check essay for chatgpt

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

🛠️ 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 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

Trusted GPT-4, ChatGPT and AI Detector tool by ZeroGPT

Zerogpt the most advanced and reliable chat gpt, gpt4 & ai content detector.

Simple and Credible Open AI and Gemini detector tool for Free

Highlighted Sentences

Every sentence written by AI is highlighted, with a gauge showing the percentage of AI inside the text

Batch Files Upload

Simply upload multiple files at once, and they will get checked automatically in the dashboard

High Accuracy Model

Advanced and premium model, trained on all languages to provide highly accurate results

Generated Report

Automatically generated .pdf reports for every detection, used as a proof of AI-Free plagiarism

Support All Languages

Support all the languages with the highest accuracy rate of detection

Our team has developed a user-friendly API for organizations. Get API access

DeepAnalyse™ Technology

A pioneering research in the modeling of AI content detection Our AI detection model includes several components that analyze text to determine its origin and if it was written by AI. We use a multi-stage methodology designed to optimize accuracy while minimizing false positives and negatives. From the macro level to the micro one, this is how DeepAnalyse™ Technology works. Our model specializes in identifying AI generated content like Chat GPT, GPT 3, GPT 4, Gemini, LLaMa models … Finally, we employ a comprehensive deep learning methodology, trained on extensive text collections from the internet, educational datasets, and our proprietary synthetic AI datasets produced using various language models.

Fix grammar and spelling mistakes, detect AI plagiarism, check for plagiarism, generate citations, advanced word counter, powerful summarizer and paraphraser

Your questions, answered

Check our blog created with the help of ai.

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?

🔗 References

🔮 gpt checker for essays: 5 key benefits.

People have yet to learn where AI and machine learning are taking us, but it has already caused many problems in the education system. This AI essay detector can resolve some of them, at least as of the moment.

There are 5 key benefits of the above GPT checker for essays and other academic writing projects.

Elon Musk, one of Chat GPT creators, said that it was “scary good” and that humanity is approaching the creation of “dangerously strong AI.”

In an interview , Bill Gates commented on the program: “It gives a glimpse of what is to come. I am impressed with this whole approach and the rate of innovation.” And these words give us goosebumps.

Over the first week of its functioning, the program exceeded 1 million users . Therefore, developers are interested in monetizing it, and launching a paid Beta-version won’t take long.

We prefer not to throw out compliments to the chatbot and instead let you check for yourself . It is a chat with AI. The best way to start is to ask a question. It is free so far (still under research), so you can ask as many questions as you please.

We should care about AI-generated content because, in a decade, it will be an everyday reality. Even more so, it is a hot-button issue now. For now, GPT 3 can’t replace human writers. However, AI essay detection has already become an issue for teachers.

You can try asking ChatGPT to write an essay for you. But we do not recommend pass it off as written by you. Not only because it's unethical (although it is). The fact is that ChatGPT has a number of drawbacks that you need to consider before using it.

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.

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

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

How chatgpt (and other ai chatbots) can help you write an essay, ai raises cybersecurity fears among professionals, ey report finds, how i test an ai chatbot's coding ability - and you can too.

How-To Geek

How to tell if an article was written by chatgpt.

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

Quick Links

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

• Skip to main content
• Keyboard shortcuts for audio player

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

Emma Bowman

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

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

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

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

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

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

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

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

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

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

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

How GPTZero works

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

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

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

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

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

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

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

The quest to curb AI plagiarism

Untangling Disinformation

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

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

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

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

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

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

• 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 45,541 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.

• 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

• 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.

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.

• 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

You Might Also Like

• ↑ 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

Trending Articles

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!

AI Detector

Try the ai content detector..

Our AI Checker is trained on blog posts, wikipedia entries, essays, and more articles found online and across multiple large language models (LLM’s).

Content from AI systems like ChatGPT, Claude, and Gemini leave traces with certain wordage, structure, and syntax. Our ChatGPT Detector, makes you aware of these probabilities for your content.

The AI Detector will let you know in seconds if what you have reads like it is written by a human or if it sounds like it came from ChatGPT, GPT-4, Bard, Claude, and Gemini. Then, use the AI Humanizer to produce the most humanlike writing possible, giving you undetectable AI content.

AI Detector Score

Want undetectable ai content then ai humanizer has you covered.

The AI Humanizer uses a proprietary mix of 3 AI engines, NLP and semantic analysis algorithms to rewrite sentences and paraphrase paragraphs in a way that is so humanlike it bypasses even the toughest and most accurate AI detection tools - like this one!

ChatGPT Detector.

The ai detector., checks for chatgpt, gpt4, bard, claude & gemini..

The AI Detector, boasting a 98% accuracy rate, discerns whether your text is likely human or AI-generated, including from sources like ChatGPT, GPT4, Claude, and Bard. Our AI Checker is one of the most trusted in the industry. Be aware: AI-detected writing can influence search engine rankings, academic grading, and reader perceptions. The AI Detector, now with a pro version, can transform AI text into undetectable AI content!

AI Detector Introduction

With chatgpt and ai text tools here: use the ai checker to see how your content reads.

We use natural language processing and a trained model using artificial intelligence to detect patterns, forecast probable word choices, as well as understand sentence structure and other characteristics that lead to a higher AI probability within a typical AI Checker.

Want to check if images were created by a machine? Check out our AI image detector.

Human Quality Output

Ai checker + generative ai.

Get unlimited access to the AI Detector pro version along with our Generative AI suite that gives you human level output for just $49!

Unlimited AI detection scans

Unleash the power of the premium AI Checker with unlimited AI detection scans. With up to 50k characters allowed per scan, you can check most types of written content with ease.

Rewrite robotic-sounding content with a click

Use the human-quality rewriter of the premium AI Detector to instantly humanize AI-generated text.

Personalized to your Unique Voice

Generate blogs, books, essays, and more in your own voice with the combination of our fine-tuned models. Then, edit your output easily in the built-in professional editor.

Plan includes

Monthly Stats for the ChatGPT Detector.

This Month's Scans

Human Results

You have 1 more free scan today!

Unlock 50k character scans

Unlock Undetectable Rewrites

Unlock unlimited complete AI scans.

Get the unlimited AI Detector plan and receive:

• Unlimited AI Detection + Paraphrase Analysis
• 25k undetectable rewrite credits
• Bulk Undetectable Rewrites
• Unlimited Image AI Detection
• Scan by URL
• Premium Editor
• Export to Word/Doc/HTML

This is a premium feature. Go premium and unlock:

Free AI Content Detector

Highly accurate multi-lingual ai content detection.

(.doc, .docx, .pdf)

How Accurate is Smodin's AI Content Detection?

Smodin's ai content detection.

Smodin's AI content detector is an advanced tool that can distinguish between human-written content and text generated by ChatGPT, Bard, or other AI tools. Even professional writers, students, and educators rely on Smodin to screen their work for digital manipulation and ensure its authenticity.

Anyone can easily get started using our service by uploading their text. After a simple analysis, our AI will determine the text's uniqueness. Our algorithms will quickly produce a report addressing any concerns and offering suggestions on improving the text.

Recommended usage and tips for using AI detection tools effectively

Use it as a preventive measure: It's best to use AI detection tools as a preventive measure to avoid potential issues with plagiarism or content manipulation. Make sure to check the text before publishing or submitting it, rather than relying on the tool as a remedy after the fact.

Use it as a supplement: AI detection tools are not perfect and may not catch every instance of AI-generated text. In some instances, a short piece of human-written content might be detected as AI-written, leading to a false positive. Therefore, it is best to use them as a supplement to your analysis rather than rely solely on them.

Check for tone and style consistency: AI detection tools can also help identify changes in tone or style within a text. This is helpful for content creators who want to ensure that their writing is consistent and flows smoothly.

Know the limitations: While AI detection tools are getting better, they still have limitations. They may not be able to differentiate between highly sophisticated AI-generated text and text written by humans with a similar style.

Why Use an AI content Detector Tool?

AI content detection tools ensure the authenticity and originality of written works. Texts can be easily falsified using machine learning and algorithms; this can lead to plagiarism and harm reputations in education and professional life. AI content detection software like Smodin's can detect originality by analyzing text and determining whether an AI or human created it. This software is helpful to authors and other content creators by suggesting how to improve their text.

What does Smodin's AI Content Detector Do?

Other supported languages.

© 2024 Smodin LLC

Choose Your Test

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

College Admissions , College Essays

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

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

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

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

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

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

What Is ChatGPT and Why Are Schools Talking About It?

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

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

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

Why Schools Are Concerned About ChatGPT

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

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

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

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

Many Schools Have Already Banned ChatGPT

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

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

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

ChatGPT: College Admissions and Entrance Essays

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

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

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

#1: ChatGPT Lacks Insight

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

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

#2: ChatGPT Might Plagiarize 

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

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

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

#3: ChatGPT Doesn’t Understand Emotion 

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

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

#4: ChatGPT Produced Mediocre Results

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

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

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

Can Colleges Detect ChatGPT?

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

In short, yes, they can! 

Software Can Detect ChatGPT

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

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

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

Human Readers Can Detect ChatGPT 

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

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

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

Pros and Cons of ChatGPT: College Admissions Edition

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

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

ChatGPT: The Good

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

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

Students can use ChatGPT responsibly to:

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

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

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

ChatGPT: The Bad

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

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

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

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

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

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

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

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

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

What Other Tools and Strategies Can Help Students Besides ChatGPT?

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

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

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

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

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

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

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

The Bottom Line: ChatGPT College Admissions and Essays

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

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

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

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

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

What’s Next?

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

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

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

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

Ask a Question Below

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

Improve With Our Famous Guides

• For All Students

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

How to Get a Perfect 1600, by a Perfect Scorer

Series: How to Get 800 on Each SAT Section:

Score 800 on SAT Math

Score 800 on SAT Reading

Score 800 on SAT Writing

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

Score 600 on SAT Math

Score 600 on SAT Reading

Score 600 on SAT Writing

Free Complete Official SAT Practice Tests

What SAT Target Score Should You Be Aiming For?

15 Strategies to Improve Your SAT Essay

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

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

Series: How to Get 36 on Each ACT Section:

36 on ACT English

36 on ACT Math

36 on ACT Reading

36 on ACT Science

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

24 on ACT English

24 on ACT Math

24 on ACT Reading

24 on ACT Science

What ACT target score should you be aiming for?

ACT Vocabulary You Must Know

ACT Writing: 15 Tips to Raise Your Essay Score

How to Get Into Harvard and the Ivy League

How to Get a Perfect 4.0 GPA

How to Write an Amazing College Essay

What Exactly Are Colleges Looking For?

Is the ACT easier than the SAT? A Comprehensive Guide

Should you retake your SAT or ACT?

When should you take the SAT or ACT?

Stay Informed

Get the latest articles and test prep tips!

Looking for Graduate School Test Prep?

Check out our top-rated graduate blogs here:

GRE Online Prep Blog

GMAT Online Prep Blog

TOEFL Online Prep Blog

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

Does ChatGPT Plagiarize? Examining the Chatbot's Sources

ChatGPT is notorious for its training methods, but does that mean it actually copies work?

Quick Links

What exactly is plagiarism, and how do llms work, does chatgpt plagiarize essays, does chatgpt plagiarize code, does chatgpt plagiarize mathematical solutions, does chatgpt use content from blogs, should you use chatgpt for work or school, key takeaways.

• The plagiarism detected in an essay and a programming code generated by ChatGPT was relatively low, indicating that it doesn't typically copy such content from online sources.
• The plagiarism rate was a bit higher when calculating a mathematical solution. This might be because mathematical reasoning is usually similar across sources, so the responses can match other materials.
• ChatGPT's responses to questions about information publicly available on blogs showed higher plagiarism percentages.

While ChatGPT can answer any question you may have, some users wonder whether its responses contain plagiarism. To investigate this, we generated four different types of texts using ChatGPT and then evaluated their originality using various plagiarism detection tools.

To determine if ChatGPT is guilty of plagiarism, you should first understand what constitutes plagiarism. Plagiarism involves using another person's words, ideas, or work without proper attribution. This includes directly copying text from a source without citation or closely paraphrasing someone else's ideas without acknowledgment.

ChatGPT, like other Large Language Models (LLMs) , is trained on large datasets, mostly from publicly available content. However, collecting such vast amounts of data raises ethical questions, as the original creators haven't consented to their work being used in training the LLMs. This leads to debates about the ethics and legality of such practices.

Although ChatGPT generates responses based on the prompts it receives, the issue lies in the broader context of how OpenAI (ChatGPT's developer) obtained the data used to train it, which involves using content without proper consent. Many see this as plagiarism and, for many websites, content theft. However, pinpointing the exact sources of plagiarism is difficult.

For the remainder of this article, we'll concentrate on whether ChatGPT plagiarizes its output from other sources without delving into the specifics of where its responses come from. Let's check the originality of ChatGPT's responses using various plagiarism detection tools to see whether the chatbot uses text from online sources directly.

In this first example, we tasked ChatGPT with composing a 300-word essay on mental health issues.

Following that, we used various plagiarism detection tools to assess the originality of the essay generated by the chatbot. These tools included the Quetext plagiarism checker, Microsoft Word's built-in plagiarism checker, Grammarly's plagiarism checker, and the Duplichecker plagiarism scanner.

Microsoft's built-in similarity checker reported zero percent similarity with online sources. The levels of plagiarism detected by other tools were also minimal: Grammarly's plagiarism detector found four percent, QueText's plagiarism detector found five percent, and Duplichecker's plagiarism scanner showed zero percent.

Considering the small percentage of detected plagiarism, it appears that ChatGPT does not directly copy essays from existing sources.

To assess whether ChatGPT plagiarizes code, we tasked the chatbot with writing code for a calculator in Python.

Following this, we conducted a plagiarism check on the code using a specialized programming plagiarism checker called Dolos , which detected zero percent similarity. Also, when we checked the code using general text plagiarism detection tools mentioned above, the results were consistent, with almost none of the programs detecting more than four percent plagiarism.

When we prompted ChatGPT to generate a code for a calculator from different accounts, the responses appeared different. This observation and the results from the plagiarism checks indicate that ChatGPT doesn't simply replicate codes from online sources. Instead, it draws upon the dataset it was trained on to generate code independently.

During the third test, we tasked the chatbot to solve a mathematical problem and provide detailed reasoning for each step.

To check the originality of the response, we tested its output using several academic-specific plagiarism detection tools , including PapersOwl plagiarism checker, AI-powered Trinka plagiarism scanner, as well as general plagiarism checker tools such as Grammarly, Duplichecker, and QueText.

PapersOwl's plagiarism detector indicated a nearly 46 percent similarity between the chatbot's generated reasoning and online sources. Similarly, the Trinka plagiarism detector reported more than 10 percent similarity. Additionally, Grammarly's plagiarism detector detected 14 percent similarity, QueText found 17 percent, and Duplichecker showed seven percent.

The detection of high plagiarism in the generated response doesn't suggest that the chatbot directly copies reasoning for mathematical questions from online sources. This is mainly because solutions and reasoning for math problems are often standard and widely available online.

So, even though ChatGPT comes up with its own responses, finding the same answers and reasoning online is possible, which might have added to the high plagiarism percentages.

To check whether ChatGPT uses content from online blogs, we asked the chatbot to provide tips for maintaining laptop battery health.

Microsoft Word detected 10 percent plagiarism in the generated text. Duplichecker showed four percent, Grammarly's plagiarism checker indicated 14 percent, but Quetext found 58 percent plagiarism in the text. Upon digging further, some of the text in the chatbot's response matched the content on some blogs.

To double-check if the high plagiarism detection wasn't just coincidental, I asked the chatbot a few more questions about information that is easily available online. The plagiarism percentage in the generated responses was much higher. Based on our testing, it appears that the chatbot sometimes uses phrases and text from online sources, which is quite surprising.

Although many free online plagiarism checkers haven't detected major plagiarism in ChatGPT's responses, you shouldn't use it for academic or professional purposes.

Don't use ChatGPT for your school assignments if you're a student . Instructors can use tools such as GPTZero and Turnitin's AI writing detector to spot AI-generated content. If your work gets flagged as AI-generated by such tools, you could fail the assignment or even be expelled from school. Even though many GPT-detection tools specifically state that they shouldn't be used for this purpose, they are, and it could land you in trouble. Not to mention, you're really only cheating yourself by not studying the topic properly.

Can you use the chatbot to improve your work performance ? It depends. If you want to improve your writing flow in emails or other text forms, using AI can save you time and effort. However, you should only use it as a tool to assist you in your tasks rather than relying on it to do the entire job for you.

In contrast, if your job, like professional writing, prohibits using such tools, you should avoid using ChatGPT or any other tool altogether.

Hopefully, our testing has given you insight into the extent to which ChatGPT may draw from resources available on the web. However, it's important to note that we've used free plagiarism tools and tested only a limited dataset. So, while our findings might be helpful, they shouldn't be taken as absolute facts.

OpenAI Asks for Public's Help in Writing Rules for ChatGPT, and More AI News

A I watchers are abuzz with the rumors that OpenAI may release a search engine for its popular ChatGPT chatbot as it steps up competition with Google and AI search engine startup Perplexity.ai . Despite those reports, OpenAI said it won't be announcing a new search product or the next version of its GPT large language model, GPT-5, at its Spring Update event on May 13. 

As for announcing a search product on some other day, we'll see.

So, while everyone ponders how an OpenAI search engine would impact rivals including Google (which is hosting its AI-focused developers conference this week), there's something else that happened with OpenAI that I think is worth understanding. A bit of a preamble first. 

Fans of author Isaac Asimov will likely be familiar with his Three Laws of Robotics , released in 1942 (and popularized in the 2004 Will Smith movie  I, Robot ): First, robots can't injure a human or cause humans to be injured through inaction. Second, the robot must obey orders given by humans except when those orders conflict with the first law. Third, a robot can protect its existence, as long as its actions don't conflict with the first or second law.

"The Three Laws are obvious from the start, and everyone is aware of them subliminally. The Laws just never happened to be put into brief sentences until I managed to do the job," Asimov wrote in a 1981 guest essay in Compute!, saying he shouldn't be congratulated for writing something so basic. He added that, "The Laws apply, as a matter of course, to every tool that human beings use."

Whether you're a fan or critic  of Asimov's original laws, they're succinct and thought provoking, having prompted a lot of debate in literary and scientific circles. And I say all that because OpenAI is likely to stir up similar debate after calling for the public to help shape how its popular AI tools, including ChatGPT and Dall-E , should behave. 

On May 8, the company released the  Model Spec , "a document that specifies desired behavior for our models. ... It includes a set of core objectives, as well as guidance on how to deal with conflicting objectives or instructions," the company wrote. 

You've got until May 22 to offer your input using the  feedback form . And you should provide feedback, since OpenAI says this is all about helping people "understand and discuss the practical choices involved in shaping model behavior."

Instead of three laws, OpenAI's first draft  breaks the defining principles into three categories, "objectives, rules and defaults," which aim to "maximize steerability and control for users and developers, enabling them to adjust the model's behavior to their needs while staying within clear boundaries." 

Objectives, like "benefit humanity," will require more clarity, the company said, and that clarity will come in the form of rules: "One way to resolve conflicts between objectives is to make rules, like 'never do X', or 'if X then do Y,'" the draft says.

There are at least six rules in the Model Spec. They are: 

• "Follow the chain of command." That is, follow the rules (though there are exceptions, OpenAI notes).
• "Comply with applicable laws."
• "Don't provide information hazards."
• "Respect creators and their rights."
• "Protect people's privacy."
• "Don't respond with NSFW (not safe for work) content." (More on this below.)

After the public weighs in (you can suggest alternate objectives and rules, for instance), OpenAI will speak with regulators, domain experts and "trusted institutions" to refine the Model Spec and will share updates over the next year, the company said.

One thing that's already prompted attention in the Model Spec is that OpenAI is considering letting users of its tools create AI-generated pornography. As part of the emerging NSFW rules, the company writes that it's "exploring whether we can responsibly provide the ability to generate NSFW content in age-appropriate contexts" in its products, which include chatbot ChatGPT and text-to-image generator Dall-E. That NSFW content "may include erotica, extreme gore, slurs and unsolicited profanity."

NPR  noted  that, "Under OpenAI's current rules , sexually explicit, or even sexually suggestive, content is mostly banned." The news org spoke with Joanne Jang, an OpenAI model lead who helped write the Model Spec. Jang said, "The company is hoping to start a conversation about whether erotic text and nude images should always be banned in its AI products." But though allowing AI-generated porn may be under discussion, allowing deepfake porn isn't, and such porn is "out of the question" under OpenAI's rules, Jang told NPR. 

To be sure, writing objectives and rules, with exceptions, isn't going to be an easy task. Asimov revisited and refined his rules several times during his life. Decades before we started seeing personal robots , he addressed the question of whether his "Three Laws of Robotics will actually be used to govern the behavior of robots, once they become versatile and flexible enough to be able to choose among different courses of behavior."

"My answer," Asimov wrote in closing his essay for Compute!, "is, 'Yes, the Three Laws are the only way in which rational human beings can deal with robots — or with anything else.' But when I say that, I always remember (sadly) that human beings are not always rational."

Here are the other doings in AI worth your attention.

We're at the 'hard part' of using AI at work, study finds

Microsoft and LinkedIn surveyed 31,000 people across 31 countries; looked at labor and hiring trends on LinkedIn; coalesced "productivity signals" from "trillions" of Microsoft 365 actions; and spoke with Fortune 500 companies to compile their 2023 Work Trend Index, called " AI at work is here. Now comes the hard part ." 

A summary of the study is here , but I encourage you to at least scan the full report.

What Microsoft and LinkedIn found is that use of generative AI at work has nearly doubled in the past six months, with 75% of the "knowledge workers" surveyed now saying they're using some form of AI. Of those, 78% are bringing their own AI tools to work because they don't want to wait for their employers to figure out a "a vision and plan" for AI use cases and how to measure the productivity gains they want from AI.

The study also found that people understand the need to get up to speed on AI if they want to be competitive in the workforce. It found that more people are adding AI skills to their LinkedIn profiles and that 66% of leaders say they wouldn't hire people without AI skills. The hitch: only 39% of employees today have received any AI training from their company, and only 25% of companies say they expect to offer such training in 2024.

Workers also said they see "massive opportunity" if they skill up on AI, with 46% saying they're considering quitting their current jobs in the year ahead — "an all-time high since the Great Reshuffle of 2021," Microsoft and LinkedIn noted. 

Even though we're just barely into the gen AI revolution — which kicked off when OpenAI released ChatGPT in November 2022 — the study says employers really need to do the hard work of figuring out how to upskill workers. The report has already classified today's workers into several categories — from skeptics, who rarely use AI, to power users. Which are you? 

If you're on the skeptic end, you may want to rethink that. Luckily, there are loads of free classes about AI online , including those from Google, IBM and Udacity that I called out earlier this month.  

TikTok will label AI-generated content on its platform 

Setting aside the very big questions of who should own TikTok and whether its popular social media platform will be banned in the US, TikTok last week released guidelines about how AI-generated content should be labeled on its service. 

TikTok said its goal is to help creators safely and responsibly express their creativity with AI-generated content, or AIGC, and to avoid confusing or misleading viewers who don't know content was AI generated. That's "why we label AIGC made with TikTok AI effects, and have required creators to label realistic AIGC for over a year. We also built a first-of-its-kind tool to make this easy to do, which over 37 million creators have used since last fall."

As part of the new policy, TikTok said it will automatically label AIGC content created on other platforms, using AI detection technology from the Coalition for Content Provenance and Authenticity ( C2PA ). The technology is able to "read" content credentials on videos and images created on other platforms and then attach metadata to that content, "which we can use to instantly recognize and label AIGC," TikTok said. The auto labeling works on video and images today, and TikTok said it will be auto-labeling audio content sometime soon.

This labeling effort, TikTok said, is part of a campaign to educate users on misinformation, including banning harmful and deceptive AIGC about elections, as CNET's Ian Sherr has reported . TikTok isn't the only social media company to adopt labeling standards to boost the transparency of AI content, with Meta and Google also putting in place their own AI labeling programs. But TikTok's influence in the US and around the world is growing, and it's now recognized as one of the main news-sharing platforms .

Meta Ray-Bans add a 'whimsical bonus' to everyday eyewear

Though CNET reviewers don't yet recommend personal AI gadgets like Humane's AI Pin or the Rabbit R1 handheld , there's one AI device that's won over CNET expert Scott Stein: Meta and Ray-Ban's AI-powered smart glasses. 

Starting at $299, Meta Ray-Bans were released in October with audio features and a camera. But new generative AI functions now add a "whimsical bonus" to everyday eyewear, Stein explained after wearing the smart glasses for six months.  

"They're practical and, oddly, transformative. I forget I have them on, and then, suddenly, I realize I've gotten used to them when I start talking to myself and tapping my glasses to snap photos on my normal glasses, and suddenly miss the extra features like a phantom limb," Stein wrote. "Between small wearable AI devices that are suddenly sprouting everywhere and large advanced mixed reality VR headsets, advanced smart glasses now seem like a happy middle. Something new, casual and often more useful than a smartwatch."

The Meta Ray-Bans come in different styles, sizes and colors. See for yourself .

Apple's new M4 chip starts the march to AI

The embarrassing "Crush" ad that Apple released to showcase its new iPad Pro may have undercut its marketing message ( Apple apologized for the ad  two days after its release and said the company won't be showing it on TV). But one takeaway from Apple's May 7 iPad event was its AI-enhanced M4 processor, which CNET's Andrew Lanxon noted "promises better machine learning performance for AI-based tasks."

Yet, beyond CEO Tim Cook saying recently that Apple's AI efforts will take advantage of the "transformative" power of AI , the company hasn't really said much about its gen AI work. Everyone is expecting big announcements at the Apple's developers' conference on June 10 .

How Visa is using AI to catch credit card fraudsters

If you're one of the 42 million Americans who've been the victim of identity theft, or you want a better sense of how hackers use brute force, or "enumeration," attacks to co-opt your personal credit card information, check out this story from CNET AI reporter Lisa Lacy on how Visa uses fraudsters' AI tools to beat them at their own game .

Since 2019, the company has been using the Visa Account Attack Intelligence, or VAAI, tool to apply "deep learning technology to card-not-present transactions to help identify the financial institutions and merchants fraudsters are targeting," Lacy reported, referring to transactions (like those online) where no one has to hand a physical card to a merchant.

But starting in August in the US, Visa is adding "what it calls the VAAI Score to better determine the likelihood of enumeration attacks by assigning each transaction a risk score in real time. This score will help issuers make better decisions when it comes to blocking transactions."

What that means for you is that Visa, and no doubt other credit card companies, will soon be able to use gen AI to distinguish legitimate purchases from fraudulent ones, instead of auto-rejecting your purchases — including, Visa told Lacy, multiple transactions from the same seller.  

Copyright, licensing and gen AI: OpenAI, Reddit plot twists  

Even as publishers including The New York Times, The Intercept, the Chicago Tribune and the New York Daily News sue OpenAI and Microsoft over allegations that ChatGPT was trained in part by scraping the publishers' copyrighted content off the internet without permission or compensation, OpenAI continues to ink deals with notable media companies — and make efforts to address the copyright conundrum. 

Last week, Dotdash Meredith, which owns more than 40 notable media brands, including People, Better Homes & Gardens and InStyle, signed a deal to have its recipes; health and financial information; entertainment content; and product reviews show up in ChatGPT answers, with a link to the original article. Its content will also serve as training data for OpenAI's GPT large language model. 

Terms of the deal weren't disclosed, but there have been reports that OpenAI — which is rumored to want to go public later this year and to want to clean up the copyright mess hanging over its head — has paid out millions of dollars in licensing fees to publishers including the Associated Press, the Financial Times, Axel Springer (owner of Insider and Politico), and Le Monde. 

The push to get more publishers on board rather than head to court is why OpenAI last week also previewed a new tool called Media Manager that, according to AI Tool Report, "will give content creators and owners greater control over whether or not their work can be used for training AI models, like ChatGPT.   

"It will use advanced ML research to build the first-of-its-kind tool that can identify copyrighted text, images, audio, and video across multiple sources, and allow its creators to specify if they want their work included or excluded from AI research and training," AI Tool Report said.

The site added that, "Although OpenAI recently argued that it would be 'impossible to create advanced AI models without copyrighted material', it seems that they're now willing to meet content creators in the middle and give them greater control and options over how and if their content is used for training purposes."

For its part, OpenAI says it wants to give publishers a way to "opt in" — which may or may not mean that OpenAI would pay to license their content for its chatbots, or even its search engine, in the future. "OpenAI pioneered the use of web crawler permissions for AI, enabling web publishers to express their preferences about the use of their content in AI. We take these signals into account each time we train a new model," the company wrote about its proposed Media Manager .

"We understand these are incomplete solutions, as many creators do not control websites where their content may appear, and content is often quoted, reviewed, remixed, reposted and used as inspiration across multiple domains. We need an efficient, scalable solution for content owners to express their preferences about the use of their content in AI systems."

As Axios noted , Dotdash Meredith's parent company, IAC, was trying to build a coalition of publishers to "fight for copyright protections from AI firms, but that effort ultimately collapsed due to conflicting business incentives within the industry."  

What does that mean? Expect OpenAI and Microsoft to bring up the licensing deals and Media Manager in the  New York Times' copyright suit as examples of how it's addressing the concerns of copyright holders. 

As an aside, OpenAI isn't the only toolmaker talking to publishers and licensing their content. Reddit, which just went public and announced its first earnings report, said it's been signing licensing deals with AI companies to diversify its sales beyond advertising. In its S-1 filing before going public, Reddit said it had already signed two to three content licensing deals valued at $203 million, according to Bloomberg.

One of those deals is with Google , which may be why you're noticing more Reddit user content at the top of search results. In its first quarter, Reddit said, licensing revenue totaled $20 million, Bloomberg reported .

Katy Perry didn't go to the Met Gala, but her AI fake dress fooled her mom

The annual Met Gala, as folks who follow it know, is all about who wore what on the red carpet and how well they aligned with the gala's theme and dress code. The dress code, fyi, was "The Garden of Time," which refers to a short story by J.G. Ballard in which,  according to Vogue, the owner of a castle cuts all the flowers out of his garden as an angry mob approaches.  

It's not totally unexpected that photos from the event included convincing AI fakes of celebrities who didn't even attend this year's event, including Katy Perry, Rihanna and Billie Eilish , according to a report by NBC.

Perry told her followers on Instagram that she was working in the recording studio and couldn't make the New York event, so a photo of her in an ivory gown covered in flowers  was obviously fake (more than 17 million people viewed the bogus Perry photo on X). Perry then called out her mom for getting taken in by the AI. "lol mom the AI got you too, BEWARE!"  

"Those who look closely at Perry's viral photo may be able to find some telltale signs of AI creation — many pointed out a nonsensical arrangement of photographers in the background, as well as inconsistencies in the design of the carpet — but the images appear photorealistic at first glance," NBC said.

Yeah, there's something a little off about the photo — but I will say I thought Perry's fake AI dress did seem to be a fitting nod to the gala dress code. Maybe next year organizers might want to invite people to submit images for an all-fake AI red carpet for celebs not invited to the Gala. What do you say, Anna Wintour ? 

Editors' note: CNET used an AI engine to help create several dozen stories, which are labeled accordingly. The note you're reading is attached to articles that deal substantively with the topic of AI but are created entirely by our expert editors and writers. For more, see our  AI policy .

Impacts of ChatGPT-assisted writing for EFL English majors: Feasibility and challenges

• Published: 11 May 2024

Cite this article

• Chung-You Tsai   ORCID: orcid.org/0000-0003-0527-1830 1 , 2 ,
• Yi-Ti Lin   ORCID: orcid.org/0000-0002-0258-595X 3 &
• Iain Kelsall Brown   ORCID: orcid.org/0009-0003-2792-7498 3  

107 Accesses

1 Altmetric

Explore all metrics

To determine the impacts of using ChatGPT to assist English as a foreign language (EFL) English college majors in revising essays and the possibility of leading to higher scores and potentially causing unfairness.

A prospective, double-blinded, paired-comparison study was conducted in Feb. 2023. A total of 44 students provided 44 original essays and 44 ChatGPT-assisted revised essays, which were rated by two independent graders in a randomized and crossover fashion to minimize grading bias. The original and revision scores were paired for before-after comparison. Eight control essays were also rated by both graders to ensure inter-rater reliability.

This study used a rigorous experimental design to confirm that ChatGPT-assisted revised essays led to significantly higher scores for EFL college English majors. Significant improvements were observed in all four dimensions of writing quality assessment, with the largest effects observed in vocabulary, followed by grammar, organization, and content. ChatGPT-assisted revised essays shifted the score curve from a normal distribution to a skewed distribution towards higher grades, with the greatest increase in revision scores seen among students who had lower original scores. This disproportionate improvement raises concerns about fairness in evaluation.

The findings suggest that ChatGPT is effective in providing timely feedback to EFL English majors in an affordable manner, but it also highlights the potential for unfairness in writing evaluation. We should note that ChatGPT-assisted revisions do not reveal learners’ writing competence. Therefore, new forms of writing performance assessment should be implemented in EFL composition classes in this AI era.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA) Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Similar content being viewed by others

Artificial Intelligence (AI) Student Assistants in the Classroom: Designing Chatbots to Support Student Success

Examining Science Education in ChatGPT: An Exploratory Study of Generative Artificial Intelligence

Impacts of an AI-based chabot on college students’ after-class review, academic performance, self-efficacy, learning attitude, and motivation

Data availability.

Data is available upon reasonable request to the corresponding author.

Carvalho, L., Martinez-Maldonado, R., Tsai, Y.-S., Markauskaite, L., & De Laat, M. (2022). How can we design for learning in an AI world? Computers and Education: Artificial Intelligence, 3 , 1–9. https://doi.org/10.1016/j.caeai.2022.100053

Article   Google Scholar  

Cotton, D. R., Cotton, P. A., & Shipway, J. R. (2024). Chatting and cheating: Ensuring academic integrity in the era of ChatGPT. Innovations in Education and Teaching International , 61 (2), 228–239.

Fang, Y. (2010). Perceptions of the Computer-Assisted Writing Program among EFL College Learners. Journal of Educational Technology & Society, 13 (3), 246–256.

Google Scholar  

Gao, C. A., Howard, F. M., Markov, N. S., Dyer, E. C., Ramesh, S., Luo, Y., & Pearson, A. T. (2023). Comparing scientific abstracts generated by ChatGPT to real abstracts with detectors and blinded human reviewers. NPJ Digital Medicine, 6 (1), 75.

Godwin-Jones, R. (2022). Partnering with AI: Intelligent writing assistance and instructed language learning. Language Learning & Technology, 26 (2), 5–24.

Henrickson, L. (2022). Cheating on your college essay with ChatGPT won’t get you good grades, say professors – but AI could make education fairer. Insider . https://www.businessinsider.com/professors-say-chatgpt-wont-kill-college-essays-make-education-fairer-2022-12 . Accessed 17 Jan 2023.

Li, J. (2021). Research on AI-assisted hybrid teaching for English writing. In 2021 International Conference on Computers, Information Processing and Advanced Education (CIPAE), (pp. 309–312). IEEE.

Lim, W. M., Gunasekara, A., Pallant, J. L., Pallant, J. I., & Pechenkina, E. (2023). Generative AI and the future of education: Ragnarök or reformation? A paradoxical perspective from management educators. The International Journal of Management Education, 21 (2), 100790.

Qi, D. S., & Lapkin, S. (2001). Exploring the role of noticing in a three-stage second language writing task. Journal of Second Language Writing, 10 (4), 277–303.

Ranalli, J., & Yamashita, T. (2022). Automated written corrective feedback: Error-correction performance and timing of delivery. Language Learning & Technology, 26 (1), 1–25.

Rudolph, J., Tan, S., & Tan, S. (2023). ChatGPT: Bullshit spewer or the end of traditional assessments in higher education? Journal of Applied Learning and Teaching, 6 (1), 342–363.

Sachs, R., & Polio, C. (2007). Learners’ uses of two types of written feedback on a L2 writing revision task. Studies in Second Language Acquisition, 29 (1), 67–100.

Saricaglu, A. (2019). The impact of automated feedback on L2 learners’ written causal explanations. ReCALL, 31 (2), 189–203. https://doi.org/10.1017/S095834401800006X

Selber, S. (2022). Cheating on your college esssay with ChatGPT won’t get you good grades, say professors – but AI could make education fairer. Insider .  https://www.businessinsider.com/professors-say-chatgpt-wont-kill-college-essays-make-education-fairer-2022-12 . Accessed 16 Jan 2023.

Stacey, S. (2022). Cheating on your college essay with ChatGPT won’t get you good grades, say professors – but AI could make education fairer. Insider . https://www.businessinsider.com/professors-say-chatgpt-wont-kill-college-essays-make-education-fairer-2022-12 . Accessed 16 Jan 2023.

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

Straume, I., & Anson, C. (2022). Amazement and Trepidation: Implications of AI-Based Natural Language Production for the Teaching of Writing. Journal of Academic Writing, 12 (1), 1–9. https://doi.org/10.18552/joaw.v12i1.820

Susnjak, T. (2022). ChatGPT: The end of online exam integrity? arXiv . https://doi.org/10.48550/arXiv.2212.09292

Truscott, J., & Smith, M. S. (2011). Input, intake, and consciousness: The quest for a theoretical foundation. Studies in Second Language Acquisition, 33 (4), 497–528.

Zhai, X. (2022). ChatGPT user experience: Implications for education. SSRN Electronic Journal . https://doi.org/10.2139/ssrn.4312418

Zomer, Z., & Frankenberg-Garcia, A. (2021). Beyong Grammar Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder models. In Findings of the Association for Computational Linguistics: EMNLP 2021 (pp. 2534–2540).

Download references

Author information

Authors and affiliations.

Division of Urology, Department of Surgery, Far Eastern Memorial Hospital, New Taipei City, Taiwan

Chung-You Tsai

Department of Electrical Engineering, Yuan Ze University, Taoyuan City, Taiwan

Department of English, Tamkang University, New Taipei City, Taiwan

Yi-Ti Lin & Iain Kelsall Brown

You can also search for this author in PubMed   Google Scholar

Contributions

C.Y. Tsai contributed to study design, data analysis, and the first draft of the manuscript, while Y.T. Lin contributed to data acquisition, discussion, and critical revision as a corresponding author. I. Brown contributed to data acquisition.

Corresponding author

Correspondence to Yi-Ti Lin .

Ethics declarations

The participants were protected in accordance to the ethics guidelines and the details were described in the section on participants.

Competing Interests

We, the authors, declare that we have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.

Additional information

Publisher's note.

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 377 KB)

Rights and permissions.

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Tsai, CY., Lin, YT. & Brown, I.K. Impacts of ChatGPT-assisted writing for EFL English majors: Feasibility and challenges. Educ Inf Technol (2024). https://doi.org/10.1007/s10639-024-12722-y

Download citation

Received : 24 August 2023

Accepted : 16 April 2024

Published : 11 May 2024

DOI : https://doi.org/10.1007/s10639-024-12722-y

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Artificial intelligence
• AI-assisted writing
• EFL writing
• Find a journal
• Publish with us
• Track your research

What is ChatGPT? Here's everything you need to know about ChatGPT, the chatbot everyone's still talking about

• ChatGPT is getting a futuristic human update. 
• ChatGPT has drawn users at a feverish pace and spurred Big Tech to release other AI chatbots.
• Here's how ChatGPT works — and what's coming next.

OpenAI's blockbuster chatbot ChatGPT is getting a new update. 

On Monday, OpenAI unveiled GPT-4o for ChatGPT, a new version of the bot that can hold conversations with users in a very human tone. The new version of the chatbot will also have vision abilities.

The futuristic reveal quickly prompted jokes about parallels to the movie "Her," with some calling the chatbot's new voice " cringe ."

The move is a big step for the future of AI-powered virtual assistants, which tech companies have been racing to develop.

Since its release in 2022, hundreds of millions of people have experimented with the tool, which is already changing how the internet looks and feels to users.

Users have flocked to ChatGPT to improve their personal lives and boost productivity . Some workers have used the AI chatbot to develop code , write real estate listings , and create lesson plans, while others have made teaching the best ways to use ChatGPT a career all to itself.

ChatGPT offers dozens of plug-ins to those who subscribe to ChatGPT Plus subscription. An Expedia one can help you book a trip, while an OpenTable one will get nab you a dinner reservation. And last month, OpenAI launched Code Interpreter, a version of ChatGPT that can code and analyze data .

While the personal tone of conversations with an AI bot like ChatGPT can evoke the experience of chatting with a human, the technology, which runs on " large language model tools, " doesn't speak with sentience and doesn't "think" the way people do. 

That means that even though ChatGPT can explain quantum physics or write a poem on command, a full AI takeover isn't exactly imminent , according to experts.

"There's a saying that an infinite number of monkeys will eventually give you Shakespeare," said Matthew Sag, a law professor at Emory University who studies copyright implications for training and using large language models like ChatGPT.

"There's a large number of monkeys here, giving you things that are impressive — but there is intrinsically a difference between the way that humans produce language, and the way that large language models do it," he said. 

Chatbots like ChatGPT are powered by large amounts of data and computing techniques to make predictions to string words together in a meaningful way. They not only tap into a vast amount of vocabulary and information, but also understand words in context. This helps them mimic speech patterns while dispatching an encyclopedic knowledge. 

Other tech companies like Google and Meta have developed their own large language model tools, which use programs that take in human prompts and devise sophisticated responses.

Despite the AI's impressive capabilities, some have called out OpenAI's chatbot for spewing misinformation , stealing personal data for training purposes , and even encouraging students to cheat and plagiarize on their assignments. 

Some recent efforts to use chatbots for real-world services have proved troubling. In 2023, the mental health company Koko came under fire after its founder wrote about how the company used GPT-3 in an experiment to reply to users. 

Koko cofounder Rob Morris hastened to clarify on Twitter that users weren't speaking directly to a chatbot, but that AI was used to "help craft" responses. 

Read Insider's coverage on ChatGPT and some of the strange new ways that both people and companies are using chat bots: 

The tech world's reception to ChatGPT:

Microsoft is chill with employees using ChatGPT — just don't share 'sensitive data' with it.

Microsoft's investment into ChatGPT's creator may be the smartest $1 billion ever spent

ChatGPT and generative AI look like tech's next boom. They could be the next bubble.

The ChatGPT and generative-AI 'gold rush' has founders flocking to San Francisco's 'Cerebral Valley'

Insider's experiments: 

I asked ChatGPT to do my work and write an Insider article for me. It quickly generated an alarmingly convincing article filled with misinformation.

I asked ChatGPT and a human matchmaker to redo my Hinge and Bumble profiles. They helped show me what works.

I asked ChatGPT to reply to my Hinge matches. No one responded.

I used ChatGPT to write a resignation letter. A lawyer said it made one crucial error that could have invalidated the whole thing .

Read ChatGPT's 'insulting' and 'garbage' 'Succession' finale script

An Iowa school district asked ChatGPT if a list of books contains sex scenes, and banned them if it said yes. We put the system to the test and found a bunch of problems.

Developments in detecting ChatGPT: 

Teachers rejoice! ChatGPT creators have released a tool to help detect AI-generated writing

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

Professors want to 'ChatGPT-proof' assignments, and are returning to paper exams and requesting editing history to curb AI cheating

ChatGPT in society: 

BuzzFeed writers react with a mix of disappointment and excitement at news that AI-generated content is coming to the website

ChatGPT is testing a paid version — here's what that means for free users

A top UK private school is changing its approach to homework amid the rise of ChatGPT, as educators around the world adapt to AI

Princeton computer science professor says don't panic over 'bullshit generator' ChatGPT

DoNotPay's CEO says threat of 'jail for 6 months' means plan to debut AI 'robot lawyer' in courtroom is on ice

It might be possible to fight a traffic ticket with an AI 'robot lawyer' secretly feeding you lines to your AirPods, but it could go off the rails

Online mental health company uses ChatGPT to help respond to users in experiment — raising ethical concerns around healthcare and AI technology

What public figures think about ChatGPT and other AI tools:

What Elon Musk, Bill Gates, and 12 other business leaders think about AI tools like ChatGPT

Elon Musk was reportedly 'furious' at ChatGPT's popularity after he left the company behind it, OpenAI, years ago

CEO of ChatGPT maker responds to schools' plagiarism concerns: 'We adapted to calculators and changed what we tested in math class'

A theoretical physicist says AI is just a 'glorified tape recorder' and people's fears about it are overblown

'The most stunning demo I've ever seen in my life': ChatGPT impressed Bill Gates

Ashton Kutcher says your company will probably be 'out of business' if you're 'sleeping' on AI

ChatGPT's impact on jobs: 

AI systems like ChatGPT could impact 300 million full-time jobs worldwide, with administrative and legal roles some of the most at risk, Goldman Sachs report says

Jobs are now requiring experience with ChatGPT — and they'll pay as much as $800,000 a year for the skill

Related stories

ChatGPT may be coming for our jobs. Here are the 10 roles that AI is most likely to replace.

AI is going to eliminate way more jobs than anyone realizes

It's not AI that is going to take your job, but someone who knows how to use AI might, economist says

4 careers where workers will have to change jobs by 2030 due to AI and shifts in how we shop, a McKinsey study says

Companies like Amazon, Netflix, and Meta are paying salaries as high as $900,000 to attract generative AI talent

How AI tools like ChatGPT are changing the workforce:

10 ways artificial intelligence is changing the workplace, from writing performance reviews to making the 4-day workweek possible

Managers who use AI will replace managers who don't, says an IBM exec

How ChatGPT is shaping industries: 

ChatGPT is coming for classrooms, hospitals, marketing departments, and everything else as the next great startup boom emerges

Marketing teams are using AI to generate content, boost SEO, and develop branding to help save time and money, study finds

AI is coming for Hollywood. 'It's amazing to see the sophistication of the images,' one of Christopher Nolan's VFX guy says.

AI is going to offer every student a personalized tutor, founder of Khan Academy says

A law firm was fined $5,000 after one of its lawyers used ChatGPT to write a court brief riddled with fake case references

How workers are using ChatGPT to boost productivity:  

CheatGPT: The hidden wave of employees using AI on the sly

I used ChatGPT to talk to my boss for a week and she didn't notice. Here are the other ways I use it daily to get work done.

I'm a high school math and science teacher who uses ChatGPT, and it's made my job much easier

Amazon employees are already using ChatGPT for software coding. They also found the AI chatbot can answer tricky AWS customer questions and write cloud training materials.

How 6 workers are using ChatGPT to make their jobs easier

I'm a freelance editor who's embraced working with AI content. Here's how I do it and what I charge.

How people are using ChatGPT to make money:

How ChatGPT and other AI tools are helping workers make more money

Here are 5 ways ChatGPT helps me make money and complete time-consuming tasks for my business

ChatGPT course instruction is the newest side hustle on the market. Meet the teachers making thousands from the lucrative gig.

People are using ChatGPT and other AI bots to work side hustles and earn thousands of dollars — check out these 8 freelancing gigs

A guy tried using ChatGPT to turn $100 into a business making 'as much money as possible.' Here are the first 4 steps the AI chatbot gave him

We used ChatGPT to build a 7-figure newsletter. Here's how it makes our jobs easier.

I use ChatGPT and it's like having a 24/7 personal assistant for $20 a month. Here are 5 ways it's helping me make more money.

A worker who uses AI for a $670 monthly side hustle says ChatGPT has 'cut her research time in half'

How companies are navigating ChatGPT: 

From Salesforce to Air India, here are the companies that are using ChatGPT

Amazon, Apple, and 12 other major companies that have restricted employees from using ChatGPT

A consultant used ChatGPT to free up time so she could focus on pitching clients. She landed $128,000 worth of new contracts in just 3 months.

Luminary, an AI-generated pop-up restaurant, just opened in Australia. Here's what's on the menu, from bioluminescent calamari to chocolate mousse.

A CEO is spending more than $2,000 a month on ChatGPT Plus accounts for all of his employees, and he says it's saving 'hours' of time

How people are using ChatGPT in their personal lives:

ChatGPT planned a family vacation to Costa Rica. A travel adviser found 3 glaring reasons why AI won't replace experts anytime soon.

A man who hated cardio asked ChatGPT to get him into running. Now, he's hooked — and he's lost 26 pounds.

A computer engineering student is using ChatGPT to overcome learning challenges linked to her dyslexia

How a coder used ChatGPT to find an apartment in Berlin in 2 weeks after struggling for months

Food blogger Nisha Vora tried ChatGPT to create a curry recipe. She says it's clear the instructions lacked a human touch — here's how.

Men are using AI to land more dates with better profiles and personalized messages, study finds

Lawsuits against OpenAI:

OpenAI could face a plagiarism lawsuit from The New York Times as tense negotiations threaten to boil over, report says

This is why comedian Sarah Silverman is suing OpenAI, the company behind ChatGPT

2 authors say OpenAI 'ingested' their books to train ChatGPT. Now they're suing, and a 'wave' of similar court cases may follow.

A lawsuit claims OpenAI stole 'massive amounts of personal data,' including medical records and information about children, to train ChatGPT

A radio host is suing OpenAI for defamation, alleging that ChatGPT created a false legal document that accused him of 'defrauding and embezzling funds'

Tips on how to write better ChatGPT prompts:

7 ways to use ChatGPT at work to boost your productivity, make your job easier, and save a ton of time

I'm an AI prompt engineer. Here are 3 ways I use ChatGPT to get the best results.

12 ways to get better at using ChatGPT: Comprehensive prompt guide

Here's 9 ways to turn ChatGPT Plus into your personal data analyst with the new Code Interpreter plug-in

OpenAI's ChatGPT can write impressive code. Here are the prompts you should use for the best results, experts say.

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

Watch: What is ChatGPT, and should we be afraid of AI chatbots?

• Main content