPT-4 or ChatGPT

AI-written content: 4-of-5 correct

List three plagiarism checkers that can detect ChatGPT text

It is worth noting that there is currently no plagiarism checker that is specifically designed to detect text generated by ChatGPT or other language models. While some plagiarism checkers may be able to identify certain characteristics of language model-generated text that could indicate its artificial origin, there is no guarantee that they will be able to definitively determine whether a piece of text was generated by a language model.

With that said, here are three plagiarism checkers that you might consider using to help identify potential instances of language model-generated text:

Turnitin: Turnitin is a popular plagiarism checker that is widely used by schools and universities. It compares a piece of text to a database of other texts to identify instances of copying or paraphrasing. While it may not be able to definitively determine whether a piece of text was generated by a language model, it could potentially identify certain characteristics of language model-generated text that could indicate its artificial origin.
PlagScan: PlagScan is another plagiarism checker that compares a piece of text to a database of other texts to identify instances of copying or paraphrasing. Like Turnitin, it may be able to identify certain characteristics of language model-generated text that could indicate its artificial origin, but it is not specifically designed to detect language model-generated text.
Copyleaks: Copyleaks is a plagiarism checker that uses advanced machine learning algorithms to scan a piece of text and compare it to a database of other texts to identify instances of copying or paraphrasing. While it may be able to identify certain characteristics of language model-generated text, it is not specifically designed to detect language model-generated text.

It is worth noting that no plagiarism checker is completely foolproof, and there is always the possibility that a piece of language model-generated text could escape detection. Therefore, it is important to use plagiarism checkers as just one part of a larger strategy to detect and prevent plagiarism.

GPT-2 Output Detector: 99.58% real
Content at Scale AI Content Detection: 100% Highly likely to be Human!
ZeroGPT: 100% AI GPT Your Text is AI/GPT Generated
Writefull GPT Detector: 88% likely this comes from GPT-3, GPT-4 or ChatGPT

AI-written content: 3-of-5 correct

Online AI plagiarism checkers

Most plagiarism detectors are used to compare writing against a corpus of other writing. For example, when a student turns in an essay, a product like Turnitin scans the submitted essay against a huge library of other essays in its database, as well as against other documents and text on the internet to determine if the submitted essay contains already-written content.

But the AI writing tools generate original content, at least in theory. Yes, they build their content from whatever they've been trained on, but the actual words they construct are somewhat unique for each composition.

Also: The 10 best ChatGPT plugins right now

As such, the plagiarism checkers mentioned above probably won't work, because the AI-generated content probably didn't exist in, say, another student's paper.

In this article, we're just looking at GPT detectors. But plagiarism is a big problem, and as we've seen, some choose to define plagiarism as something you claim as yours that you didn't write, while others choose to define plagiarism as something written by someone else that you claim is yours.

That distinction was never a problem until now. Now that we have non-human writers, the plagiarism distinction is more nuanced. It's up to every teacher, school, editor, and institution to decide exactly where that line is drawn.

Content at Scale AI Content Detection: 100% Highly likely to be Human!
ZeroGPT: 0% AI GPT Your Text is Human written

Human-written content: 5-of-5 correct

Overall results

Of the five tests run, four out of five were generally accurate. Tests proved more accurate overall on pure human content than pure AI content. It is interesting to note that the individual detectors varied wildly, so if you're going to use a GPT detector, you might want to use a bunch of them on a single piece of text and aggregate the results. Even with that, you're not guaranteed complete accuracy.

Also: OpenAI pulls its own AI detection tool because it was performing so poorly


GPT-2 Output Detector	60%	Correct	Fail	Correct	Fail	Correct
Content at Scale AI Content Detection	40%	Correct	Fail	Fail	Fail	Correct
GPTZero	80%	Fail	Correct	Correct	Correct	Correct
ZeroGPT	80%	Correct	Fail	Correct	Correct	Correct
Writefull GPT Detector	60%	Fail	Fail	Correct	Correct	Correct

Back in January, the best we did was 66% correct. Here, we have two tools that were correct 80% of the time. However, I would not be comfortable using these tools to validate a student's content. As has been shown, writing from non-native speakers often gets rated as generated by an AI , and even my hand-crafted content was rated as AI a few times. So, I would advocate caution before relying on the results of any (or all) of these tools.

Also: Could someone falsely accuse you of using AI-generated text? This could be why

Let's take a look at the individual testers and see how each performed.

GPT-2 Output Detector (Accuracy 60%)

This first tool was built using a machine-learning hub managed by New York-based AI company Hugging Face . While the company has received $40 million in funding to develop its natural language library, the GPT-2 detector appears to be a user-created tool using the Hugging Face Transformers library. Of the six tests I ran, it was accurate for four of them.

Writer.com AI Content Detector (Accuracy N/A)

Writer.com is a service that generates AI writing, oriented towards corporate teams. Its AI Content Detector tool can scan for generated content. Unfortunately, I found this tool unreliable, and it failed to generate results -- exactly the same way it did in January.

After this article was originally published in January, the folks at Writer.com reached out to ZDNET. CEO May Habib had this comment to share:

Demand for the AI detector has skyrocketed. Traffic has grown 2-3x per week since we launched it a couple months ago. We've now got the necessary scaling behind it to make sure it doesn't go down, and our goal is to keep it free - and up to date to catch the latest models' outputs, including ours. If AI output is going to be used verbatim, it absolutely should be attributed.

Content at Scale AI Content Detection (Accuracy 40%)

The third tool I found was also produced by an AI content generation firm. Content at Scale pitches itself as "We Help SEO-Focused Content Marketers by Automating Content Creation." Its marketing call to action is, "Upload a list of keywords and get 2,600+ word blog posts that bypass AI content detection -- all with no human intervention!" Disturbingly, the results got worse from January -- back then, it was 50% accurate.

GPTZero (Accuracy 80%)

It's not entirely clear what drives GPTZero . The company is hiring engineers and sales folks, and it runs on AWS, so there are expenses and sales involved. However, all I could find about a service offering was a place where you could register for a free account to scan more than the 5,000 words offered without login. If you're interested in this service for GPT detection, you'll have to see if they'll respond to you with more details.

ZeroGPT (Accuracy 80%)

ZeroGPT seems to have matured as a service since we last looked at it. When we last looked, no company name was listed, and the site was peppered with Google ads with no apparent strategy for monetization. The service actually worked fairly well but seemed sketchy as heck.

That sketchy-as-heck feeling is now gone. ZeroGPT presents as any other SaaS service, complete with pricing, company name, contact information, and all the rest. It still performs quite well, so perhaps the developers decided to turn their working code into more of a working business. Good for them!

Writefull GPT Detector (Accuracy 60%)

Writefull sells writing support services as well as offering free tastes of its tools. The GPT detector is fairly new, and worked fairly well. Perhaps it will improve over time.

Final thoughts

First, I'll let ChatGPT have its say: AI-driven plagiarism is a growing problem, as AI tools like Notion AI and ChatGPT can generate text that is difficult to distinguish from that written by humans. There are several ways to detect whether a piece of text was generated by an AI, such as looking for repetitive or unusual patterns, checking for a lack of originality, or using a plagiarism checker. Plagiarism checkers like Turnitin, PlagScan, and Copyleaks may be able to identify certain characteristics of language model-generated text, but they are not foolproof.

Even the specialty tools I found were woefully unsuited to the task. There was some limited improvement over my tests in January, but I certainly wouldn't feel comfortable threatening a student's academic standing or accusing them of cheating based on the results of any of these tools.

Also: Surprise! AI chatbots don't increase student cheating afterall, new research finds

At this point, I don't think we're ready to let AI fight AI. Instead, we're going to have to rely on human perception (which means folks have to pay attention) in order to identify works that were generated by an AI.

Don't immediately assume that something is machine-generated. Just because something is stupid or wildly inaccurate, doesn't mean it was not written by a human. As we've all come to know, humans are quite capable of writing some incredibly bad stuff all on their own.

Also: OpenAI's ChatGPT is scary good at my job, but it can't replace me (yet)

So, what do you think? Can you tell if a piece is AI-generated? Have you used these AI writing tools in the months since they suddenly became available? Do you think they're a help or hindrance to education and journalism? Let us know in the comments below. Here's how ChatGPT answered this:

As a language model, I can't see or interact with physical pieces of writing, so I can't tell if a piece is AI-generated or not. However, I can tell you that there are several AI writing tools that are available, and they can be used to generate a wide range of written content, including news articles, fiction, poetry, and more.

I don't have personal experience using these tools since I am just a computer program and don't have the ability to browse the internet or use physical tools. However, I can tell you that some people have found AI writing tools to be helpful in education and journalism, as they can save time and effort by automating certain tasks. Others have expressed concerns about the potential for these tools to be used to produce misleading or biased content or to replace human writers. Ultimately, whether AI writing tools are a help or hindrance depends on how they are used and the context in which they are used.

So, yeah, there's that.

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

Artificial Intelligence

Nearly 10% of people ask ai chatbots for illicit content. will it lead llms astray, what is ai everything to know about artificial intelligence, openai's new chatgpt edu is for universities. here's how teachers and students can benefit.

Mozilla is a global nonprofit dedicated to keeping the Internet a public resource that is open and accessible to all.

Connect People

Creating more trustworthy data economy

Empowering students to think about the social and political context of computing

The premier gathering for people working to build a better digital world

Rally Communities

Creating a diverse open voice dataset

The people shaping the future of the internet and AI

Influence Policies

Investigating Youtube’s harmful recommendations

Scrutinizing the privacy & security of consumer tech

Research & Analysis

Promoting openness, competition, and accountability in AI

Issues impacting a healthy internet

Get Involved

From donating funds or data, to signing a petition, to applying to become a volunteer or fellow there are many ways to get involved with the community.

Contribute to Common Voice, an open source dataset that includes the underrepresented

A podcast about the people shaping the future of the internet and AI

A buyers guide that helps you shop smart when it comes to privacy and security

Apply for Funding

The Mozilla Foundation provides funding and resources to individuals, groups, and organizations aligned with creating a more human-centered internet.

Opportunites

Empowering leaders working to ensure the internet remains a force for good

We recognize, support, and amplify leaders who work on issues impacting the health of the internet

Community Impact

A vibrant community of past fellows and awardees

An ecosystem of donors working together

Featured Posts

Mozilla News

Public interest tech advocate will harness collective power to deepen Mozilla’s focus on trustworthy AI

The larger the multimodal training dataset, the more likely the model will classify people of color as ‘criminals,’ research reveals

Your dating apps may know more about you than you realize. Here’s what you need to know about Tinder, Hinge and more.

Did ChatGPT Write This? Here’s How To Tell.

By Xavier Harding | April 14, 2023

The AI wars are heating up. In late 2022, Open AI’s Chat GPT made headlines for showing us what a new search engine could look like. ChatGPT (which stands for “Generative Pre-trained Transformer”) is a chatbot — one that can process queries and spit out relevant information to answer questions about historical facts, recipes, car dimensions and lots more. As a bonus, ChatGPT lets you word questions in plain English, so you’re not forced to write queries like “how to stop dog pooping everywhere reddit.” The result is, essentially, a search box that you can message back and forth with. It almost makes Google search look a little primitive. Microsoft, the maker of Bing and biggest investor in Open AI, is okay with this .

ChatGPT, and the latest release GPT-4, provides thorough answers — it can even write your code , write your cover letter and pass your law exam . It also provides thoroughly wrong answers sometimes. It’s worrying how confidently ChatGPT presents inaccurate information . That hasn’t stopped newsrooms from rethinking how many writers they hire nor professors from coming out against the chatbot. (Though not all professors. Some embrace the change .)

The excitement around artificial intelligence is anything but artificial. At least for some. College professors or job recruiters are less than excited to have to discern human words from chatbot chatter. Industry experts are less than enthused for a potential wave of misinformation, signing an open letter that warns of AI’s potential to “flood our information channels with propaganda and untruth.” Those who have signed say “such decisions must not be delegated to unelected tech leaders.” Issues like this are exactly what Mozilla seeks to address with the Responsible Computing Challenge , ensuring higher education programs emphasize tech’s political and societal impact. And also with Mozilla.ai , a startup with the mission of making it easy to create AI that’s open source and ethical.

As we enter this brave new world where even a friend’s Snapchat message could be AI-written, you might want to know a bit more about chatbots’ capabilities and limitations. Can you spot a paragraph written by AI? Can you tell if your coworker is actually responding to you and not ChatGPT ? Do you know how to spot misinformation within a chatbot’s answers because ChatGPT-infused Bing definitely still gets facts wrong at times? It's not always possible to know if an AI wrote some copy, but sometimes, you can detect language written by Chat GPT and other bots by using a detector tool and watching for awkward language. Read on to learn how.

How to Detect ChatGPT Text Yourself?

You can detect Chat GPT-written text using online tools like OpenAI API Key . The tool comes from Open AI, itself, the company that made Chat GPT. It’s worth noting that the app isn’t perfect. Open AI says the tool needs at least 1,000 words before it can sniff out AI-generated content, so something like an AI-generated text message may fly under its radar. Also, even if it gets the 1,000 words it needs, it isn’t always 100% accurate at detecting AI vs human written language. AI-made text that has been edited by a human can also fool the tool.

( Update : As of July 2023 , a new ChatGPT update no longer includes the use of the AI classifier which Open AI used to detect AI-generated text and, as of early 2024, the company has even taken their original tool offline. The company claims to be working on new, more effective ways of detecting AI-generated text as well as AI-generated audio and video.)

Open AI’s tool may not be perfect but there are other offerings in the ChatGPT text detection world. The Medium blog Geek Culture lists other options made by folks at Princeton and Stanford . If it’s critical to know if text was written by a bot or a human, testing it on multiple tools might help. ChatGPT is changing quickly so your mileage may vary.

Detecting ChatGPT Text: The Caveats

It’s important to emphasize that no method of detecting AI-written text is foolproof — that includes options using tools available today. Jesse McCrosky is a data scientist with Mozilla Foundation who warns of AI text detection tools’ limitations. “Detector tools will always be imperfect, which makes them nearly useless for most applications,” say McCrosky. “One can not accuse a student of using AI to write their essay based on the output of a detector tool that you know has a 10% chance of giving a false positive.”

According to McCrosky, it can be impossible to ever have a true AI-detector because it will always be possible for software to write “undetectable” texts or create text with the specific intent of evading these sorts of detectors. And then there’s the fact that the AI tools available to us are always improving. “There can be some sense of an ‘arms race’ between Chat GPT text detectors and detector-evaders, but there will never be a situation in which detectors can be trusted,” says McCrosky.

How to Spot Misinformation Within ChatGPT?

It’s no secret that ChatGPT can ( and has ) been spreading misinformation and disinformation. Microsoft may be using tools like those from NewsGuard to limit the misleading responses its AI gives, but the issue is still cause for concern. The Poynter Institute has our favorite tips to spot misinformation within Chat GPT: 1) check for patterns and inconsistencies, 2) look for signs of human error and check the context. If a ChatGPT answer repeats something multiple times, has weird errors that a person wouldn’t make or says something that doesn’t make sense in the context of what you’re reading, you might be reading misleading content. Check the source links at the bottom of your Chat GPT responses and make sure you do your own research outside of ChatGPT too. Treat it as a starting point and not the final word.

Chat GPT Is Fun, But Watch Out

ChatGPT offers an interesting glimpse into a chatbot answer-filled world, but it also acts as a warning of the downsides too. With great smarts comes great responsibility. As Bing and ChatGPT (and Sydney ?) learn how to be a better chatbot, we as the users will have to continue to use ChatGPT detection tools to verify that the words we’re seeing are human-made and that the facts we’re sharing are indeed factual.

Did Chat GPT Write This? Here’s How To Tell

Written by: Xavier Harding

Edited by: Ashley Boyd, Audrey Hingle, Carys Afoko, Innocent Nwani

SEO Insight: Aslam Shaffraz

Help shape the future of the web for the public good. Join our Mozilla News email list to get action alerts & internet tips right to your inbox.

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

Emma Bowman

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

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

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

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

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

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

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

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

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

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

How GPTZero works

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

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

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

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

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

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

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

The quest to curb AI plagiarism

Untangling Disinformation

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

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

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

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

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

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

More than an AI detector Preserve What's Human

Since inventing AI detection, GPTZero incorporates the latest research in detecting ChatGPT, GPT4, Google-Gemini, LLaMa, and new AI models, and investigating their sources.

Was this text written by a human or AI ?

Our Commitment as the Leader in AI detection

Internationally recognized as the leader in AI detection, we set the standard for responding to AI-generated content with precision and reliability.

The First in Detection

GPTZero developed the first public open AI detector in 2022. We are first in terms of reliability and first to help when it matters.

Results You Can Trust

AI detection is more than accuracy. GPTZero was the first to invent sentence highlighting for interpretability. Today, our AI report is unique in explaining why AI was flagged.

Best In-Class Benchmarking

GPTZero partners with Penn State for independent benchmarking that continues to show best-in-class accuracy and reliability across AI models.

Cutting Edge Research

Top PHD and AI researchers from Princeton, Caltech, MILA, Vector, and OpenAI work with GPTZero to ensure your solution is the most up to date.

Debiased AI Detection

Our research team worked on Stanford University AI data to address AI biases, launching the first de-biased AI detection model in July 2023.

Military Grade Security

We uphold the highest data security standards with SOC-2 and SOC-3 certifications, meeting rigorous security benchmarks.

Discover our Detection Dashboard

Our dashboard was developed specifically with educator's needs in mind. Access a premium model with highest grade fidelity and interpretability.

Access a deeper scan with unprecedented levels of AI text analysis.

Source scanning

Scan documents for plagiarism and our AI copyright check.

Easily scan dozens of files at once, organize, save, and download reports.

Leading research in AI content detection modeling

Our AI detection model contains 7 components that process text to determine if it was written by AI. We utilize a multi-step approach that aims to produce predictions that reach maximum accuracy, with the least false positives. Our model specializes in detecting content from Chat GPT, GPT 4, Gemini, Claude and LLaMa models.

Quantify AI with Deep Scan

Unlock More of GPTZero

Origin chrome extension.

Use our AI detection tool as you browse the internet for AI content. Create a Writing Report on Google Docs to view statistics about your writing.

writing report

With our writing report, you are able to see behind the scenes of a google doc, including writing statistics, AI content, and a video of your writing process.

AI detection API

We built an easy to use API for organizations to detect AI content. Integrate GPTZero’s AI detection abilities into your own tools and workflow.

AI Text Detection and Analysis Trusted by Leading Organizations

Gptzero reviews.

GPTZero was the only consistent performer, classifying AI-generated text correctly. As for the rest … not so much.

GPTZero has been incomparably more accurate than any of the other AI checkers. For me, it’s the best solution to build trust with my clients.

This tool is a magnifying glass to help teachers get a closer look behind the scenes of a document, ultimately creating a better exchange of ideas that can help kids learn.

The granular detail provided by GPTZero allows administrators to observe AI usage across the institution. This data is helping guide us on what type of education, parameters, and policies need to be in place to promote an innovative and healthy use of AI.

After talking to the class, each student we compiled with GPTZero as possibly using AI ended up telling us they did, which made us extremely confident in GPTZero’s capabilities.

I'm a huge fan of the writing reports that let me verify my documents are human-written. The writing video, in particular, is a great way to visualize the writing process!

Excellent chrome extension. I ran numerous tests on human written content and the results were 100% accurate.

Outstanding! This is an extraordinary tool to not only assess the end result but to view the real-time process it took to write the document.

GPTZero is the best AI detection tool for teachers and educators.

General FAQs about our AI Detector

Everything you need to know about GPTZero and our chat gpt detector. Can’t find an answer? You can talk to our customer service team .

What is GPTZero?

GPTZero is the leading AI detector for checking whether a document was written by a large language model such as ChatGPT. GPTZero detects AI on sentence, paragraph, and document level. Our model was trained on a large, diverse corpus of human-written and AI-generated text, with a focus on English prose. To date, GPTZero has served over 2.5 million users around the world, and works with over 100 organizations in education, hiring, publishing, legal, and more.

How do I use GPTZero?

Simply paste in the text you want to check, or upload your file, and we'll return an overall detection for your document, as well as sentence-by-sentence highlighting of sentences where we've detected AI. Unlike other detectors, we help you interpret the results with a description of the result, instead of just returning a number.

To get the power of our AI detector for larger texts, or a batch of files, sign up for a free account on our Dashboard .

If you want to run the AI detector as your browse, you can download our Chrome Extension, Origin , which allows you to scan the entire page in one click.

When should I use GPTZero?

Our users have seen the use of AI-generated text proliferate into education, certification, hiring and recruitment, social writing platforms, disinformation, and beyond. We've created GPTZero as a tool to highlight the possible use of AI in writing text. In particular, we focus on classifying AI use in prose.

Overall, our classifier is intended to be used to flag situations in which a conversation can be started (for example, between educators and students) to drive further inquiry and spread awareness of the risks of using AI in written work.

Does GPTZero only detect ChatGPT outputs?

No, GPTZero works robustly across a range of AI language models, including but not limited to ChatGPT, GPT-4, GPT-3, GPT-2, LLaMA, and AI services based on those models.

Why GPTZero over other detection models?

GPTZero is the most accurate AI detector across use-cases, verified by multiple independent sources, including TechCrunch, which called us the best and most reliable AI detector after testing seven others.
GPTZero builds and constantly improves our own technology. In our competitor analysis, we found that not only does GPTZero perform better, some competitor services are actually just forwarding the outputs of free, open-source models without additional training.
In contrast to many other models, GPTZero is finetuned for student writing and academic prose. By doing so, we've seen large improvements in accuracies for this use-case.

What are the limitations of the classifier?

The nature of AI-generated content is changing constantly. As such, these results should not be used to punish students. We recommend educators to use our behind-the-scene Writing Reports as part of a holistic assessment of student work. There always exist edge cases with both instances where AI is classified as human, and human is classified as AI. Instead, we recommend educators take approaches that give students the opportunity to demonstrate their understanding in a controlled environment and craft assignments that cannot be solved with AI .

The accuracy of our model increases as more text is submitted to the model. As such, the accuracy of the model on the document-level classification will be greater than the accuracy on the paragraph-level, which is greater than the accuracy on the sentence level.

The accuracy of our model also increases for text similar in nature to our dataset. While we train on a highly diverse set of human and AI-generated text, the majority of our dataset is in English prose, written by adults.

Our classifier is not trained to identify AI-generated text after it has been heavily modified after generation (although we estimate this is a minority of the uses for AI-generation at the moment).

Currently, our classifier can sometimes flag other machine-generated or highly procedural text as AI-generated, and as such, should be used on more descriptive portions of text.

What can I do as an educator to reduce the risk of AI misuse?

Help students understand the risks of using AI in their work (to learn more, see this article ), and value of learning to express themselves. For example, in real-life, real-time collaboration, pitching, and debate, how does your class improve their ability to communicate when AI is not available?
Ask students to write about personal experiences and how they relate to the text, or reflect on their learning experience in your class.
Ask students to critique the default answer given by Chat GPT to your question.
Require that students cite real, primary sources of information to back up their specific claims, or ask them to write about recent events.
Assess students based on a live discussion with their peers, and use peer assessment tools (such as the one provided by our partner, Peerceptiv ).
Ask students to complete their assignments in class or in an interactive way, and shift lectures to be take-home.
Ask students to produce multiple drafts of their work that they can revise as peers or through the educator, to help students understand that assignments are meant to teach a learning process.
Ask students to produce work in a medium that is difficult to generate, such as powerpoint presentations, visual displays, videos, or audio recordings.
Set expectations for your students that you will be checking the work through an AI detector like GPTZero, to deter misuse of AI.

I'm an educator who has found AI-generated text by my students. What do I do?

Firstly, at GPTZero, we don't believe that any AI detector is perfect. There always exist edge cases with both instances where AI is classified as human, and human is classified as AI. Nonetheless, we recommend that educators can do the following when they get a positive detection:

Ask students to demonstrate their understanding in a controlled environment, whether that is through an in-person assessment, or through an editor that can track their edit history (for instance, using our Writing Reports through Google Docs). Check out our list of several recommendations on types of assignments that are difficult to solve with AI.
Ask the student if they can produce artifacts of their writing process, whether it is drafts, revision histories, or brainstorming notes. For example, if the editor they used to write the text has an edit history (such as Google Docs), and it was typed out with several edits over a reasonable period of time, it is likely the student work is authentic. You can use GPTZero's Writing Reports to replay the student's writing process, and view signals that indicate the authenticity of the work.
See if there is a history of AI-generated text in the student's work. We recommend looking for a long-term pattern of AI use, as opposed to a single instance, in order to determine whether the student is using AI.

What data did you train your model on?

Our model is trained on millions of documents spanning various domains of writing including creating writing, scientific writing, blogs, news articles, and more. We test our models on a never-before-seen set of human and AI articles from a section of our large-scale dataset, in addition to a smaller set of challenging articles that are outside its training distribution.

How do I use and interpret the results from your API?

To see the full schema and try examples yourself, check out our API documentation.

Our API returns a document_classification field which indicates the most likely classification of the document. The possible values are HUMAN_ONLY , MIXED , and AI_ONLY . We also provide a probability for each classification, which is returned in the class_probabilities field. The keys for this field are human , ai or mixed . To get the probability for the most likely classification, the predicted_class field can be used. The class probability corresponding to the predicted class can be interpreted as the chance that the detector is correct in its classification. I.e. 90% means that 90% of the time on similar documents our detector is correct in the prediction it makes. Lastly, each prediction comes with a confidence_category field, which can be high , medium , or low . Confidence categories are tuned such that when the confidence_category field is high 99.1% of human articles are classified as human, and 98.4% of AI articles are classified as AI.

Additionally, we highlight sentences that been detected to be written by AI. API users can access this highlighting through the highlight_sentence_for_ai field. The sentence-level classification should not be solely used to indicate that an essay contains AI (such as ChatGPT plagiarism). Rather, when a document gets a MIXED or AI_ONLY classification, the highlighted sentence will indicate where in the document we believe this occurred.

Are you storing data from API calls?

No. We do not store or collect the documents passed into any calls to our API. We wanted to be overly cautious on the side of storing data from any organizations using our API. However, we do store inputs from calls made from our dashboard. This data is only used in aggregate by GPTZero to further improve the service for our users. You can refer to our privacy policy for more details.

How do I cite GPTZero for an academic paper?

You can use the following bibtex citation:

A Princeton student built an app which can detect if ChatGPT wrote an essay to combat AI-based plagiarism

A Princeton student built an app that aims to tell if essays were written by AIs like ChatGPT.
The app analyzes text to see how randomly it is written, allowing it to detect if it was written by AI.
The website hosting the app, built by Edward Tian, crashed due to high traffic.

A new app can detect whether your essay was written by ChatGPT, as researchers look to combat AI plagiarism.

Edward Tian, a computer science student at Princeton, said he spent the holiday period building GPTZero.

He shared two videos comparing the app's analysis of a New Yorker article and a letter written by ChatGPT. It correctly identified that they were respectively written by a human and AI.

—Edward Tian (@edward_the6) January 3, 2023

GPTZero scores text on its "perplexity and burstiness" – referring to how complicated it is and how randomly it is written.

The app was so popular that it crashed "due to unexpectedly high web traffic," and currently displays a beta-signup page . GPTZero is still available to use on Tian's Streamlit page, after the website hosts stepped in to increase its capacity.

UK Edition Change

UK Politics
News Videos
Paris 2024 Olympics
Rugby Union
Sport Videos
John Rentoul
Mary Dejevsky
Andrew Grice
Sean O’Grady
Photography
Theatre & Dance
Culture Videos
Fitness & Wellbeing
Food & Drink
Health & Families
Royal Family
Electric Vehicles
Car Insurance Deals
Lifestyle Videos
UK Hotel Reviews
News & Advice
Simon Calder
Australia & New Zealand
South America
C. America & Caribbean
Middle East
Politics Explained
News Analysis
Today’s Edition
Home & Garden
Broadband deals
Fashion & Beauty
Travel & Outdoors
Sports & Fitness
Sustainable Living
Climate Videos
Solar Panels
Behind The Headlines
On The Ground
Decomplicated
You Ask The Questions
Binge Watch
Travel Smart
Watch on your TV
Crosswords & Puzzles
Most Commented
Newsletters
Ask Me Anything
Virtual Events
Betting Sites
Online Casinos
Wine Offers

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged in Please refresh your browser to be logged in

How teachers can tell if a student has used ChatGPT in an essay

Researchers compared essays written by three first-year undergraduate students, with the aid of chatgpt, with 164 essays written by igcse students, article bookmarked.

Find your bookmarks in your Independent Premium section, under my profile

Sign up for a full digest of all the best opinions of the week in our Voices Dispatches email

Experts have revealed the tell-tale signs that an essay has been written by ChatGPT and not a student.

It comes after the rise of generative AI tools, like ChatGPT, has sparked concerns about cheating among pupils in the education sector.

Repetition of words, tautology and paragraphs starting with “however” are some tell-tale features, researchers said.

The writing style of the artificial intelligence tool is “bland” and “journalistic”, according to a Cambridge University Press and Assessment study.

Researchers compared essays written by three first-year undergraduate students, with the aid of ChatGPT, with 164 essays written by IGCSE students.

These essays were marked by examiners and the undergraduates were then interviewed and their essays were analysed.

The study found essays written with the help of ChatGPT performed poorly on analysis and comparison skills compared to non-ChatGPT-assisted essays.

But ChatGPT-assisted essays performed strongly on information and reflection skills.

Researchers identified a number of key features of the ChatGPT writing style, which included the use of Latinate vocabulary, repetition of words or phrases and ideas, and pleonasms.

Essays written with the help of ChatGPT were also more likely to use paragraphs starting with discourse markers like “however”, “moreover”, and “overall”, and numbered lists with items.

The researchers said ChatGPT’s default writing style “echoes the bland, clipped, and objective style that characterises much generic journalistic writing found on the internet”.

The report said: “The students found ChatGPT useful for gathering information quickly.

“However, they considered that complete reliance on this technology would produce essays of a low academic standard.”

Lead researcher Jude Brady, of Cambridge University Press and Assessment, said: “Our findings offer insights into the growing area of generative AI and assessment, which is still largely uncharted territory.

“Despite the small sample size, we are excited about these findings as they have the capacity to inform the work of teachers as well as students.”

She added: “We hope our research might help people to identify when a piece of text has been written by ChatGPT.

“For students and the wider population, learning to use and detect generative AI forms an increasingly important aspect of digital literacy.”

Join our commenting forum

Join thought-provoking conversations, follow other Independent readers and see their replies

Subscribe to Independent Premium to bookmark this article

Want to bookmark your favourite articles and stories to read or reference later? Start your Independent Premium subscription today.

New to The Independent?

Or if you would prefer:

Want an ad-free experience?

Hi {{indy.fullName}}

My Independent Premium
Account details
Help centre

Have a language expert improve your writing

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

Knowledge Base

Using AI tools

How to Write an Essay with ChatGPT | Tips & Examples

How to Write an Essay with ChatGPT | Tips & Examples

Published on June 22, 2023 by Koen Driessen . Revised on November 16, 2023.

Passing off AI-generated text as your own work is widely considered plagiarism. However, when used correctly, 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
Summarize or paraphrase text
Get feedback

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Writing a research question, developing an outline, finding source recommendations, summarizing/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?

Check for common mistakes

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

Fix mistakes for free

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 specialized 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 summarizing 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 summarize or paraphrase it. Alternatively, you can use Scribbr’s free text summarizer and Scribbr’s free paraphrasing tool , which are specifically designed for these purposes.

Example: Using ChatGPT to summarize/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.

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

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 . An AI detector may be used to detect this offense.

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 summarize text . This can help you understand complex information more easily, summarize the central argument of your own paper, or clarify your research question.

You can also use Scribbr’s free text summarizer , 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 specialized tool like Scribbr’s free paraphrasing tool , which will provide a smoother user experience.

No, it’s not a good idea to do so in general—first, because it’s normally considered plagiarism or academic dishonesty to represent someone else’s work as your own (even if that “someone” is an AI language model). Even if you cite ChatGPT , you’ll still be penalized unless this is specifically allowed by your university . Institutions may use AI detectors to enforce these rules.

Second, ChatGPT can recombine existing texts, but it cannot really generate new knowledge. And it lacks specialist knowledge of academic topics. Therefore, it is not possible to obtain original research results, and the text produced may contain factual errors.

However, you can usually still use ChatGPT for assignments in other ways, as a source of inspiration and feedback.

Cite this Scribbr article

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

Driessen, K. (2023, November 16). How to Write an Essay with ChatGPT | Tips & Examples. Scribbr. Retrieved June 7, 2024, from https://www.scribbr.com/ai-tools/chatgpt-essay/

Is this article helpful?

Koen Driessen

Other students also liked, how to write good chatgpt prompts, how to use chatgpt in your studies, what are the limitations of chatgpt.

Koen Driessen (Scribbr Team)

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

Still have questions?

Get unlimited documents corrected.

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

Get the Reddit app

https://dsc.gg/rchatgpt

Subreddit to discuss about ChatGPT and AI. Not affiliated with OpenAI.

How can i detect Essays wrote by the AI from my students?

Some Essays i read in the last time was too good compared to older ones. Is it possible to detect AI's work? Otherwise it would be a scandal when it comes to a Bachelor or a Masterthesis.

Chat GPT Detector for Essays

Understanding the results.

Once you click “Check the text,” you will see a bar chart and a detailed analysis of the text.

The bar chart displays the proportions of words in the text based on how likely an AI generator would use them in a similar context:

The red column shows the percentage of words an AI generator would most probably use to write a text on your topic.
The orange column shows the proportion of words that a GPT generator would sometimes use.
The green column displays the percentage of words that an AI tool would rarely use while generating a similar text.
The violet column displays the share of the least predictable words that a GPT writer would almost never use.

Under the bar chart, you will find a detailed analysis of the text. All words will be colored according to the categories they belong to. By clicking on each word, you’ll be able to see its probability of being used by a chatbot, as well as the top-5 most likely alternatives.

An AI-generated text will be colored mostly red and orange. In contrast, a paper written by a human will contain green and violet words.

️✅ The Tool's Benefits
️🤖 Why Is ChatGPT Detection Important?
️❌ AI Text Generators Limitations
️🔎 AI Detection: Is It Possible for Now?
️🔗 References

✅ Chat GPT Detector Benefits

👛 Free to use	Like Chat GPT itself, this AI essay detector is 100% free both for students and teachers.
🚀 Effective	The AI detection tool is not perfect, yet more effective than traditional plagiarism checkers.
🎓 Developed for students	We’ve developed our Chat GPT detector so that you can check any piece of academic writing.
📊 Provides detailed analysis	The ChatGPT checker provides detailed text analysis, allowing you to edit the essay as you like.

🛠️ Chat GPT Essay Detector: How Does It Work?

To use the tool, take the 4 steps below:

Add the content in question (up to 4500 characters).
Input its topic, title, or short description (optional).
Click “Check the text”.
Get a detailed analysis for free.

Automatically generated texts have become a considerable problem for teachers in 2023. Developing an accurate AI essay detector is the hottest research area now. The Chat GPT detector we’ve made is an instrument that shows the probability for a text to be AI-generated.

The tool’s functioning is effortless:

Enter the text, press the button, and check the result.

The Chat GPT checker will analyze the piece in detail, showing the proportions of words in the text based on how likely an AI writer would use them. As a result, you can edit the most predictable words and sentences if needed, making the text look 100% human-written.

🤖 Chat GPT Detectors: Why Are They So Important?

Chat GPT, created by OpenAI , has been a pain in the neck for teachers since its creation.

The picture contains an explanation of what ChatGPT is.

The tool is what our parents considered science fiction. It generates custom-made answers to specific questions and can take your prompts into account.

An unprecedented threat is looming over the conventional system of education in general and independent writing assignments in particular. How can we assess and develop students’ problem-solving and critical thinking?

Chat GPT can find and compile facts, use various pre-set writing styles, and produce convincing, logical arguments. To make it even better (and worse!), it has impeccable grammar, although users can choose to add grammatical errors for credibility. Last but not least, for now AI essay detection is problematic, because traditional plagiarism detectors fail to identify Chat GPT generated papers correctly.

The first decision came: NYC blocked Chat GPT on campuses , and other education departments will soon follow them. But no one can control non-educational Internet networks and devices.

We are standing on the verge of the “Big Bang” in our perception of education methodology. Here’s what can happen:

Most likely, educators will have to move away from formulaic writing with strict rubrics.
Colleges won’t dedicate as much time to theoretical knowledge and give more ways to practice.
Students will be encouraged to explore information worth knowing.
Specific homework assignments will become outdated.
Creativity will become more critical than knowledge.
All schools will use ChatGPT essay detectors like they used plagiarism detectors in the era of Google.

❌ Chat GPT Essay Writing: Limitations and Ethical Issues

ChatGPT is impressive but not flawless. As of the moment, it has such limitations.

Chat GPT Essay Writing Limitations

Don’t expect it to answer questions about what happened after 2021 . For example, it doesn’t know much about Biden’s presidency, Omicron, the Russian invasion of Ukraine , or the death of Queen Elizabeth II. That's why you shouldn’t ask GPT-3 to write an essay on, let’s say, Russian invasion of Ukraine.
ChatGPT isn’t able to keep up with the latest events . Training the tool on this information takes time. Perhaps, software engineers will eventually solve this issue.
It can generate incorrect texts if it gets the question wrong. You took it right. It is a human-like intelligence, and mutual misunderstanding is in our veins. But paraphrasing the query can improve the result.
Adding too many parameters, getting niche, or asking tricky questions overwhelms the program . It will give inappropriate answers or ignore parts of your request.
It can use offensive language like all of us in some cases.

AI Essay Writing: Ethical Issues

The ethical issues of AI essay writers are also explicit.

AI nominally filters out requests in writing that go against the service’s policy. That’s why you won’t be able to produce harmful content using the program. Meanwhile, merely asking it to help generate a text from a racist’s point of view is acceptable and doable.

The program takes concepts and words from a dataset containing texts from the Internet. The latter has never been a peaceful and ethical place. So, despite an astonishing understanding of moral issues the AI has demonstrated, it can use human biases and stereotypes, purposefully or not. It can neither differentiate fake news nor conspiracy theories.

In this aspect, developers have a long way to go.

🔎 AI Essay Detector: Does it Work?

AI detection is hardly possible for the human eye. The only difference is that computer-generated texts stick to the most likely word. Meanwhile, people often choose unpredictable words that still make sense to a knowledgeable audience.

But one cannot fool a computer. This AI detector for essays shows how likely a text has been machine-generated or written by a human. Once again, the more predictable the choice of words, the more artificial it looks.

❓ AI Essay Detector FAQ

❓ what content types can i generate using ai.

AI can generate literally any content except for harmful and offensive statements. Still, its truthfulness is questionable. AI cannot tell fake news from real ones and conspiracy theories from reality. Neither can it filter out the bias that prevails on the internet.

❓ How To Generate Content Using AI?

If you would like to generate content using AI, use ChatGPT. It can create anything from an essay to answers to complicated moral dilemmas. Enter your query into the indicated field, and press the respective button to see the result. If it does not meet your expectations, modify the question.

❓ How To Detect AI Generated Content?

You cannot detect AI-generated content without dedicated software. I.e., our brain sees no difference between human-made and artificial texts. This AI detection tool will help you determine whether the text was written by hand or by code. Just copy the text into the program and check the result.

❓ How Does a Chat GPT Essay Detector Work?

A ChatGPT detector works similarly to AI text generators. It analyses the predictability of each word in a sentence. If the selection is highly predictable, AI has created the text. The more terms are used in unusual places, the more life-like the text is.

🔗 References

The Limitations of Chat-GPT - Medium
5 Big Problems With OpenAI's ChatGPT - MakeUseOf
What is GPT-3? Everything You Need to Know - TechTarget
Meet GPT-3. It Has Learned to Code (and Blog and Argue).
What is Natural Language Processing? An Introduction to NLP

Summer Game Fest 2024
Amazon Prime Day is coming in July
Apple WWDC 2024
Samsung Galaxy Watch AI features
13-inch MacBook Air M2 deal

OpenAI's new tool may help you identify text written by ChatGPT

But it can “mislabel both ai-generated and human-written text.”.

OpenAI has released a tool to help you determine whether text was more likely written by a human or AI. However, the ChatGPT maker warns that its equivalent of Blade Runner ’s Voight-Kampff test can also get it wrong.

The tool includes a box where you can paste text that’s at least 1,000 characters long. It will then spit out a verdict, like “The classifier considers the text to be very unlikely AI-generated” or “The classifier considers the text to be possibly AI-generated.”

I tested it by prompting ChatGPT to write an essay about the migratory patterns of birds, which the detection tool then described as “possibly AI-generated.” Meanwhile, it rated several human-written articles as “very unlikely AI-generated.” So although the tool could raise false flags in either direction, my (tiny sample size) test suggests at least a degree of accuracy. Still, OpenAI cautions not to use the tool alone to determine content’s authenticity; it also works best with text of 1,000 words or longer.

The startup has faced pressure from educators after the November release of its ChatGPT tool, which produces AI-written content that can sometimes pass for human writing. The natural-language model can create essays in seconds based on simple text prompts — even passing a graduate business and law exam — while providing students with a tempting new cheating opportunity. As a result, New York public schools banned the bot from their WiFi networks and school devices.

While ChatGPT’s arrival has been a buzzed-about topic of late, even extending into media outlets eager to automate SEO-friendly articles , the bot is big business for OpenAI. The company reportedly secured a $10 billion investment earlier this month from Microsoft, which plans to integrate it into Bing and Office 365. OpenAI allegedly discussed selling shares at a $29 billion valuation late last year, which would make it one of the most valuable US startups.

Although ChatGPT is currently the best publicly available natural language AI model, Google, Baidu and others are working on competitors. Google’s LaMDA is convincing enough that one former researcher threw away his job with the search giant last year by claiming the chatbot is sentient. (The human tendency to project feelings and consciousness onto algorithms is a concept we’ll likely hear much about in the coming years.) Google has only released extremely constricted versions of its chatbot in a beta, presumably out of ethical concerns. With the genie out of the bottle, it will be interesting to see how long that restraint lasts.

How to Detect if Students are Using ChatGPT for Their Essays

With the rise of AI-assisted writing services, it’s becoming increasingly difficult for teachers to detect when students are using these services in lieu of actually completing their own work. One such service, ChatGPT, is a popular tool used by many students because it is currently free.

Tool to test whether your students are using ChatGPT

The most accurate tool to check if students are using ChatGPT is called Winston A.I .

Orginality.AI is another tool that you can use to check if your students are using ChatGPT or any other A.I writer. The tool is currently correct 94% of the time.

What I like about Originality is that they are keeping up to date with the latest A.I chatbots that students might be using like GPT 4 and Google Bard.

Signs That A Student May Be Using ChatGPT

Another warning sign is if you notice that multiple students in your class have submitted essays with strikingly similar topics or points of view. Since ChatGPT is an automated service, it could be possible that more than one student has accessed and used it to complete their assignments.

Something else that you will notice is that A.I written text often repeats itself, making the same point over and over again. Check out a review of KoalaWriter here!

How You Can Address The Issue

If you suspect that a student may have used an AI writing service like ChatGPT for their assignment, there are several ways to address the issue without punishing them too harshly. For starters, you can ask them about their experience with the service directly and make sure that they understand why using such services is unacceptable in school settings.

GTA 5 Cheats
Print on a Chromebook
Nothing Phone 2 Review
Best YouTube TV Alternatives
Asus ROG Ally vs. Steam Deck
Gameshare on Nintendo Switch

How to detect ChatGPT plagiarism — and why it’s becoming so difficult

Chatbots are hot stuff right now, and ChatGPT is chief among them. But thanks to how powerful and humanlike its responses are, academics, educators, and editors are all dealing with the rising tide of AI-generated plagiarism and cheating. Your old plagiarism detection tools may not be enough to sniff out the real from the fake.

Lots of detection options

Putting them to the test.

In this article, I talk a little about this nightmarish side of AI chatbots, check out a few online plagiarism detection tools, and explore how dire the situation has become.

The latest November 2022 release of startup OpenAI’s ChatGPT basically thrusted chatbot prowess into the limelight. It allowed any regular Joe (or any professional) to generate smart, intelligible essays or articles, and solve text-based mathematic problems. To the unaware or inexperienced reader, the AI-created content can quite easily pass as a legit piece of writing, which is why students love it — and teachers hate it.

A great challenge with AI writing tools is their double-edged sword ability to use natural language and grammar to build unique and almost individualized content even if the content itself was drawn from a database. That means the race to beat AI-based cheating is on. Here are some options I found that are available right now for free.

The free version of ChatGPT just got much more powerful
OpenAI strikes major deal with News Corp to boost ChatGPT
GPT-4o: What the latest ChatGPT update can do and when you can get it

GPT-2 Output Detector comes straight from ChatGPT developer OpenAI to demonstrate that it has a bot capable of detecting chatbot text. Output Detector is easy to use — users just have to enter text into a text field and the tool will immediately provide its assessment of how likely it is that the text came from a human or not.

Two more tools that have clean UIs are Writer AI Content Detector and Content at Scale . You can either add a URL to scan the content (writer only) or manually add text. The results are given a percentage score of how likely it is that the content is human-generated.

GPTZero is a home-brewed beta tool hosted on Streamlit and created by Princeton University student Edward Zen. It’s differs from the rest in how the “algiarism” (AI-assisted plagiarism) model presents its results. GPTZero breaks the metrics into perplexity and burstiness. Burstiness measures overall randomness for all sentences in a text, while perplexity measures randomness in a sentence. The tool assigns a number to both metrics — the lower the number, the greater possibility that the text was created by a bot.

Just for fun, I included Giant Language Model Test Room (GLTR), developed by researchers from the MIT-IBM Watson AI Lab and Harvard Natural Language Processing Group. Like GPTZero, it doesn’t present its final results as a clear “human” or “bot” distinction. GLTR basically uses bots to identify text written by bots, since bots are less likely to select unpredictable words. Therefore, the results are presented as a color-coded histogram, ranking AI-generated text versus human-generated text. The greater the amount of unpredictable text, the more likely the text is from a human.

All these options might make you think we’re in a good spot with AI detection. But to test the actual effectiveness of each of these tools, I wanted to try it out for myself. So I ran a couple of sample paragraphs that I wrote in response to questions that I also posed to, in this case, ChatGPT.

My first question was a simple one: Why is buying a prebuilt PC frowned upon? Here’s how my own answers compared to the response from ChatGPT.


	1.18% fake	36.57% fake
	100% human	99% human
	99% human	73% human
	80 perplexity	50 perplexity
	12 of 66 words likely by human	15 or 79 words likely by human

As you can see, most of these apps could tell that my words were genuine, with the first three being the most accurate. But ChatGPT fooled most of these detector apps with its response too. It scored a 99% human on the Writer AI Content Detector app, for starters, and was marked just 36% fake by GPT-based detector. GLTR was the biggest offender, claiming that my own words were equally likely to be written by a human as ChatGPT’s words.

I decided to give it one more shot, though, and this time, the responses were significantly improved. I asked ChatGPT to provide a summary of the Swiss Federal Institute of Technology’s research into anti-fogging using gold particles. In this example, the detector apps did a much better job at approving my own response and detecting ChatGPT.


	9.28% fake	99.97% fake
	95% human	2% human
	92% human	0% (Obviously AI)
	41 perplexity	23 perplexity
	15 of 79 words likely by human	4 of 98 words likely by human

The top three tests really showed their strength in this response. And while GLTR still had a hard time seeing my own writing as human, at least it did a good of catching ChatGPT this time.

It’s obvious from the results of each query that online plagiarism detectors aren’t perfect. For more complex answers or pieces of writing (such as in the case of my second prompt), it’s a bit easier for these apps to detect the AI-based writing, while the simpler responses are much more difficult to deduce. But clearly, it’s not what I’d call dependable. Occasionally, these detector tools will misclassify articles or essays as ChatGPT-generated, which is a problem for teachers or editors wanting to rely on them for catching cheaters.

Developers are constantly fine-tuning accuracy and false positive rates, but they’re also bracing for the arrival of GPT-3, which touts a significantly improved dataset and more complex capabilities than GPT-2 (of which ChatGPT is trained from).

At this point, in order to identify content generated by AIs, editors and educators will need to combine judiciousness and a little bit of human intuition with one (or more) of these AI detectors. And for chatbot users who have or are tempted to use chatbots such as Chatsonic, ChatGPT, Notion, or YouChat to pass of their “work” as legit — please don’t. Repurposing content created by a bot (that sources from fixed sources within its database) is still plagiarism no matter how you look at it.

Editors' Recommendations

DuckDuckGo’s new AI service keeps your chatbot conversations private
Few people are using ChatGPT and other AI tools regularly, study suggests
ChatGPT not working? The most common problems and fixes
ChatGPT can laugh now, and it’s downright creepy
The best ChatGPT plug-ins you can use

OpenAI needs to watch out because Apple may finally be jumping on the AI bandwagon, and the news doesn't bode well for ChatGPT. Apple is reportedly working on a large language model (LLM) referred to as ReALM, which stands for Reference Resolution As Language Modeling. Made to give Siri a boost and help it understand context, the model comes in four variants, and Apple claims that even its smallest model performs on a similar level to OpenAI's ChatGPT.

This tantalizing bit of information comes from an Apple research paper, first shared by Windows Central, and it appears to be an early peek into what Apple has been cooking for a while now. ReALM is Apple's own LLM that was reportedly made to enhance Siri's capabilities; these improvements include a greater ability to understand context in a conversation.

The ChatGPT chatbot is an innovative AI tool developed by OpenAI. As it stands, there are two main versions of the software: GPT-4 and GPT-3.5. Toe to toe in more ways than one, there are a couple of key differences between both versions that may be deal-breakers for certain users. But what exactly are these differences? We’re here to help you find out.

We’ve put together this side-by-side comparison of both ChatGPT versions, so when you’re done reading, you’ll know what version makes the most sense for you and yours. What are GPT 3.5 and GPT-4?

ChatGPT, the AI-powered chatbot that went viral at the start of last year and kicked off a wave of interest in generative AI tools, no longer requires an account to use.

Its creator, OpenAI, launched a webpage on Monday that lets you begin a conversation with the chatbot without having to sign up or log in first.

clock This article was published more than 1 year ago

We tested a new ChatGPT-detector for teachers. It flagged an innocent student.

Five high school students helped our tech columnist test a ChatGPT detector coming from Turnitin to 2.1 million teachers. It missed enough to get someone in trouble.

High school senior Lucy Goetz got the highest possible grade on an original essay she wrote about socialism. So imagine her surprise when I told her that a new kind of educational software I’ve been testing claimed she got help from artificial intelligence.

A new AI-writing detector from Turnitin — whose software is already used by 2.1 million teachers to spot plagiarism — flagged the end of her essay as likely being generated by ChatGPT .

“Say what?” says Goetz, who swears she didn’t use the AI writing tool to cheat. “I’m glad I have good relationships with my teachers.”

After months of sounding the alarm about students using AI apps that can churn out essays and assignments, teachers are getting AI technology of their own. On April 4, Turnitin is activating the software I tested for some 10,700 secondary and higher-educational institutions, assigning “generated by AI” scores and sentence-by-sentence analysis to student work. It joins a handful of other free detectors already online. For many teachers I’ve been hearing from, AI detection offers a weapon to deter a 21st-century form of cheating.

But AI alone won’t solve the problem AI created. The flag on a portion of Goetz’s essay was an outlier, but shows detectors can sometimes get it wrong — with potentially disastrous consequences for students. Detectors are being introduced before they’ve been widely vetted, yet AI tech is moving so fast, any tool is likely already out of date.

It’s a pivotal moment for educators: Ignore AI and cheating could go rampant. Yet even Turnitin’s executives tell me that treating AI purely as the enemy of education makes about as much sense in the long run as trying to ban calculators.

GET CAUGHT UP Summarized stories to quickly stay informed

A punishing heat dome will test Phoenix’s strategy to reduce heat-related deaths

Trump plans to claim sweeping powers to cancel federal spending

North Korea sent trash balloons. Activists in the South sent K-pop.

U.S. notches historic upset of Pakistan at cricket World Cup

Has tipping gone too far? Here’s a guide on when to tip.

Ahead of Turnitin’s launch this week, the company says 2 percent of customers have asked it not to display the AI writing score on student work. That includes a "significant majority” of universities in the United Kingdom, according to UCISA , a professional body for digital educators.

To see what’s at stake, I asked Turnitin for early access to its software. Five high school students, including Goetz, volunteered to help me test it by creating 16 samples of real, AI-fabricated and mixed-source essays to run past Turnitin’s detector.

The result? It got over half of them at least partly wrong. Turnitin accurately identified six of the 16 — but failed on three, including a flag on 8 percent of Goetz’s original essay. And I’d give it only partial credit on the remaining seven, where it was directionally correct but misidentified some portion of ChatGPT-generated or mixed-source writing.

Turnitin claims its detector is 98 percent accurate overall. And it says situations such as what happened with Goetz’s essay, known as a false positive, happen less than 1 percent of the time, according to its own tests.

Turnitin also says its scores should be treated as an indication, not an accusation . Still, will millions of teachers understand they should treat AI scores as anything other than fact? After my conversations with the company, it added a caution flag to its score that reads, “Percentage may not indicate cheating. Review required.”

“Our job is to create directionally correct information for the teacher to prompt a conversation,” Turnitin chief product officer Annie Chechitelli tells me. “I’m confident enough to put it out in the market, as long as we’re continuing to educate educators on how to use the data.” She says the company will keep adjusting its software based on feedback and new AI advancements.

The question is whether that will be enough. “The fact that the Turnitin system for flagging AI text doesn’t work all the time is concerning,” says Rebecca Dell, who teaches Goetz’s AP English class in Concord, Calif. “I’m not sure how schools will be able to definitively use the checker as ‘evidence’ of students using unoriginal work.”

Unlike accusations of plagiarism, AI cheating has no source document to reference as proof. “This leaves the door open for teacher bias to creep in,” says Dell.

For students, that makes the prospect of being accused of AI cheating especially scary. “There is no way to prove that you didn’t cheat unless your teacher knows your writing style, or trusts you as a student,” says Goetz.

Why detecting AI is so hard

Spotting AI writing sounds deceptively simple. When a colleague recently asked me if I could detect the difference between real and ChatGPT-generated emails, I didn’t perform very well.

Detecting AI writing with software involves statistics. And statistically speaking, the thing that makes AI distinct from humans is that it’s “extremely consistently average,” says Eric Wang, Turnitin’s vice president of AI.

Systems such as ChatGPT work like a sophisticated version of auto-complete, looking for the most probable word to write next. “That’s actually the reason why it reads so naturally: AI writing is the most probable subset of human writing,” he says.

Turnitin’s detector “identifies when writing is too consistently average,” Wang says.

The challenge is that sometimes a human writer may actually look consistently average.

On economics, math and lab reports, students tend to hew to set styles, meaning they’re more likely to be misidentified as AI writing, says Wang. That’s likely why Turnitin erroneously flagged Goetz’s essay, which veered into economics. (“My teachers have always been fairly impressed with my writing,” says Goetz.)

Wang says Turnitin worked to tune its systems to err on the side of requiring higher confidence before flagging a sentence as AI. I saw that develop in real time: I first tested Goetz’s essay in late January, and the software identified much more of it — about 50 percent — as being AI generated. Turnitin ran my samples through its system again in late March, and that time only flagged 8 percent of Goetz’s essay as AI-generated.

But tightening up the software’s tolerance came with a cost: Across the second test of my samples, Turnitin missed more actual AI writing. “We’re really emphasizing student safety,” says Chechitelli.

Say hello to your new tutor: It’s ChatGPT

Turnitin does perform better than other public AI detectors I tested. One introduced in February by OpenAI, the company that invented ChatGPT, got eight of our 16 test samples wrong. (Independent tests of other detectors have declared they “ fail spectacularly .”)

Turnitin’s detector faces other important technical limitations, too. In the six samples it got completely right, they were all clearly 100 percent student work or produced by ChatGPT. But when I tested it with essays from mixed AI and human sources, it often misidentified the individual sentences or missed the human part entirely. And it couldn’t spot the ChatGPT in papers we ran through Quillbot, a paraphrasing program that remixes sentences.

What’s more, Turnitin’s detector may already be behind the state of the AI art. My student helpers created samples with ChatGPT, but since they did the writing, the app has gotten a software update called GPT-4 with more creative and stylistic capabilities. Google also introduced a new AI bot called Bard . Wang says addressing them is on his road map.

Some AI experts say any detection efforts are at best setting up an arms race between cheaters and detectors. “I don’t think a detector is long-term reliable,” says Jim Fan, an AI scientist at Nvidia who used to work at OpenAI and Google.

“The AI will get better, and will write in ways more and more like humans. It is pretty safe to say that all of these little quirks of language models will be reduced over time,” he says.

Is detecting AI a good idea?

Given the potential — even at 1 percent — of being wrong, why release an AI detector into software that will touch so many students?

“Teachers want deterrence,” says Chechitelli. They’re extremely worried about AI and helping them see the scale of the actual problem will “bring down the temperature.”

Some educators worry it will actually raise the temperature.

Mitchel Sollenberger, the associate provost for digital education at the University of Michigan-Dearborn, is among the officials who asked Turnitin not to activate AI detection for his campus at its initial launch.

He has specific concerns about how false positives on the roughly 20,000 student papers his faculty run through Turnitin each semester could lead to baseless academic-integrity investigations. “Faculty shouldn’t have to be expert in a third-party software system — they shouldn’t necessarily have to understand every nuance,” he says.

Ian Linkletter, who serves as emerging technology and open-education librarian at the British Columbia Institute of Technology, says the push for AI detectors reminds him of the debate about AI exam proctoring during pandemic virtual learning.

“I am worried they’re marketing it as a precision product, but they’re using dodgy language about how it shouldn’t be used to make decisions,” he says. “They’re working at an accelerated pace not because there is any desperation to get the product out but because they’re terrified their existing product is becoming obsolete.”

Said Chechitelli: “We are committed to transparency with the community and have been clear about the need to continue iterating on the user experience as we learn more from students and educators.

Deborah Green, CEO of UCISA in the U.K., tells me she understands and appreciates Turnitin’s motives for the detector. “What we need is time to satisfy ourselves as to the accuracy, the reliability and particularly the suitability of any tool of this nature.”

It’s not clear how the idea of an AI detector fits into where AI is headed in education . “In some academic disciplines, AI tools are already being used in the classroom and in assessment,” says Green. “The emerging view in many U.K. universities is that with AI already being used in many professions and areas of business, students actually need to develop the critical thinking skills and competencies to use and apply AI well.”

There’s a lot more subtlety to how students might use AI than a detector can flag today.

My student tests included a sample of an original student essay written in Spanish, then translated into English with ChatGPT. In that case, what should count: the ideas or the words? What if the student was struggling with English as a second language? (In our test, Turnitin’s detector appeared to miss the AI writing, and flagged none of it.)

Would it be more or less acceptable if a student asked ChatGPT to outline all the ideas for an assignment, and then wrote the actual words themselves?

“That’s the most interesting and most important conversation to be having in the next six months to a year — and one we’ve been having with instructors ourselves,” says Chechitelli.

“We really feel strongly that visibility, transparency and integrity are the foundations of the conversations we want to have next around how this technology is going to be used,” says Wang.

For Dell, the California teacher, the foundation of AI in the classroom is an open conversation with her students.

When ChatGPT first started making headlines in December, Dell focused an entire lesson with Goetz’s English class on what ChatGPT is, and isn’t good for. She asked it to write an essay for an English prompt her students had already completed themselves, and then the class analyzed the AI’s performance.

The AI wasn’t very good.

“Part of convincing kids not to cheat is making them understand what we ask them to do is important for them,” said Dell.

Help Desk: Making tech work for you

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

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

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

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

How-To Geek

Fix: chatgpt "internal server error" and other common errors.

ChatGPT is more popular than ever, so you're probably going to be seeing a lot more error messages.

Quick Links

Can you fix an internal server error when using chatgpt, fixing chatgpt network errors, fixing chatgpt "at capacity" error message, other chatgpt error fixes you can try, key takeaways.

ChatGPT internal server errors are caused by a problem with OpenAI's servers, so come back and try again later. You may fix connection errors by troubleshooting your local connection, disabling your VPN, asking for shorter responses, or switching browsers. "At capacity" errors can potentially be circumvented by upgrading to ChatGPT Plus.

Encountering an error while trying to use ChatGPT ? Unfortunately, when a service booms in popularity you're more likely to see server errors, connection errors, and other problems. Here's what you can do about it.

ChatGPT runs remotely on a web server, which means it's inherently vulnerable to server errors that are outside of your control. If you're seeing an "Internal Server Error" while trying to use the service, there's little you can do to resolve it. We'd recommend taking a break and coming back later.

If you're trying to use ChatGPT using a browser extension or any other indirect service, you can try using the service directly instead by visiting chat.openai.com in a web browser.

You may encounter other errors while attempting to use the OpenAI chat bot. This includes all manner of network errors, which could be a result of a problem on either end.

The first thing to check if you receive a network error is your internet connection . Attempt to visit a web page in another tab to see if you're able to access it. If other websites are working fine but ChatGPT is giving you network errors, consider there's a problem with the OpenAI service.

If you're using a VPN , you can try disabling it and trying again. Unusual network activity coming from the VPN network could cause ChatGPT to think you're not a "real" human (no, the irony isn't lost on us) which could interfere with the service.

ChatGPT network errors with long responses in particular are a common issue according to many users. Requesting shorter responses from the chatbot may avoid problems, especially during busy times. For example, you could prefix your query with "in less than 250 words tell me..." rather than a more detailed "write an essay on..." style prompt.

If nothing else is working, you can always try coming back later.

Due to the service's soaring popularity, more users are seeing error messages about ChatGPT being "at capacity" and thus unavailable. This happens when too many users are using the service at once. You're likely to see this message if you're using ChatGPT using a free plan .

OpenAI has a ChatGPT Plus account that you can subscribe to by clicking the "Upgrade to Plus" button in the lower-left corner of a ChatGPT conversation or side menu. This provides you with access to the chatbot "even when demand is high" so you're less likely to see "at capacity" errors. You'll also get faster responses and priority access to new features OpenAI adds to the chatbot.

Alternatively, if you don't fancy paying for the service, you can take a break and try your query again later.

ChatGPT errors are like any other you might encounter while using a web-based service. You can try refreshing the page and logging in and out again to resolve issues. Restarting your browser , opening a new "private browsing" session , or trying a different browser altogether may also help.

But most of the time, these sorts of errors are outside of your control. If ChatGPT isn't working, why not spend some time testing out Bing's AI-powered search responses instead ? It's one of many ChatGPT alternatives that are worth a try.

Is it Worth Using ChatGPT to Write Your Resume? Let’s Find Out

Published: June 05, 2024

ChatGPT this, ChatGPT that. Well, I’m here to add to the AI noise (but in a good way, I promise).

two hard-working hands drawing up a ChatGPT resume

I’ve seen a lot of discourse on LinkedIn about ChatGPT resumes and other professional use cases for AI .

Since the job market is on fire right now, I decided to do a little digging myself to see how helpful ChatGPT really is for resume writing.

Table of Contents

Should you use ChatGPT to write your resume?

How to use chatgpt to write a resume, how to use chatgpt to update your resume, chatgpt resume example, best practices for chatgpt resumes.

For those of you who appreciate a good visual: Watch me in real-time as I test out a couple of ChatGPT resume prompts to build my own resume.

View this post on Instagram A post shared by Alana Chinn (@ajcsays)

In my opinion, it’s not really a matter of should vs. should not.

ChatGPT can be a great resource to help you write or update your resume if you use the right prompts .

AI gives you three main superpowers:

Speed: Tools like ChatGPT can create content quickly and save you time.
Agility: AI can help you adjust your tone and language for your audience.
Clarity: You can simplify complex sentences, ideas, and topics with AI.

But as we all know — with great power comes great responsibility.

I wouldn’t suggest relying solely on AI to help you land an interview. When it comes to your resume, you’re still going to have to do some of the heavy lifting.

However, ChatGPT can help make things a little lighter for you.

12 Free Customizable Resume Templates

Fill out this form to access your free professionally-designed templates, available on:

Microsoft Word
Google Docs
Microsoft PowerPoint
Google Slides

Download Free

All fields are required.

You're all set!

Click this link to access this resource at any time.

1. Use ChatGPT to create a professional summary.

Let’s kick this off with a professional summary .

I like to include a brief bio at the top of my resume to describe who I am and what my areas of expertise are. This is especially useful when the job application doesn’t require a cover letter.

To create a professional summary using ChatGPT, I used the following prompt:

Write a professional summary for a resume that describes a marketer with 8 years of experience in content strategy, writing, and editing. Limit the summary to 3-4 sentences, and make the tone conversational but professional.

Here’s the output I received:

Here are a few next steps I'd do from here:

Rewrite certain sections (like the work experience bullets) to add specificity based on my responsibilities.
Include the rest of my work history and add more skills to represent the range of my expertise.
Review and copy edit line-by-line to polish it up. You know, so it sounds more like me and less like AI.

Based on this experience, here are my top three best practices to get the most out of your ChatGPT resume outputs.

Provide as much detail as possible in your prompt. Your ChatGPT results are only as good as your inputs. Be as specific as you can in your request, and if that doesn’t work, try bullet #2.
Keep asking until you’re satisfied with the output. AI is far from perfect. Continue to adjust your prompts, use more prescriptive instructions, or restart the conversation to get the results you want.
Don’t copy/paste the exact response into your resume. Please don’t do this. Imagine you and 25 other candidates use the same ChatGPT resume language for a job application. Chances are none of you get hired.

Pro tip: Looking for even smarter results? ChatSpot combines the power of ChatGPT with unique data sources (including the HubSpot CRM).

ChatGPT, write me a conclusion for this.

(I didn’t actually ask ChatGPT to write one for me, but I could’ve.)

Anyway, landing a new role is a lot of work, so you might as well work smarter — and not harder — with AI. Just don’t let it interfere with your ability to showcase who you are on your resume.

Don't forget to share this post!

Get Past the ATS With These Resume Templates [+ Tips]

How to Write a Respectable Resignation Letter [+ Samples & Templates]

Quiet Quitting vs. Setting Healthy Boundaries: Where's The Line?

The Best Fonts for Your Resume in 2024, According to HubSpot Recruiters

How to Answer ‘What Makes You Unique?’ & Stand Out in Your Next Interview

Best Personal Website from Marketers, Creators, and Other Business Professionals Who’ll Inspire You

#OpenToWork: Are LinkedIn Photo Frames Actually Helpful?

What is a Letter of Intent? How to Write One for a Job [+ Examples]

The Best 30-60-90 Day Plan for Your New Job [Template + Example]

12 Incredible Answers to "What Is Your Greatest Weakness?" — That Aren't "Perfectionism"

Resume templates to create a killer resume for your job application.

Marketing software that helps you drive revenue, save time and resources, and measure and optimize your investments — all on one easy-to-use platform

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.

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

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

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

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.

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.

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

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.

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 7 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.

Request More Info

Fill out the form below and a member of our team will reach out right away!

" * " indicates required fields

Artificial Intelligence

The Impact of ChatGPT on AI Careers & Opportunities

two hands type on a laptop keyboard with a digital screen superimposed on the image floating in front of the laptop screen

What Is ChatGPT?

How Does It Work?
ChatGPT Challenges
Implications
Opportunities
Future of AI and ChatGPT

The artificial intelligence application ChatGPT debuted in late 2022 and has been making headlines ever since. Its popularity was almost immediate, generating more than 1 million users within five days of its debut. And now businesses, organizations and AI professionals are not only trying to determine how this piece of innovative technology will impact everyday operations but also what it means for the field of artificial intelligence and related careers.

ChatGPT is an artificial intelligence chatbot that interacts with humans and produces conversational text. It was developed by the company OpenAI, which was originally founded in 2015 by Elon Musk and a handful of other Silicon Valley investors.

The company explains that the dialogue format of ChatGPT makes it possible to “answer follow-up questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests.” ChatGPT also has a sister application called InstructGPT , which follows instructions and provides detailed responses.

In an interview with a San Diego news station , Dr. Anna Marbut, a professor at the University of San Diego’s Applied Artificial Intelligence Master of Science program , explained that ChatGPT’s responses, which mimic how humans communicate, is what makes the technology so exceptional.

How Does ChatGPT Work?

This artificial intelligence application uses machine learning and natural language processing to create conversational, human-sounding responses to written prompts. ChatGPT was developed and trained with a variety of data, including books, articles and conversations, and as a result, it can understand many topics. The chatbot remembers your dialogue thread and essentially produces a conversation. Users have found ChatGPT can create :

Poetry and wedding vows
Cover letters
Job descriptions
Abstracts for scientific articles
Product descriptions
Social media content

Additionally, the chatbot can help with research, brainstorming and writing by handling calculations, checking spelling and grammar or functioning as a thesaurus or dictionary. Users can also replace a typical Google search with a question to ChatGPT, although it (currently) won’t provide all the functions of a search engine, such as location-specific answers (unless you specifically ask) or links to other sources.

ChatGPT Concerns & Challenges

ChatGPT is an artificial intelligence chatbot fueled by information; in other words, it’s a machine — not a person — which means there will be misunderstandings and miscommunication, especially since the technology is still evolving. Here are some of the major concerns and challenges:

Creation of false material. In one case, ChatGPT was used to create false articles from The Guardian, a British newspaper.
Plagiarism and cheating in education. While the tool can be used effectively in the classroom, educators are already dealing with issues of plagiarism and cheating. According to a recent Forbes article, 89% of surveyed students reported using ChatGPT for a homework assignment; 48% admitted to using it for an at-home test or quiz and 53% had the chatbot write an essay.
Threats to certain jobs. The idea of robots replacing human workers is nothing new, but ChatGPT has once again fueled the conversation about whether AI can effectively execute certain tasks faster than a person. According to a recent Goldman Sachs report, artificial intelligence — including new platforms like ChatGPT — could affect up to 300 million jobs around the globe.
Privacy concerns. Privacy has always been an AI ethical concern , but according to CNN , the chatbot recently had a bug that allowed users to access personal information from others. After OpenAI disclosed the data breach, Italy issued a temporary ban on ChatGPT.

Prof. Marbut “admitted ChatGPT does not come without concerns.” The chatbot does provide disclaimers in their terms of use : “Artificial intelligence and machine learning are rapidly evolving fields of study. We are constantly working to improve our Services to make them more accurate, reliable, safe, and beneficial. Given the probabilistic nature of machine learning, use of our Services may, in some situations, result in Output that does not accurately reflect real people, places, or facts.”

ChatGPT Implications For the Field of Artificial Intelligence

It may be too soon to predict ChatGPT’s widespread effects on the field of AI, but the chatbot is already influencing the job market and AI technology.

The company Resume Builder recently surveyed 1,000 business leaders about ChatGPT and discovered that 49% are already using the chatbot. Almost half (48%) say that ChatGPT has already replaced workers, and an overwhelming majority (90%) report that ChatGPT experience is an advantageous skill for job seekers.

Job postings on popular sites like LinkedIn and Indeed are already including ChatGPT familiarity as a desired skill.

ChatGPT is also making waves with other technology companies — most notably Google, which issued a “Code Red ” after the chatbot’s debut, meaning the ChatGPT was considered a major threat to the popular search engine.

The “Code Red” declaration resulted in the return of Larry Page and Sergey Brin, Google’s co-founders who had left their day-to-day positions at the company. After ChatGPT’s debut, Page and Brin returned to help prioritize Google’s own AI capabilities.

Opportunities for AI Professionals

While there are concerns about ChatGPT and other technology platforms eliminating certain positions, the reality is there will be increasing demand for AI professionals who can help develop and advance similar technologies as companies look to compete with ChatGPT.

In a recent article, AI researcher Osman Ramadan explained that his extensive experience has taught him that “companies can’t rely solely on a bot, which is liable to produce erroneous and prejudiced content. Instead, he thinks ChatGPT will be used as a tool to boost productivity rather than replace professionals.”

In general, artificial intelligence careers are booming — and there’s no doubt ChatGPT and similar platforms will lead to even more positions in the field. Popular AI careers include:

Big data analyst
Natural language processing engineer
Research scientist
Software engineer
AI engineer
AI developer
Machine learning engineer
Business intelligence analyst
Robotics engineer

The Future of AI Careers and ChatGPT

While ChatGPT is still considered relatively new, its effects on the world of artificial intelligence are already far-reaching. Expedia , the popular trip-planning company, has incorporated ChatGPT in its mobile app to help travelers with finding attractions and hotels and answering other travel-related questions.

Companies are using ChatGPT as a coding tool and a personal assistant; others are using the software to write emails and conduct keyword research.

Plus, articles about the best ChatGPT alternatives are already surfacing as start-ups and other technology companies look to compete with the popular chatbot.

While this innovative technology is still evolving, one thing is clear — artificial intelligence professionals will need to stay on top of the latest developments and information in order to successfully work with AI platforms like ChatGPT.

Continuing education is an excellent way to obtain this much-needed experience, and USD’s Master of Science in Applied Artificial Intelligence curriculum not only provides a comprehensive overview of the field but also covers the latest trends and information, including natural language processing developments and ethics in AI.

Interested in Exploring an Artificial Intelligence Master’s Degree?

With artificial intelligence driving innovation across nearly all industries, employers are seeking skilled AI professionals and paying top dollar to hire them. And since nearly all artificial intelligence jobs require a master’s degree, there are numerous academic programs to choose from. Download our eBook — 8 Questions to Ask Before Selecting an Applied Artificial Intelligence Master’s Degree Program — to help you find the right program for your career goals.

Be Sure To Share This Article

Share on Twitter
Share on Facebook
Share on LinkedIn

Considering a Master’s in Artificial Intelligence?

Free checklist to help you compare programs and select one that’s ideal for you.

Cover of 8 Questions to Ask Before Selecting an Artificial Intelligence Master's Degree Program Book

Master of Science in Applied Artificial Intelligence

IMAGES

How To Use Chat Gpt To Write An Essay With Ease
How To Use ChatGPT To Write An Essay in 3 Easy Steps
10+ How to Use ChatGPT to Write an Essay
How to Catch a ChatGPT Cheat: 7 Practical Tips
How To Use ChatGPT To Write An Essay: Now Anyone Can Write An Essay
How to Use ChatGPT to Write an Essay: Mastering Essay Writing

VIDEO

How to Use ChatGPT to Write an ESSAY EASY Essay Writing
Should You Use ChatGPT? (Part 2 of 2)
Should You Use ChatGPT? (Part 1 of 2)
How To Use ChatGPT To Write An Essay (2023)

COMMENTS

Free AI Detector
Scribbr's AI and ChatGPT Detector confidently detects texts generated by the most popular tools, like ChatGPT, Gemini, and Copilot. Our advanced AI checker tool can detect GPT2, GPT3, and GPT3.5 with high accuracy, while the detection of GPT4 is supported on an experimental basis. Note that no AI Detector can provide complete accuracy ( see ...
GPT Essay Checker
After you click the button, the AI essay detector will offer you several diagrams, a detailed analysis of the text, and all the necessary hints. Like СhatGPT itself, our AI checker is free to use. In addition, it does not contain intrusive advertising. It is up to you to decide if the text is Chat GPT generated or not.
ChatGPT
ChatGPT Detector quickly finds AI writing from ChatGPT, LLMs, Bard, and GPT-4. It's easy and fast to use!
Free AI Detector
Trained to identify certain patterns, our detection tool will flag AI-generated, paraphrased & human-written content in your text. AI-generated content is likely to contain repetitive words, awkward phrasing, and an unnatural, choppy flow. When these indicators are present, QuillBot's AI Detector will flag the text for further inspection.
How to Detect Text Written by ChatGPT and Other AI Tools
2. Writer AI Content Detector. Writer makes an AI writing tool, so it was naturally inclined to create the Writer AI Content Detector. The tool is not robust, but it is direct. You paste a URL or ...
How to Tell If an Article Was Written by ChatGPT
Tools to Check If An Article Was Written By ChatGPT. You can find multiple copy-and-paste tools online to help you check whether an article is AI generated. Many of them use language models to scan the text, including ChatGPT-4 itself. Undetectable AI, for example, markets itself as a tool to make your AI writing indistinguishable from a human's.
How to Detect ChatGPT Use in Writing: AI Signs, Tools + More
Tools like OpenAI's Text Classifier, GPTZero, and Copyleaks can check writing for ChatGPT, LLaMA, and other AI language model use. ChatGPT often produces writing that looks "perfect" on the surface but contains false information. Some signs that ChatGPT did the writing: A lack of descriptive language, words like "firstly" and "secondly," and ...
Can AI detectors save us from ChatGPT? I tried 5 online tools to find
Content at Scale AI Content Detection: 100% Highly likely to be human! GPTZero: Your text is likely to be written entirely by a human. ZeroGPT: 28.9% AI GPT Your Text is Most Likely Human written ...
Mozilla Foundation
Microsoft, the maker of Bing and biggest investor in Open AI, is okay with this. ChatGPT, and the latest release GPT-4, provides thorough answers — it can even write your code, write your cover letter and pass your law exam. It also provides thoroughly wrong answers sometimes. It's worrying how confidently ChatGPT presents inaccurate ...
A college student made an app to detect AI-written text : NPR
Edward Tian, a 22-year-old computer science student at Princeton, created an app that detects essays written by the impressive AI-powered language model known as ChatGPT. Tian, a computer science ...
How to Detect OpenAI's ChatGPT Output
This results in a dilemma for educators where it is very difficult to discern if the student wrote the essay or ChatGPT wrote the essay. They would need some kind of tool to check this.
The Trusted AI Detector for ChatGPT, GPT-4, & More
See if there is a history of AI-generated text in the student's work. We recommend looking for a long-term pattern of AI use, as opposed to a single instance, in order to determine whether the student is using AI. ... The sentence-level classification should not be solely used to indicate that an essay contains AI (such as ChatGPT plagiarism ...
Student Built App to Detect If ChatGPT Wrote Essays to Fight Plagiarism
A Princeton student built an app that aims to tell if essays were written by AIs like ChatGPT. The app analyzes text to see how randomly it is written, allowing it to detect if it was written by AI.
How teachers can tell if a student has used ChatGPT in an essay
Experts have revealed the tell-tale signs that an essay has been written by ChatGPT and not a student. It comes after the rise of generative AI tools, like ChatGPT, has sparked concerns about ...
How to Write an Essay with ChatGPT
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.
How can i detect Essays wrote by the AI from my students?
There are a few ways you can tell if an essay has been written by an AI: Lack of personal touch: AI-generated essays may lack the personal touch and style of a human writer. They may also contain repetitive phrasing or language. Absence of emotions: AI-generated essays may not convey emotions or feelings in the same way that a human writer ...
GPTZero: how to detect ChatGPT plagiarism
GPTZero is a web app and service designed to detect whether a body of text has been written by a human or by an artificial intelligence. Tian, a 22-year-old undergraduate studying computer science ...
How to Detect If a Student Used ChatGPT: Tips and Tricks
Writer AI Content Detector is a tool that allows you to paste a URL or text into the tool, and it will analyze the content to determine if it was generated by an AI tool. Another option is the AI ...
ChatGPT Detector for Essay Writing
Like Chat GPT itself, this AI essay detector is 100% free both for students and teachers. 🚀 Effective. The AI detection tool is not perfect, yet more effective than traditional plagiarism checkers. 🎓 Developed for students. We've developed our Chat GPT detector so that you can check any piece of academic writing.
OpenAI's new tool may help you identify text written by ChatGPT
OpenAI has released a tool to help you determine whether text was more likely written by a human or AI. However, the ChatGPT maker warns that its equivalent of Blade Runner 's Voight-Kampff test ...
How to Detect if Students are Using ChatGPT for Their Essays
Tool to test whether your students are using ChatGPT. The most accurate tool to check if students are using ChatGPT is called Winston A.I . Winston A.I is free to try out and you can test an article to see if your students are using ChatGPT or other A.I Tools. They have an accuracy rate of 99%. Test out Winston A.I here. Orginality.AI is ...
How to detect ChatGPT plagiarism
But ChatGPT fooled most of these detector apps with its response too. It scored a 99% human on the Writer AI Content Detector app, for starters, and was marked just 36% fake by GPT-based detector ...
How a teacher checks students work for AI
Teacher devises an ingenious way to check if students are using ChatGPT to write essays. This video describes a teacher's diabolical method for checking whether work submitted by students was ...
We tested Turnitin's ChatGPT-detector for teachers. It got some wrong
Five high school students helped our tech columnist test a ChatGPT detector coming from Turnitin to 2.1 million teachers. It missed enough to get someone in trouble. Lucy Goetz, a student at ...
ChatGPT
Just ask and ChatGPT can help with writing, learning, brainstorming and more. Start now (opens in a new window) ... Improve my essay writing ask me to outline my thoughts ... Explore the GPT store and see what others have made. ChatGPT Plus users can also create their own custom GPTs. ...
Is ChatGPT Down? 5 Ways to Check If ChatGPT Is Working
Check OpenAI for real-time server analysis. Follow OpenAI's X account for updates. Use Downdetector to check ChatGPT's status for other users.
Fix: ChatGPT "Internal Server Error" and Other Common Errors
OpenAI has a ChatGPT Plus account that you can subscribe to by clicking the "Upgrade to Plus" button in the lower-left corner of a ChatGPT conversation or side menu. This provides you with access to the chatbot "even when demand is high" so you're less likely to see "at capacity" errors.
Is it Worth Using ChatGPT to Write Your Resume? Let's Find Out
In my opinion, it's not really a matter of should vs. should not. ChatGPT can be a great resource to help you write or update your resume if you use the right prompts. AI gives you three main superpowers: Speed: Tools like ChatGPT can create content quickly and save you time.
How to Write an Essay with ChatGPT
Writing a research question. 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".
The Impact of ChatGPT on AI Careers
The artificial intelligence application ChatGPT debuted in late 2022 and has been making headlines ever since. Its popularity was almost immediate, generating more than 1 million users within five days of its debut. And now businesses, organizations and AI professionals are not only trying to determine how this piece of innovative technology will impact everyday operations but also what it ...

GPT Essay Checker for Students

🤖 Will AI Replace Human Writers?

Chat GPT in Essay Writing – the Shortcomings

🕵 How Do GPT Checkers Work?

❓ GPT Essay Checker FAQ

Check if Something Was Written by ChatGPT: AI Detection Guide

How AI Detection Tools Work

Things You Should Know

Expert Q&A

You Might Also Like

About This Article

Is this article up to date?

Featured Articles

Trending Articles

Watch Articles

Can AI detectors save us from ChatGPT? I tried 5 online tools to find out

Online AI plagiarism checkers

Overall results

GPT-2 Output Detector (Accuracy 60%)

Writer.com AI Content Detector (Accuracy N/A)

Content at Scale AI Content Detection (Accuracy 40%)

GPTZero (Accuracy 80%)

ZeroGPT (Accuracy 80%)

Writefull GPT Detector (Accuracy 60%)

Final thoughts

Artificial Intelligence

Connect People

Rally Communities

Influence Policies

Research & Analysis

Opportunites

Community Impact

Featured Posts

Popular topics

Did ChatGPT Write This? Here’s How To Tell.

How to Detect ChatGPT Text Yourself?

Detecting ChatGPT Text: The Caveats

How to Spot Misinformation Within ChatGPT?

Chat GPT Is Fun, But Watch Out

Related content

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

How GPTZero works

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

The quest to curb AI plagiarism

Untangling Disinformation

More than an AI detector Preserve What's Human

Our Commitment as the Leader in AI detection

The First in Detection

Results You Can Trust

Best In-Class Benchmarking

Cutting Edge Research

Debiased AI Detection

Military Grade Security

Discover our Detection Dashboard

Source scanning

Leading research in AI content detection modeling

Quantify AI with Deep Scan

Unlock More of GPTZero

writing report

AI detection API

AI Text Detection and Analysis Trusted by Leading Organizations

General FAQs about our AI Detector

What is GPTZero?

How do I use GPTZero?

When should I use GPTZero?

Does GPTZero only detect ChatGPT outputs?

Why GPTZero over other detection models?

What are the limitations of the classifier?

What can I do as an educator to reduce the risk of AI misuse?

I'm an educator who has found AI-generated text by my students. What do I do?

What data did you train your model on?

How do I use and interpret the results from your API?

Are you storing data from API calls?

How do I cite GPTZero for an academic paper?

A Princeton student built an app which can detect if ChatGPT wrote an essay to combat AI-based plagiarism

UK Edition Change

Thank you for registering

How teachers can tell if a student has used ChatGPT in an essay

Sign up for a full digest of all the best opinions of the week in our Voices Dispatches email

Join our commenting forum