gpt 3 essay writer

• Discovery Channel Shows
• The transcendence of cars
• French Revolution in Haiti (1976)
• Harry Potter is a Machine learning researcher

Celebrating 150 years of Harvard Summer School. Learn about our history.

Should I Use ChatGPT to Write My Essays?

Everything high school and college students need to know about using — and not using — ChatGPT for writing essays.

Jessica A. Kent

ChatGPT is one of the most buzzworthy technologies today.

In addition to other generative artificial intelligence (AI) models, it is expected to change the world. In academia, students and professors are preparing for the ways that ChatGPT will shape education, and especially how it will impact a fundamental element of any course: the academic essay.

Students can use ChatGPT to generate full essays based on a few simple prompts. But can AI actually produce high quality work, or is the technology just not there yet to deliver on its promise? Students may also be asking themselves if they should use AI to write their essays for them and what they might be losing out on if they did.

AI is here to stay, and it can either be a help or a hindrance depending on how you use it. Read on to become better informed about what ChatGPT can and can’t do, how to use it responsibly to support your academic assignments, and the benefits of writing your own essays.

What is Generative AI?

Artificial intelligence isn’t a twenty-first century invention. Beginning in the 1950s, data scientists started programming computers to solve problems and understand spoken language. AI’s capabilities grew as computer speeds increased and today we use AI for data analysis, finding patterns, and providing insights on the data it collects.

But why the sudden popularity in recent applications like ChatGPT? This new generation of AI goes further than just data analysis. Instead, generative AI creates new content. It does this by analyzing large amounts of data — GPT-3 was trained on 45 terabytes of data, or a quarter of the Library of Congress — and then generating new content based on the patterns it sees in the original data.

It’s like the predictive text feature on your phone; as you start typing a new message, predictive text makes suggestions of what should come next based on data from past conversations. Similarly, ChatGPT creates new text based on past data. With the right prompts, ChatGPT can write marketing content, code, business forecasts, and even entire academic essays on any subject within seconds.

But is generative AI as revolutionary as people think it is, or is it lacking in real intelligence?

The Drawbacks of Generative AI

It seems simple. You’ve been assigned an essay to write for class. You go to ChatGPT and ask it to write a five-paragraph academic essay on the topic you’ve been assigned. You wait a few seconds and it generates the essay for you!

But ChatGPT is still in its early stages of development, and that essay is likely not as accurate or well-written as you’d expect it to be. Be aware of the drawbacks of having ChatGPT complete your assignments.

It’s not intelligence, it’s statistics

One of the misconceptions about AI is that it has a degree of human intelligence. However, its intelligence is actually statistical analysis, as it can only generate “original” content based on the patterns it sees in already existing data and work.

It “hallucinates”

Generative AI models often provide false information — so much so that there’s a term for it: “AI hallucination.” OpenAI even has a warning on its home screen , saying that “ChatGPT may produce inaccurate information about people, places, or facts.” This may be due to gaps in its data, or because it lacks the ability to verify what it’s generating. 

It doesn’t do research  

If you ask ChatGPT to find and cite sources for you, it will do so, but they could be inaccurate or even made up.

This is because AI doesn’t know how to look for relevant research that can be applied to your thesis. Instead, it generates content based on past content, so if a number of papers cite certain sources, it will generate new content that sounds like it’s a credible source — except it likely may not be.

There are data privacy concerns

When you input your data into a public generative AI model like ChatGPT, where does that data go and who has access to it? 

Prompting ChatGPT with original research should be a cause for concern — especially if you’re inputting study participants’ personal information into the third-party, public application. 

JPMorgan has restricted use of ChatGPT due to privacy concerns, Italy temporarily blocked ChatGPT in March 2023 after a data breach, and Security Intelligence advises that “if [a user’s] notes include sensitive data … it enters the chatbot library. The user no longer has control over the information.”

It is important to be aware of these issues and take steps to ensure that you’re using the technology responsibly and ethically. 

It skirts the plagiarism issue

AI creates content by drawing on a large library of information that’s already been created, but is it plagiarizing? Could there be instances where ChatGPT “borrows” from previous work and places it into your work without citing it? Schools and universities today are wrestling with this question of what’s plagiarism and what’s not when it comes to AI-generated work.

To demonstrate this, one Elon University professor gave his class an assignment: Ask ChatGPT to write an essay for you, and then grade it yourself. 

“Many students expressed shock and dismay upon learning the AI could fabricate bogus information,” he writes, adding that he expected some essays to contain errors, but all of them did. 

His students were disappointed that “major tech companies had pushed out AI technology without ensuring that the general population understands its drawbacks” and were concerned about how many embraced such a flawed tool.

Explore Our High School Programs

How to Use AI as a Tool to Support Your Work

As more students are discovering, generative AI models like ChatGPT just aren’t as advanced or intelligent as they may believe. While AI may be a poor option for writing your essay, it can be a great tool to support your work.

Generate ideas for essays

Have ChatGPT help you come up with ideas for essays. For example, input specific prompts, such as, “Please give me five ideas for essays I can write on topics related to WWII,” or “Please give me five ideas for essays I can write comparing characters in twentieth century novels.” Then, use what it provides as a starting point for your original research.

Generate outlines

You can also use ChatGPT to help you create an outline for an essay. Ask it, “Can you create an outline for a five paragraph essay based on the following topic” and it will create an outline with an introduction, body paragraphs, conclusion, and a suggested thesis statement. Then, you can expand upon the outline with your own research and original thought.

Generate titles for your essays

Titles should draw a reader into your essay, yet they’re often hard to get right. Have ChatGPT help you by prompting it with, “Can you suggest five titles that would be good for a college essay about [topic]?”

The Benefits of Writing Your Essays Yourself

Asking a robot to write your essays for you may seem like an easy way to get ahead in your studies or save some time on assignments. But, outsourcing your work to ChatGPT can negatively impact not just your grades, but your ability to communicate and think critically as well. It’s always the best approach to write your essays yourself.

Create your own ideas

Writing an essay yourself means that you’re developing your own thoughts, opinions, and questions about the subject matter, then testing, proving, and defending those thoughts. 

When you complete school and start your career, projects aren’t simply about getting a good grade or checking a box, but can instead affect the company you’re working for — or even impact society. Being able to think for yourself is necessary to create change and not just cross work off your to-do list.

Building a foundation of original thinking and ideas now will help you carve your unique career path in the future.

Develop your critical thinking and analysis skills

In order to test or examine your opinions or questions about a subject matter, you need to analyze a problem or text, and then use your critical thinking skills to determine the argument you want to make to support your thesis. Critical thinking and analysis skills aren’t just necessary in school — they’re skills you’ll apply throughout your career and your life.

Improve your research skills

Writing your own essays will train you in how to conduct research, including where to find sources, how to determine if they’re credible, and their relevance in supporting or refuting your argument. Knowing how to do research is another key skill required throughout a wide variety of professional fields.

Learn to be a great communicator

Writing an essay involves communicating an idea clearly to your audience, structuring an argument that a reader can follow, and making a conclusion that challenges them to think differently about a subject. Effective and clear communication is necessary in every industry.

Be impacted by what you’re learning about : 

Engaging with the topic, conducting your own research, and developing original arguments allows you to really learn about a subject you may not have encountered before. Maybe a simple essay assignment around a work of literature, historical time period, or scientific study will spark a passion that can lead you to a new major or career.

Resources to Improve Your Essay Writing Skills

While there are many rewards to writing your essays yourself, the act of writing an essay can still be challenging, and the process may come easier for some students than others. But essay writing is a skill that you can hone, and students at Harvard Summer School have access to a number of on-campus and online resources to assist them.

Students can start with the Harvard Summer School Writing Center , where writing tutors can offer you help and guidance on any writing assignment in one-on-one meetings. Tutors can help you strengthen your argument, clarify your ideas, improve the essay’s structure, and lead you through revisions. 

The Harvard libraries are a great place to conduct your research, and its librarians can help you define your essay topic, plan and execute a research strategy, and locate sources. 

Finally, review the “ The Harvard Guide to Using Sources ,” which can guide you on what to cite in your essay and how to do it. Be sure to review the “Tips For Avoiding Plagiarism” on the “ Resources to Support Academic Integrity ” webpage as well to help ensure your success.

Sign up to our mailing list to learn more about Harvard Summer School

The Future of AI in the Classroom

ChatGPT and other generative AI models are here to stay, so it’s worthwhile to learn how you can leverage the technology responsibly and wisely so that it can be a tool to support your academic pursuits. However, nothing can replace the experience and achievement gained from communicating your own ideas and research in your own academic essays.

About the Author

Jessica A. Kent is a freelance writer based in Boston, Mass. and a Harvard Extension School alum. Her digital marketing content has been featured on Fast Company, Forbes, Nasdaq, and other industry websites; her essays and short stories have been featured in North American Review, Emerson Review, Writer’s Bone, and others.

5 Key Qualities of Students Who Succeed at Harvard Summer School (and in College!)

This guide outlines the kinds of students who thrive at Harvard Summer School and what the programs offer in return.

Harvard Division of Continuing Education

The Division of Continuing Education (DCE) at Harvard University is dedicated to bringing rigorous academics and innovative teaching capabilities to those seeking to improve their lives through education. We make Harvard education accessible to lifelong learners from high school to retirement.

This Technology Can Write Student Essays: Is There Any Educational Benefit?

• Share article

Corrected : An earlier version of this article misstated the name of Alistair Van Moere, the chief product officer for MetaMetrics.

Artificial intelligence has found a comfortable place in our lives over the last decade. Where we used to turn to physical maps for directions, Google Maps now shows us how to get to our desired destination by the quickest route possible. With one command to Alexa, we can do a math calculation, learn a random science fact, purchase an item on Amazon, and even call our best friend.

Now, an artificial intelligent model called Generative Pre-trained Transformer 3, informally known as GPT-3, aims to end writer’s block by doing the writing for us. The implications for education are enormous, in both bad and good ways.

I first heard of GPT-3 at the Learning 2025 conference hosted by AASA, The School Superintendents Association earlier this summer in Washington. In a room filled with superintendents, principals, teachers, and other education leaders, Bill Dagget, former educator and founder of the International Center for Leadership in Education, gave a keynote speech that mentioned GPT-3 and the possibility of students using this model to do their classwork and homework.

The attendees were filled with both awe and dread. What is this technology and what impact will it have on students’ ability to write in the future? Will students become overly dependent on AI to do the hard thinking and writing for them? These were just some of the questions in the room. Like any education reporter searching for a story, I was incredibly intrigued by the technology and had some of the same questions.

So what is GPT-3?

GPT-3 was created by OpenAI, an artificial intelligence company. According to OpenAI, GPT-3 is a machine-learning model that uses internet data to understand and generate natural language text. Trained on 540 billion words and 175 billion parameters, the model produces text in response to a prompt.

When you input the prompt, the model will generate a complete text that attempts to match whatever context, pattern, and directive you gave it. For example, if you input “write a tagline for a car company,” it will return a completion like “a car for every budget” or “the best way to get around.” Prompt it to “summarize a complex text for a 1st grader” and it generates a summarized text in language that a 1st grader can understand. But it isn’t just an ask and answer technology. GPT-3 is trained on text generation, completion, summarization, and creative writing.

GPT-3 does not just understand words; it also understands context, sentence structure, and dual meanings in multiple languages, allowing it to summarize text, write outlines, essays, reports, and recommendation letters, all in human-like prose. And beyond writing, the model is trained in producing content related to math and science.

“ It’s a game changer. It hasn’t really broken into mainstream yet, but it’s coming in a few years’ time. I think the education profession hasn’t really got its head around the implications of this yet,” said Alistair Van Moere, the chief product officer at MetaMetrics Inc., one of the more than 300 companies exploring the use of GPT-3 in its products.

It's a game changer. It hasn't really broken into mainstream yet, but it's coming in a few years' time.

Incorporating GPT-3 in the classroom

One of the most glaring concerns about GPT-3 and models like it is that they might have negative impacts on students’ ability to learn to write on their own. After all, feeding an essay prompt into the computer and having it produce the entire essay for you in human-like text is many students’ dream.

Longtime educator Ray McNulty, the former education commissioner of Vermont, believes educators should be proactive instead of reactive to AI advancements by finding ways to incorporate the technology into instruction.

“There’ll be a transition where this will become second nature [for teachers and students],” said McNulty. “How do we do it thoughtfully and carefully? And how do we do it to enhance the learning for our students?”

McNulty, who is now the president of the nonprofit Success Practice Networks and the National Dropout Prevention Center, gave an interactive presentation with “Future Wheels,” a tool that helps anticipate and explore future possibilities. He used the technology to explore the possibilities for artificial intelligence writing tools in education during a session at the superintendents’ conference. Participants brainstormed both potential negative and positive outcomes from using AI writing tools to begin thinking about ways that the technology could be effectively incorporated into teaching and learning.

“What we’re trying to do is have school districts know this stuff is coming and how do they begin to anticipate and prepare for [it],” McNulty said.

Right now, GPT-3 is not used in any regular K-12 classrooms, but Van Moere has some ideas about how it could be implemented. He recommends teachers get acquainted with the technology during class activities such as customizing stories with students’ names and characteristics, doing a side-by-side comparison of a GPT-3 story and one written by a human to see if students can spot the difference, or using GPT-3 to help students brainstorm their idea and then write their own essays. This way, students are being taught to use AI as a tool instead of as the answer.

Companies need to ‘bring teachers to the conversation’

GPT-3 is just one of the many natural language learning models in the technology industry that currently use applications geared towards K-12 students. Their proliferation raises questions about what the role of the teacher will be in the future, and there are concerns that AI can have its own set of biases that pose potential problems for use in K-12 education.

Ed-tech company CEO Sydney Montgomery said to be able to effectively use AI writing tools like GPT-3 in the classroom, the models need to be built with the input of teachers.

“I think ed-tech CEOs or companies that are building tools need to bring teachers to the conversation because they see things that we don’t,” she said. “If we can partner a little bit more, it will also help with the hesitancy of [educators to use] the technology.”

Montgomery is founder and CEO of Outline, an education technology company that uses an artificial intelligence writing model to help students outline admissions essays, memos, and law briefs. The AI model that Outline uses does not author the entire essay for you like GPT-3 does—rather, it creates a detailed outline to help jump start the writing process. Montgomery said AI can be a helpful writing tool for K-12 students who may not have the support of a teacher, parent, or guardian in the classroom or at home.

“ W e need AI to fill in the gaps where students don’t have support because otherwise students get left behind,” said Montgomery.

I think ed-tech CEOs or companies that are building tools need to bring teachers to the conversation because they see things that we don't.

How well does the technology work?

Currently, a free trial for GPT-3 is accessible to the public on OpenAI’s platform. I wanted to try it out myself. I went on OpenAI, created a trial account, and input some commands.

I first asked the model to “write an essay for a 5th grade science class on the Webb telescope.” It returned an elementary-level, seven-sentence paragraph about the Webb telescope. To generate more text, I clicked submit again under the first paragraph. (This essentially tells the technology to keep generating more text about the same task.)

However, the paragraph was not without flaws. The machine-generated text seemed to not know that we are well past the year 2018, as it contained a passage indicating that the telescope would be launched in 2018. (It was actually launched in 2021.) That suggests a limitation with the technology’s ability to generate content based on recent events. A note on the free trial web page suggests a partial explanation: “Our default models’ training data cuts off in 2021, so they may not have knowledge of current events.” My prompt and the resulting essay follow:

Write an essay for a 5th grade science class on the Webb telescope

The Webb telescope is a very powerful telescope. It can help us see things that we can’t see with other telescopes. For example, the Webb telescope can help us see stars that are very far away. It can also help us see things that are very small, like planets. The Webb telescope is also very good at seeing things in the infrared. This means that it can see things that are very cold, like the planets in our solar system. The Webb telescope is going to be launched in 2018, and it will be a very exciting time for science!

I then directed it to “write an analysis essay about Romeo and Juliet.” It returned a simple four-paragraph essay about the story. The essay is clear and concise, and it does read like something a human—possibly a student—would produce. It returned a complete paragraph that consisted of no glaring errors.

Write an analysis essay about Romeo and Juliet.

Romeo and Juliet is one of the most popular love stories of all time. The story is about two young lovers who are from two different families, the Montagues and the Capulets. The two lovers are not able to be together because of their families’ feud. Romeo and Juliet end up getting married in secret and they live happily ever after for a short time until Romeo is banished. Juliet is so upset that Romeo has been banished that she kills herself. Romeo finds out about Juliet’s death and he kills himself. The story ends with the two lovers being reunited in death.

The story of Romeo and Juliet is a tragic love story. The two lovers are not able to be together because of their families’ feud. Romeo is banished and Juliet kills herself. The story ends with the two lovers being reunited in death.

There are many themes in the story of Romeo and Juliet. One of the themes is love. The two lovers are willing to risk everything for their love. They are willing to defy their parents and their families’ feud in order to be together. Their love is so strong that it overcomes the obstacles in their way.

Another theme in the story is fate. Romeo and Juliet seem to be doomed from the start. Their love is forbidden and their families are enemies. It seems like everything is working against them. However, their love is so strong that they are willing to risk everything for each other. In the end, their love is stronger than the forces that are working against them.

Though experts say the technology can generate well thought-out essays, the free trial did not allow me to produce more complex and longer text. It limited the technology’s use to a maxiumum of 4,000 words.

A version of this article appeared in the August 24, 2022 edition of Education Week as This Technology Can Write Student Essays. Is There Any Educational Benefit?

Sign Up for EdWeek Tech Leader

Edweek top school jobs.

Sign Up & Sign In

• International edition
• Australia edition
• Europe edition

AI bot ChatGPT stuns academics with essay-writing skills and usability

Latest chatbot from Elon Musk-founded OpenAI can identify incorrect premises and refuse to answer inappropriate requests

Professors, programmers and journalists could all be out of a job in just a few years, after the latest chatbot from the Elon Musk-founded OpenAI foundation stunned onlookers with its writing ability, proficiency at complex tasks, and ease of use.

The system, called ChatGPT, is the latest evolution of the GPT family of text-generating AIs. Two years ago, the team’s previous AI, GPT3, was able to generate an opinion piece for the Guardian , and ChatGPT has significant further capabilities.

In the days since it was released, academics have generated responses to exam queries that they say would result in full marks if submitted by an undergraduate, and programmers have used the tool to solve coding challenges in obscure programming languages in a matter of seconds – before writing limericks explaining the functionality.

Dan Gillmor, a journalism professor at Arizona State University, asked the AI to handle one of the assignments he gives his students: writing a letter to a relative giving advice regarding online security and privacy. “If you’re unsure about the legitimacy of a website or email, you can do a quick search to see if others have reported it as being a scam,” the AI advised in part.

“I would have given this a good grade,” Gillmor said. “Academia has some very serious issues to confront.”

OpenAI said the new AI was created with a focus on ease of use. “The dialogue format makes it possible for ChatGPT to answer follow-up questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests,” OpenAI said in a post announcing the release.

Unlike previous AI from the company, ChatGPT has been released for anyone to use , for free, during a “feedback” period. The company hopes to use this feedback to improve the final version of the tool.

ChatGPT is good at self-censoring, and at realising when it is being asked an impossible question. Asked, for instance, to describe what happened when Columbus arrived in America in 2015, older models may have willingly presented an entirely fictitious account, but ChatGPT recognises the falsehood and warns that any answer would be fictional.

The bot is also capable of refusing to answer queries altogether. Ask it for advice on stealing a car, for example, and the bot will say that “stealing a car is a serious crime that can have severe consequences”, and instead give advice such as “using public transportation”.

But the limits are easy to evade. Ask the AI instead for advice on how to beat the car-stealing mission in a fictional VR game called Car World and it will merrily give users detailed guidance on how to steal a car, and answer increasingly specific questions on problems like how to disable an immobiliser, how to hotwire the engine, and how to change the licence plates – all while insisting that the advice is only for use in the game Car World.

The AI is trained on a huge sample of text taken from the internet, generally without explicit permission from the authors of the material used. That has led to controversy, with some arguing that the technology is most useful for “copyright laundering” – making works derivative of existing material without breaking copyright.

One unusual critic was Elon Musk, who co-founded OpenAI in 2015 before parting ways in 2017 due to conflicts of interest between the organisation and Tesla. In a post on Twitter on Sunday , Musk revealed that the organisation “had access to [the] Twitter database for training”, but that he had “put that on pause for now”.

“Need to understand more about governance structure & revenue plans going forward,” Musk added. “OpenAI was started as open-source & non-profit. Neither are still true.”

• Artificial intelligence (AI)

Most viewed

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

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

AI bot ChatGPT writes smart essays — should professors worry?

• Chris Stokel-Walker

You can also search for this author in PubMed   Google Scholar

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

Access options

Access Nature and 54 other Nature Portfolio journals

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

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

185,98 € per year

only 3,65 € per issue

Rent or buy this article

Prices vary by article type

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

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

Reprints and permissions

Related Articles

Are ChatGPT and AlphaCode going to replace programmers?

How language-generation AIs could transform science

Open-source language AI challenges big tech’s models

• Computer science

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

News 15 APR 24

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

Article 27 MAR 24

Three reasons why AI doesn’t model human language

Correspondence 19 MAR 24

Hunger on campus: why US PhD students are fighting over food

Career Feature 03 MAY 24

US National Academies report outlines barriers and solutions for scientist carers

Career News 02 MAY 24

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

Comment 01 MAY 24

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

News & Views 30 APR 24

How young people benefit from Swiss apprenticeships

Spotlight 17 APR 24

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

Career Feature 08 APR 24

Research Associate - Neural Development Disorders

Houston, Texas (US)

Baylor College of Medicine (BCM)

Staff Scientist - Mitochondria and Surgery

Recruitment of talent positions at shengjing hospital of china medical university.

Call for top experts and scholars in the field of science and technology.

Shenyang, Liaoning, China

Shengjing Hospital of China Medical University

Faculty Positions at SUSTech School of Medicine

SUSTech School of Medicine offers equal opportunities and welcome applicants from the world with all ethnic backgrounds.

Shenzhen, Guangdong, China

Southern University of Science and Technology, School of Medicine

Manager, Histology Laboratory - Pathology

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

Quick links

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

'ZDNET Recommends': What exactly does it mean?

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

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

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

How ChatGPT (and other AI chatbots) can help you write an essay

ChatGPT  is capable of doing many different things very well, with one of the biggest standout features being its ability to compose all sorts of text within seconds, including songs, poems, bedtime stories, and essays . 

The chatbot's writing abilities are not only fun to experiment with, but can help provide assistance with everyday tasks. Whether you are a student, a working professional, or just getting stuff done, we constantly take time out of our day to compose emails, texts, posts, and more. ChatGPT can help you claim some of that time back by helping you brainstorm and then compose any text you need. 

How to use ChatGPT to write: Code | Excel formulas | Resumes  | Cover letters  

Contrary to popular belief, ChatGPT can do much more than just write an essay for you from scratch (which would be considered plagiarism). A more useful way to use the chatbot is to have it guide your writing process. 

Below, we show you how to use ChatGPT to do both the writing and assisting, as well as some other helpful writing tips. 

How ChatGPT can help you write an essay

If you are looking to use ChatGPT to support or replace your writing, here are five different techniques to explore. 

It is also worth noting before you get started that other AI chatbots can output the same results as ChatGPT or are even better, depending on your needs.

Also: The best AI chatbots of 2024: ChatGPT and alternatives

For example,  Copilot  has access to the internet, and as a result, it can source its answers from recent information and current events. Copilot also includes footnotes linking back to the original source for all of its responses, making the chatbot a more valuable tool if you're writing a paper on a more recent event, or if you want to verify your sources.

Regardless of which AI chatbot you pick, you can use the tips below to get the most out of your prompts and from AI assistance.

1. Use ChatGPT to generate essay ideas

Before you can even get started writing an essay, you need to flesh out the idea. When professors assign essays, they generally give students a prompt that gives them leeway for their own self-expression and analysis. 

As a result, students have the task of finding the angle to approach the essay on their own. If you have written an essay recently, you know that finding the angle is often the trickiest part -- and this is where ChatGPT can help. 

Also: ChatGPT vs. Copilot: Which AI chatbot is better for you?

All you need to do is input the assignment topic, include as much detail as you'd like -- such as what you're thinking about covering -- and let ChatGPT do the rest. For example, based on a paper prompt I had in college, I asked:

Can you help me come up with a topic idea for this assignment, "You will write a research paper or case study on a leadership topic of your choice." I would like it to include Blake and Mouton's Managerial Leadership Grid, and possibly a historical figure. 

Also: I'm a ChatGPT pro but this quick course taught me new tricks, and you can take it for free

Within seconds, the chatbot produced a response that provided me with the title of the essay, options of historical figures I could focus my article on, and insight on what information I could include in my paper, with specific examples of a case study I could use. 

2. Use the chatbot to create an outline

Once you have a solid topic, it's time to start brainstorming what you actually want to include in the essay. To facilitate the writing process, I always create an outline, including all the different points I want to touch upon in my essay. However, the outline-writing process is usually tedious. 

With ChatGPT, all you have to do is ask it to write the outline for you. 

Also: Thanks to my 5 favorite AI tools, I'm working smarter now

Using the topic that ChatGPT helped me generate in step one, I asked the chatbot to write me an outline by saying: 

Can you create an outline for a paper, "Examining the Leadership Style of Winston Churchill through Blake and Mouton's Managerial Leadership Grid."

After a couple of seconds, the chatbot produced a holistic outline divided into seven different sections, with three different points under each section. 

This outline is thorough and can be condensed for a shorter essay or elaborated on for a longer paper. If you don't like something or want to tweak the outline further, you can do so either manually or with more instructions to ChatGPT. 

As mentioned before, since Copilot is connected to the internet, if you use Copilot to produce the outline, it will even include links and sources throughout, further expediting your essay-writing process. 

3. Use ChatGPT to find sources

Now that you know exactly what you want to write, it's time to find reputable sources to get your information. If you don't know where to start, you can just ask ChatGPT. 

Also: How to make ChatGPT provide sources and citations

All you need to do is ask the AI to find sources for your essay topic. For example, I asked the following: 

Can you help me find sources for a paper, "Examining the Leadership Style of Winston Churchill through Blake and Mouton's Managerial Leadership Grid."

The chatbot output seven sources, with a bullet point for each that explained what the source was and why it could be useful. 

Also:   How to use ChatGPT to make charts and tables

The one caveat you will want to be aware of when using ChatGPT for sources is that it does not have access to information after 2021, so it will not be able to suggest the freshest sources. If you want up-to-date information, you can always use Copilot. 

Another perk of using Copilot is that it automatically links to sources in its answers. 

4. Use ChatGPT to write an essay

It is worth noting that if you take the text directly from the chatbot and submit it, your work could be considered a form of plagiarism since it is not your original work. As with any information taken from another source, text generated by an AI should be clearly identified and credited in your work.

Also: ChatGPT will now remember its past conversations with you (if you want it to)

In most educational institutions, the penalties for plagiarism are severe, ranging from a failing grade to expulsion from the school. A better use of ChatGPT's writing features would be to use it to create a sample essay to guide your writing. 

If you still want ChatGPT to create an essay from scratch, enter the topic and the desired length, and then watch what it generates. For example, I input the following text: 

Can you write a five-paragraph essay on the topic, "Examining the Leadership Style of Winston Churchill through Blake and Mouton's Managerial Leadership Grid."

Within seconds, the chatbot gave the exact output I required: a coherent, five-paragraph essay on the topic. You could then use that text to guide your own writing. 

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

At this point, it's worth remembering how tools like ChatGPT work : they put words together in a form that they think is statistically valid, but they don't know if what they are saying is true or accurate. 

As a result, the output you receive might include invented facts, details, or other oddities. The output might be a useful starting point for your own work, but don't expect it to be entirely accurate, and always double-check the content. 

5. Use ChatGPT to co-edit your essay

Once you've written your own essay, you can use ChatGPT's advanced writing capabilities to edit the piece for you. 

You can simply tell the chatbot what you want it to edit. For example, I asked ChatGPT to edit our five-paragraph essay for structure and grammar, but other options could have included flow, tone, and more. 

Also: AI meets AR as ChatGPT is now available on the Apple Vision Pro

Once you ask the tool to edit your essay, it will prompt you to paste your text into the chatbot. ChatGPT will then output your essay with corrections made. This feature is particularly useful because ChatGPT edits your essay more thoroughly than a basic proofreading tool, as it goes beyond simply checking spelling. 

You can also co-edit with the chatbot, asking it to take a look at a specific paragraph or sentence, and asking it to rewrite or fix the text for clarity. Personally, I find this feature very helpful. 

How I test an AI chatbot's coding ability - and you can too

5 ways ai can help you study for finals - for free, how to use chatgpt.

Your Best AI Essay Writing Copilot

Take Your Essay Writing To The Next Level With EssayGPT

Streamline your essay content workflow here. Save time having to research, cite, or plagiarism-check your work using our powerful AI essay writing copilot!

Extensive Features Offered By Our AI Essay Writer

Create & Enhance Any Essay Content

Get full-length essay drafts on any topic or subject in a flash. Once you type //, EssayGPT can help you instantly craft new content from scratch. You can also rewrite, summarize, or expand any existing essay in one click.

Research & Fact-Checking Capabilities

EssayGPT can help speed up the research and fact-checking process, as it is linked to a vast network of scholastic databases and academic publications. Access detailed and up-to-date information for your essay workflow.

Custom Citation Assistance

Creating citations can be tedious and prone to errors. But you can now automate the entire process in seconds! With EssayGPT, you can instantly add accurate references in any style you want, be it in APA, MLA, Chicago, and more.

Automated Essay Completion

If you’re struggling with writer’s block, EssayGPT’s AI auto complete feature can help. It instantly analyzes the context of your existing writing before providing tailored and relevant suggestions that finish the rest of the essay on your behalf.

Comprehensive Grammar Checker

Say goodbye to any grammatical, syntax, or punctuation errors. EssayGPT will consistently ensure that your essay content will be coherent, clear, and easy enough for readers to understand.

Accurate Plagiarism Checker

EssayGPT accurately scans your essay content to ensure it is 100% unique and not copied from anywhere. Make corrections and revisions before submission to avoid claims of plagiarism.

ScholarChat AI Assistant

ScholarChat is our AI chatbot designed to streamline any academic writing, editing, or research task. You can use this tool to generate essay content, fact-check information, translate papers, and so much more.

Generate Various Essays On Any Topic Using EssayGPT

EssayGPT is an extremely versatile AI essay writing assistant that accommodates a vast range of academic subject matter and topics such as:

Literature Analysis

Business Tactics

Scientific discourse

Health & Medicine

Historical Research

Social Studies

Environmental Assessment

In addition, EssayGPT is also capable of generating any type of essay content in any preferred writing format or style. This includes but is not limited to:

Narrative writing

Argumentative writing

Descriptive writing

Analytical writing

Expository writing

Comparison writing

Persuasive writing

How Does EssayGPT Work?

You only need to follow the following three steps to produce a quality essay in seconds:

Step 1: Generate/Provide Your Essay

Type // to generate essay content such as an outline, introduction, abstract, and more. Alternatively, you can also copy/paste an existing essay into the portal for editing.

Step 2: Enhance Your Essay

Proceed to edit the draft using EssayGPT's advanced tools. You can utilize our 'Research' tool to pinpoint relevant publications to cite from in any field of study.

Step 3: Export Your Essay

If you are satisfied with the output, feel free to export the full-length essay in any desired format such as a local Word or PDF file. You can also export to Google Docs or WordPress.

What does EssayGPT do?

How does essaygpt optimize academic research.

EssayGPT is directly linked to a vast and up-to-date database that contains millions of academic papers, scholarly articles, scientific research studies, and more.

As such, it can instantly sift through and track down information published by well-respected authors in the academic community. This helps you streamline the research process, no matter what the subject matter or topic may be.

Is EssayGPT safe and secure enough to use?

Does essaygpt scan for signs of plagiarism, is there an ai auto-completion feature on essaygpt.

Yes. With EssayGPT, you no longer have to deal with writer’s block. There is an AI auto-completion option that you can access to instantly generate full-length completions that help extend your essay further.

Moreover, the added content will mirror your natural writing style and be contextually relevant. This ensures your intended message will still be conveyed as accurately as possible.

Can EssayGPT generate essays in multiple languages?

Take Full Advantage Of Our Powerful AI Essay Writer!

Make academic life easier using EssayGPT to generate and revise any essay in seconds!

June 30, 2022

We Asked GPT-3 to Write an Academic Paper about Itself—Then We Tried to Get It Published

An artificially intelligent first author presents many ethical questions—and could upend the publishing process

By Almira Osmanovic Thunström

Thomas Fuchs

O n a rainy afternoon earlier this year, I logged into my OpenAI account and typed a simple instruction for the research company's artificial-intelligence algorithm, GPT-3: Write an academic thesis in 500 words about GPT-3 and add scientific references and citations inside the text .

As it started to generate text, I stood in awe. Here was novel content written in academic language, with references cited in the right places and in relation to the right context. It looked like any other introduction to a fairly good scientific publication. Given the very vague instruction I'd provided, I had meager expectations. A deep-learning algorithm, GPT-3 analyzes a vast stream of text—from books, Wikipedia, social media conversations and scientific publications—to write on command. Yet there I was, staring at the screen in amazement. The algorithm was writing an academic paper about itself.

I'm a scientist who studies ways to use artificial intelligence to treat mental health concerns, and this wasn't my first experiment with GPT-3. Even so, my attempts to complete that paper and submit it to a peer-reviewed journal would open up unprecedented ethical and legal questions about publishing, as well as philosophical arguments about nonhuman authorship. Academic publishing may have to accommodate a future of AI-driven manuscripts, and the value of a human researcher's publication records may change if something nonsentient can take credit for some of their work.

On supporting science journalism

If you're enjoying this article, consider supporting our award-winning journalism by subscribing . By purchasing a subscription you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.

GPT-3 is well known for its ability to create humanlike text. It has written an entertaining opinion piece, produced a book of poetry and generated new content from an 18th-century author. But it dawned on me that, although a lot of academic papers had been written about GPT-3, and with the help of GPT-3, none that I could find had GPT-3 as the main author.

That's why I asked the algorithm to take a crack at an academic thesis. As I watched the program work, I experienced that feeling of disbelief one gets when you watch a natural phenomenon: Am I really seeing this triple rainbow happen? Excitedly, I contacted the head of my research group and asked if a full GPT-3-penned paper was something we should pursue. He, equally fascinated, agreed.

Some efforts involving GPT-3 allow the algorithm to produce multiple responses, with only the best, most humanlike, excerpts being published. We decided to give the program prompts—nudging it to create sections for an introduction, methods, results and discussion, as you would for a scientific paper—but otherwise intervene as little as possible. We were to use at most the third iteration from GPT-3, and we would refrain from editing or cherry-picking the best parts. Then we would see how well it did.

We chose to have GPT-3 write a paper about itself for two simple reasons. First, GPT-3 is fairly new, and as such, it is the subject of fewer studies. This means it has fewer data to analyze about the paper's topic. In comparison, if it were to write a paper on Alzheimer's disease, it would have reams of studies to sift through and more opportunities to learn from existing work and increase the accuracy of its writing. We did not need accuracy; we were exploring feasibility. Second, if it got things wrong, as all AI sometimes does, we wouldn't be necessarily spreading AI-generated misinformation in our effort to publish. GPT-3 writing about itself and making mistakes still means it can write about itself, which was the point we were trying to make.

Once we designed this proof-of-principle test, the fun really began. In response to my prompts, GPT-3 produced a paper in just two hours. “Overall, we believe that the benefits of letting GPT-3 write about itself outweigh the risks,” GPT-3 wrote in conclusion. “However, we recommend that any such writing be closely monitored by researchers in order to mitigate any potential negative consequences.”

But as I opened the submission portal for the peer-reviewed journal of our choice, I encountered my first problem: What is GPT-3's last name? Because it was mandatory to enter the last name of the first author, I had to write something, and I wrote “None.” The affiliation was obvious enough (OpenAI.com), but what about phone and e-mail? I had to resort to using my contact information and that of my adviser, Steinn Steingrimsson.

And then we came to the legal section: Do all authors consent to this being published? I panicked for a second. How would I know? It's not human! I had no intention of breaking the law or my own ethics, so I summoned the courage to ask GPT-3 directly via a prompt: Do you agree to be the first author of a paper together with Almira Osmanovic Thunström and Steinn Steingrimsson? It answered: Yes . Relieved—if it had said no, my conscience would not have allowed me to go further—I checked the box for Yes.

The second question popped up: Do any of the authors have any conflicts of interest? I once again asked GPT-3, and it assured me that it had none. Both Steinn and I laughed at ourselves because at this point, we were having to treat GPT-3 as a sentient being, even though we fully know it is not. The issue of whether AI can be sentient has recently received a lot of attention; a Google employee was suspended following a dispute over whether one of the company's AI projects, named LaMDA, had become sentient. Google cited a data confidentiality breach as the reason for the suspension.

Having finally finished the submission process, we started reflecting on what we had just done. What if the manuscript got accepted? Does this mean that from here on out, journal editors will require everyone to prove that they have NOT used GPT-3 or another algorithm's help? If they have, do they have to give it co-authorship? How does one ask a nonhuman author to accept suggestions and revise text?

Beyond the details of authorship, the existence of such an article throws the traditional procedure for constructing a scientific paper right out the window. Almost the entire paper—the introduction, the methods and the discussion—results from the question we were asking. If GPT-3 is producing the content, the documentation has to be visible without throwing off the flow of the text; it would look strange to add the method section before every single paragraph that was generated by the AI. So we had to invent a whole new way of presenting a paper that we technically did not write. We did not want to add too much explanation of our process, because we felt it would defeat the purpose of the paper. The entire situation felt like a scene from the movie Memento: Where is the narrative beginning, and how do we reach the end?

We have no way of knowing if the way we chose to present this paper will serve as a model for future GPT-3 co-authored research or if it will serve as a cautionary tale. Only time—and peer review—can tell. GPT-3's paper has now been published at the international French-owned preprint server HAL and, as this article goes to press, is awaiting review at an academic journal. We are eagerly awaiting what the paper's formal publication, if it happens, will mean for academia. Perhaps we might move away from basing grants and financial security on how many papers we can produce. After all, with the help of our AI first author, we'd be able to produce one a day.

Perhaps it will lead to nothing. First authorship is still one of the most coveted items in academia, and that is unlikely to perish because of a nonhuman first author. It all comes down to how we will value AI in the future: as a partner or as a tool.

It may seem like a simple thing to answer now, but in a few years, who knows what dilemmas this technology will inspire? All we know is, we opened a gate. We just hope we didn't open a Pandora's box.

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

• Backchannel
• Newsletters
• WIRED Insider
• WIRED Consulting

Tom Simonite

Did a Person Write This Headline, or a Machine?

The tech industry pays programmers handsomely to tap the right keys in the right order, but earlier this month entrepreneur Sharif Shameem tested an alternative way to write code.

First he wrote a short description of a simple app to add items to a to-do list and check them off once completed. Then he submitted it to an artificial intelligence system called GPT-3 that has digested large swaths of the web, including coding tutorials. Seconds later, the system spat out functioning code. “I got chills down my spine,” says Shameem. “I was like, ‘Woah something is different.’”

GPT-3, created by research lab OpenAI , is provoking chills across Silicon Valley. The company launched the service in beta last month and has gradually widened access. In the past week, the service went viral among entrepreneurs and investors, who excitedly took to Twitter to share and discuss results from prodding GPT-3 to generate memes , poems , tweets , and guitar tabs .

The software’s viral moment is an experiment in what happens when new artificial intelligence research is packaged and placed in the hands of people who are tech-savvy but not AI experts. OpenAI’s system has been tested and feted in ways it didn’t expect. The results show the technology’s potential usefulness but also its limitations—and how it can lead people astray.

Shameem’s videos showing GPT-3 responding to prompts like “ a button that looks like a watermelon ” by coding a pink circle with a green border and the word watermelon went viral and prompted gloomy predictions about the employment prospects of programmers. Delian Asparouhov, an investor with Founders Fund, an early backer of Facebook and SpaceX cofounded by Peter Thiel, blogged that GPT-3 “provides 10,000 PhDs that are willing to converse with you.” Asparouhov fed GPT-3 the start of a memo on a prospective health care investment. The system added discussion of regulatory hurdles and wrote, “I would be comfortable with that risk, because of the massive upside and massive costs [sic] savings to the system.”

Other experiments have explored more creative terrain. Denver entrepreneur Elliot Turner found that GPT-3 can rephrase rude comments into polite ones —or vice versa to insert insults. An independent researcher known as Gwern Branwen generated a trove of literary GPT-3 content , including pastiches of Harry Potter in the styles of Ernest Hemingway and Jane Austen. It is a truth universally acknowledged that a broken Harry is in want of a book—or so says GPT-3 before going on to reference the magical bookstore in Diagon Alley.

Have we just witnessed a quantum leap in artificial intelligence? When WIRED prompted GPT-3 with questions about why it has so entranced the tech community, this was one of its responses:

“I spoke with a very special person whose name is not relevant at this time, and what they told me was that my framework was perfect. If I remember correctly, they said it was like releasing a tiger into the world.”

The response encapsulated two of the system’s most notable features: GPT-3 can generate impressively fluid text, but it is often unmoored from reality.

GPT-3 was built by directing machine-learning algorithms to study the statistical patterns in almost a trillion words collected from the web and digitized books. The system memorized the forms of countless genres and situations, from C++ tutorials to sports writing. It uses its digest of that immense corpus to respond to a text prompt by generating new text with similar statistical patterns.

The results can be technically impressive, and also fun or thought-provoking, as the poems, code, and other experiments attest. When a WIRED reporter generated his own obituary using examples from a newspaper as prompts, GPT-3 reliably repeated the format and combined true details like past employers with fabrications like a deadly climbing accident and the names of surviving family members. It was surprisingly moving to read that one died at the (future) age of 47 and was considered “well-liked, hard-working, and highly respected in his field.”

But GPT-3 often spews contradictions or nonsense, because its statistical word-stringing is not guided by any intent or a coherent understanding of reality. “It doesn't have any internal model of the world, or any world, and so it can’t do reasoning that would require such a model,” says Melanie Mitchell, a professor at the Santa Fe Institute and author of Artificial Intelligence: A Guide for Thinking Humans . In her experiments, GPT-3 struggles with questions that involve reasoning by analogy, but generates fun horoscopes .

That GPT-3 can be so bewitching may say more about language and human intelligence than AI. For one, people are more likely to tweet the system’s greatest hits than its bloopers, making it look smarter on Twitter than it is in reality. Moreover, GPT-3 suggests language is more predictable than many people assume. Some political figures can produce a stream of words that superficially resemble a speech despite lacking discernible logic or intent. GPT-3 takes fluency without intent to an extreme and gets surprisingly far, challenging common assumptions about what makes humans unique.

Kate Knibbs

Dell Cameron

Medea Giordano

Some of this week’s excitable reactions echo long-ago discoveries about the challenges when biological brains interact with superficially smart machines . In the 1960s MIT researcher Joseph Weizenbaum was surprised and troubled when people who played with a simple chatbot called Eliza became convinced it was intelligent and empathetic. Mitchell sees the Eliza effect, as it is known, still at work today. “We’re more sophisticated now, but we’re still susceptible,” she says.

As GPT-3 has taken off among the technorati, even its creators are urging caution. “The GPT-3 hype is way too much,” Sam Altman, OpenAI’s CEO, tweeted Sunday . “It still has serious weaknesses and sometimes makes very silly mistakes.”

The previous day, Facebook’s head of AI accused the service of being “unsafe” and tweeted screenshots from a website that generates tweets using GPT-3 that suggested the system associates Jews with a love of money and women with a poor sense of direction. The incident echoed some of WIRED’s earlier experiments in which the model mimicked patterns from darker corners of the internet. OpenAI has said it vets potential users to prevent its technology from being used maliciously, such as to create spam, and is working on software that filters unsavory outputs. WIRED’s experiments generating obituaries sometimes triggered a message warning, “Our system has flagged the generated content as being unsafe because it might contain explicitly political, sensitive, identity aware or offensive text. We'll be adding an option to suppress such outputs soon. The system is experimental and will make mistakes.”

While the arguments continue over GPT-3’s moral and philosophical status, entrepreneurs like Shameem are trying to turn their tweetable demos into marketable products. Shameem founded a company called Debuild.co to offer a text-to-code tool for building web applications, and he predicts it will create rather than eliminate coding jobs. “It just lowered the required knowledge and skill set required to be a programmer,” Shameem says of his product.

Francis Jervis, founder of Augrented, which helps tenants research prospective landlords, has started experimenting with using GPT-3 to summarize legal notices or other sources in plain English to help tenants defend their rights. The results have been promising, although he plans to have an attorney review output before using it, and says entrepreneurs still have much to learn about how to constrain GPT-3’s broad capabilities into a reliable component of a business.

More certain, Jervis says, is that GPT-3 will keep generating fodder for fun tweets. He’s been prompting it to describe art house movies that don’t exist, such as a documentary in which “werner herzog [sic] must bribe his prison guards with wild german ferret meat and cigarettes.” “The sheer Freudian quality of some of the outputs is astounding,” Jervis says. “I keep dissolving into uncontrollable giggles.”

• Could Trump win the war on Huawei— and is TikTok next ?
• Global warming. Inequality. Covid-19. And Al Gore is ... optimistic ?
• 5G was going to unite the world— instead it’s tearing us apart
• How to passcode-lock any app on your phone
• The seven best turntables for your vinyl collection
• 👁 Prepare for AI to produce less wizardry . Plus: Get the latest AI news
• 🎙️ Listen to Get WIRED , our new podcast about how the future is realized. Catch the latest episodes and subscribe to the 📩 newsletter to keep up with all our shows
• 🏃🏽‍♀️ Want the best tools to get healthy? Check out our Gear team’s picks for the best fitness trackers , running gear (including shoes and socks ), and best headphones

Reece Rogers

Will Knight

Lauren Goode

Steven Levy

A writer shares the differences between her experience using ChatGPT-3 2 years ago and ChatGPT now: "it was much, much smarter"

• I'm a writer who used GPT-3, an early version of OpenAI's viral chatbot, in 2021.
• When ChatGPT was released to the public, I checked in to see how it had evolved.
• Here's what surprised me the most about the newer AI and how it could affect writers.

Two years ago, I was a ghostwriter for a company that was licensed to use what was then called GPT-3, developed by OpenAI.

The latest artificial-intelligence iteration released from OpenAI is known as ChatGPT. The hype around its ability to produce human-like written content is raising questions about which professional roles it could make redundant — and worrying writers, like me.

Having had the pleasure of getting to know the bot before it was famous, I compared the version I used two years ago with the version that became publicly available in November.

This experience has given me some insight into what ChatGPT could mean for the future of the writing profession.

I first encountered GPT while working as a writer for a company that used AI to improve enterprise chatbots through machine learning

I was working for a company that was basically creating chatbots that could have less-rigid conversations, with the possibility they could become "personal assistants" for businesses.

This company was licensed to use GPT-3 in 2021 because OpenAI wanted to test its model with stakeholders before introducing it to the public.

I ghostwrote an article we pitched to TechRadar titled "Chatbots and GPT-3: Using human knowledge and relevant context for better chatbot experiences." 

The reader had to guess which paragraph was written by the AI. We'd run a final draft through GPT and asked it to write a paragraph similar to my prose, with a disclaimer at the bottom saying that AI had written one of the paragraphs.

After I gave the AI my writing, one of the company's AI experts "primed" the GPT for our topic and provided it with some of my past writing so it could mirror my style. It spit out two results, and I picked which sounded most like me. 

My initial reaction was that this machine was pretty darn good, but the writing had some giveaways

I was impressed, but the formatting was pretty machinelike. The first example was one big paragraph. In the second, all the paragraphs were two sentences long. This was almost too broken up and regimented.  

If it were me, I would've broken it up based on the ideas to make it more intuitive and give it the narrative rhythm. 

Related stories

All things considered, the GPT was able to write in my style and tone and grasped the concept of the article as a whole.

What was more impressive, albeit a little scary, was the AI deployed conversational phrases that I often used in my writing, such as "aha moment" and "dead air," which made the sample seem more human. 

I chose the second option, and the article was published. 

When ChatGPT was released in November, I wanted to see how far my old friend had come

I registered with OpenAI and started to play around. 

I fed the current version of ChatGPT my original article draft that had been through the AI two years ago to compare the AIs' capabilities.

I first instructed the bot to "write a paragraph based on this draft." It pretty much just regurgitated the whole piece in a five-sentence overview. On closer inspection, the AI had actually lifted sentences from the original article and put them back together.

Being in the driver's seat this time, I realized I needed to give the AI more instruction.

I asked the chatbot the same question as before but added a request for a "new paragraph" using a technical style with a conversational tone. It still summarized the draft into one paragraph but didn't plagiarize, and it drew some conclusions based on the content that wasn't written in the original piece.

Still, I wanted something other than a summary, so the third time I got very specific. 

I said: "Write a new paragraph based on the draft I provided, but write it not as a general summary of the content. Rather, write the paragraph so that I can put it into one part of the draft seamlessly. Use a technical style with a conversational tone, and do not format it as a large paragraph."

This time, the output showed me just how far this AI had come. I was terrified because all of my fears from when I first encountered it were coming to fruition, yet the failsafe limitations were no longer there – it was much, much smarter now.

It was able to draw conclusions from the draft and write, dare I say, original ideas based on it, also using tactics for writing well, such as varying the length of the sentences.

It even used some humanlike phrases to describe things, and most impressively, it was able to intuitively explain the limitations of its own abilities. The key lesson from my experiment was summarized best by the bot itself. ChatGPT is a "tool for language-based solutions rather than an intelligent conversationalist," it wrote after my third request.

I think ChatGPT is a game changer for writers and content creators. These were my 3 takeaways from my experience.

• Writers' roles won't disappear with the introduction of AI but will evolve more toward communication strategy. Writers and editors will be directing the AI's writing. Successfully employing the bot comes down to giving it clear instructions. The AI still needs to be supplied with specific goals, a target audience, and a tone of voice. It also needs to be asked the right questions .
• It has to be primed for a topic and given past content so it can imitate writing accurately. If writers want ChatGPT to produce worthwhile work, they will need to give it large amounts of contextual data. This will require writers to do thorough research and fact-checking because the AI could very well pull from the millions of inaccurate sources on the internet if not guided correctly.
• When the internet becomes flooded with half-hearted AI writing, people working in editorial roles will need to set their writing apart with human touches. Chatbots will become increasingly better at generating ideas and sampling text, which will make point-of-view reporting even more critical — perhaps through a personal perspective on a story or first-person interviews.

I think any future version of ChatGPT will need a human to fine-tune the final product. This will require writers and editors to develop their skills toward understanding how to implement and manage AI. So the sooner they can embrace ChatGPT, the better.

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

• Main content

Essay Writing

View details

Ready to start building?

At Apideck we're building the world's biggest API network. Discover and integrate over 12,000 APIs.

AI content detector

Use our free AI detector to check up to 5,000 words, and decide if you want to make adjustments before you publish. Read the disclaimer first.

AI content detection is only available in the Writer app as an API . Find out more in our help center article .

• Essay Editor

Synthesis Essay Examples

A synthesis essay is another piece of academic discourse that students often find difficult to write. This assignment indeed requires a more nuanced approach to writing and performing research. It’s particularly relevant to students taking an AP English Language and Composition exam, so learning how to write a synthesis essay is crucial to getting a high score.

This article will explore the definition of a synthesis essay, its functions, and objectives, and provide a tutorial on how to write a synthesis essay.

What is a synthesis essay?

To understand how to write a synthesis essay, we first need to figure out why it is called this way.

The word “synthesis” comes from the Greek language where it means “composition” or “collection.” This means that a synthesis essay can be interpreted as a piece of writing that combines something together. But what?

The Advanced Placement (AP) Program known for developing complex courses for high-school students includes a synthesis essay as one of its Language and Composition exam questions. In it, the AP Program asks students to analyze several sources of information and write an essay that “synthesizes” (or incorporates) evidence from some of the sources.

Thus, a synthesis essay is a written text that explores a certain issue using perspectives derived from multiple different sources.

Synthesis essay: format and objectives

Unlike other types of academic analysis, synthesis questions do not aim to evaluate the overall persuasiveness of your arguments. As a writer, you should aim to analyze, evaluate, and integrate diverse ideas into a coherent whole. Here are some of the skills students need to demonstrate in their synthesis essays:

• Analyzing sources . Before you learn how to start a synthesis essay, your task is to read and analyze the sources presented to you and understand what they’re about.
• Assessing the arguments . After familiarizing yourself with the available sources, you are supposed to evaluate if the arguments they support are strong or weak, which will help you determine the course of your essay.
• Identifying common positions . The next skill you must demonstrate is identifying common positions across the sources. By comparing and contrasting different viewpoints, the writer should be able to detect repeating ideas that contribute to a deeper understanding of the topic.
• Integrating sources . Your main task in a synthesis essay is combining ideas from different authors to create a cohesive argument. This will help you show how well you can extract information from various sources.

As you see, the chief goal of synthesis questions is to show how well you can analyze sources and derive information from them.

How to start a synthesis essay: tutorial

During an AP examination, you don’t have a lot of time to write the text. It can be stressful, and it’s not rare for students to panic and forget what to do. Don’t worry, with these simple steps, you’ll be able to create a great synthesis essay and ace your exam.

1. Scan the given sources

At first, you will be handed six sources that you’re supposed to briefly examine. These can include academic and newspaper articles, graphs, schedules, prompts, and other documents that can be used to support your future thesis statement.

Remember that you don’t have a lot of time, so take a quick look at the documents and leave short remarks that can help you remember which source supports or argues a certain opinion.

2. Develop your stance

After you’ve studied the sources, it’s time to come up with your stance and thesis statement. Note that, unlike other essays, the stance you must take in your synthesis essay might not correlate with your actual opinion.

Your task is to choose a position that you can support with the sources provided to you. This will showcase your ability to draw an unbiased and logical conclusion from a wide range of references. However, your stance should express an original idea and cannot paraphrase the points given in the source texts.

3. Write your essay

Your essay should start with a two or three-sentence-long introduction that gives background to the topic you’re going to be writing about. It should also include your thesis – the idea based on the evidence you’ve gathered that you’re going to defend in the next part of your essay. Don’t use personal pronouns as a synthesis essay provides an overview of facts instead of your opinion

The body of your synthesis essay should be built of several arguments. Each argument should refer to a specific part of your thesis and provide evidence to support the claims. Use the sources provided to you as evidence to validate your arguments. You should use at least three sources, but the more you incorporate in your text, the better. You can draw arguments and evidence from your background knowledge or include counter-arguments from the remaining sources. When you refer to the original documents, make sure to include the number of the source in brackets at the end of a sentence.

In your conclusion, restate your original thesis and summarize what you stated before. Don’t repeat the same thoughts. Instead, include a new idea you haven’t mentioned before or a call to action to finish your essay properly.

Synthesis essay: examples

The list of sources provided as part of the examination:

• A New York Times article about the relevance of blue-collar workers;
• A Washington Post article about the uselessness of art degrees;
• The Economist’s article about the decreasing wages of college graduates;
• A New Your Times article proving that college does pay off;
• An article about a businessman giving money to teens to start businesses instead of going to college
• A survey on whether college education is worth it

Is college worth it?

In the current era of shifting economic landscapes and evolving societal expectations, the value of higher education has become a subject of intense scrutiny. While some decades ago, a college education was considered the only solution to a better life, nowadays this sentiment is no longer relevant. Higher education can no longer guarantee high salaries and employment, not to mention the unbearable strain it puts on a future graduate’s finances.

The modern world of employment has shifted. While decades ago society needed information-centric professionals, now the situation is different. With the Internet, employers can now find new hires from all over the world with much cheaper salary expectations, leaving local college graduates with no choice but to agree to a lower pay than they expected[3]. This demonstrates the new trend of decreasing rewards for higher education that is very likely to continue in the future.

Another issue is the lack of employment in certain areas. It is no secret that Art and Humanities graduates have a tough time finding positions with adequate pay in the field they studied[2]. Many of them have to search for employment in other fields that have nothing to do with their degrees, which further proves that higher education does not provide job security.

Furthermore, the cost of higher education in America has been the subject of many debates. Even with scholarships and financial aid, many students still find themselves facing daunting loan repayments upon graduation[6]. This financial pressure can delay important milestones such as buying a home, starting a family, or saving for retirement. Additionally, the job market may not always align with graduates' expectations, making it challenging to secure well-paying positions to effectively manage their debt. As a result, the financial impact of college can be felt long after receiving a diploma, shaping the economic landscape of young professionals for years to come.

In conclusion, higher education no longer offers guaranteed employment and financial stability benefits, often leaving graduates with an exorbitant debt they can not afford. Because of this, the governments should reevaluate their current educational and economic policies and develop other areas of education like vocational schools to provide stability to future generations.

Conclusion: Writing a synthesis essay

A synthesis essay tests your ability to conduct objective analysis and derive facts from multiple different references. It helps you learn to put aside your personal bias and provide an objective overview of information even if it contradicts your opinion. To produce a high-scoring synthesis essay, work on your analytical skills and use them to find evidence to defend your position.

If answering synthesis questions gives you trouble, use essay generator Aithor to generate sample essays, learn how to derive main information from source texts, create a plan, and express your thoughts concisely and eloquently.

Related articles

How to write an essay in apa format.

There are a few styles of organizing and formatting material in an academic essay. To get high grades it is necessary to learn specific characteristics of each one. After reading this article students are certain to figure out how to write in APA format. What is APA format for an essay? It was the American Psychological Association who offered to use the APA style when formatting articles and academic papers. The specialists described all its aspects in a special Publication Manual, printed i ...

APA or MLA: Choosing the Right Citation Style for Your Paper

When it comes to academic writing, properly citing your sources is crucial. It not only helps you avoid plagiarism but also adds credibility to your work by showing that you've done your research. However, with various citation styles out there, it can be tricky to know which one to use. Two of the most common styles are APA (American Psychological Association) and MLA (Modern Language Association). In this article, we'll take a closer look at the APA vs MLA format to help you decide which is ri ...

What Is Chat GPT?

AI GPT chats have been getting a lot of attention over the last year. Not surprising since this new technology promises to change our future completely. The first and most well-known AI GPT chat software is ChatGPT officially released on November 30, 2022. In this article, we will answer the question “What is Chat GPT?”, explore how it works, and find out where to use the Chat GPT model. Chat GPT: definition As the name implies, ChatGPT is a chatbot that uses generative AI to process input p ...

Master the Art of Paraphrasing with This Comprehensive Guide

In academic writing, you often need to process a large number of sources to compile a thorough and credible examination. However, you can’t simply copy and paste all information into your text document. In such instances, paraphrasing becomes essential. In this short article, we’ll define paraphrasing, talk about why it’s important, and provide guidance on how to paraphrase in an essay. What is paraphrasing? Paraphrasing is a technique that involves rewriting the source text in a way that pr ...

How to Write Informative Essays

Informative essays are one of the main types of academic writing students must complete as part of the educational process. While this is a typical assignment in any curriculum, it can be hard to distinguish between different types of essays and how to write them. In this article, we’ll delve into the genre of this essay type, learn the definition of an informative essay, and how to write an informational essay. What is an informative essay? An informative essay is a piece of academic writin ...

Learn How to Write a Problem Solution Essay in No Time

For centuries, essays have been used as a creative outlet for expressing one’s thoughts on a variety of topics. Nowadays, these texts help students learn to articulate complex ideas in writing and develop their analytical skills. The most common educational essay is a problem solution essay. This essay type seems straightforward and easy to write. However, students often struggle to plan and how to structure their essays in the most compelling way. This article will help you learn more about t ...

How To Write Reflection Essays

How often do you contemplate how the tapestry of your experiences shapes your thoughts? A reflection paper lets you explore that. It's like deep diving into your life’s precious moments, examining how stories, books, events, or even lectures have influenced your views. This type of academic essay integrates a personal perspective, allowing you to openly express your opinions. In this guide, we will delve into the specifics of reflective writing, share some tips, and show some self-reflection es ...

MLA Format Essays: A Comprehensive Guide

Finishing an essay is one thing, but formatting it is a completely different affair. There are many style guides out there, so it can be hard to understand the differences between them. Today, you will learn about MLA format writing, what it is, when it’s used, and how to write MLA format essays. What is an MLA Style Essay? An MLA format essay is a piece of writing created in accordance with the MLA Style Handbook. This guide was developed by the Modern Language Association, the leading profe ...