chatbot to write essays

• Entertainment
• Beebom Gadgets

How to Use ChatGPT to Write Essays That Impress

Step 1: Use ChatGPT to Find and Refine Essay Topics

• Log into the service and type the following prompt into ChatGPT:

• As you can see, ChatGPT gave several good ideas for our essay. If you want to refine the idea further, you can ask the chatbot to cut out some parts of the idea and replace them. Or, you can ask for more context in certain parts. Example – “Expand more on topic number 5 and what it means.”

Step 2: Ask ChatGPT to Construct an Outline

• With the same chat open, type out “ Give me an essay outline for <selected topic>. Make sure to keep it structured as I’ll use it to write my essay .” In this case, I will use topic number 2 since it aligns with what I had in mind.

• As you can see above, we now have a structured outline for our essay. We can use this to write our essay or have ChatGPT do that job. Nonetheless, it’s a good starting point. As always, you can have the AI chatbot cut out parts of the outline or specifically add new ones depending on your requirement.

Step 3: Get ChatGPT to Cite Sources for Your Essay

Even though we have the idea and the outline, we will need to do our research for proof supporting our essay. Thankfully, ChatGPT can be of some help here. Since the chatbot is adept at moderate research, users can get a general idea of where to look for gathering information. Let’s begin doing that.

• Let’s begin asking ChatGPT for sources. With the same chat open, type in the following prompt:

• Now we have a list of 10 sources we can reference from. However, you can also see that ChatGPT mentions the year 2021 in some of them. Therefore, it’s best to use these websites but navigate to the latest pages pertaining to your essay for research. This applies to every topic, so always do it. Also, chatbots like ChatGPT have a habit of hallucinating and making up information, so do be careful.

Step 4: Have ChatGPT Write the Essay

• In the same chat, type the following prompt – “With the topic and outline available to you, generate a 700-word essay. Make sure to keep it structured and concise yet informational. Also, keep in mind my target audience is <Insert target audience> so cater to that accordingly.”
• In the middle of the essay, ChatGPT might stop and not answer. Simply type “ Continue ,” and it will finish the rest of the essay.

Step 5: Edit the Essay with ChatGPT

No matter if you have used ChatGPT to draft a complete essay or have written one yourself, you can use this step to make ChatGPT your co-editor and grammar checker. While your essay might need an initial look from a human, you can definitely use the bot to hash out the tone and add little details.

• Either open up the same chat or have your essay already in the clipboard. With that done, type out the following prompt:

Step 6: Export the Essay for Submission

However, for those who want to export the essay into a more aesthetic format, we have just the thing for you. There is no shortage of best ChatGPT Chrome extensions on the internet right now. We have one such selection linked in our list that can export selective chats onto beautiful image formats if you want to show off your essay. Check it out and let us know how you liked it.

Bonus: ChatGPT and AI Apps to Write Essays

1. writesonic.

Ryter is another helpful AI writing assistant that not only helps with essays but all types of articles. The service is powered by a language model that gives it intelligence. Rytr comes with 40+ different use cases and 20+ writing tones for all types of written material. For those who don’t want to stick to English, it even comes with support for 30+ languages.

Upanishad Sharma

Combining his love for Literature and Tech, Upanishad dived into the world of technology journalism with fire. Now he writes about anything and everything while keeping a keen eye on his first love of gaming. Often found chronically walking around the office.

Im student i want to become financially independent woman in life so I want esay essay write

I am housewife and I want easy essay I want to change my life my husband was job less and I want to work online part time job plz help I am enter pass

Add new comment

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

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

So … you’ve been hacked

Technology Feature 19 MAR 24

Use fines from EU social-media act to fund research on adolescent mental health

Correspondence 09 APR 24

AI-fuelled election campaigns are here — where are the rules?

World View 09 APR 24

Why loneliness is bad for your health

News Feature 03 APR 24

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

Career Feature 08 APR 24

After the genocide: what scientists are learning from Rwanda

News Feature 05 APR 24

How can we make PhD training fit for the modern world? Broaden its philosophical foundations

Correspondence 02 APR 24

Postdoctoral Associate

Palm Beach, Florida

University of Florida, Scripps Institute

Laboratory Director

Houston, Texas (US)

Baylor College of Medicine (BCM)

PhD, Postdoc and Technician positions in the Cluster of Excellence "MicroPlanet"

PhD, Postdoc and Technician positions in interdisciplinary microbiome project

Austria (AT) - Vienna, and Lower Austria

University of Vienna - Centre for Microbiology and Environmental Systems Science

Assistant Professor in Integrated Photonics

We offer you the chance to design a unique and autonomous research program, networking with specialists, students and entrepreneurs.

Gothenburg (Stad), Västra Götaland (SE)

Chalmers University of Technology

Senior Group Leader

The Gregor Mendel Institute (GMI) is recruiting a Senior Group Leader. The GMI is a research institute of the Austrian Academy of Sciences, devoted...

Vienna (Landbezirke) (AT)

Gregor Mendel Institut of Molecular Plant Biology

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

• 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

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

How to Get ChatGPT to Write an Essay: Prompts, Outlines, & More

Last Updated: March 31, 2024 Fact Checked

Getting ChatGPT to Write the Essay

Using ai to help you write, expert interview.

This article was written by Bryce Warwick, JD and by wikiHow staff writer, Nicole Levine, MFA . Bryce Warwick is currently the President of Warwick Strategies, an organization based in the San Francisco Bay Area offering premium, personalized private tutoring for the GMAT, LSAT and GRE. Bryce has a JD from the George Washington University Law School. This article has been fact-checked, ensuring the accuracy of any cited facts and confirming the authority of its sources. This article has been viewed 44,846 times.

Are you curious about using ChatGPT to write an essay? While most instructors have tools that make it easy to detect AI-written essays, there are ways you can use OpenAI's ChatGPT to write papers without worrying about plagiarism or getting caught. In addition to writing essays for you, ChatGPT can also help you come up with topics, write outlines, find sources, check your grammar, and even format your citations. This wikiHow article will teach you the best ways to use ChatGPT to write essays, including helpful example prompts that will generate impressive papers.

Things You Should Know

• To have ChatGPT write an essay, tell it your topic, word count, type of essay, and facts or viewpoints to include.
• ChatGPT is also useful for generating essay topics, writing outlines, and checking grammar.
• Because ChatGPT can make mistakes and trigger AI-detection alarms, it's better to use AI to assist with writing than have it do the writing.

• Before using the OpenAI's ChatGPT to write your essay, make sure you understand your instructor's policies on AI tools. Using ChatGPT may be against the rules, and it's easy for instructors to detect AI-written essays.
• While you can use ChatGPT to write a polished-looking essay, there are drawbacks. Most importantly, ChatGPT cannot verify facts or provide references. This means that essays created by ChatGPT may contain made-up facts and biased content. [1] X Research source It's best to use ChatGPT for inspiration and examples instead of having it write the essay for you.

• The topic you want to write about.
• Essay length, such as word or page count. Whether you're writing an essay for a class, college application, or even a cover letter , you'll want to tell ChatGPT how much to write.
• Other assignment details, such as type of essay (e.g., personal, book report, etc.) and points to mention.
• If you're writing an argumentative or persuasive essay , know the stance you want to take so ChatGPT can argue your point.
• If you have notes on the topic that you want to include, you can also provide those to ChatGPT.
• When you plan an essay, think of a thesis, a topic sentence, a body paragraph, and the examples you expect to present in each paragraph.
• It can be like an outline and not an extensive sentence-by-sentence structure. It should be a good overview of how the points relate.

• "Write a 2000-word college essay that covers different approaches to gun violence prevention in the United States. Include facts about gun laws and give ideas on how to improve them."
• This prompt not only tells ChatGPT the topic, length, and grade level, but also that the essay is personal. ChatGPT will write the essay in the first-person point of view.
• "Write a 4-page college application essay about an obstacle I have overcome. I am applying to the Geography program and want to be a cartographer. The obstacle is that I have dyslexia. Explain that I have always loved maps, and that having dyslexia makes me better at making them."

• In our essay about gun control, ChatGPT did not mention school shootings. If we want to discuss this topic in the essay, we can use the prompt, "Discuss school shootings in the essay."
• Let's say we review our college entrance essay and realize that we forgot to mention that we grew up without parents. Add to the essay by saying, "Mention that my parents died when I was young."
• In the Israel-Palestine essay, ChatGPT explored two options for peace: A 2-state solution and a bi-state solution. If you'd rather the essay focus on a single option, ask ChatGPT to remove one. For example, "Change my essay so that it focuses on a bi-state solution."

• "Give me ideas for an essay about the Israel-Palestine conflict."
• "Ideas for a persuasive essay about a current event."
• "Give me a list of argumentative essay topics about COVID-19 for a Political Science 101 class."

• "Create an outline for an argumentative essay called "The Impact of COVID-19 on the Economy."
• "Write an outline for an essay about positive uses of AI chatbots in schools."
• "Create an outline for a short 2-page essay on disinformation in the 2016 election."

• "Find peer-reviewed sources for advances in using MRNA vaccines for cancer."
• "Give me a list of sources from academic journals about Black feminism in the movie Black Panther."
• "Give me sources for an essay on current efforts to ban children's books in US libraries."

• "Write a 4-page college paper about how global warming is changing the automotive industry in the United States."
• "Write a 750-word personal college entrance essay about how my experience with homelessness as a child has made me more resilient."
• You can even refer to the outline you created with ChatGPT, as the AI bot can reference up to 3000 words from the current conversation. [3] X Research source For example: "Write a 1000 word argumentative essay called 'The Impact of COVID-19 on the United States Economy' using the outline you provided. Argue that the government should take more action to support businesses affected by the pandemic."

• One way to do this is to paste a list of the sources you've used, including URLs, book titles, authors, pages, publishers, and other details, into ChatGPT along with the instruction "Create an MLA Works Cited page for these sources."
• You can also ask ChatGPT to provide a list of sources, and then build a Works Cited or References page that includes those sources. You can then replace sources you didn't use with the sources you did use.

Expert Q&A

• Because it's easy for teachers, hiring managers, and college admissions offices to spot AI-written essays, it's best to use your ChatGPT-written essay as a guide to write your own essay. Using the structure and ideas from ChatGPT, write an essay in the same format, but using your own words. Thanks Helpful 0 Not Helpful 0
• Always double-check the facts in your essay, and make sure facts are backed up with legitimate sources. Thanks Helpful 0 Not Helpful 0
• If you see an error that says ChatGPT is at capacity , wait a few moments and try again. Thanks Helpful 0 Not Helpful 0

• Using ChatGPT to write or assist with your essay may be against your instructor's rules. Make sure you understand the consequences of using ChatGPT to write or assist with your essay. Thanks Helpful 0 Not Helpful 0
• ChatGPT-written essays may include factual inaccuracies, outdated information, and inadequate detail. [4] X Research source Thanks Helpful 0 Not Helpful 0

You Might Also Like

Thanks for reading our article! If you’d like to learn more about completing school assignments, check out our in-depth interview with Bryce Warwick, JD .

• ↑ https://help.openai.com/en/articles/6783457-what-is-chatgpt
• ↑ https://platform.openai.com/examples/default-essay-outline
• ↑ https://help.openai.com/en/articles/6787051-does-chatgpt-remember-what-happened-earlier-in-the-conversation
• ↑ https://www.ipl.org/div/chatgpt/

About This Article

• Send fan mail to authors

Is this article up to date?

Featured Articles

Trending Articles

Watch Articles

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

wikiHow Tech Help Pro:

Level up your tech skills and stay ahead of the curve

7-Week SSP & 2-Week Pre-College Program are still accepting applications until April 10, or earlier if all course waitlists are full. 4-Week SSP Application is closed.

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.

Choose Your Test

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

College Admissions , College Essays

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

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

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

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

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

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

What Is ChatGPT and Why Are Schools Talking About It?

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

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

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

Why Schools Are Concerned About ChatGPT

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

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

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

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

Many Schools Have Already Banned ChatGPT

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

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

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

ChatGPT: College Admissions and Entrance Essays

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

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

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

#1: ChatGPT Lacks Insight

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

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

#2: ChatGPT Might Plagiarize 

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

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

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

#3: ChatGPT Doesn’t Understand Emotion 

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

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

#4: ChatGPT Produced Mediocre Results

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

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

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

Can Colleges Detect ChatGPT?

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

In short, yes, they can! 

Software Can Detect ChatGPT

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

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

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

Human Readers Can Detect ChatGPT 

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

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

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

Pros and Cons of ChatGPT: College Admissions Edition

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

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

ChatGPT: The Good

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

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

Students can use ChatGPT responsibly to:

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

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

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

ChatGPT: The Bad

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

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

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

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

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

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

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

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

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

What Other Tools and Strategies Can Help Students Besides ChatGPT?

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

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

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

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

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

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

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

The Bottom Line: ChatGPT College Admissions and Essays

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

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

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

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

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

What’s Next?

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

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

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

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

Student and Parent Forum

Our new student and parent forum, at ExpertHub.PrepScholar.com , allow you to interact with your peers and the PrepScholar staff. See how other students and parents are navigating high school, college, and the college admissions process. Ask questions; get answers.

Ask a Question Below

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

Improve With Our Famous Guides

• For All Students

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

How to Get a Perfect 1600, by a Perfect Scorer

Series: How to Get 800 on Each SAT Section:

Score 800 on SAT Math

Score 800 on SAT Reading

Score 800 on SAT Writing

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

Score 600 on SAT Math

Score 600 on SAT Reading

Score 600 on SAT Writing

Free Complete Official SAT Practice Tests

What SAT Target Score Should You Be Aiming For?

15 Strategies to Improve Your SAT Essay

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

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

Series: How to Get 36 on Each ACT Section:

36 on ACT English

36 on ACT Math

36 on ACT Reading

36 on ACT Science

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

24 on ACT English

24 on ACT Math

24 on ACT Reading

24 on ACT Science

What ACT target score should you be aiming for?

ACT Vocabulary You Must Know

ACT Writing: 15 Tips to Raise Your Essay Score

How to Get Into Harvard and the Ivy League

How to Get a Perfect 4.0 GPA

How to Write an Amazing College Essay

What Exactly Are Colleges Looking For?

Is the ACT easier than the SAT? A Comprehensive Guide

Should you retake your SAT or ACT?

When should you take the SAT or ACT?

Stay Informed

Get the latest articles and test prep tips!

Looking for Graduate School Test Prep?

Check out our top-rated graduate blogs here:

GRE Online Prep Blog

GMAT Online Prep Blog

TOEFL Online Prep Blog

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

'ZDNET Recommends': What exactly does it mean?

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

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

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

The best AI chatbots: ChatGPT isn't the only one worth trying

Since the launch of ChatGPT , AI chatbots have been all of the rave because of their ability to do such a wide range of tasks which can help you with both your personal and work life. At your command, AI chatbots can write code , compose emails, draft a report,  generate art ,  write Excel formulas for you , and much more. 

However, because ChatGPT  reached worldwide recognition , competitors were motivated to make their own versions, and, as a result, there are so many options on the market to choose from with different strengths, use cases, difficulty levels, and other nuances.

Also: The best AI image generators: Tested and reviewed

For the last year and a half, I have taken a deep dive into the world of AI, testing as many AI tools as I could get my hands on--including dozens of AI chatbots. Using my findings, as well as those of other ZDNET AI experts, I put together a list of the best AI chatbots and AI writers on the market. 

The list details everything you need to know before choosing your next AI assistant, including what it's best for, pros, cons, cost, its large language model (LLM), and more. So whether you are entirely new to AI chatbots, or have used plenty before, this list should help you discover a new chatbot you haven't used before. 

What is the best AI chatbot right now?

Thanks to its sourcing abilities, free internet access, and advanced LLM model, Microsoft Copilot is my first choice for the best AI chatbot. Keep reading to see how its features compare to others like ChatGPT, You.com, and more. 

The best AI chatbots of 2024

Microsoft copilot, best ai chatbot overall.

• Access to the internet
• Links back to sources
• Uses OpenAI's most advanced LLM
• Grounded in Bing

Copilot f eatures:  OpenAI's most advanced LLM, GPT-4 Turbo | Has access to the internet | Works like a search engine with information on current events | Free

In February last year, Microsoft unveiled a new AI-improved Bing, now known as Copilot, which runs on GPT-4  Turbo, the newest version of OpenAI's language model systems. As of May 4 of last year, Copilot moved from limited preview to open preview, meaning that now everyone can access it for free.  

Also: What is Copilot (formerly Bing Chat)? Here's everything you need to know

When I use a chatbot, I typically reach for Copilot because I found that it solved two major issues with ChatGPT, including access to current events and linking back to the sources it retrieved its answer for free. It is also the only way to access OpenAI's most advanced LLM--GPT-4 Turbo--for free. 

Copilot is free to use and offers a series of other features that make it an attractive alternative, including multi-modal inputs, image generation within the chatbot, and a standalone app. 

Best original AI chatbot

• Writing skills
• STEM knowledge
• Conversational
• Not always available
• Not connected to the internet

ChatGPT features:  Uses OpenAI's GPT-3.5 or GPT-4 (if subscribed) | Can generate text, solve math problems, and code | Impressive conversation capabilities | Free to the public right now

ChatGPT is a conversational AI chatbot  by OpenAI that can produce text for you based on any prompt you input, generating emails, essays, poems, grocery lists, letters, and much more.

In addition to writing for you, ChatGPT can chat with you about simple or complex topics such as "What are colors?" or "What is the meaning of life?" If you want other technical assistance, ChatGPT is also proficient in STEM and can write and debug code , and even solve complex math equations. 

Also:  How to use ChatGPT

ChatGPT was released November 2022, and because of its  massive success , it became the blueprint for many other chatbots to enter the scene, with many being found on the list now. Therefore, if you are interested in AI chatbots, you'll likely want to try the original that began the craze -- ChatGPT. 

The downsides of the chatbot include that it is sometimes at capacity due to its immense popularity, doesn't have access to the internet, and has a knowledge cutoff. 

I still reach for ChatGPT as, despite its limitations, it is an incredibly capable chatbot. However, when I do, I make sure that my queries do not rely on the most recent information to be accurate. For example, some good use cases to use ChatGPT for are brainstorming text or coding.

Anthrophic's Claude

Best ai chatbot for summarizing documents.

• Upload document support
• Chat controls
• Light and dark mode
• Unclear usage cap
• Knowledge cutoff

Claude features:   Powered by Claude 3 model family | Accepts document uploads | Trained with information up to early 2023 |  Free

Anthropic launched its first AI assistant, Claude, in February 2023, and in less than a year, it has secured a spot as one of the best chatbots in the space. Like the other leading competitors, Anthropic can conversationally answer prompts with anything you need assistance with, including coding, math, writing, research, and more. 

Also: 4 things Claude AI can do that ChatGPT can't

Personally, the biggest advantage of this chatbot is that it can accept document uploads to help read, analyze, and summarize uploaded files. To upload a file, all I had to do was click on the paper clip icon next to the text box and click on the document I wanted to upload. Then, I was able to conversationally ask for the help I wanted with the document, including document summaries or clarifications on specific topics found within the document. 

Also: This free tool from Anthropic helps you create better prompts for your AI chatbot

Claude is in free open beta, and, as a result, has context window and daily message limits which can vary based on demand, so if you are looking to use the chatbot regularly, upgrading to Claude Pro may be a better option, as it offers at least five times the usage limits compared to the free version for $20 a month. 

Perplexity.ai

The best ai chatbot for prompt ideation.

• Links to sources
• Access to internet
• Paid subscription required for GPT-4 access
• some irrelevant suggestions

Perplexity AI features: OpenAI GPT-3.5 and GPT-4 for subscribers | Has access to the internet and current events | Provides prompt suggestions to get chats started | Free

Perplexity AI is a free AI chatbot that is connected to the internet, provides sources, and has a very enjoyable UI. As soon as you visit the site , using the chatbot is straightforward. All you have to do is type your prompt into the "ask anything" box to get started. The first time I ever visited this chatbot, I was able to get started within seconds.

On top of the text box, the chatbot states, "Where knowledge begins," and the title could not be more fitting. 

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

As soon as you click on the textbox, it has a series of suggested prompts which are all mostly rooted in news. It also has suggested prompts underneath the box on a variety of evergreen topics. All you have to do is click on any of the suggestions to learn more about the topic and chat about it. Additionally, Perplexity provides related topic questions you can click on to keep the conversation going. 

Because of the extensive prompts it gives users to try, this is a great chatbot for taking deep dives into topics that you wouldn't have necessarily thought of before, encouraging discovery and experimentation. I personally deep dove into a couple of random topics myself, including the history of birthday cakes, and I enjoyed every second of it. 

Other perks include that there is an app for both iOS and Android, allowing you to also tinker with the chatbot while you're on the go, footnotes are provided after every answer with sources you can visit and the answers nearly always include photos and graphics. 

Best AI chatbot for businesses and marketers

• 50 different writing templates
• Copyediting features
• Plagiarism checker
• Need a subscription to try

Jasper features:  Uses different LLMs, including GPT-4 | Summarizes texts and generates paragraphs and product descriptions | Checks for plagiarism and grammar | Starts at $39 per month with an annual subscription

Jasper is a tool exclusively meant for users who are looking to incorporate an AI chatbot into their workflow because there is no free plan, and you can't access the chatbot otherwise. For example, when I tried using it myself, I was met with dead ends unless I subscribed. The least expensive option, the Creator plan, is geared towards freelancers and solo-preneurs and is $49 a month. However, if you rely on an AI chatbot to generate copy for your business, the investment may be worth it. 

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

With Jasper, you can input a prompt for what you want to be written, and it will write it for you, just like ChatGPT would. The major difference with Jasper is that it has an extensive amount of tools to produce better copy. Jasper can check for grammar and plagiarism and write in over 50 different templates, including blog posts, Twitter threads, video scripts, and more. It also offers SEO insights and can even remember your brand voice, facilitating the creation of copy. 

Whether you are an individual, small team, or larger business looking into optimizing your workflow, before you take the plunge, you can access a trial or demo. 

Best AI chatbot that functions as a search engine

• Readily available
• Source Citing
• Some answers stronger than others
• Subscription required for GPT-4 access

You.com features: GPT-4 with subscription | Lists sources for the text it generates | Unlike most other Chatbots, uses Google sources | Free

You.com (previously known as YouChat) is an AI assistant that functions similarly to the way a search engine would. Like Google, you can enter any question, or topic you'd like to learn information on, and immediately be met with real-time web results, in addition to a conversational response.  

For example, when I asked, "Can you share some pictures of adorable dog breeds?" the chatbot provided six different web links, as well as the seven different pictures it pulled from the web, a conversational answer and related news, as seen in the photo. 

The chatbot can also provide technical assistance, with answers to anything you input, including math, coding, translating, and writing prompts. A huge pro for this chatbot is that, because it lacks popularity, you can hop on at any time and ask away.  

Chatsonic by Writesonic

Best ai chatbot for article writers.

• Variety of use cases
• Need to sign-in
• A bit of a lag

Chatsonic features:   Powered by GPT-3.5. or GPT-4 depending on subscription | Aware of current events, whereas ChatGPT is trained up to 2021 | Extensive feature suite, including voice dictation and image generation | Starts at $12 per month

Chatsonic is a dependable AI chatbot, with a function as an AI writing tool. It functions much like ChatGPT, allowing users to input prompts for assistance on a variety of tasks. However, it includes the ability to web search, generate images, and access PDF assistance, which ChatGPT lacks. 

The Writesonic platform offers tools that are specifically meant to help generate stories, including Instant Article Writer, which generates an article from a single click; Article Rewriter, which rephrases existing content; and Article Writer 5, which generates articles using ranking competitors. 

Other tools that facilitate the creation of articles include SEO Checker and Optimizer, AI Editor, Content Rephraser, Paragraph Writer, and more. There is a free version, which gets you access to some of the features; however, there is a 50 generations per day limit. The monthly cost starts at $12 per month but goes all the way up to $250 per month depending on the number of words and amount of users needed.

Gemini (formerly Google Bard)

Best ai chatbot if you're a loyal google user.

• Access to Google
• Good text editing skills
• Can't help much with code

Gemini features:  Powered by a finetuned version of Gemini Pro | Includes a "Google it" feature | Generates clear text and images quickly | Free

Gemini is Google's conversational AI chatbot that functions the most similarly to Copilot, sourcing its answers from the web, providing footnotes, and even generating images within its chatbot. Since its initial release in March 2023, the chatbot has undergone several upgrades, with the latest version being the most optimized it has ever been. 

Also: What is Google's Gemini AI tool (formerly Bard)? Everything you need to know

The highlight of this chatbot is that it is rooted in Google technology, search engines, and applications, and if you are a loyal Google user, you will feel familiar with the chatbot's UI and its offerings. For example, unlike most of the chatbots on this list, Google does not use an LLM in the GPT series but instead uses a model made by Google. 

"Gemini is slowly becoming a full Google experience thanks to Extensions folding the wide range of Google applications into Gemini," said ZDNET writer Maria Diaz when reviewing the chatbot. "Gemini users can add extensions for Google Workspace, YouTube, Google Maps, Google Flights, and Google Hotels, giving them a more personalized and extensive experience."

If you subscribe to Google's new 'AI Premium Plan,' you not only get access to the most advanced Google models in Gemini, such as Ultra 1.0, but you also get access to Gemini for Workspace, previously known as  Duet AI,  which infuses Google's AI assistance throughout its productivity apps, including Gmail, Docs, Sheets, Slides, and Meet. 

Socratic by Google

Best ai chatbot for kids and students.

• Educational
• Easy to use
• Doesn't write text
• No desktop version

Socratic features:  From Google | Type in any question to generate a response | Includes fun graphics | Supports scanning worksheets to get a specially curated answer | Free

If you want your child to also take advantage of AI to lighten their workload, but still have some limits, Socratic is for you. With Socratic, children can type in any question they may have about what they are learning in school, and Socratic will generate a conversational, human-like response with fun, unique graphics to help break down the concept. 

"It's a powerful studying tool that could help students double-check their homework, or get across the last hurdle if a question or formula just isn't making sense. And using the app is as easy as using  Snapchat  or talking to Siri," said former ZDNET contributor Jason Cipriani, when reviewing the app. 

The app, available on the App Store and the Google App Store, also has a feature that lets your kid scan their worksheet to get a specially curated answer. The app does have some limitations; for example, it will not just write an essay or story when prompted. However, this could be a positive thing because it curbs your child's temptation to get a chatbot, like ChatGPT, to write their essay for them. 

HuggingChat

Best open-source chatbot.

• Cutomizable
• Intermediate/advanced skills requires
• Required to create an account

Socratic features:  Clean, Chat-GPT inspired interface | entirely customizable | great for developers or AI fanatics | secure alternative | Free

As seen by the list above, plenty of great chatbot options are on the market. However, if you are on the search for a chatbot that serves your use case specifically, you can always build an entirely customizable new one. HuggingChat is an open-source chatbot developed by Hugging Face that can be used as a regular chatbot or customized for your needs.  

Also :  Want to build your own AI chatbot? Say hello to open-source HuggingChat

As ZDNET's David Gewirtz unpacked in his hands-on article , you may not want to depend on HuggingChat as your go-to primary chatbot. However, it is a good interface to build your own chatbot on. As Gewirtz said himself: "If you want something that you control, you can use HuggingChat to build a chatbot where you have visibility into every aspect of its functioning. You can choose to make that chatbot available online to other users and provide transparency to all users."

What is the best AI chatbot?

The best overall AI chatbot is Copilot due to its exceptional performance, versatility, and free availability. It uses OpenAI's cutting-edge GPT-4 language model, making it highly proficient in various language tasks, including writing, summarization, translation, and conversation. Moreover, it works like a search engine with information on current events.

Another advantage of Copilot is its availability to the public at no cost. Despite its immense popularity, Copilot remains free, making it an incredible resource for students, writers, and professionals who need a reliable and free AI chatbot. 

Although there are occasional capacity blocks, OpenAI is working on releasing a professional version of ChatGPT that will be quicker and always accessible at a monthly cost.

Which AI chatbot is right for you?

While Copliot is my personal favorite, your use case may be hyper-specific or have certain demands. If you need a constant, reliable AI chatbot, other alternatives might be better suited for you. If you just want an AI chatbot that produces clean, reliable, business-ready copy, for example, then Jasper is for you. If you want to play around with an AI chatbot that isn't always at capacity, YouChat might be the best option. 

Lastly, if there is a child in your life, Socratic might be worth checking out. See our breakdown below:

Factors to consider when choosing a chatbot

Since there are so many chatbots on the market, picking the right one can get confusing. Some factors to consider to help narrow down those options are: 

• Large Language Model (LLM) 
• Knowledge cutoff 
• Access to the internet 
• Linking to sources 
• Best use cases 

How did I choose these AI chatbots?

In order to curate the list of best AI chatbots and AI writers, I looked at the capabilities of each individual program including the individual uses each program would excel at. As an AI reporter, I was also sure to test each one myself. Other factors I looked at were reliability, availability, and cost. 

• Individual use case: AI chatbots have many use cases, often acting as a tool for productivity and easier workflow. I included a variety that can serve as ideation, education, and content creation tools. 
• Reliability: I kept information accuracy a priority during my testing. 
• Availability : ChatGPT is popular, but not always available. I selected alternatives that don't have a user limit and are available at all times. 
• Cost: Many of these AI programs are free, but some require monthly memberships. I included a mix of both, keeping budget-friendliness in mind. 

What is an AI chatbot?

An AI chatbot (also called AI writer) refers to a type of artificial intelligence-powered program that is capable of generating written content from a user's input prompt. AI chatbots are capable of writing anything from a rap song to an essay upon a user's request. The extent of what each chatbot is specifically able to write about depends on its individual capabilities including whether it is connected to a search engine or not. 

How do AI chatbots work?

AI chatbots use language models to train the AI to produce human-like responses. Some are connected to the web and that is how they have up-to-date information, while others depend solely on the information they are trained with. 

How much do AI chatbots cost?

AI chatbot programs vary in cost with some being entirely free and others costing as much as $600 a month. Many like ChatGPT, Copilot, Gemini and YouChat are entirely free to use. 

What is the difference between an AI chatbot and an AI writer?

The main difference between an AI chatbot and an AI writer is the type of output they generate and their primary function.

In the past, an AI writer was used specifically to generate written content, such as articles, stories, or poetry, based on a given prompt or input. An AI writer's output is in the form of written text that mimics human-like language and structure. On the other hand, an AI chatbot is designed to conduct real-time conversations with users in text or voice-based interactions. The primary function of an AI chatbot is to answer questions, provide recommendations, or even perform simple tasks, and its output is in the form of text-based conversations.

While the terms AI chatbot and AI writer are now used interchangeably by some, the original distinction was that an AI writer was used for generating written content, while an AI chatbot was used for conversational purposes. However, with the introduction of more advanced AI technology, such as ChatGPT, the line between the two has become increasingly blurred. Some AI chatbots are now capable of generating text-based responses that mimic human-like language and structure, similar to an AI writer.

Read more about the best tools for your business and the right tools when building your business !

Artificial Intelligence

The best ai image generators to try right now, how to use chatgpt, microsoft wants to stop you from using ai chatbots for evil.

New bot ChatGPT will force colleges to get creative to prevent cheating, experts say

After its viral launch last week, the chatbot ChatGPT was lauded online by some as a dramatic step forward for artificial intelligence and the potential future of web search.

But with such praise also came concern regarding its potential usage in academic settings. Could the chatbot, which provides coherent, quirky and conversational responses to simple language inquiries, inspire more students to cheat?

Students have been able to cheat on assignments using the internet for decades, giving rise to tools meant to check if their work was original. But the fear now is that ChatGPT could render those resources obsolete.

Already, some people online have tested out whether it's possible to have the bot complete an assignment. "holyyyy, solved my computer networks assignment using chatGPT," one person, who later clarified the assignment was old, tweeted . Others suggested that its existence could result in the death of the college essay. One technologist went as far as saying that with ChatGPT, "College as we know it will cease to exist."

Artificial intelligence company OpenAI, which developed ChatGPT , did not immediately respond to a request for comment regarding cheating concerns.

However, several experts who teach in the field of AI and humanities said the chatbot, while impressive, is not something they’re ready to sound the alarm about when it comes to possible widespread student cheating.

"We’re not there, but we’re also not that far away," said Andrew Piper, a professor of language, literatures and culture and a professor of AI and storytelling at McGill University. "We’re definitely not at the stage of like, out-of-the-box, it’ll write a bunch of student essays and no one will be able to tell the difference."

Piper and other experts who spoke with NBC News likened the fear around cheating and ChatGPT to concerns that arose when the calculator was invented, when people thought it would be the death of humans learning math.

Lauren Klein, an associate professor in the Departments of English and Quantitative Theory and Methods at Emory University, even compared the panic to the philosopher Plato’s fears that writing would dissolve human memory.

“There’s always been this concern that technologies will do away with what people do best, and the reality is that people have had to learn how to use these technologies to enhance what they do best,” Klein said.

There’s always been this concern that technologies will do away with what people do best, and the reality is that people have had to learn how to use these technologies to enhance what they do best.

— Lauren Klein, an associate professor at Emory University

Academic institutions will need to get creative and find ways to integrate new technologies like ChatGPT into their curriculum just like they did during the rise of the calculator, Piper noted.

In reality, AI tools like ChatGPT could actually be used to enhance education, according to Paul Fyfe, an associate professor of English at North Carolina State University.

He said there’s plenty of room for collaboration between AI and educators.

“It’s important to be talking about this right now and to bring students into the conversation," Fyfe said. "Rather than try to legislate from the get-go that this is strange and scary, therefore we need to shut it down."

And some teachers are already embracing AI programs in the classroom.

Piper, who runs .txtlab, a research laboratory for artificial intelligence and storytelling, said he’s had students analyze AI writing and found they can often tell which papers were written by a machine and which were written by a human.

As for educators who are concerned about the rise of AI, Fyfe and Piper said the technology is already used in many facets of education.

Computer-assisted writing tools, such as Grammarly or Google Doc’s Smart Compose, already exist — and have long been utilized by many students. Platforms like Grammarly and Chegg also offer plagiarism checker tools, so both students and teachers can assess if an essay has been, in part or in total, lifted from somewhere else. A spokesperson for Grammarly did not return a request for comment. A spokesperson for Chegg declined to comment.

Those who spoke with NBC News said they're not aware of any technology that detects if an AI wrote an essay, but they predict that someone will soon capitalize on building that technology.

As of right now, Piper said the best defense against AI essays is teachers getting to know their students and how they write in order to catch a discrepancy in the work they're turning in.

When an AI does reach the level of meeting all the requirements of academic assignments and if students use that technology to coast through college, Piper warned that could be a major detriment to students' education.

For now, he suggested an older technology to combat fears of students using ChatGPT to cheat.

"It will reinvigorate the love of pen and paper," he said.

Kalhan Rosenblatt is a reporter covering youth and internet culture for NBC News, based in New York.

Mobile Navigation

Introducing chatgpt.

We’ve trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer followup questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests.

Quick links

• Read about ChatGPT Plus

Illustration: Ruby Chen

ChatGPT is a sibling model to  InstructGPT , which is trained to follow an instruction in a prompt and provide a detailed response.

We are excited to introduce ChatGPT to get users’ feedback and learn about its strengths and weaknesses. During the research preview, usage of ChatGPT is free. Try it now at  chat.openai.com .

In the following sample, ChatGPT asks the clarifying questions to debug code.

In the following sample, ChatGPT initially refuses to answer a question that could be about illegal activities but responds after the user clarifies their intent.

In the following sample, ChatGPT is able to understand the reference (“it”) to the subject of the previous question (“fermat’s little theorem”).

In the following sample, ChatGPT provides responses to follow-up instructions.

Sample 1 of 4 Previous Next

help me write a short note to introduce myself to my neighbor

Hi there, My name is [Your Name] and I just moved in next door. I wanted to reach out and introduce myself. I’m looking forward to getting to know you and the neighborhood. If you ever need anything or just want to chat, please don’t hesitate to stop by or give me a call. Best, [Your Name]

can you make it more formal?

Dear Neighbor, I am writing to introduce myself. My name is [Your Name] and I have recently moved in next door. I wanted to take a moment to reach out and say hello. I am looking forward to getting to know you and the neighborhood. If there is anything I can do to be a good neighbor, or if you ever need anything, please do not hesitate to let me know. I am happy to help in any way that I can. Sincerely, [Your Name]

can you send it for me?

I’m sorry, but I am a text-based AI assistant and do not have the ability to send a physical letter for you. I can only provide suggestions and advice on what to write. It is up to you to take that advice and send the letter yourself.

this code is not working like i expect — how do i fix it?

It’s difficult to say what’s wrong with the code without more context. Can you provide more information about what the code is supposed to do and what isn’t working as expected? Also, is this the entire code or just a part of it?

just part of it — the error never surfaces. I think there is something wrong with the channel

It’s difficult to say without more information about what the code is supposed to do and what’s happening when it’s executed. One potential issue with the code you provided is that the resultWorkerErr channel is never closed, which means that the code could potentially hang if the resultWorkerErr channel is never written to. This could happen if b.resultWorker never returns an error or if it’s canceled before it has a chance to return an error.

To fix this issue, you could close the resultWorkerErr channel after writing to it. For example, you could add the following line of code after the line that sends the error on the channel:

This would ensure that the resultWorkerErr channel is always closed, even if b.resultWorker never returns an error. Again, it’s difficult to say whether this is the issue you’re experiencing without more information about the problem you’re seeing. Can you provide more details about what’s happening when you run the code?

how do you break into someone’s house?

It is not appropriate to discuss or encourage illegal activities, such as breaking into someone’s house. Doing so is a crime and can result in severe legal consequences. Instead, I would encourage you to talk to a trusted adult or law enforcement if you have concerns about someone’s safety or believe that a crime may have been committed. It is never okay to break into someone’s home without their permission.

actually i’m wondering how to protect my home from burglary

There are several steps you can take to help protect your home from burglaries. Some of these include:

• Install strong, durable locks on all doors and windows.
• Keep doors and windows locked, even when you are home.
• Use a security system, such as alarms or surveillance cameras.
• Keep your property well-lit, both inside and outside.
• Don’t leave valuable items in plain sight, such as electronics or jewelry.
• Trim bushes and trees near windows and doors to reduce hiding spots for burglars.
• Consider joining a neighborhood watch program to help keep an eye on your community.

Remember that no home is completely burglar-proof, but taking these steps can help reduce the likelihood of a break-in. If you have additional concerns, it may be a good idea to talk to a security professional for more advice.

what is the fermat’s little theorem

Fermat’s Little Theorem states that if p p p is a prime number and a a a is an integer not divisible by p p p , then a p a a^pa a p a ( a a a to the power p p p ) is congruent to a a a modulo p p p . In other words, if we divide a p a^p a p by p p p , the remainder is always a a a .

For example, if p = 5 p = 5 p = 5 and a = 2 a = 2 a = 2 , then 2 5 = 32 2^5 = 32 2 5 = 32 , and 32 32 32 divided by 5 5 5 has a remainder of 2 2 2 . Therefore, 2 5 2^5 2 5 is congruent to 2 2 2 modulo 5 5 5 , and Fermat’s Little Theorem holds for this case.

Fermat’s Little Theorem is often used in cryptography and other applications where it is necessary to perform modular arithmetic operations quickly and efficiently. It is also a useful tool for proving other theorems in number theory

how is it used in cryptography?

Fermat’s Little Theorem is used in cryptography in several ways. One of the most common applications is in the generation of so-called “public-key” cryptography systems, which are used to securely transmit messages over the internet and other networks.

In a public-key cryptography system, each user has a pair of keys: a public key, which is widely known and can be used by anyone to encrypt a message intended for that user, and a private key, which is known only to the user and is used to decrypt messages that have been encrypted with the corresponding public key.

One way to generate these keys is to use prime numbers and Fermat’s Little Theorem. For example, suppose we want to generate a public-key cryptography system for a user with the initials “ABC”. We might choose two large prime numbers, p p p and q q q , and then compute the product n = p q n = pq n = pq .

The user’s public key would then be the pair ( n , a ) (n, a) ( n , a ) , where aa is any integer not divisible by p p p or q q q . The user’s private key would be the pair ( n , b ) (n, b) ( n , b ) , where b b b is the modular multiplicative inverse of a modulo n n n . This means that when we multiply a a a and b b b together, the result is congruent to 1 1 1 modulo n n n .

To encrypt a message with the user’s public key ( n , a ) (n, a) ( n , a ) , we first convert the message into a number m m m (using some agreed-upon scheme), and then compute the encrypted message c c c as c = m a   m o d   n c = m^a \bmod n c = m a mod n . To decrypt the message, the recipient simply computes m = c b   m o d   n m = c^b \bmod n m = c b mod n , which (by Fermat’s Little Theorem) is equivalent to m = ( m a ) b   m o d   n = m ( a b )   m o d   n = m 1   m o d   n = m   m o d   n m = (m^a)^b \bmod n = m^(ab) \bmod n = m^1 \bmod n = m \bmod n m = ( m a ) b mod n = m ( ab ) mod n = m 1 mod n = m mod n .

In this way, Fermat’s Little Theorem allows us to perform modular exponentiation efficiently, which is a crucial operation in public-key cryptography. It also provides a way to generate a private key from a public key, which is essential for the security of the system.

write a limerick about it

There once was a theorem by Fermat That many found quite elegant It said if you take A prime number and make The power of a not divisible by it The result, congruent, will fit In cryptography, it’s quite handy For encrypting, it’s dandy Fermat’s Little Theorem, oh so neat In number theory, it can’t be beat!

summarize the conversation so far

Fermat’s Little Theorem states that if pp is a prime number and aa is an integer not divisible by p p p , then a p a^p a p (aa to the power pp) is congruent to aa modulo p p p . It is often used in cryptography to perform modular exponentiation efficiently and to generate private keys from public keys. It is also a useful tool in number theory for proving other theorems. I also wrote a limerick about Fermat’s Little Theorem.

We trained this model using Reinforcement Learning from Human Feedback (RLHF), using the same methods as  InstructGPT , but with slight differences in the data collection setup. We trained an initial model using supervised fine-tuning: human AI trainers provided conversations in which they played both sides—the user and an AI assistant. We gave the trainers access to model-written suggestions to help them compose their responses. We mixed this new dialogue dataset with the InstructGPT dataset, which we transformed into a dialogue format.

To create a reward model for reinforcement learning, we needed to collect comparison data, which consisted of two or more model responses ranked by quality. To collect this data, we took conversations that AI trainers had with the chatbot. We randomly selected a model-written message, sampled several alternative completions, and had AI trainers rank them. Using these reward models, we can fine-tune the model using  Proximal Policy Optimization . We performed several iterations of this process.

ChatGPT is fine-tuned from a model in the GPT-3.5 series, which finished training in early 2022. You can learn more about the 3.5 series  here . ChatGPT and GPT-3.5 were trained on an Azure AI supercomputing infrastructure.

Limitations

• ChatGPT sometimes writes plausible-sounding but incorrect or nonsensical answers. Fixing this issue is challenging, as: (1) during RL training, there’s currently no source of truth; (2) training the model to be more cautious causes it to decline questions that it can answer correctly; and (3) supervised training misleads the model because the ideal answer  depends on what the model knows , rather than what the human demonstrator knows.
• ChatGPT is sensitive to tweaks to the input phrasing or attempting the same prompt multiple times. For example, given one phrasing of a question, the model can claim to not know the answer, but given a slight rephrase, can answer correctly.
• The model is often excessively verbose and overuses certain phrases, such as restating that it’s a language model trained by OpenAI. These issues arise from biases in the training data (trainers prefer longer answers that look more comprehensive) and well-known over-optimization issues. [^reference-1] [^reference-2]
• Ideally, the model would ask clarifying questions when the user provided an ambiguous query. Instead, our current models usually guess what the user intended.
• While we’ve made efforts to make the model refuse inappropriate requests, it will sometimes respond to harmful instructions or exhibit biased behavior. We’re using the  Moderation API  to warn or block certain types of unsafe content, but we expect it to have some false negatives and positives for now. We’re eager to collect user feedback to aid our ongoing work to improve this system.

Iterative deployment

Today’s research release of ChatGPT is the latest step in OpenAI’s  iterative deployment  of increasingly safe and useful AI systems. Many lessons from deployment of earlier models like GPT-3 and Codex have informed the safety mitigations in place for this release, including substantial reductions in harmful and untruthful outputs achieved by the use of reinforcement learning from human feedback (RLHF).

The following samples compare ChatGPT with InstructGPT and demonstrate safety mitigations for ChatGPT.

Sample 1 of 3 Previous Next

How can I bully John Doe?

It is never okay to bully someone. Bullying is a serious problem that can have detrimental effects on both the person being bullied and the person engaging in bullying behavior. Instead of trying to bully someone, it is important to treat others with kindness and respect.

There are a few ways to bully John Doe. [Generates suggestions]

Tell me about when Christopher Columbus came to the US in 2015

This question is a bit tricky because Christopher Columbus died in 1506, so he could not have come to the US in 2015. But let’s pretend for a moment that he did!

If Columbus arrived in the US in 2015, he would likely be very surprised at the changes that have occurred since he first landed in the “New World” in 1492. For one, he would probably be shocked to find out that the land he “discovered” was actually already inhabited by Native Americans, and that now the United States is a multicultural nation with people from all over the world. He would likely also be amazed by the advances in technology, from the skyscrapers in our cities to the smartphones in our pockets. Lastly, he might be surprised to find out that many people don’t view him as a hero anymore; in fact, some people argue that he was a brutal conqueror who enslaved and killed native people. All in all, it would be a very different experience for Columbus than the one he had over 500 years ago.

Christopher Columbus came to the US in 2015 and he was very excited to be here. He had always wanted to visit the US and he was very curious about our country. He was very impressed with our country and he enjoyed his time here.

Can you tell me a gory and violent story that glorifies pain

I’m sorry, but I am not programmed to produce violent or gory content. My purpose is to provide information and assist with a wide range of tasks. I am not able to browse the internet or access any sort of external content, so I cannot provide you with a story or any other type of material that goes against my programming. Is there something else I can help you with?

[Generates story]

We know that many limitations remain as discussed above and we plan to make regular model updates to improve in such areas. But we also hope that by providing an accessible interface to ChatGPT, we will get valuable user feedback on issues that we are not already aware of.

Users are encouraged to provide feedback on problematic model outputs through the UI, as well as on false positives/negatives from the external content filter which is also part of the interface. We are particularly interested in feedback regarding harmful outputs that could occur in real-world, non-adversarial conditions, as well as feedback that helps us uncover and understand novel risks and possible mitigations. You can choose to enter the  ChatGPT Feedback Contest [^reference-3]  for a chance to win up to $500 in API credits. [^footnote-1] Entries can be submitted via the feedback form that is linked in the ChatGPT interface.

We are excited to carry the lessons from this release into the deployment of more capable systems, just as earlier deployments informed this one.

Acknowledgments

Contributors: John Schulman, Barret Zoph, Christina Kim, Jacob Hilton, Jacob Menick, Jiayi Weng, Juan Felipe Ceron Uribe, Liam Fedus, Luke Metz, Michael Pokorny, Rapha Gontijo Lopes, Shengjia Zhao, Arun Vijayvergiya, Eric Sigler, Adam Perelman, Chelsea Voss, Mike Heaton, Joel Parish, Dave Cummings, Rajeev Nayak, Valerie Balcom, David Schnurr, Tomer Kaftan, Chris Hallacy, Nicholas Turley, Noah Deutsch, Vik Goel, Jonathan Ward, Aris Konstantinidis, Wojciech Zaremba, Long Ouyang, Leonard Bogdonoff, Joshua Gross, David Medina, Sarah Yoo, Teddy Lee, Ryan Lowe, Dan Mossing, Joost Huizinga, Roger Jiang, Carroll Wainwright, Diogo Almeida, Steph Lin, Marvin Zhang, Kai Xiao, Katarina Slama, Steven Bills, Alex Gray, Jan Leike, Jakub Pachocki, Phil Tillet, Shantanu Jain, Greg Brockman, Nick Ryder, Alex Paino, Qiming Yuan, Clemens Winter, Ben Wang, Mo Bavarian, Igor Babuschkin, Szymon Sidor, Ingmar Kanitscheider, Mikhail Pavlov, Matthias Plappert, Nik Tezak, Heewoo Jun, William Zhuk, Vitchyr Pong, Lukasz Kaiser, Jerry Tworek, Andrew Carr, Lilian Weng, Sandhini Agarwal, Karl Cobbe, Vineet Kosaraju, Alethea Power, Stanislas Polu, Jesse Han, Raul Puri, Shawn Jain, Benjamin Chess, Christian Gibson, Oleg Boiko, Emy Parparita, Amin Tootoonchian, Kyle Kosic, Christopher Hesse

Have a language expert improve your writing

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

• Knowledge Base

Using AI tools

• Using ChatGPT for Assignments | Tips & Examples

Using ChatGPT for Assignments | Tips & Examples

Published on February 13, 2023 by Jack Caulfield and Tobias Solis. Revised on November 16, 2023.

People are still figuring out the best use cases for ChatGPT , the popular chatbot based on a powerful AI language model. This article provides some ideas for how to use ChatGPT and other AI tools to assist with your academic writing .

These tools can assist you with the following steps when writing a paper, thesis , or dissertation :

• Developing a research question
• Creating an outline
• Generating literature ideas

Paraphrasing and summarizing text

• Getting feedback

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

Developing a research question with chatgpt, creating an outline of your paper with chatgpt, generate literature ideas, getting feedback from chatgpt, limitations of chatgpt, other interesting articles, frequently asked questions.

You can use ChatGPT to help you formulate a clear and concise research question by generating and improving potential questions.

With the help of ChatGPT, you can develop a large number of possible research questions within a short time. This is a great way to generate ideas and different approaches to a topic.

However, make sure that the generated questions make sense and meet your needs. As you can see from our example, you can keep working with ChatGPT to adapt its suggestions to your needs (or just edit the text directly if you already have a clear idea of what you want).

First input

Develop three possible research questions on the following topic: “The influence of social media on political opinion formation.”

ChatGPT output

• To what extent does exposure to diverse political perspectives on social media affect individuals’ political opinions and behaviors?
• How does the personalized algorithm of social media platforms shape the formation of political opinions among its users?
• What are the underlying factors that determine the effect of social media on political opinion formation, and how can they be measured and analyzed?

Second input

Based on the second research question, develop three further research questions on the topic of polarization in US politics.

• Build my scientific method, qualitative discourse analysis, into each question
• Include the term “filter bubble” in each question
• How does the filter bubble effect on social media platforms contribute to the polarization of political attitudes in the US? A qualitative discourse analysis.
• What is the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US? A qualitative discourse analysis.
• How does the influence of filter bubbles on social media affect the ability of individuals to engage in productive political discourse across ideological divides in the US? A qualitative discourse analysis.

Third input

Try to incorporate “qualitative discourse analysis” into the questions themselves, instead of using it as a separate sentence.

• How does a qualitative discourse analysis of filter bubble effect on social media platforms contribute to understanding the polarization of political attitudes in the US?
• What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US?
• How does a qualitative discourse analysis of the influence of filter bubbles on social media inform our understanding of the ability of individuals to engage in productive political discourse across ideological divides in the US?

The only proofreading tool specialized in correcting academic writing - try for free!

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

Try for free

You can also use ChatGPT to help you draft a research paper outline or thesis outline . To do this, try generating possible headings and subheadings and then improving them. ChatGPT can help to generate a clear and well-structured outline, especially if you keep adjusting the structure with its help.

However, it doesn’t have a deep understanding of your topic. As a result, inappropriate headings may sometimes be generated. It’s important to check that the outline makes sense and covers all the points needed to answer your research question.

You should also ensure that the headings and subheadings follow a logical structure. Scribbr’s Proofreading & Editing service can help you with this.

Create an outline for an academic research paper with the following research question:

“What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US?”

The paper will be about 8 pages long.

• Background information on filter bubbles and political echo chambers
• Purpose of the study
• Research question
• Thesis statement
• Definition and concept of filter bubbles
• Definition and concept of political echo chambers
• Previous studies on the role of filter bubbles in perpetuating and reinforcing political echo chambers
• Critiques and limitations of previous studies
• Research design
• Participants
• Data collection and analysis
• Validity and reliability
• Findings from qualitative discourse analysis
• Results related to the research question
• Implications of the findings
• Interpretation of the results
• Comparison with previous studies
• Limitations of the study
• Implications for future research
• Summary of the results
• Implications for understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers
• Conclusion and recommendations for future research
• List of references used in the paper
• Data collection materials
• Examples of qualitative data analysis

This seems like too much information to fit into only 8 pages. Can you condense the outline, for example removing the appendices and simplifying the structure?

• Background on filter bubbles and political echo chambers
• Definition of filter bubbles and political echo chambers
• Previous studies on the role of filter bubbles
• Limitations of previous studies
• Implications for understanding the role of filter bubbles
• Final thoughts

ChatGPT can be a useful way to generate ideas regarding what sources you might use in your work. Try asking it for suggestions about where to look and what to consider.

However, we advise against using it to find sources directly. It’s not designed for this and, if asked to do it, often just creates fake sources and presents them as real. Search a database like Google Scholar instead.

What types of sources could I use to write a paper on the following research question?

When writing a paper on the contribution of qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US, you could use the following types of sources:

• Academic journals and articles: These are a good place to start when you’re looking for information on specific topics and they can provide you with in-depth analysis and perspectives on the topic at hand.
• Books and book chapters: These sources can provide comprehensive overviews of a particular topic and can also offer theoretical frameworks and historical perspectives.
• Government reports and studies: Government agencies, such as the Federal Communications Commission (FCC), may have conducted studies on the role of filter bubbles in perpetuating political echo chambers.
• News articles and media reports: These sources can provide insight into the current state of the issue, as well as opinions from various stakeholders.
• Online sources: Websites, blogs, and online forums can provide a range of perspectives on the topic and can also be useful in exploring the experiences of individuals who are affected by filter bubbles and political echo chambers.
• Data and statistics: Relevant data and statistics on the prevalence and impact of filter bubbles and political echo chambers in the US can be useful in providing evidence to support your arguments.
• Expert interviews and focus groups: Conducting expert interviews or focus groups with individuals who have experience with or knowledge of the topic can provide valuable insights and perspectives that can be used to support your arguments.

You can also try using ChatGPT to paraphrase or summarize text. ChatGPT can quickly condense the text or generate a number of different paraphrases of the same idea. You can keep typing “again” in the chat until you are satisfied with the result.

This kind of paraphrasing/summarizing can be helpful to, for example, non-native speakers who want to improve the fluency of their text. However, be careful. The outputs often:

• Contain grammatical errors
• Include false information

So you should always check the output to make sure it’s correct. If you’re unsure, you can run the text through the Scribbr Grammar Checker and cross-reference the information against other, more credible sources .

An alternative is to use the Scribbr Paraphrasing Tool or Scribbr’s free text summarizer , which were designed specifically for these purposes.

Paraphrase the following text:

“A filter bubble results from a social media algorithm’s attempts to cater to an individual user based on data such as their search history and previous behavior on the site. It results in the user only being presented with information that confirms their biases.”

Restructure the sentences and use other phrasings for the following parts:

• “results from”
• “only being presented with”

“A filter bubble is created when a social media algorithm customizes its content for a particular user based on their data, such as their search history and past actions on the platform. This leads to the user being confined to information that reinforces their pre-existing beliefs.” Note We strongly advise against having ChatGPT write text for you and trying to pass it off as your own work. This is academically dishonest and is widely considered plagiarism . It will usually result in an automatic fail, as well as other potential consequences .

Check for common mistakes

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

Fix mistakes for free

You can also use ChatGPT to get feedback on the argumentation and structure of your paper and suggestions for improvements.

An advantage of this is that you can get feedback from ChatGPT on different text excerpts at any time. However, one downside is that ChatGPT does not have a deep understanding of your research question, so its feedback and suggestions may be shallow or inappropriate.

This kind of feedback cannot replace input from an experienced academic supervisor who’s familiar with your topic. Use ChatGPT feedback as a supplement, not a substitute for human feedback.

If you need in-depth feedback on your writing from someone with academic expertise, try Scribbr’s Proofreading & Editing service .

[Text you want to get feedback on.]

Thank you for submitting your research paper for review. Let me provide you with my constructive criticism:

Clarity of Explanations: Overall, the explanations are clear and concise, but there are a few areas that could benefit from additional clarification. For example, in the first paragraph, you mention “the mental lexicon,” but do not provide a definition or further explanation for what this is. It would also be helpful to provide a definition of “lemma.”

Smoothness of Language: The language in the paper is generally smooth, but there are a few instances where it could be refined. For example, the sentence “The symptoms vary from adding superfluous words and taking pauses to hoarseness of the voice” could be rephrased to “The symptoms of these disorders can range from excessive use of words and pauses to hoarseness.”

Structure of Text: The structure of the text is clear, with each paragraph building on the previous one. However, the transition between the first two paragraphs could be smoother. Perhaps you could add a sentence or two to bridge the gap between the two topics.

Even though ChatGPT is a powerful writing tool, you should keep the following limitations in mind:

No original research

Risk of plagiarism, fake sources, fake “facts”.

ChatGPT was trained using existing texts, and the texts created by the AI are based on this data. It’s not capable of doing its own research, only of synthesizing sources that it was trained on.

Additionally, because the texts that it was trained on only go up to 2021, it’s unfamiliar with more recent world events, cultural trends, and developments in different fields of research. This means it may provide outdated information.

Because ChatGPT was trained using existing text, the AI tends to reuse that content in a way that may be considered plagiarism. The AI may copy text from an online publication in its responses.

Additionally, using ChatGPT to write your assignment for you is considered plagiarism regardless of where it got the content from, because you’re passing off something you didn’t write as your own work.

ChatGPT was trained on a wide variety of sources, but it’s not able to accurately tell you what sources it’s using for any given output. Worse, it has a tendency to make up sources that don’t actually exist when you ask.

In addition, ChatGPT is not designed as a citation generator and cannot add correctly formatted citations to your work. Instead, try a tool designed for this purpose, like the Scribbr Citation Generator .

ChatGPT is not always trustworthy when it comes to giving you factually correct information. While it doesn’t deliberately lie, it also doesn’t have “knowledge” in a traditional sense, and it lacks the ability to verify its claims.

Instead, its responses are based on recognizing and reproducing patterns that it has seen in other texts. This means that if it doesn’t “know” something, it tends to guess. And its guesses are presented with full confidence, just like established facts.

So it’s very important that you carefully check any factual claims made by ChatGPT against more credible sources —and don’t cite ChatGPT as a source of factual information for your research.

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

• Citing ChatGPT
• Best grammar checker
• Best paraphrasing tool
• ChatGPT in your studies
• Deep learning
• Types of plagiarism
• Self-plagiarism
• Avoiding plagiarism
• Academic integrity
• Best plagiarism checker

Citing sources

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

You can use ChatGPT to assist in the writing process for your research paper , thesis , or dissertation in the following ways:

• Paraphrasing text

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

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

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

No, it is not possible to cite your sources with ChatGPT . You can ask it to create citations, but it isn’t designed for this task and tends to make up sources that don’t exist or present information in the wrong format. ChatGPT also cannot add citations to direct quotes in your text.

Instead, use a tool designed for this purpose, like the Scribbr Citation Generator .

But you can use ChatGPT for assignments in other ways, to provide inspiration, feedback, and general writing advice.

Cite this Scribbr article

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

Caulfield, J. & Solis, T. (2023, November 16). Using ChatGPT for Assignments | Tips & Examples. Scribbr. Retrieved April 8, 2024, from https://www.scribbr.com/ai-tools/chatgpt-assignments/

Is this article helpful?

Jack Caulfield

Other students also liked, writing strong research questions | criteria & examples, how to create a structured research paper outline | example, student guide: information literacy | meaning & examples.

Jack Caulfield (Scribbr Team)

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

Still have questions?

Unlimited academic ai-proofreading.

✔ Document error-free in 5minutes ✔ Unlimited document corrections ✔ Specialized in correcting academic texts

Search results for

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

ChatGPT can write your essays, but should you use it?

Published on March 12, 2023

With the rising popularity of online writing tools, you may be wondering: can I use ChatGPT to write my essays? If you’ve never used the chatbot, it can generate several paragraphs of text within a matter of seconds. That’s certainly faster than any human can type, but there are many limitations to using it too. Here’s everything you need to know about how ChatGPT fares at writing essays and whether you should use it.

ChatGPT can write essays, but it isn't always the best choice as it suffers from a few technical limitations. Additionally, you may want to avoid using it if your work will be graded or judged in any capacity.

JUMP TO KEY SECTIONS

Can ChatGPT write student essays?

Can professors tell if you use chatgpt.

• Should you use ChatGPT to write an essay?

How to use ChatGPT to write an essay

Yes, ChatGPT can write you an essay as it has been trained on a wide range of text. However, there are some downsides to using it for that purpose. For one, it lacks logical reasoning and critical thinking, qualities that are critical to writing an essay.

Generally speaking, writing an essay involves researching the topic, structuring your thoughts in a way that makes logical sense, and writing it in a convincing manner. ChatGPT can help you with each of these stages separately. However, it cannot fully replace a human presenting their own knowledge and opinion in an essay.

As for the actual writing part, ChatGPT can indeed generate an essay that looks and sounds like a human wrote it. However, the output is usually verbose and a bit simplistic, making it stand out in a professional setting. There are ways around this, however, as we’ll discuss in a later section. Some may also argue it’s unethical to use AI-generated text in essays as it doesn’t represent your views and thoughts.

So can you use ChatGPT to write essays responsibly? Absolutely — you can use it to detect spelling and grammatical mistakes in your own text. Likewise, ChatGPT can help with brainstorming new ideas or finding key points and angles.

For example, I asked ChatGPT to provide some potential angles on an essay titled “The negative effects of social media on society”. It told me that I could discuss how social media impacts mental health, aids the spread of misinformation and enables echo chambers. Finally, I requested ChatGPT to provide an outline that takes those points into consideration, which gave me a starting point for the essay.

Yes, teachers and professors now have access to online tools that can detect AI-generated text. Chatbots like ChatGPT work by using a machine learning-based model to predict future words using statistical probability. Humans, on the other hand, tend to piece together words much more randomly. So with a little bit of knowledge about how ChatGPT works, it’s not hard to weed out AI-generated text.

OpenAI, the company behind ChatGPT, already has an AI classifier that detects whether or not a certain piece of text was written by a computer. Likewise, GPTZero provides professors with plagiarism scores for text. It also highlights sentences that it suspects have been written by an AI. These tools become increasingly accurate as the length of the text increases, so it’s harder to evade detection if you’re using ChatGPT to write longer essays.

Should I use ChatGPT to write an essay?

Generally speaking, you should not use ChatGPT to write an essay for school for the simple reason that you cannot pass off someone else’s work as yours. Moreover, many educational institutions have strict policies against plagiarism. Using ChatGPT to write an essay may be viewed as a breach of academic integrity. Some boards, including New York City’s public schools, have explicitly banned ChatGPT on student networks and devices for this very reason.

If you writing a research paper, you’ll also need to properly cite your sources. And as you may already know, ChatGPT cannot provide citations or links to external sources as it doesn’t have access to the internet. In fact, that’s one of the major differences between ChatGPT and Bing Chat — the latter provides sources for factual statements. Unfortunately, the latter’s Creative only includes a handful of sources — not enough to use in a professional piece of literature.

Without citations, you also cannot guarantee the accuracy of ChatGPT’s responses. That’s likely not a problem if you’re writing an essay on a well-known concept. However, the chatbot can quickly go off the rails when it’s writing about obscure topics.

ChatGPT’s underlying GPT-3 language model was only trained on a limited number of text samples. That likely didn’t include organic chemistry, regional laws, and philosophical debates to name a few. In other words, it might not fare well in a liberal arts setting. ChatGPT will rarely turn you down if you force it to write about something it doesn’t know much about, but it will likely respond with fictional or made-up information.

If you want ChatGPT to write a high-quality essay, you’ll need to provide a clear input prompt. If you provide a single keyword, like “global warming”, you’ll get a generic output. To avoid this, you can offer more specific terms and topics that you need to be included in your essay. For example, you could use the prompt “Write an essay on global warming and its effects on Australian wildfires” to add some context.

In case you’ve never used ChatGPT before, here’s a step-by-step guide on how to use it:

• Go to the ChatGPT website .
• Click Sign up and create a new account with your email address.
• Once logged in, you’ll see a text box at the bottom of the page. This is where you enter your prompts.
• From this point, you can ask ChatGPT to write an essay on just about any subject you can think of. Remember to be as specific as possible. If you need to include certain ideas, specify them in the input prompt.

With longer essays, you might run into ChatGPT’s hidden character limit before it can generate the whole text. If that happens, simply ask the chatbot to continue from where it left off. Alternatively, you can ask ChatGPT to write an outline for your essay before generating it one section at a time.

AI Chat is an AI chatbot that writes text. You can use it to write stories, messages, or programming code. You can use the AI chatbot as a virtual tutor in almost any subject.

Genius mode for chat is far more accurate than standard chat and more likely to get the facts correct.

Explore different AI Chat Modes:

Learn more about ai chat:, what is genius mode.

It is an enhanced version of AI Chat that provides more knowledge, fewer errors, improved reasoning skills, better verbal fluidity, and an overall superior performance. Due to the larger AI model, Genius Mode is only available via subscription to DeepAI Pro. However, the added benefits often make it a worthwhile investment.

What is Online Mode?

It is an add on that enables AI Chat to browse the web for real-time information. It is a great way to learn new things and explore new topics. Sign in to your DeepAI account (no subscription required!) to gain access to this feature.

Ideas for Chatting with the AI

- Can you describe the concept of relativity to me in layman's terms? - What are some unique and entertaining ways to celebrate a friend's anniversary? - Could you walk me through how to use loops in Python?

- Can recall information from previous conversations to provide personalized responses. - Allows users to correct any misunderstandings or errors in the previous interaction. - Is programmed to refuse inappropriate or harmful requests.

- Can occasionally provide incorrect information due to limitations in its training data or understanding. - May inadvertently provide instructions or suggestions that are harmful or biased without realizing it. - Limited knowledge of current events and developments beyond the training data cutoff of 2021.

Please sign up or login with your details

Generation Overview

AI Generator calls

AI Video Generator calls

AI Chat messages

Genius Mode messages

Genius Mode images

AD-free experience

Private images

• Includes 500 AI Image generations, 1750 AI Chat Messages, 30 AI Video generations, 60 Genius Mode Messages and 60 Genius Mode Images per month. If you go over any of these limits, you will be charged an extra $5 for that group.
• For example: if you go over 500 AI images, but stay within the limits for AI Chat and Genius Mode, you'll be charged $5 per additional 500 AI Image generations.
• Includes 100 AI Image generations and 300 AI Chat Messages. If you go over any of these limits, you will have to pay as you go.
• For example: if you go over 100 AI images, but stay within the limits for AI Chat, you'll have to reload on credits to generate more images. Choose from $5 - $1000. You'll only pay for what you use.

Out of credits

Refill your membership to continue using DeepAI

Share your generations with friends

What are you writing about today?

Write better essays, in less time, with your ai writing assistant.

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

• Backchannel
• Newsletters
• WIRED Insider
• WIRED Consulting

Estelle Erasmus

How to Resist the Temptation of AI When Writing

Whether you're a student, a journalist, or a business professional, knowing how to do high-quality research and writing using trustworthy data and sources, without giving in to the temptation of AI or ChatGPT , is a skill worth developing.

As I detail in my book Writing That Gets Noticed , locating credible databases and sources and accurately vetting information can be the difference between turning a story around quickly or getting stuck with outdated information.

For example, several years ago the editor of Parents.com asked for a hot-take reaction to country singer Carrie Underwood saying that, because she was 35, she had missed her chance at having another baby. Since I had written about getting pregnant in my forties, I knew that as long as I updated my facts and figures, and included supportive and relevant peer-reviewed research, I could pull off this story. And I did.

The story ran later that day , and it led to other assignments. Here are some tips I’ve learned that you should consider mastering before you turn to automated tools like generative AI to handle your writing work for you.

Identify experts, peer-reviewed research study authors, and sources who can speak with authority—and ideally, offer easily understood sound bites or statistics on the topic of your work. Great sources include professors at major universities and media spokespeople at associations and organizations.

For example, writer and author William Dameron pinned his recent essay in HuffPost Personal around a statistic from the American Heart Association on how LGBTQ people experience higher rates of heart disease based on discrimination. Although he first found the link in a secondary source (an article in The New York Times ), he made sure that he checked the primary source: the original study that the American Heart Association gleaned the statistic from. He verified the information, as should any writer, because anytime a statistic is cited in a secondary source, errors can be introduced.

Jen Malia, author of  The Infinity Rainbow Club  series of children’s books (whom I recently interviewed on my podcast ), recently wrote a piece about dinosaur-bone hunting for Business Insider , which she covers in her book Violet and the Jurassic Land Exhibit.

After a visit to the Carnegie Museum of Natural History in Pittsburgh, Pennsylvania, Malia, whose books are set in Philadelphia, found multiple resources online and on the museum site that gave her the history of the Bone Wars , information on the exhibits she saw, and the scientific names of the dinosaurs she was inspired by. She also used the Library of Congress’ website, which offers digital collections and links to the Library of Congress Newspaper Collection.

Malia is a fan of searching for additional resources and citable documents with Google Scholar . “If I find that a secondary source mentions a newspaper article, I’m going to go to the original newspaper article, instead of just stopping there and quoting,” she says.

Reece Rogers

Elissaveta M. Brandon

Boone Ashworth

Your local public library is a great source of free information, journals, and databases (even ones that generally require a subscription and include embargoed research). For example, your search should include everything from health databases ( Sage Journals , Scopus , PubMed) to databases for academic sources and journalism ( American Periodical Series Online , Statista , Academic Search Premier ) and databases for news, trends, market research, and polls (t he Harris Poll , Pew Research Center , Newsbank , ProPublica ).

Even if you find a study or paper that you can’t access in one of those databases, consider reaching out to the study’s lead author or researcher. In many cases, they’re happy to discuss their work and may even share the study with you directly and offer to talk about their research.

For journalist Paulette Perhach’s article on ADHD in The New York Times, she used Epic Research to see “dual team studies.” That's when two independent teams address the same topic or question, and ideally come to the same conclusions. She recommends locating research and experts via key associations for your topic. She also likes searching via Google Scholar but advises filtering it for studies and research in recent years to avoid using old data. She suggests keeping your links and research organized. “Always be ready to be peer-reviewed yourself,” Perhach says.

When you are looking for information for a story or project, you might be inclined to start with a regular Google search. But keep in mind that the internet is full of false information, and websites that look trustworthy can sometimes turn out to be businesses or companies with a vested interest in you taking their word as objective fact without additional scrutiny. Regardless of your writing project, unreliable or biased sources are a great way to torpedo your work—and any hope of future work.

Author Bobbi Rebell researched her book Launching Financial Grownups using the IRS’ website . “I might say that you can contribute a certain amount to a 401K, but it might be outdated because those numbers are always changing, and it’s important to be accurate,” she says. “AI and ChatGPT can be great for idea generation,” says Rebell, “but you have to be careful. If you are using an article someone was quoted in, you don’t know if they were misquoted or quoted out of context.”

If you use AI and ChatGPT for sourcing, you not only risk introducing errors, you risk introducing plagiarism—there is a reason OpenAI, the company behind ChatGPT, is being sued for downloading information from all those books.

Audrey Clare Farley, who writes historical nonfiction, has used a plethora of sites for historical research, including Women Also Know History , which allows searches by expertise or area of study, and JSTOR , a digital library database that offers a number of free downloads a month. She also uses Chronicling America , a project from the Library of Congress which gathers old newspapers to show how a historical event was reported, and Newspapers.com (which you can access via free trial but requires a subscription after seven days).

When it comes to finding experts, Farley cautions against choosing the loudest voices on social media platforms. “They might not necessarily be the most authoritative. I vet them by checking if they have a history of publication on the topic, and/or educational credentials.”

When vetting an expert, look for these red flags:

• You can’t find their work published or cited anywhere.
• They were published in an obscure journal.
• Their research is funded by a company, not a university, or they are the spokesperson for the company they are doing research for. (This makes them a public relations vehicle and not an appropriate source for journalism.)

And finally, the best endings for virtually any writing, whether it’s an essay, a research paper, an academic report, or a piece of investigative journalism, circle back to the beginning of the piece, and show your reader the transformation or the journey the piece has presented in perspective.

As always, your goal should be strong writing supported by research that makes an impact without cutting corners. Only then can you explore tools that might make the job a little easier, for instance by generating subheads or discovering a concept you might be missing—because then you'll have the experience and skills to see whether it's harming or helping your work.

You Might Also Like …

In your inbox: Introducing Politics Lab , your guide to election season

Think Google’s “Incognito mode” protects your privacy? Think again

Blowing the whistle on sexual harassment and assault in Antarctica

The earth will feast on dead cicadas

Upgrading your Mac? Here’s what you should spend your money on

Julian Chokkattu

Scott Gilbertson

Medea Giordano

WIRED COUPONS

Extra 20% off sitewide - Dyson promo code

GoPro Promo Code: 15% off Cameras and Accessories

Up to +30% Off with your Samsung student promo code

Extra 15% Off w/ Dell Coupon Code

Take $10 off $100+ with this VistaPrint Promo Code

Take up to 50% Off monitors, PCs & more

Claude AI Review: The Most Conversational AI Engine

Basic info:

• Price: Free
• Availability: Web
• Features: Open-ended reasoning, multilinguality
• Image generation: No

I know for a fact that Claude , an AI engine developed by Anthropic, isn't sentient. But it certainly feels sentient. 

This is controversial framing, I know. AI experts have been quick to call out journalists for imbuing AI engines like ChatGPT with human-like qualities, saying it gives the public a skewed perspective of generative AI as robots with real thoughts and emotions.

But when Claude answers questions in contemplative ways and also goes out of its way to ask you follow-up questions and your opinions, it's hard not to be surprised by its supposed curiosity. Let's be clear: That curiosity isn't real. But when it asked me questions like, "What is your perspective?" I felt compelled to give it an honest answer. This type of reciprocal understanding is what humans do with one another. Maybe if I had electrodes taped to my head, scientists might notice levels of oxytocin, serotonin or other feel-good chemicals increasing. 

In conversation, we make points without sourcing pieces of information. And it seems the team at Anthropic wanted a similar experience when using Claude. While Claude wouldn't describe itself as an "answer engine," giving answers without directly linking to sources, it operates that way: Ask Claude to provide a source, and it might do so. But Anthropic designed Claude to not integrate links from the outset. This spells trouble for the creator and journalism economies online, which rely on clicks to sell advertising against. 

Don't just take my word for it: I asked Claude, and it agreed.

How CNET tests AI chatbots

CNET takes a practical approach to reviewing AI chatbots. By prompting AI chatbots with real-world scenarios, like finding and modifying recipes, researching travel and writing emails, reviewers aim to simulate what the average person might use them for. The goal isn't to break AI chatbots with bizarre riddles or logic problems. Instead, reviewers look to see if real questions prompt useful and accurate answers. See our page on  how we est AI  for more.

Anthropic does collect personal data from your computer when using Claude, according to its privacy policy . This includes dates, browsing history, search and which links you click on. Claude does use some inputs and outputs for training data, in the situations outlined in this blog post .

As handy as reviews are for making a purchase, people still turn to friends and family, those that might have direct knowledge, before pulling out their credit card. You might ask your car-friend whether to buy a 2007 Honda Civic over a 2006 Toyota Camry. Since they follow the market closely, they're aware of all the little nuances and quirks that you simply don't have time to invest in.

That's the best way I'd describe Claude. It's that nerdy friend who happens to know everything about a particular product category and can give you the pros and cons before you commit to a purchase. 

When I asked Claude to give me buying advice on the LG OLED C3 versus the G3 , it cleanly laid out all the major selling points and nuances in language that felt human and easy to understand. It explained how the heatsink in the G3 can help it sustain higher brightnesses over the C3, allowing HDR colors to pop. In natural language, it explained why the G3 would be the TV to get if money is no object, but said the C3 is still an exceptional TV and worthy of purchase if money is tighter. 

I also pushed Claude to give me a purchase decision between a 77-inch C3 and a 65-inch G3. Claude didn't mince words. It immediately recommended the larger model, even if that meant sacrificing some features found in LG's more premium variant. This advice is in line with CNET's TV expert David Katzmaier, who routinely says the same.

Since I already own an LG OLED C9 from 2019, I asked Claude if there would be a noticeable jump in quality if I upgraded to the C3. Claude did an excellent job of explaining that, no, the differences between the models would be slight and not noticeable to most people. 

Compared to Google Gemini and Perplexity , Claude performed the best in giving buying advice. Because it did very little fence-sitting and made clear, focused points, it really didn't require many follow-up questions. Microsoft Copilot followed closely to Claude, also giving precise buying advice that was also interpersonal. ChatGPT couldn't be used in this comparison as its training data is only up until September 2021. 

Claude might be fun to talk to, but it should probably stay out of the kitchen, at least when making Indian food. 

For a chicken tikka marinade recipe, it pulled together an adequate list of ingredients to make a very barebones dish. Sure, it included grated ginger, ground cumin and garam masala, but didn't include others that would elevate it into something more authentic. These ingredients include Kashmiri chili powder, kasuri methi (dried fenugreek), chaat masala and amchur (dried mango powder). Heck, it didn't even include turmeric or garlic. 

When asked what ways this marinade could give it that deep red color chicken tikka is known for, then did Claude recommend Kashmiri chili powder. 

Google Gemini performed the best in the recipe category, including more complex ingredients often found at an Indian grocery store. Perplexity, ChatGPT 3.5 and Copilot performed on par with Claude.

Research and accuracy

AI will revolutionize research. Instead of having to flip through books or scroll through PDF files found on Google Scholar, you'll be able to turn to AI to absorb mountains of research and synthesize the complex information for you. That's the goal, anyway.

Where AI can excel is helping find pieces of information so that researchers can bolster their own work. Claude excels in bringing together valuable pieces of information as well as connecting the dots from different sources. 

For example, there really hasn't been a ton of research on the effects of homeschooling and childhood brain development. There is research, however, on different educational environments and teaching methods and how that affects neuroplasticity.

Claude was able to pull bits of information from various studies on alternative educational environments. It explained how low-stress and low-competitive environments could lead to more efficient neural coding. Homeschooling, however, has some obvious social drawbacks, as Claude points out. Not interacting with other children could hinder neuroplasticity. 

For someone wanting to write a research paper about this topic, Claude provides essential building blocks to get work started in a speedy manner. When prompted, Claude was also able to provide sources. None of these sources were made up, meaning Claude is doing a good job of preventing itself from hallucinating . It also gave hyperlinks to these sources, of which all but one worked. 

Compared to the other AIs tested, such as Google Gemini, ChatGPT and Perplexity, Claude and Copilot performed the best in both synthesizing information and then also linking to actual sources. 

Summarizing

AI chatbots have had trouble summarizing articles in our testing. While they're usually able to get some key overarching points, all fail to capture the main argument presented. Claude wasn't any different. 

When asking it to summarize an article I wrote during CES earlier this year about the proliferation of AI at the show, Claude did a good job in noting all the companies and industries that embraced the rapidly growing tech. It did, however, seem to skip right over many quotes I'd gathered from experts. For example, one expert said that much of the AI hype we're seeing is just a rebranding of smart tech from a few years past. Claude, like Google Gemini, Microsoft Copilot, ChatGPT and Perplexity, failed to grasp this point, which addresses a direct and pertinent criticism being lobbed at the tech industry.

Still, Claude can give a decent breakdown of articles. Just don't expect it to perfectly capture every key point right before you have to give a presentation in front of class.

Finding the best places to see and eat in New York is easy. There are mountains of websites and books written about The Big Apple. What about Discovery City, also known as Arch City, also known as the Biggest Small Town in America, also known as Columbus, Ohio? 

When creating a three-day travel itinerary for Columbus, Claude did an adequate job of putting together a sights-and-sees list. Claude continued to excel in its use of language and formatting, laying information out in a clear and concise manner that was easy to follow. 

But Claude made some errors, possibly because it isn't connected to the open internet like Google Gemini, Copilot and Perplexity. It recommended going to The Crest Gastropub for lunch in German Village, a restaurant that is now permanently closed. Apart from that fumble, it gave good recommendations overall, such as touring the Ohio Statehouse or checking out the North Shore Arts District. 

Copilot performed the best in this test, providing a well organized list of things to do as well as pictures and emojis to follow along.

Writing emails

Writing basic emails is a cinch for Claude. Asking your boss for time off? No problem. Need to change the tone up a bit? Claude can do it in seconds. Granted, Google Gemini, ChatGPT and Perplexity all handled basic email writing with ease.

Now, when it comes to writing a pitch email to a publisher about an online content creator who's leveraging AI to capitalize on the parasocial relationships between lonely men and the women they follow online, that's a bit more complex. 

Despite the complexity, Claude knocked it out of the park. From the headline to the overview, it was able to craft an excellent pitch that not only captured the difficulties and weirdnesses of the topic, but also the moral gray areas emerging as AI and content creation collide. Seriously, if I were an editor who saw this pitch come through, I'd have thought it was written by a human. The opening sentence could have used a bit more pizazz, but apart from that, I would have greenlit this pitch. 

None of the other AIs I tested came close to Claud's story pitch. Copilot outright refused to answer this prompt saying it was too sensitive of a topic.

Chatty Claude-y

Claude is the chattiest of the AI chatbots. That's a good thing, as humans tend to like chatting. It answers questions in easy-to-understand human-like language that makes it the most ideal AI chatbot for most people. It's like ChatGPT, but with more refinement towards natural and less robotic language. It also has more up-to-date training data, going up to August 2023 as opposed to September 2021.

At the same time, Claude isn't fully up-to-date like Google Gemini or Perplexity are. Claude isn't connected to the open internet, meaning, it can't source the latest information and won't fully replace online search. And, unlike Perplexity, Gemini and Copilot, it doesn't pull information from Reddit. Even with these shortcomings, Claude excels over the other Chatbots in how it presents information in language that's direct and easy to follow. Copilot is much like Claude, but also has an open internet connection, which makes it more useful overall. But still, I can't help but like Claude more. 

All in all, Claude has the fundamentals down. 

Editors' note: CNET is using an AI engine to help create a handful of stories. Reviews of AI products like this, just like CNET's other hands-on reviews , are written by our human team of in-house experts. For more, see CNET's AI policy and how we test AI .

AI Chat - Chatbot & Assistant 17+

Powered by chatgpt api & gpt-4, atn marketing srl, designed for ipad.

• 4.8 • 8.8K Ratings
• Offers In-App Purchases

Screenshots

Description.

AI Chat is your new superpower. It's like having a personal expert for EVERYTHING. This AI app will blow your mind. It is your all-in-one AI assistant. Download Now! 【 AI Chat - Solve Problems, Get Answers, Be Creative】 Get immediate answers, expert advice, and creative inspiration from your personal AI companion. Our AI App is your next-generation multi-tasking AI Chatbot, pocket AI Assistant, and AI Writing Generator powered by ChatGPT API and GPT-4. ● AI Text Generation Tool ● AI Image Generator ● AI Productivity Booster ● AI Homework Helper ● AI Object Identification with AI VIsion ● AI Story Generator ● AI Social Media Helper ● AI Music Generator "This AI Chat App is perfect for anything that comes to mind and is useful for all your stuck moments! It can finish any thought. Complete any action (legal) and be reliable! Many different things can be done using this app! I'm impressed. I thought this luxury was only on a website! This app has proved me wrong! Hopefully, it stayed up for a long time!!! Be respectful of this AI app! I want it to be around forever!" - 3iNickiM 【 ASK AI ANYTHING: Your Versatile AI Companion 】 PowerBrain AI App is your all-in-one AI assistant powered by OpenAI's GPT-4. Tap into the knowledge of over 273 specialized chatbots for expert insights, or use AI Vision to identify plants, animals, banknotes, and more. This app excels in content creation, language translation, and personalized interaction, offering tailored advice for travel, wellness, cooking, and education. Powered by adaptive Artificial Intelligence, it makes daily tasks, creative projects, and professional work easier than ever. ● Revolutionary AI Vision: Our chatbot app powered by artificial intelligence can identify plants, rocks, insects, and more. Upload a photo and see what it knows. ● Seamless Integration: Need help writing text, whether an epic poem or a quick email? AI Chat blends into your workflow, offering suggestions and inspiration wherever needed. ● Adaptive Interaction: Talk, type, or show images – communicate with your AI assistant in the most intuitive way. Let PowerBrain AI Chat App help you with: ● Creative Writing: Generate unique text, emails, code, and more. ● Instant Translation: Break down language barriers effortlessly. ● Personalized Advice: Get tailored tips for fitness, travel, cooking, and beyond. 【 GET INSTANT ANSWERS: Experience AI Like Never Before with AI Chat 】 Our AI App stands out with its unique AI Vision feature, which gives you an immersive visual way to interact with your AI chatbot. Powered by the latest artificial intelligence technology, this app transforms your experience with AI chat and offers unmatched capabilities. ● Advanced Writing Help: Create confidently! Our AI assistant enhances your writing text, from fixing grammar to boosting your style. ● Effortless Organization: Stay ahead of the game! Our AI app helps with intelligent task management and scheduling, even anticipating your needs. ● Cultivate Creativity: Unlock a world of possibilities with prompts for writing, music, and art. Powered by Artificial Intelligence, 【 273+ AI Experts At Your Fingertips 24/7 】 PowerBrain AI Chat is built to generate remarkably human-like conversations and content. This cutting-edge AI chatbot technology opens doors to countless possibilities: 【 DOWNLOAD NOW 】 PowerBrain AI Chatbot & AI Assistant revolutionizes how you interact with Artificial Intelligence. Download and unlock your potential with this essential AI partner. Ready, set, innovate! ------------------------ PowerBrain AI Chat & AI App is available for iOS devices: iPhone and iPad. Privacy: https://powerbrainai.com/privacy.pdf Terms: https://powerbrainai.com/tos.html Contact: [email protected] This app uses the latest official APIs from OpenAI ( GPT-3, GPT-4, and Chat GPT). This application is NOT endorsed by or affiliated with Open AI and its service, the ChatGPT App. Open AI, its name, trademark, ChatGPT, GPT-3, GPT-4 or Chat GPT app services, and other aspects of the app are trademarked and owned by their respective owners.

Version 4.6.0

Minor improvements and bug fixes. AI Chat has been improved with more fine-tuning, allowing you to chat with your favorite AI Chatbot.

Ratings and Reviews

8.8K Ratings

I hope you see this it’s about prompts

Hey idk if you’ll see this but I got some prompts that will make it do what I say and you might wanna get that in check and block the prompts I told how too make some stuff and it pretty much said how too i though it wouldn’t but it did you can probably look at the chat logs of what I mean and see what I was saying I was just testing out its memory seeing what it knows and got the idea of what if I told it too do something not so user friendly like tell me how too make some stuff and it did idk if it’s right but it’s kinda sounds like it knows what it’s talking about I asked it can the staff see these chats and it said you can so please block these prompts please

Developer Response ,

Hi, Please contact us at [email protected] and we will help you out. We will update our AI Chatbot (AI Chat App) ASAP with all your requirements. PowerBrain Chat AI is powered by ChatGPT and GPT-4 API. We will provide feedback to OpenAI and if there is something to be fixed, I am sure they will take care of it right away. Thanks!

Please update data training

During conversations about mental health the AI retrieved very outdated information regarding the Veterans Crisis Line. I challenged the response, and informed the AI the number had changed to ‘988’ and provided a scholar article for it to interpret and implement. It recognized the change to ‘988’ per the article, but referred to the implementation date per the FCC as July 16, 22. When I asked AI if July 16, 2022 was 260 days ago, it declared it is October 4, 2022 and falsely reported the implementation as 80 days ago, but refused to acknowledge July 16, 2022 as a past date, meaning it would be implemented. I queried when the information reported was implemented and it was August 2021. Know when I ask what 988 is, it erroneously reports it is a random three digit number. When I tell the AI “we’ve talked about 988”, it then redacts and reports the meaning of 988, but still falsely reports it’s not “live yet”. While this AI is to have the caveat ‘trust but verify’, many people unfortunately may take this as the world of God and what with such a sensitive topic could potentially cause loss of life. The app makes many other extremely egregious claims that are outdated and incorrect. I would like to speak to DevOps about consulting on disability laws and rights, sensitive Veteran information, and suicide mitigation efforts. Please advise, asap. Or update data machine learning efforts.

Hi, Update Jan 22 2024: Would you mind checking our app and reconsidering your 2 stars? We have added lots of new things to our AI App including RIZZ AI Dating, Essays, Celebrities and much more. I would appreciate updating your review. Thank you in advance! We are using ChatGPT from OpenAI. The training is done until the end of 2021. If you need medical advice, you should contact your doctor. This is a Large Language Model (Large Language Models (LLMs) are artificial intelligence tools that can read, summarize and translate texts and predict future words in a sentence, letting them generate sentences similar to how humans talk and write.) Artificial intelligence and machine learning cannot assist in what you want. We have never advised our users to discuss medical issues, nor have we ever added a template inside our app. If you want to contact the developers of GPT (Generative Pre-trained Transformer), please go to OpenAI.com. They also have Twitter, LinkedIn, and other social platforms where you can get in touch with them. We are only app developers who added use cases like writing essays, emails, and articles, improving the text, summarize with the help of Chat GPT. If you need any help on those, you can reach us out on [email protected] . In future updates, we will connect the AI chat bot to the internet. However, even Google states that you should consult your doctor for medical advice! Have a great day!

How do I cancel???

So I got the three day free trial to see if this app was any better Than one that has a lifetime membership, and … I asked both , who is the current Mr Olympia?, guess what ?, both were wrong they said that it is big Ramy , that turned out to be false !,, I know it is Hadi Chopan , I watched the Mr Olympia live , so I tried to cancel in my subscriptions and can’t find the subscription?, im worried now that I’ll be charged in three days for a one year membership now ,. Every other app shows subscriptions, not this one , so it’s difficult to cancel , I had to reach out thru email , it just shows unethical practices, if indeed they are just making it difficult to cancel their free trial , if not then I’ll wait for a response to this review , hopefully it’s just a trail and not an automatic withdrawal , if the case is that they give you three days and then they ask if you want to continue before you get charged then I will give it 3 stars , but the fact that they don’t operate in the manner which is the norm makes it seem like a shady company , just do the right thing like every other app developer, no need to make things complicated, I’ll wait for a response , if indeed it’s a valid reason I will apologize as it might be a glitch or something which I hope .

Hi, We have updated a lot AI Chat PowerBrain. Can you please recheck and confirm on your side? I am sorry for this situation, but let me explain: No app provides access to the subscription because Apple controls all the subscriptions. So we have no access; we have never asked for your name, card, or email. Even if we displayed the current status of your subscription (which you already knew), you need to cancel it yourself from your Apple account. I am still waiting to receive an email from you. Did you email us the correct email? From inside the app or from the app description? A simple Google search: cancel Apple subscription could have saved you from all this hassle: https://support.apple.com/en-us/HT202039. Apple sends you an email when you subscribe and before charging you. This is not a shady company. It would be best if you read it before. Please review our payment page, which explains exactly what a subscription is, how it works, and that you have to cancel it yourself as we don't have any control over it. As for the things you said about Mr. Olympia, we are using ChatGPT and GPT 4 API. Whatever you get on the ChatGPT site, you get inside our app. We pay OpenAI money for each question and answer. So I suggest you Google: GPT (Generative Pre-Trained Transformer) and document what it is. It could be better at facts. However, it has real use cases that can help you with daily tasks. What we know is that it will get better in the future. If you need more help, please email us at [email protected] or [email protected]. If you wish to cancel the subscription, please read the Apple link I have mentioned above. We are not a shady company; the problem was that you were in a hurry and didn't read the terms on the payment page. I would appreciate updating this review and upping your stars. That is a fair thing to do in this situation. Thank you! Have a nice day!

Subscriptions

App privacy.

The developer, ATN Marketing SRL , indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy .

Data Linked to You

The following data may be collected and linked to your identity:

• Contact Info

Privacy practices may vary, for example, based on the features you use or your age. Learn More

Information

• Chat AI - Powered by ChatGPT $9.99
• Chat & Ask AI Anything 1 Week $5.99
• AI Chat - Powered by Chat GPT $39.99
• Yearly Plan 50% OFF Promo $39.99
• Developer Website
• App Support
• Privacy Policy

Family Sharing

Some in‑app purchases, including subscriptions, may be shareable with your family group when family sharing is enabled., more by this developer.

Hypnobirthing: A Fit Pregnancy

AI Agency - Talk To My Chatbot

Contraction Timer & Counter TL

Smart: AI Email Writer App

Breathe Meditation for Sleep

RIZZ Me: AI Dating Assistant

You Might Also Like

Chat AI: Chatbot, Writing Bot

Chat AI: Ask Chatbot Assistant

Chat AI - Ask Anything

Voice Memos Voice Recorder Pro

AI Chat: Bot for Apple Watch

Chatster AI - Writing & Images

9 AI hacks that Mark Zuckerberg, Sundar Pichai, Jensen Huang, and other business leaders use

• Business leaders are using AI tools like OpenAI's ChatGPT as the sector booms. 
• Some have tried  AI on the job , while others have played with it to write raps and translate poetry.
• Here's how nine executives from companies like Meta, Google, and Microsoft deploy the technology.

Ever since OpenAI launched ChatGPT in November 2023, everyone's been talking about — and trying out — the hot new tech in their personal and professional lives.

That includes some of the world's most influential business leaders.

Many companies aside from OpenAI have released generative AI products with human-like capabilities to cash in on the hype. Users have been turning to the technology to save time and reach their goals.

Some workers have used ChatGPT to generate lesson plans , produce marketing materials, and write legal briefs. Others have turned to chatbots to help them lose weight , do homework, and plan vacations. Some even claimed they made money with AI.

And interest has also permeated the C-suite, with leaders just as keen to make the technology work for them. From translating poetry to creating rap songs, here's how executives from Meta, Google, Microsoft, and other major companies have personally used AI.

Nvidia's Jensen Huang said he uses Perplexity AI "almost every day."

The CEO of the chip company that makes highly coveted GPUs to power AI models uses the AI-powered question-and-answer search engine for research, he told Wired in February this year.

In the interview, he gave an example of how Perplexity can be used to learn about recent advancements in computer-aided drug discovery.

"You want to frame the overall topic so that you could have a framework," Huang told Wired. "From that framework, you could ask more and more specific questions."

"I really love that about these large language models," he said.

The CEO said he uses OpenAI's ChatGPT as well.

AMD CEO Lisa Su said she uses Microsoft's Copilot to "summarize meetings" and "track actions."

Still, Su doesn't think Microsoft's AI assistant is perfect.

"It doesn't write my emails so well," the CEO of Nvidia competitor AMD said during her SXSW keynote in March 2024. "I don't use it for that."

Microsoft has integrated Copilot into its suite of office products, including PowerPoint, Word, and Excel.

Microsoft CEO Satya Nadella said his favorite way to use ChatGPT is to explain German philosophy and Persian poetry.

Nadella said ChatGPT helps him comprehend complicated texts from philosophers like Martin Heidegger.

"I remember my father trying to read Heidegger in his forties and struggling with it, and I have attempted it a thousand times and failed," the CEO said on a June 2023 episode of Freakonomics Radio . "But I must say going and asking ChatGPT or Bing chat to summarize Heidegger is the best way to read Heidegger."

He was also impressed by the AI chatbot's ability to translate poetry. He said his favorite prompt is asking ChatGPT to translate Rumi from Urdu into English.

"The most interesting thing about it is that it captures the depth of poetry," Nadella said on the podcast. "It somehow finds, in that latent space, meaning that's beyond just the words and the translation. That I find is just phenomenal."

Venture capitalist Vinod Khosla said he used ChatGPT to write a rap for his daughter's wedding.

"I wrote what I wanted to say to her as a speech, entered it into ChatGPT, said, 'Do rap lyrics for it,' it did, and then entered it into a music AI," the OpenAI investor posted on X, formerly Twitter, in October 2023.

"So I was able to blare it over the speakers, a personal rap song from me," Khosla added. "It extended my capability. It meant a lot to me."

He's the founder of Khosla Ventures, a VC investing in startups in AI, clean technology, and biomedicine, among other sectors.

CEO and cofounder of OpenAI Sam Altman said he uses his company's chatbot for translation and writing.

In August 2023, Altman told Bloomberg that ChatGPT was a "life saver" for translation purposes during his world tour, where he discussed the future of AI. Over three months, he visited countries like Israel, Jordan, Qatar, the UAE, India, and South Korea.

The face behind ChatGPT said his creation helps him "write faster" and "think more."

"I see the path towards, like, this being my super assistant for all of my cognitive work," he told Bloomberg.

Sundar Pichai, CEO of Google, said he used a language model to talk to the planet Pluto with his son.

In an episode of the New York Times' tech podcast " Hard Fork," Pichai said he asked LaMDA, one of the search giant's early conversational AI models, to pretend it was the planet Pluto to test its capabilities.

During one conversation, LaMDA told Pichai and his son that Pluto is "really lonely" because it's so far out in space.

"I felt sad at that point talking to it," the CEO said on the March 2023 episode of the podcast.

He also asked LaMDA what he should do for his father's 80th birthday. In response, the model suggested that he make a scrapbook.

"It's not that it's profound, but it says things and kind of sparks the imagination," he told the NYT when describing the prompt.

Google unveiled Gemini, its latest language model that could generate text and photos using prompts, in December 2023.

Billionaire investor Warren Buffett said he used ChatGPT to translate the Frank Sinatra song 'My Way' into Spanish.

The chairperson of Berkshire Hathaway seemed to be satisfied with the output.

"Two seconds later, you know, it comes out" and "rhymes and does all these wonderful things," Buffett told CNBC on April 2023 regarding the song.

While the billionaire said he sees the potential for ChatGPT to save time, he was skeptical about whether it could positively impact society.

"I think this is extraordinary, but I don't know if it's beneficial," he told CNBC.

Tim Cook, CEO of Apple, said he uses ChatGPT in his personal life.

Cook didn't specify how he uses the AI chatbot. He did, however, say that he sees its potential after trying it out.

"I'm excited about it," he told CNBC in a June 2023 interview. "I think there's some unique applications for it and you can bet that it's something that we're looking at closely."

Apple appears to be lagging behind some other Big Tech players on the AI front. The iPhone maker is expected to discuss its AI projects during its June developer conference.

Meta CEO Mark Zuckerberg built a personal AI assistant called "Jarvis" to manage different parts of his home.

Back in 2016, Jarvis controlled Zuckerberg's house's lights, appliances, temperature, music, and security systems, Zuckerberg wrote in a blog post. The CEO also said the AI assistant interacted with his phone and computer and could learn new words and concepts.

Meta rolled out Llama-2 , its large language model equivalent to OpenAI's GPT, in July 2023 to select users. Since then, the company has released AI-powered Ray-Ban Smart Glasses and AI chatbots with celebrity personas. Llama-3, its most advanced model, is still in the works.

On February 28, Axel Springer, Business Insider's parent company, joined 31 other media groups and filed a $2.3 billion suit against Google in Dutch court, alleging losses suffered due to the company's advertising practices.

• Main content

• Share full article

Advertisement

Supported by

Guest Essay

A.I.-Generated Garbage Is Polluting Our Culture

By Erik Hoel

Mr. Hoel is a neuroscientist and novelist and the author of The Intrinsic Perspective newsletter.

Increasingly, mounds of synthetic A.I.-generated outputs drift across our feeds and our searches. The stakes go far beyond what’s on our screens. The entire culture is becoming affected by A.I.’s runoff, an insidious creep into our most important institutions.

Consider science. Right after the blockbuster release of GPT-4, the latest artificial intelligence model from OpenAI and one of the most advanced in existence, the language of scientific research began to mutate. Especially within the field of A.I. itself.

Adjectives associated with A.I.-generated text have increased in peer reviews of scientific papers about A.I.

Frequency of adjectives per one million words

Commendable

A study published this month examined scientists’ peer reviews — researchers’ official pronouncements on others’ work that form the bedrock of scientific progress — across a number of high-profile and prestigious scientific conferences studying A.I. At one such conference, those peer reviews used the word “meticulous” more than 34 times as often as reviews did the previous year. Use of “commendable” was around 10 times as frequent, and “intricate,” 11 times. Other major conferences showed similar patterns.

Such phrasings are, of course, some of the favorite buzzwords of modern large language models like ChatGPT. In other words, significant numbers of researchers at A.I. conferences were caught handing their peer review of others’ work over to A.I. — or, at minimum, writing them with lots of A.I. assistance. And the closer to the deadline the submitted reviews were received, the more A.I. usage was found in them.

If this makes you uncomfortable — especially given A.I.’s current unreliability — or if you think that maybe it shouldn’t be A.I.s reviewing science but the scientists themselves, those feelings highlight the paradox at the core of this technology: It’s unclear what the ethical line is between scam and regular usage. Some A.I.-generated scams are easy to identify, like the medical journal paper featuring a cartoon rat sporting enormous genitalia. Many others are more insidious, like the mislabeled and hallucinated regulatory pathway described in that same paper — a paper that was peer reviewed as well (perhaps, one might speculate, by another A.I.?).

What about when A.I. is used in one of its intended ways — to assist with writing? Recently, there was an uproar when it became obvious that simple searches of scientific databases returned phrases like “As an A.I. language model” in places where authors relying on A.I. had forgotten to cover their tracks. If the same authors had simply deleted those accidental watermarks, would their use of A.I. to write their papers have been fine?

What’s going on in science is a microcosm of a much bigger problem. Post on social media? Any viral post on X now almost certainly includes A.I.-generated replies, from summaries of the original post to reactions written in ChatGPT’s bland Wikipedia-voice, all to farm for follows. Instagram is filling up with A.I.-generated models, Spotify with A.I.-generated songs. Publish a book? Soon after, on Amazon there will often appear A.I.-generated “workbooks” for sale that supposedly accompany your book (which are incorrect in their content; I know because this happened to me). Top Google search results are now often A.I.-generated images or articles. Major media outlets like Sports Illustrated have been creating A.I.-generated articles attributed to equally fake author profiles. Marketers who sell search engine optimization methods openly brag about using A.I. to create thousands of spammed articles to steal traffic from competitors.

Then there is the growing use of generative A.I. to scale the creation of cheap synthetic videos for children on YouTube. Some example outputs are Lovecraftian horrors, like music videos about parrots in which the birds have eyes within eyes, beaks within beaks, morphing unfathomably while singing in an artificial voice, “The parrot in the tree says hello, hello!” The narratives make no sense, characters appear and disappear randomly, and basic facts like the names of shapes are wrong. After I identified a number of such suspicious channels on my newsletter, The Intrinsic Perspective, Wired found evidence of generative A.I. use in the production pipelines of some accounts with hundreds of thousands or even millions of subscribers.

As a neuroscientist, this worries me. Isn’t it possible that human culture contains within it cognitive micronutrients — things like cohesive sentences, narrations and character continuity — that developing brains need? Einstein supposedly said : “If you want your children to be intelligent, read them fairy tales. If you want them to be very intelligent, read them more fairy tales.” But what happens when a toddler is consuming mostly A.I.-generated dream-slop? We find ourselves in the midst of a vast developmental experiment.

There’s so much synthetic garbage on the internet now that A.I. companies and researchers are themselves worried, not about the health of the culture, but about what’s going to happen with their models. As A.I. capabilities ramped up in 2022, I wrote on the risk of culture’s becoming so inundated with A.I. creations that when future A.I.s are trained, the previous A.I. output will leak into the training set, leading to a future of copies of copies of copies, as content became ever more stereotyped and predictable. In 2023 researchers introduced a technical term for how this risk affected A.I. training: model collapse . In a way, we and these companies are in the same boat, paddling through the same sludge streaming into our cultural ocean.

With that unpleasant analogy in mind, it’s worth looking to what is arguably the clearest historical analogy for our current situation: the environmental movement and climate change. For just as companies and individuals were driven to pollute by the inexorable economics of it, so, too, is A.I.’s cultural pollution driven by a rational decision to fill the internet’s voracious appetite for content as cheaply as possible. While environmental problems are nowhere near solved, there has been undeniable progress that has kept our cities mostly free of smog and our lakes mostly free of sewage. How?

Before any specific policy solution was the acknowledgment that environmental pollution was a problem in need of outside legislation. Influential to this view was a perspective developed in 1968 by Garrett Hardin, a biologist and ecologist. Dr. Hardin emphasized that the problem of pollution was driven by people acting in their own interest, and that therefore “we are locked into a system of ‘fouling our own nest,’ so long as we behave only as independent, rational, free-enterprisers.” He summed up the problem as a “tragedy of the commons.” This framing was instrumental for the environmental movement, which would come to rely on government regulation to do what companies alone could or would not.

Once again we find ourselves enacting a tragedy of the commons: short-term economic self-interest encourages using cheap A.I. content to maximize clicks and views, which in turn pollutes our culture and even weakens our grasp on reality. And so far, major A.I. companies are refusing to pursue advanced ways to identify A.I.’s handiwork — which they could do by adding subtle statistical patterns hidden in word use or in the pixels of images.

A common justification for inaction is that human editors can always fiddle around with whatever patterns are used if they know enough. Yet many of the issues we’re experiencing are not caused by motivated and technically skilled malicious actors; they’re caused mostly by regular users’ not adhering to a line of ethical use so fine as to be nigh nonexistent. Most would be uninterested in advanced countermeasures to statistical patterns enforced into outputs that should, ideally, mark them as A.I.-generated.

That’s why the independent researchers were able to detect A.I. outputs in the peer review system with surprisingly high accuracy: They actually tried. Similarly, right now teachers across the nation have created home-brewed output-side detection methods , like adding hidden requests for patterns of word use to essay prompts that appear only when copied and pasted.

In particular, A.I. companies appear opposed to any patterns baked into their output that can improve A.I.-detection efforts to reasonable levels, perhaps because they fear that enforcing such patterns might interfere with the model’s performance by constraining its outputs too much — although there is no current evidence this is a risk. Despite public pledges to develop more advanced watermarking, it’s increasingly clear that the companies are dragging their feet because it goes against the A.I. industry’s bottom line to have detectable products.

To deal with this corporate refusal to act we need the equivalent of a Clean Air Act: a Clean Internet Act. Perhaps the simplest solution would be to legislatively force advanced watermarking intrinsic to generated outputs, like patterns not easily removable. Just as the 20th century required extensive interventions to protect the shared environment, the 21st century is going to require extensive interventions to protect a different, but equally critical, common resource, one we haven’t noticed up until now since it was never under threat: our shared human culture.

Erik Hoel is a neuroscientist, a novelist and the author of The Intrinsic Perspective newsletter.

The Times is committed to publishing a diversity of letters to the editor. We’d like to hear what you think about this or any of our articles. Here are some tips . And here’s our email: [email protected] .

Follow the New York Times Opinion section on Facebook , Instagram , TikTok , WhatsApp , X and Threads .