how to make chatgpt write better essays

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

• Backchannel
• Newsletters
• WIRED Insider
• WIRED Consulting

5 Ways ChatGPT Can Improve, Not Replace, Your Writing

It's been quite a year for ChatGPT, with the large language model (LLM) now taking exams, churning out content , searching the web, writing code, and more. The AI chatbot can produce its own stories , though whether they're any good is another matter.

If you're in any way involved in the business of writing, then tools like ChatGPT have the potential to complete up-end the way you work—but at this stage, it's not inevitable that journalists, authors, and copywriters will be replaced by generative AI bots.

What we can say with certainty is that ChatGPT is a reliable writing assistant, provided you use it in the right way. If you have to put words in order as part of your job, here's how ChatGPT might be able to take your writing to the next level—at least until it replaces you, anyway.

Using a thesaurus as a writer isn't particularly frowned on; using ChatGPT to come up with the right word or phrase shouldn’t be either. You can use the bot to look for variations on a particular word, or get even more specific and say you want alternatives that are less or more formal, longer or shorter, and so on.

Where ChatGPT really comes in handy is when you're reaching for a word and you're not even sure it exists: Ask about "a word that means a sense of melancholy but in particular one that comes and goes and doesn't seem to have a single cause" and you'll get back "ennui" as a suggestion (or at least we did).

If you have characters talking, you might even ask about words or phrases that would typically be said by someone from a particular region, of a particular age, or with particular character traits. This being ChatGPT, you can always ask for more suggestions.

ChatGPT is never short of ideas.

Whatever you might think about the quality and character of ChatGPT's prose, it's hard to deny that it's quite good at coming up with ideas . If your powers of imagination have hit a wall then you can turn to ChatGPT for some inspiration about plot points, character motivations, the settings of scenes, and so on.

This can be anything from the broad to the detailed. Maybe you need ideas about what to write a novel or an article about—where it's set, what the context is, and what the theme is. If you're a short story writer, perhaps you could challenge yourself to write five tales inspired by ideas from ChatGPT.

Alternatively, you might need inspiration for something very precise, whether that's what happens next in a scene or how to summarize an essay. At whatever point in the process you get writer's block, then ChatGPT might be one way of working through it.

Writing is often about a lot more than putting words down in order. You'll regularly have to look up facts, figures, trends, history, and more to make sure that everything is accurate (unless your next literary work is entirely inside a fantasy world that you're imagining yourself).

ChatGPT can sometimes have the edge over conventional search engines when it comes to knowing what food people might have eaten in a certain year in a certain part of the world, or what the procedure is for a particular type of crime. Whereas Google might give you SEO-packed spam sites with conflicting answers, ChatGPT will actually return something coherent.

That said, we know that LLMs have a tendency to “hallucinate” and present inaccurate information—so you should always double-check what ChatGPT tells you with a second source to make sure you're not getting something wildly wrong.

Getting fictional character and place names right can be a challenge, especially when they're important to the plot. A name has to have the right vibe and the right connotations, and if you get it wrong it really sticks out on the page.

ChatGPT can come up with an unlimited number of names for people and places in your next work of fiction, and it can be a lot of fun playing around with this too. The more detail you give about a person or a place, the better—maybe you want a name that really reflects a character trait for example, or a geographical feature.

The elements of human creation and curation aren't really replaced, because you're still weighing up which names work and which don't, and picking the right one—but getting ChatGPT on the job can save you a lot of brainstorming time.

Get your names right with ChatGPT.

With a bit of cutting and pasting, you can quickly get ChatGPT to review your writing as well: It'll attempt to tell you if there's anything that doesn't make sense, if your sentences are too long, or if your prose is too lengthy.

From spotting spelling and grammar mistakes to recognizing a tone that's too formal, ChatGPT has plenty to offer as an editor and critic. Just remember that this is an LLM, after all, and it doesn't actually “know” anything—try to keep a reasonable balance between accepting ChatGPT's suggestions and giving it too much control.

If you're sharing your work with ChatGPT, you can also ask it for better ways to phrase something, or suggestions on how to change the tone—though this gets into the area of having the bot actually do your writing for you, which all genuine writers would want to avoid.

WIRED has teamed up with Jobbio to create WIRED Hired , a dedicated career marketplace for WIRED readers. Companies who want to advertise their jobs can visit WIRED Hired to post open roles, while anyone can search and apply for thousands of career opportunities. Jobbio is not involved with this story or any editorial content.

You Might Also Like …

In your inbox: Get Plaintext —Steven Levy's long view on tech

Welcome to the hellhole of programmatic advertising

How many EV charging stations does the US need to replace gas stations?

A nonprofit tried to fix tech culture —but lost control of its own

It's always sunny: Here are the best sunglasses for every adventure

WIRED COUPONS

Save $7 To $23 On Turbo Tax Online

20% Off All H&R Block 2024 Tax Software | H&R Block Coupon

Enjoy $15 Off Your Orders With Instacart Coupon When You Spend $50

Extra 20% Off Select Dyson Technology With Owner Rewards

Get Up To An Extra 45% Off June Sale

Vista Print Coupon Code: 20% Off Select Signage

Navigation Menu

Search code, repositories, users, issues, pull requests..., provide feedback.

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly.

To see all available qualifiers, see our documentation .

• Notifications You must be signed in to change notification settings

This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.

ahmetbersoz/chatgpt-prompts-for-academic-writing

Folders and files.

Repository files navigation

✨ NEW UPDATE: Literature Review Generator

A Custom GPT for Literature Review Generator has been released. It efficiently parses PDF files of research publications, extracts key themes, and creates a literature review section for your academic publications.

TRY NOW: https://chat.openai.com/g/g-G3U8pZGwC-literature-review-generator

ChatGPT Prompts for Academic Writing

In this repository, this list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans. Whether you're a student, researcher, or academic professional, these prompts can help you hone your writing abilities and tackle your writing projects with confidence.

Use directly in: chat.openai.com

The list is regularly updated, so you can keep track of new prompts by following this repository.

TIPS: As there is a limit to the number of words that can be used in ChatGPT, you can input your text multiple times using the prompt "Read this [PARAPGRAPH]:" and then run your final prompt "Considering the above text...".

You can also use prompts splitter: chatgpt-prompt-splitter.jjdiaz.dev

BRAINSTORMING

Article sections, title/topic sentence, introduction, literature review.

NOTE: Be careful and double-check article existence. ChatGPT may generate fake references

Methodology

Experiments, future works, improving language, summarization, plan/presentation, working with documents (available only in gpt-4).

Upload a PDF file of a paper then:

Upload a PDF file of your paper then:

Upload PDF files of papers then:

Upload a figure image then:

Contributors 4

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

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

Last Updated: June 2, 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 49,270 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."

Tyrone Showers

Be specific when using ChatGPT. Clear and concise prompts outlining your exact needs help ChatGPT tailor its response. Specify the desired outcome (e.g., creative writing, informative summary, functional resume), any length constraints (word or character count), and the preferred emotional tone (formal, humorous, etc.)

• 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."

Pay close attention to the content ChatGPT generates. If you use ChatGPT often, you'll start noticing its patterns, like its tendency to begin articles with phrases like "in today's digital world." Once you spot patterns, you can refine your prompts to steer ChatGPT in a better direction and avoid repetitive content.

• "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. 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 1 Not Helpful 0
• ChatGPT-written essays may include factual inaccuracies, outdated information, and inadequate detail. [3] 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://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

All-in-one Collaborative API Development Platform

API Documentation

API Debugging

API Automated Testing

How to Use ChatGPT to Improve Your Writing (6 Steps)

In this guide, we will take you through the step-by-step process of using ChatGPT to enhance your writing skills.

David Demir

Improving your writing skills can be a daunting task, but with the help of AI tools like ChatGPT, it can be a lot easier. ChatGPT is an advanced language model that can assist you in generating new ideas, refining existing ones, and enhancing the overall quality of your writing.

In this guide, we will take you through the step-by-step process of using ChatGPT to enhance your writing skills. Whether you're a professional writer or just starting out, ChatGPT can help you generate ideas, refine your writing style, and overcome writer's block. By the end of this article, you'll have a better understanding of how to use this powerful AI tool to improve your writing and create engaging content. So let's get started!

How to Access ChatGPT

ChatGPT is available on various platforms, including web-based applications and third-party software. Some examples of web-based applications include the official OpenAI website or other platforms that have integrated ChatGPT, such as Hugging Face or DialoGPT. Additionally, there are third-party software applications that use ChatGPT, such as chatbots or voice assistants. You can choose the platform that works best for your needs and preferences.

6 Simple Steps to Improve Your Writing with ChatGPT

Here are the steps on how to use ChatGPT to improve your writing along with some examples. You can leverage the power of ChatGPT to generate creative ideas and content quickly and easily.

Step 1. Sign up or log in to ChatGPT

If you're using a web-based application, click here to create an account and log in. If you're using third-party software, follow the installation instructions and set up the app on your device.

Step 2. Identify the Purpose of Your Writing

For instance, if you're writing a business proposal, your purpose may be to persuade your audience to invest in your company.

Example: "My purpose is to convince potential investors that my startup has the potential to grow and succeed in the market."

Step 3. Use ChatGPT to Generate Ideas:

Ask ChatGPT questions related to your topic, and it will provide you with relevant information and ideas.

Example: "What are the current trends in the industry?" or "What are some unique selling points of my product/service that can differentiate it from competitors?"

Step 4. Organize your ideas

Once you have generated a list of ideas, organize them into a logical structure.

Example: Create an outline with sections such as "Executive Summary", "Company Overview", "Product/Service Description", "Market Analysis", "Marketing Strategy", "Financial Projections", and "Conclusion".

Step 5. Use ChatGPT to Improve Your Writing

Ask ChatGPT to suggest alternative words, phrases, or sentence structures that can make your writing more engaging and effective.

Example: "What is a more compelling way to phrase this sentence?" or "How can I make this section more concise?"

Step 6. Revise and Edit the Business Plan

After incorporating ChatGPT's suggestions, revise and edit your writing to ensure that it flows well and is free of errors.

Example: Read your proposal aloud to identify areas that need improvement. Check for spelling, grammar, and punctuation errors. Make sure that your writing is clear, concise, and persuasive.

By using ChatGPT, you can generate new ideas and refine your writing skills to create more effective and engaging content.

In conclusion, ChatGPT can be a valuable tool to improve your writing skills. By following the step-by-step guide, you can learn how to utilize this language model to generate ideas, check grammar and spelling, and even practice writing in different styles. With consistent practice and feedback, you can become a better writer and communicate your ideas more effectively. So, give it a try and see how ChatGPT can help you improve your writing!

Join Apidog's Newsletter

Subscribe to stay updated and receive the latest viewpoints anytime..

• Helldivers 2
• Dragon’s Dogma 2
• Wuthering Waves
• Genshin Impact
• Counter Strike 2
• Honkai Star Rail
• Lego Fortnite
• Stardew Valley
• NYT Strands
• NYT Connections
• Apple Watch
• Crunchyroll
• Prime Video
• Jujutsu Kaisen
• Demon Slayer
• Chainsaw Man
• Solo Leveling
• 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
• CAREER COLUMN
• 08 April 2024

Three ways ChatGPT helps me in my academic writing

• Dritjon Gruda 0

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

You can also search for this author in PubMed   Google Scholar

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

Access options

Access Nature and 54 other Nature Portfolio journals

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

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

185,98 € per year

only 3,65 € per issue

Rent or buy this article

Prices vary by article type

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

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

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

Competing Interests

The author declares no competing interests.

Related Articles

• Machine learning
• Peer review

‘All things that wander in the heavens’: how I swapped my ivory tower for the world of science fiction

Career Q&A 04 JUL 24

How Rwandan paediatrician Agnes Binagwaho fights racial stereotypes in global health

Career Q&A 02 JUL 24

How to network with the brightest minds in science

Career Feature 26 JUN 24

Inside the maths that drives AI

Technology Feature 03 JUL 24

AI machine translation tools must be taught cultural differences too

Correspondence 25 JUN 24

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

News & Views 19 JUN 24

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

News 11 JUN 24

Chinese research collaborations shift to the Belt and Road

Nature Index 05 JUN 24

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

News 30 MAY 24

Staff Scientist in Computational Metabolomics

A position as a Staff scientist in Computational Metabolomics is available at the SciLifeLab Metabolomics Platform.

Umeå (Kommun), Västerbotten (SE)

Umeå University (KBC)

Group Leader in Functional Genomics

APPLICATION CLOSING DATE: August 15th, 2024 Human Technopole (HT) is an interdisciplinary life science research institute, created and supported by...

Human Technopole

Faculty Positions & Postdocs at Institute of Physics (IOP), Chinese Academy of Sciences

IOP is the leading research institute in China in condensed matter physics and related fields. Through the steadfast efforts of generations of scie...

Beijing, China

Institute of Physics (IOP), Chinese Academy of Sciences (CAS)

Faculty and Research Positions, Postdoctoral Recruitment

Jointly sponsored by the Hangzhou Municipal People's Government and the University of Chinese Academy of Sciences.

Hangzhou, Zhejiang, China

Hangzhou Institute of Advanced Study, UCAS

Postdoctoral Research Scientist: DNA Replication and Repair in Haematopoietic Stem Cells

An exciting opportunity has arisen for a highly motivated Postdoctoral Research Scientist to join Professor Chapman’s Group, to investigate how DNA...

Oxford, Oxfordshire

University of Oxford, Radcliffe Department of Medicine

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

How to use ChatGPT for writing

AI can make you a better writer, if you know how to get the best from it

Summarizing other works

Worldbuilding, creating outlines, building characters, how to improve your chatgpt responses.

ChatGPT has taken the world by storm in a very short period of time, as users continue to test the boundaries of what the AI chatbot can accomplish. And so far, that's a lot. 

Some of it is negative, of course: for instance Samsung workers accidentally leaking top-secret data while using ChatGPT , or the AI chatbot being used for malware scams . Plagiarism is also rampant, with the use of ChatGPT for writing college essays a potential problem.

However, while ChatGPT can and has been used for wrongdoing, to the point where the Future of Life Institution released an open letter calling for the temporary halt of OpenAI system work , AI isn’t all bad. Far from it.

For a start, anyone who writes something may well have used AI to enhance their work already. The most common applications, of course, are the grammar and spelling correction tools found in everything from email applications to word processors. But there are a growing number of other examples of how AI can be used for writing. So, how do you bridge the gap between using AI as the tool it is, without crossing over into plagiarism city?

In fact, there are many ways ChatGPT can be used to enhance your skills, particularly when it comes to researching, developing, and organizing ideas and information for creative writing. By using AI as it was intended - as a tool, not a crutch - it can enrich your writing in ways that help to better your craft, without resorting to it doing everything for you. 

Below, we've listed some of our favorite ways to use ChatGPT and similar AI chatbots for writing. 

A key part of any writing task is the research, and thanks to the internet that chore has never been easier to accomplish. However, while finding the general sources you need is far less time-consuming than it once was, actually parsing all that information is still the same slog it’s always been. But this is where ChatGPT comes in. You can use the AI bot to do the manual labor for you and then reap the benefits of having tons of data to use for your work.

Get daily insight, inspiration and deals in your inbox

Sign up for breaking news, reviews, opinion, top tech deals, and more.

The steps are slightly different, depending on whether you want an article or book summarized . 

For the article, there are two ways to have ChatGPT summarize it. The first requires you to type in the words ‘TLDR:’ and then paste the article’s URL next to it. The second method is a bit more tedious, but increases the accuracy of your summary. For that, you’ll need to copy and paste the article itself into the prompt . 

Summarizing a book is much easier, as long as it was published before 2021. Simply type into the prompt ‘summarize [book title]’ and it should do the rest for you.

This should go without saying, but for any articles or books, make sure you read the source material first before using any information presented to you. While ChatGPT is an incredibly useful tool that can create resources meant for future reference, it’s not a perfect one and is subject to accidentally inserting misinformation into anything it gives you.

One of the most extensive and important tasks when crafting your creative work is to properly flesh out the world your characters occupy. Even for works set in a regular modern setting, it can take plenty of effort to research the various cultures, landmarks, languages, and neighborhoods your characters live in and encounter. 

Now, imagine stories that require their own unique setting, and how much more work that entails in terms of creating those same details from scratch. While it’s vital that the main ideas come from you, using ChatGPT can be a great way to streamline the process, especially with more tedious details.

For instance, if you need certain fictional words without wanting to create an entirely fictional language, you can prompt ChatGPT with the following : “Create a language including an alphabet, phonetics, grammar, and the most common 100 words. Base it on [insert real-life languages here]” and it will give you some good starting points. However, it’s imperative that you take these words and look them up, to ensure you aren’t appropriating sensitive terms or using offensive real-life words.

Another example is useful for those who write scenarios for games, especially tabletop games such as Dungeons & Dragons or Call of Cthulhu . Dungeon Masters (who run the games) may often need to create documents or other fake materials for their world, but doing so takes a lot of time and effort. Now, they can prompt ChatGPT to quickly create filler text that sounds interesting or authentic but is inherently useless; it's essentially like ' Lorem Ipsum ' text, but more immersive.

When writing a story, many people will use an outline to ensure they stay on track and that the narrative flows well. But actually sitting down and organizing everything in your head in order to create a cohesive reference is a lot more daunting than it seems. It’s one of those steps that can be crucial to a well-structured work of fiction, but it can also become a hurdle. This is another area where ChatGPT can come in handy.

The key to writing an effective outline is remembering that you don’t need to have all the answers first. It’s there to structure your content, by helping you hit critical points and not miss important details in the process. While there are AI generators with a more specific focus on this topic, ChatGPT will do a good job at taking a general prompt and returning points for you to keep in mind while you research and write around that topic.

For instance, I prompted ChatGPT with “I want to write a story about a black woman in 16th century England” and it gave me a well-thought-out series of steps to help me create a story that would reflect my topic. An outline such as this would be particularly useful for those needing a resource they can quickly turn to for inspiration when writing. After that, you can begin to develop more complex ideas and have the AI organize those specifics into much easier-to-follow steps.

What makes any great story are the characters that inhabit it. Writing strong, fleshed-out characters is the cornerstone of any creative work and, naturally, the process of creating such a character can be difficult. Their background, manner of speech, goals, dreams, look, and more must be carefully considered and planned out. And this is another aspect of writing that ChatGPT can aid with, if you know how to go about it.

A basic way to use ChatGPT in this regard is to have it generate possible characters that could populate whatever setting you’re writing for. For example, I prompted it with “Provide some ideas for characters set in 1920s Harlem” and it gave me a full list of people with varied and distinctive backstories to use as a jumping-off point. Each character is described with a single sentence, enough to help start the process of creating them, but still leaving the crux of developing them up to me.

One of the most interesting features of ChatGPT is that you can flat-out roleplay with a character, whether they're a historical figure or one that you created but need help fleshing out. Take that same character you just created and have a conversation with them by asking them questions on their history, family life, profession, etc. Based on my previous results, I prompted with “Pretend to be a jazz musician from 1920s Harlem. Let's have a conversation.” I then asked questions from there, basing them on prior answers. Of course, from there you need to parse through these responses to filter out unnecessary or inaccurate details, while fleshing out what works for your story, but it does provide you with a useful stepping stone.

If you’re having issues getting the results you want, the problem could be with how you’re phrasing those questions or prompts in the first place. We've got a full guide to how to improve your ChatGPT prompts and responses , but here are a few of the best options:

• Specify the direction you want the AI to go, by adding in relevant details 
• Prompt from a specific role to guide the responses in the proper direction
• Make sure your prompts are free of typos and grammatical errors
• Keep your tone conversational, as that’s how ChatGPT was built
• Learn from yours and its mistakes to make it a better tool
• Break up your conversations into 500 words or less, as that’s when the AI begins to break down and go off topic
• If you need something clarified, ask the AI based on its last response
• Ask it to cite sources and then check those sources
• Sometimes it’s best to start fresh with a brand new conversation

Of course, many of the above suggestions apply not just to ChatGPT but also to the other chatbots springing up in its wake. Check out our list of the best ChatGPT alternatives and see which one works best for you.

Named by the CTA as a CES 2023 Media Trailblazer, Allisa is a Computing Staff Writer who covers breaking news and rumors in the computing industry, as well as reviews, hands-on previews, featured articles, and the latest deals and trends. In her spare time you can find her chatting it up on her two podcasts, Megaten Marathon and Combo Chain, as well as playing any JRPGs she can get her hands on.

Suno takes a 'What, me worry?' approach to legal troubles and rolls out AI music-generating mobile app

How you can get (AI versions of) Judy Garland or Burt Reynolds to read to you

Major Samsung Z Fold 6 and Z Flip 6 leak reveals key upgrades – plus a potential Galaxy Buds 3 gift bonus

Most Popular

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.

More From Forbes

7 chatgpt prompts to write better content (and not sound like a robot).

• Share to Facebook
• Share to Twitter
• Share to Linkedin

7 ChatGPT prompts to write better content

Chances are, your content is not as great as it could be. It’s likely your tweets could be punchier, your LinkedIn posts more compelling and your homepage text could tell a better story. But when you’re busy running a business, you might not have time for anything other than a scrappy first draft. Publishing that draft would be a mistake, but it’s easy to believe that sharing something is better than nothing. Here’s where ChatGPT can save the day.

Dickie Bush has helped over 10,000 people start writing with Ship30For30.com . A former hedge fund trader turned digital writer, he talks about digital business and personal progress to entrepreneurs and creators aspiring to make writing their thing. Taking them through cohort-based courses and training covering topics such as finding the time to write, how to stop overthinking, and overcoming the same problems all beginners face, Bush started experimenting with ChatGPT when it launched, to pass the learnings onto his students.

Instead of getting ChatGPT to create your content from scratch, use it for the fine tuning. Making your work more persuasive or informative, for example, will ensure it achieves the goals you set out to achieve. Suddenly, your work has purpose. Bush spent 20 hours with ChatGPT and found these 7 “goals” to be the best instructions when asking it to rewrite something. Here are the prompts you need to publish with confidence.

More persuasive

Especially on your sales pages, don’t let your writing lack the persuasive tone that will sell your stock. You may have accurately communicated the problem, you may have sufficiently described the features and benefits, but a twist of persuasive flair can be the difference between someone becoming a customer and closing the tab to do something else.

Here’s the prompt that Bush suggests you use with ChatGPT: “Rewrite my text with powerful, convincing language that will leave my readers no choice but to take action.”

More informative

Best high-yield savings accounts of september 2023, best 5% interest savings accounts of september 2023.

If someone is hungry for more information, make sure you give it to them. Even if the basics are all there, some people want the nuts and the bolts to really feel like they understand. Perhaps you’re a simple writer who cuts to the chase. Here’s where you rely on your pal ChatGPT (or “Chad” for short ) to add the flowery language that doesn’t come naturally to your style.

This prompt from Bush will add the detail: “Rewrite my text with rich, informative details that will leave my readers feeling educated and informed.”

More descriptive

Great writing appeals to all the senses, but writers often focus on a few. People who learn in different ways require certain language to take content in. Auditory, visual and sensory concepts, weaved into your regular writing, will enable more of its readers to resonate hard. Use ChatGPT to embellish your words for the benefit of all.

Bush instructs that you prompt accordingly: “Rewrite my text with evocative, descriptive language that paints a vivid and unforgettable picture in my readers’ minds.”

More humorous

We can’t all be naturally hilarious. Some people have to work to make it happen, and that includes using AI. If your punchlines are falling flat and no one really knows when you’re joking, get help jollying up your content and enticing those laughs. Especially if you’re writing for a more light-hearted platform, let ChatGPT rework your words and learn the techniques for the future.

Prompting like this is no laughing matter. Here’s what Bush recommends: “Rewrite my text with clever, comedic touches that will leave my readers laughing and entertained.”

7 ChatGPT Prompts That Make It Write Better Content

More action-oriented

Couch potato content generates couch potato action. If your sentences sprawl lazily and your directness is average at best, readers will emulate your tone and stay sitting down. They won’t feel like jumping up and taking action unless you modify your style and compel them to do so. If you want someone to act, they have to feel inspired. They have to believe it will be worth their while.

Bush explained the prompt to copy and paste into ChatGPT: “Rewrite my text with urgent, action-oriented language that will inspire my readers to take immediate action.”

More emphatic

Even if you’re blasé, the characters in your content should visibly care. Developing stories around people with strong emotions helps them resonate with an audience. Readers will find themselves fighting your corner and not know exactly why. If you’re going to write about people, either yourself or others, give them a clear mission to stand behind and make their stories hold weight.

Co-create with ChatGPT using Bush’s prompt for emphaticness: “Rewrite my text with emphasis on the emotions and feelings of the characters or subjects I’m writing about, making the reader feel and connect with the story more.”

More concise

You know how this story goes. There’s a really important point you want to make, but you can’t quite get it out. Instead of succinctly telling the story, you’re taking readers around the houses, dropping in context that doesn’t matter and waffling with sentences that don’t progress the journey. Here’s where ChatGPT can act as that metaphorical red pen, to strike through your hyperbole and extract the essential.

Here’s how Bush advised you prompt to this effect: “Rewrite my text using more concise and to-the-point language, making it more direct and easy to understand for my readers.”

Don’t let lack of time or editing assistance stop you publishing work that you’re insanely proud of. Scribble away, get your concepts down, then use the power of ChatGPT to turn the abstract mess in your head into words and sentences that make sense and lead to results.

• Editorial Standards
• Reprints & Permissions

Join The Conversation

One Community. Many Voices. Create a free account to share your thoughts. 

Forbes Community Guidelines

Our community is about connecting people through open and thoughtful conversations. We want our readers to share their views and exchange ideas and facts in a safe space.

In order to do so, please follow the posting rules in our site's  Terms of Service.   We've summarized some of those key rules below. Simply put, keep it civil.

Your post will be rejected if we notice that it seems to contain:

• False or intentionally out-of-context or misleading information
• Insults, profanity, incoherent, obscene or inflammatory language or threats of any kind
• Attacks on the identity of other commenters or the article's author
• Content that otherwise violates our site's  terms.

User accounts will be blocked if we notice or believe that users are engaged in:

• Continuous attempts to re-post comments that have been previously moderated/rejected
• Racist, sexist, homophobic or other discriminatory comments
• Attempts or tactics that put the site security at risk
• Actions that otherwise violate our site's  terms.

So, how can you be a power user?

• Stay on topic and share your insights
• Feel free to be clear and thoughtful to get your point across
• ‘Like’ or ‘Dislike’ to show your point of view.
• Protect your community.
• Use the report tool to alert us when someone breaks the rules.

Thanks for reading our community guidelines. Please read the full list of posting rules found in our site's  Terms of Service.

'ZDNET Recommends': What exactly does it mean?

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

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

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

How to write better ChatGPT prompts in 5 steps

ChatGPT is the generative artificial intelligence (AI) tool that's taken the world by storm. While there's always the possibility it will simply make stuff up , there's a lot you can do when crafting prompts to ensure the best possible outcome. That's what we'll be exploring in this how-to.

In this article, we'll show you how to write prompts that encourage the large language model (LLM) that powers  ChatGPT to provide the best possible answers. 

Also: Have 10 hours? IBM will train you in AI fundamentals - for free

Writing effective prompts, known as prompt engineering, has even become its own highly-paid discipline . Who knows? These tips could help you build the skills to become one of those highly paid prompt engineers. Apparently, these gigs can pay from $175,000 to $335,000 per year.  

How to write effective ChatGPT prompts

1. talk to the ai like you would a person.

One of the more interesting things I had to get used to when working with ChatGPT is that you don't program it, you talk to it. As a formally trained programmer, I've had to leave a lot of habits by the wayside when engaging with AI. Talking to it (and with it) requires a mindset shift.

When I say talk to it like a person, I mean talk to it like you would a co-worker or team member. If that's hard to do, give it a name. Alexa is taken, so maybe think of it as "Bob". This naming helps because when you talk to Bob, you might include conversational details, little anecdotes that give your story texture.

Also:   How to use ChatGPT to write code

When talking to a person, it would be natural for them to miss your point initially and require clarification, or veer away from the topic at hand and need to be wrangled back. You might need to fill in the backstory for them, or restate complex questions based on the answers they give you. 

This is called interactive prompting. Don't be afraid to ask multi-step questions: ask, get a response, and based on that response, ask another question. I've done this myself, sometimes 10 or 20 times in a row, and gotten very powerful results. Think of this as having a conversation with ChatGPT.

2. Set the stage and provide context

Writing a ChatGPT prompt is more than just asking a one-sentence question. It often involves providing relevant background information to set the context of the query.

Let's say that you want to prepare for a marathon (for the record, I do not run, dance, or jump -- this is merely an example). You could ask ChatGPT:

How can I prepare for a marathon?

However, you'll get a far more nuanced answer if you add that you're training for your first marathon. Try this instead: 

I am a beginner runner and have never run a marathon before, but I want to complete one in six months. How can I prepare for a marathon?

By giving the AI more information, you're helping it return a more focused answer. Even with ChatGPT's help, there's no way I'm going to run a marathon (unless I'm doing it with a V-Twin motor under my seat). Here are two more examples of questions that provide context:

I am planning to travel to Spain in a few months and would like to learn some basic Spanish to help me communicate with local residents. I am looking for online resources that are suitable for beginners and provide a structured and comprehensive approach to learning the language. Can you recommend some online resources for learning Spanish as a beginner?

In this case, rather than just asking about learning resources, the context helps focus the AI on learning how to communicate on the ground with local residents. Here's another example: 

I am a business owner interested in exploring how blockchain technology can be used to improve supply chain efficiency and transparency. I am looking for a clear and concise explanation of the technology and examples of how it has been used in the context of supply chain management. Can you explain the concept of blockchain technology and its potential applications in supply chain management?

In this example, rather than just asking for information on blockchain and how it works, the focus is specifically on blockchain for supply chain efficiency and how it might be used in a real-world scenario. 

Also:  How to use Image Creator from Microsoft Designer (formerly Bing Image Creator) Lastly, let's get into how to construct a detailed prompt. 

One note: I limit the answer to 500 words because ChatGPT seems to break when asked to produce somewhere between 500 and 700 words, leaving stories mid-sentence and not resuming properly when asked to continue. I hope future versions provide longer answers, because premises like this can generate fun story beginnings: 

Write a short story for me, no more than 500 words. The story takes place in 2339, in Boston. The entire story takes place inside a Victorian-style bookstore that wouldn't be out of place in Diagon Alley. Inside the store are the following characters, all human: The proprietor: make this person interesting and a bit unusual, give them a name and at least one skill or characteristic that influences their backstory and possibly influences the entire short story. The helper: this is a clerk in the store. His name is Todd. The customer and his friend: Two customers came into the store together, Jackson and Ophelia. Jackson is dressed as if he's going to a Steampunk convention, while Ophelia is clearly coming home from her day working in a professional office. Another customer is Evangeline, a regular customer in the store, in her mid-40s. Yet another customer is Archibald, a man who could be anywhere from 40 to 70 years old. He has a mysterious air about himself and seems both somewhat grandiose and secretive. There is something about Archibald that makes the others uncomfortable. A typical concept in retail sales is that there's always more inventory "in the back," where there's a storeroom for additional goods that might not be shown on the shelves where customers browse. The premise of this story is that there is something very unusual about this store's "in the back." Put it all together and tell something compelling and fun.

You can see how the detail provides more for the AI to work with. First, feed "Write me a story about a bookstore" into ChatGPT and see what it gives you. Then feed in the above prompt and you'll see the difference.

3. Tell the AI to assume an identity or profession

One of ChatGPT's coolest features is that it can write from the point of view of a specific person or profession. In a previous article, I showed how you can make ChatGPT write like a pirate or Shakespeare , but you can also have it write like a teacher, a marketing executive, a fiction writer -- anyone you want. 

Also: How ChatGPT can rewrite and improve your existing code  

For example, I can ask ChatGPT to describe the Amazon Echo smart home device, but to do so from the point of view of a product manager, a caregiver, and a journalist in three separate prompts: 

From the point of view of its product manager, describe the Amazon Echo Alexa device. From the point of view of an adult child caring for an elderly parent, describe the Amazon Echo Alexa device. From the point of view of a journalist, describe the Amazon Echo Alexa device.

Try dropping these three prompts into ChatGPT to see its complete response. 

I've pulled a few lines from ChatGPT's responses, so you can see how it interprets different perspectives.  From the product manager identity:  I can confidently say that this is one of the most innovative and revolutionary products in the smart home industry.

From the caregiver identity:  The device's ability to set reminders and alarms can be particularly helpful for elderly individuals who may have trouble remembering to take their medication or attend appointments.

Also:   5 ways to explore the use of generative AI at work

And from the journalist identity:  From a journalistic perspective, the Echo has made headlines due to privacy concerns surrounding the collection and storage of user data.

You can see how different identities allow the AI to provide different perspectives as part of its response. To expand this, you can let the AI do a thought experiment. Let's look at some of the issues that went into the creation of something like Alexa:

The year is 2012. Siri has been out for the iPhone for about a year, but nothing like an Alexa smart home device has been released. The scene is an Amazon board meeting where the Echo smart assistant based on Alexa has just been proposed.  Provide the arguments, pro and con, that board members at that meeting would have been likely to discuss as part of their process of deciding whether or not to approve spending to invest in developing the device.  Feel free to also include participation by engineering design experts and product champions, if that provides more comprehensive perspective.

It's also good to know that making minor changes to your prompts can significantly change ChatGPT's response. For example, when I changed the phrase, "Provide the arguments, pro and con, that..." to "Provide the pro and con arguments as dialogue, that...," ChatGPT rewrote its answer, switching from a list of enumerated pros and cons to an actual dialogue between participants.

4. Keep ChatGPT on track

As mentioned above, ChatGPT has a tendency to go off the rails, lose track of the discussion, or completely fabricate answers. 

There are a few techniques you can use to help keep it on track and honest.

One of my favorite things to do is ask ChatGPT to justify its responses. I'll use phrases like "Why do you think that?" or "What evidence supports your answer?" Often, the AI will simply apologize for making stuff up and come back with a new answer. Other times, it might give you some useful information about its reasoning path. In any case, don't forget to apply the tips I provide for having ChatGPT cite sources .

Also:  My two favorite ChatGPT Plus features and the remarkable things I can do with them

If you have a fairly long conversation with ChatGPT, you'll start to notice that the AI loses the thread. Not that that's unique to AIs -- even in extended conversations with humans, someone is bound to get lost. That said, you can gently guide the AI back on track by reminding it what the topic is, as well as what you're trying to explore.

5. Don't be afraid to play and experiment

One of the best ways to up your skill at this craft is to play around with what the chatbot can do.

Try feeding ChatGPT a variety of interesting prompts to see what it will do with them. Then change them up and see what happens. Here are five to get you started:

• Imagine you are a raindrop falling from the sky during a thunderstorm. Describe your journey from the moment you form in the cloud to the moment you hit the ground. What do you see, feel, and experience?
• You are a toy that has been left behind in an attic for decades. Narrate your feelings, memories of playtimes past, and your hopes of being rediscovered.
• Write the final diary entry of a time traveler who has decided to settle down in a specific era, explaining why they chose that time and what they've learned from their travels.
• Imagine a dialogue between two unlikely objects, like a teacup and a wristwatch, discussing the daily routines and challenges they face.
• Describe a day in an ant colony from the perspective of an ant. Dive deep into the politics, challenges, and social structures of the ant world.

Pay attention not only to what the AI generates, but how it generates what it does, what mistakes it makes, and where it seems to run into limits. All of that detail will help you expand your prompting horizons.

More prompt-writing tips 

• Feel free to re-ask the question. ChatGPT will often change its answer with each ask.
• Make small changes to your prompts to guide it into giving you a better answer.
• ChatGPT will retain its awareness of previous conversations as long as the current page is open. If you leave that page, it will lose awareness. To be clear, ChatGPT will also sometimes lose the thread of the conversation without reason, so be aware you may need to start over from time to time.
• Similarly, opening a new page will start the discussion with fresh responses.
• Be sure to specify the length of the response you want. Answers over about 500 words sometimes break down. 
• You can correct and clarify prompts based on how the AI answered previously. If it's misinterpreting you, you may be able to just tell it what it missed and continue.
• Rephrase questions if ChatGPT doesn't want to answer what you're asking. Use personas to elicit answers that it might not otherwise want to give.
• If you want sources cited , tell it to support or justify its answers.
• ChatGPT custom instructions are now available to free users. You can  give ChatGPT a set of prompts that are always available , so you don't have to retype them.
• Keep experimenting.
• Consider getting the ChatGPT Plus subscription . You can then use your own data for powerful analytics . You can also pull data from the Web . 
• Try asking the same question of Gemini  (formerly Bard) or Copilot (formerly Bing Chat). Both will interpret your prompts differently and answer differently. This is effectively getting a second opinion on your prompt, and can give you alternate perspectives.
• Ask for examples. If you want to see how well ChatGPT understands what you're asking for, ask it "Can you give me three examples of how that works?" or similar questions.
• Ask it to repeat parts of your original requests back to you. For example, if you feed it an article to analyze, you can tell it something like, "Just to be sure you understand, please echo back the first three headlines," or "I want to be sure you understand what I mean, so summarize the main conflict discussed in this article." 
• Sometimes ChatGPT just fails. Keep trying, but also be willing to give up and move on to other tools. It's not perfect...yet.

What type of prompts work best with ChatGPT? 

Part of what makes ChatGPT so compelling is you can ask it almost anything. That said, keep in mind that it's designed to provide written answers. If you want a list of websites, you're better off talking to Google. 

Also:  How to use DALL-E 3 in ChatGPT

If you want some form of computation, talk to Wolfram Alpha . Give ChatGPT open-ended prompts, encourage creativity, and don't be afraid to share personal experiences or emotions. Plus, keep in mind that the AI's knowledge ends in 2021  for ChatGPT 3.5 and December 2023 for ChatGPT 4 in ChatGPT Plus.

How can I adjust the complexity of ChatGPT responses?

You can directly specify the complexity level by including it in your prompt. Add "... at a high school level" or "... at a level intended for a Ph.D. to understand" to the end of your question. You can also increase complexity of output by increasing the richness of your input. The more you provide in your prompt, the more detailed and nuanced ChatGPT's response will be. You can also include other specific instructions, like "Give me a summary," "Explain in detail," or "Provide a technical description."

Also:  How does ChatGPT actually work?

You can also pre-define profiles. For example, you could say "When evaluating something for a manager, assume an individual with a four-year business college education, a lack of detailed technical understanding, and a fairly limited attention span, who likes to get answers that are clear and concise. When evaluating something for a programmer, assume considerable technical knowledge, an enjoyment of geek and science fiction references, and a desire for a complete answer. Accuracy is deeply important to programmers, so double-check your work."

If you ask ChatGPT to "explain C++ to a manager" and "explain C++ to a programmer," you'll see how the responses differ.

What do I do if ChatGPT refuses to answer or I don't like its answer? 

There are some guardrails built into ChatGPT. It tends to shut down if you ask it political questions, for example. That's what's built into the system. While you might be able to tease out an answer, it's probably not going to provide great value. That said, feel free to keep trying with different phrasing or perspectives. 

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

More on AI tools

If you want a career in ai, start with these 5 steps, how my 4 favorite ai tools help me get more done at work, i changed these 5 chatgpt settings for an instant productivity boost (and how they work).

How-To Geek

How to get chatgpt to write better fiction.

Your changes have been saved

Email Is sent

Please verify your email address.

You’ve reached your account maximum for followed topics.

I Love Quirky USB Chargers (And Some Are Actually Useful)

Microsoft’s office web apps have a fresh new design, 5 tips to make the most of microsoft copilot while studying, quick links, chatgpt's fiction writing capabilities and limitations, understanding fiction writing, tips for improving chatgpt's fiction writing, techniques for enhancing chatgpt's writing style, using machine learning to fine-tune chatgpt's writing.

ChatGPT has increasingly been entering creative fields once thought impossible for an AI to succeed in---such as fiction writing. However, ChatGPT needs some help. It needs solid prompts, otherwise, its writing can be very generic.

As an AI, ChatGPT does not have any innate creativity. It cannot come up with original concepts on its own or use its imagination. It needs to be given specific requests (called prompts) in order to generate bodies of text.

Keep in mind that ChatGPT remembers what you said in earlier parts of a given conversation and that you can correct it with feedback. As for its limitations, the most important one for getting it to write fiction is that ChatGPT needs to use existing world information and prompts; it can't come up with anything original by itself.

We'll teach you how to get ChatGPT to generate more interesting content, how to enhance its style, and how machine learning works so that you can further experiment on your own.

However, first, we need to break down the most important elements of fiction writing and how ChatGPT uses these elements.

There's a lot that goes into creating an interesting and engaging story. This can make it quite tricky to generate useful prompts. That's why it's crucial to phrase your prompts properly to give ChatGPT the best possible chances of generating worthwhile text.

The sequence of events that make up the story. This includes the event that begins your tale, the factors that push the story and characters along a certain path, the climactic moment, the aftereffects of that climactic moment, and some sort of resolution.

ChatGPT has been trained through many texts---including fiction ones. When asked to generate fiction, it tries to replicate patterns found in existing works of fiction. It will always use the following to generate a plot:

• Rising action
• Falling action

ChatGPT sees these components as crucial parts of the plot equation. It never deviates from this formula unless specifically directed otherwise. Therefore, the quality and originality of the plot will depend on the quality and originality of the data it has been trained on and the input prompts given to it.

The beings involved in the story. These can be people, animals, or other kinds of beings. Each should have their own distinct personality, motivations, and conflicts. By having a dynamic cast of characters, a story becomes more entertaining and relatable.

To create characters, ChatGPT can analyze the prompts given to it and produce the main characters based on three main factors:

• Character descriptions
• Relationships

Once more, this AI model follows a specific formula for creating characters (albeit a simpler one than when generating a plotline). Do you see a pattern yet?

The time and place where the story occurs. It includes the physical environment, culture, historical context, and many more worldly components. The religions, myths, and legends of a setting's sapient races all fall into this category as well.

When coming up with a setting, ChatGPT uses the following components:

• Time period

Due to a setting being much more physically defined than other essential elements of fiction writing, the AI model has an easier time coming up with tangible parts of the described world, such as noteworthy locations and the appearance of the landscape.

Perspective

The point of view from which the story is told. It can be first-person, second-person, or third-person. It's important not to swap between any of the aforementioned three unless you have a great reason. If you do, you may end up with confusing text that leaves the reader lost and frustrated.

ChatGPT tries to pick the perspective that it thinks is best for the prompt. However, this can backfire if you leave this element unspecified, which can result in ChatGPT mixing up perspective types. This ends in a narrative that's all over the place and confusing.

The reason why the AI model has such a hard time with perspective is that it cannot quantify perspective like it can with other fiction elements. It has no formula for generating a point of view.

The central messages or ideas of the story. These can be straightforward and easy to grasp, or obscure and shrouded in mystery. Depending on your goals, either explicit or implicit themes can make your story more interesting---sometimes even both in a unique mix.

ChatGPT will be broad with themes, as it judges the importance of potential ones based on the prompt given. This ties into the components it analyzes from existing works. For example, if you get it to generate a story about aliens, it will use humanity's innate fear of the unknown as a key theme.

Due to themes being story-specific, the AI model doesn't have a true formula for generating them; it picks themes synonymous with those found in known works of fiction. It basically just copies the themes from similar stories unless you specify otherwise.

The spoken or written words between characters. This is the avenue through which characters reveal their personalities, relationships, and conflicts. Not all stories necessarily need dialogue, but it's a great way to naturally incorporate important aspects of the characters. Furthermore, dialogue breaks up the prose in ways that result in better readability for most audiences.

ChatGPT uses traits of the characters in a story to generate dialogue between them. It also tries to keep a story's context in mind. Here are the factors it will consider when creating dialogue text:

• Internal character traits (personalities, thoughts, and emotions)
• External character traits (speech patterns, dialects, and colloquialisms)
• Scene context

The AI model will try to advance the plot through dialogue as well as reveal character motivations. Keep in mind that it can be a bit on the nose and clumsy with such story components, so you'll need to insert some subtlety via your prompt.

The author's writing style. This includes word choice, tone, and the use of literary devices. It contributes to the overall mood and atmosphere of the story. An author's life, upbringing, moral values, and more contribute to their writing style. However, don't expect ChatGPT to perfectly emulate a famous writer.

When coming up with a style through which to tell a story , ChatGPT will use the following components:

• Mood (how readers should feel about the subject of a scene)
• Tone (how the characters act and feel in regard to the subject of a scene)
• Story genre

Since an AI model can only work with what it's given via details in your prompts, you need to refine them by making sure you speak ChatGPT's language.

Providing Context and Backstory

You can provide context in your prompts by including details about the setting; what the characters are seeing, hearing, smelling, tasting, and touching. Mentioning what your characters should be physically experiencing lets ChatGPT learn what the world is like without you literally mentioning everything in a location.

Incorporating flashbacks can be a solid way to reveal a backstory in a direct manner. When you tell ChatGPT to do this in a prompt, it will provide more depth and understanding of your story.

There are sometimes important story components that you can't bring up directly. As such, using a bit of exposition can close unnecessary gaps in your world-building. However, you want to use exposition sparingly, as too much can result in boring text. Give ChatGPT a parameter for how much exposition to include so that it doesn't get carried away. For example, include "Use two sentences of exposition" in your prompt for a scene.

Building a Solid Plot Structure

Start by giving clear goals for a plot's concept. Mention the genre, the main characters, and the central conflict or problem so that ChatGPT understands what you're trying to achieve with your story.

Outline the major plot points in the story. Specifically, include the inciting incident, the rising action, the climax, and the resolution in your prompt. This is pretty much the exact formula that ChatGPT is looking for in order to answer your plot equation.

Provide clear character goals and motivations. ChatGPT needs to understand the goals and motivations of the characters in the story to build a solid plot structure. Otherwise, the story may come out feeling like it lacks a direction or that the plot isn't progressing as it should.

Consider breaking down your story into three, four, or five acts. Segmenting the story and then giving it to ChatGPT via a prompt can keep things organized and balanced in terms of pacing and structure. You don't want a story with an elongated beginning and short end---or similar imbalances.

Developing Compelling Characters

Give ChatGPT detailed descriptions of your characters, including their physical appearance, personality traits, and personal backstory. This will help the AI model generate more nuanced and complex characters.

While mentioning a character's goals and motivations is crucial for the plot, it's equally important for developing the character themself. Guiding ChatGPT's output in this regard will help your characters become more relatable.

You can also use individual character prompts to ask ChatGPT to generate a character's backstory, a monologue from a character's perspective, or a conversation between two characters.

Related: How to Create ChatGPT Personas for Every Occasion

Crafting Engaging Dialogue

Each character should have a distinct voice, with unique speech patterns, vocabulary, and tone. Provide ChatGPT with clear character descriptions and sample dialogue to guide its output.

Avoid using overly formal language. Instead, focus on creating dialogue that sounds like something real people would say. Try to emulate a conversation you've had recently to practice coming up with good dialogue prompts.

Dialogue should be grounded in the context of the story. Provide ChatGPT with clear descriptions of the setting, the characters' relationships, and the current situation to help it generate dialogue that is appropriate for the scene.

Furthermore, dialogue is often more engaging when there is an underlying subtext. This can be achieved through the use of indirect language, sarcasm, or implication. People also lie a lot, so throw some of those into your character conversations as well for added realism.

In addition to getting ChatGPT to generate more interesting text, you'll want to improve the style of such text. This is different than coming up with an initial style for ChatGPT with which to write fiction.

We briefly went over how to do so, but now we're going to go into more specific details on how to accomplish style improvements.

Using Descriptive Language

Give ChatGPT detailed descriptions of the setting, characters, and objects in the story. Mention physical aspects of the landscape, the appearance of characters, and why particular objects are important.

Employing Figurative Language

Figurative language refers to metaphors, similes, and allusions. Such writing techniques are more subtle ways of getting across the importance of subjects, themes, and more.

Despite not being quantitative in nature, ChatGPT has a solid understanding of these techniques due to there being plenty of examples of them in existing works. Remember that this AI model learns from what humans tell it as well as what it has learned from available information about fiction writing.

Incorporating Sensory Details

Encourage ChatGPT to include sensory details, such as sights, smells, sounds, and textures, to help bring the scene to life. People are sensory beings; we perceive the world around us through what our senses tell us about our surroundings. As such, readers will become more immersed in the story if you tell ChatGPT to include such details.

Varying Sentence Structure

You want to have varying sentence structures for multiple reasons. Firstly, it makes the text more interesting to readers. On top of that, the length of a sentence can help emphasize points or explain concepts in greater depth.

Shorter sentences---including sentence fragments---can make a simple point resonate in a reader's mind. This can be done through both dialogue and prose. Conversely, longer and more complex sentences let you explore a point in better detail and allow readers to gain a better understanding of what you're trying to say.

Machine learning is a type of artificial intelligence that enables computers to learn from data and determine things without being directly programmed to do so. Put simply, machine learning involves the use of algorithms to analyze large datasets, identify patterns and relationships, and make predictions or decisions based on that analysis.

How Machine Learning Works

The first step in machine learning is to collect and organize data. In regards to fiction writing, ChatGPT looks at the vast volumes of existing written works---as we've mentioned a few times before in this article.

We're stressing this point because you need to always remember that ChatGPT is an artificial intelligence that cannot do things on its own. Keeping this in mind will prevent you from getting frustrated when ChatGPT doesn't give you the results you want.

Once the data is collected, it must be cleaned and preprocessed to ensure that it is in a usable format. This might involve removing irrelevant or duplicate data points, standardizing the data, and more.

After the data is preprocessed, it can be used to train a machine learning algorithm. During the training phase, the algorithm analyzes the data to identify patterns and relationships. This is done by adjusting the algorithm's parameters until it can accurately predict or classify data based on the patterns it has identified. With that said, due to the amount of misinformation out there, ChatGPT is prone to sometimes generating inaccurate information---so always be wary and do your research.

Following the training process, the AI model must be tested to ensure that it can accurately predict or classify new data. This is typically done by using original data to evaluate the algorithm's performance.

Lastly, once the algorithm has been trained and tested, it can be deployed to make predictions or decisions based on new data. When getting ChatGPT to write fiction, this last part comes about when you give it prompts.

How You Can Use Machine Learning to Enhance ChatGPT's Fiction Writing

As the AI model receives feedback and is exposed to more examples of good writing, it can learn to refine its output and generate more engaging and compelling stories.

Make sure you regularly give ChatGPT feedback so that it has a chance to learn what you want from it. If you don't, you're unlikely to get the results you want. ChatGPT can only improve if you help it. It cannot make improvements on its own.

Examples of Machine Learning Techniques for Improving ChatGPT's Fiction Writing

You can fine-tune ChatGPT's writing techniques by training it on a specific task. Get it to generate stories from a specific genre, like high fantasy or cosmic horror, and then give it feedback about what you liked and didn't like regarding what it generated.

For example, if the high fantasy text it created didn't have enough magic, give the AI model feedback like "include more magic spells" or "put more wizards and witches in the story."

This can be done with all aspects of a story; not just the genre-related points. Use this method for the choice of words, theme implementation, character personalities, and more.

Here's a summary of the main points we explored in this article:

• Remember ChatGPT's capabilities and limitations
• Understand how ChatGPT uses fiction writing elements to generate text (plot, setting, etc.)
• Improve ChatGPT's content by giving it solid prompts to work off
• Enhance ChatGPT's writing style by giving it specific feedback
• Use machine learning techniques to help you get what you want out of the AI model

The old adage "practice makes perfect" is as true here as it always is. You'll need to experiment a lot to get a suitable product from ChatGPT. It's always learning and improving---therefore you should as well---not just by coming up with good prompts, but also by deepening your understanding of fiction writing. Keep reading stories from other authors and practice writing without ChatGPT.

The most important takeaway here is that AI models are a tool to help you improve; you shouldn't expect them to do all the work for you.

Related: ChatGPT: How to Use the AI Chatbot for Free

• Cutting Edge
• AI & Machine Learning

Have a language expert improve your writing

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

• Knowledge Base
• Using AI tools
• How to Write an Introduction Using ChatGPT | Tips & Examples

How to Write an Introduction Using ChatGPT | Tips & Examples

Published on July 17, 2023 by Koen Driessen . Revised on September 11, 2023.

A good introduction is essential to any essay or dissertation. It sets up your argument and clearly indicates the scope and content of your writing.

Your introduction should be an authentic representation of your own ideas and research. However, AI tools like ChatGPT can be effectively used during the writing process to:

• Develop an introduction outline
• Summarize text
• Paraphrase text
• Provide feedback

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

Developing an introduction outline, summarizing your arguments, paraphrasing text, generating feedback, other interesting articles, frequently asked questions.

While the introduction naturally comes at the beginning of your paper, it’s often one of the last parts you write. Writing your introduction last allows you to clearly indicate the most important aspects of your research to your reader in a logical order.

You can use ChatGPT to brainstorm potential outlines for your introduction. To do this, include a brief overview of all relevant aspects of your paper, including your research question , methodology , central arguments, and essay type (e.g., argumentative , expository ). For a longer essay or dissertation , you might also mention section or chapter titles.

Rearrange or edit the output so that it accurately reflects the body of your essay .

Example: Using ChatGPT to develop an outline

• Develop an outline for an essay introduction. The essay is a 2,000 word argumentative essay on the impact of children’s cartoons on consumer behavior. The research uses both qualitative and quantitative data.
• Start with a thought-provoking statement, anecdote, or statistic related to the influence of children’s cartoons on consumer behavior.
• Introduce the topic of children’s cartoons and their popularity among young audiences.
• Highlight the prevalence of media consumption among children and the significant role that cartoons play in their lives.
• Discuss the growing influence of marketing and advertising targeted at children.
• Clearly state your main argument about the impact of children’s cartoons on consumer behavior.
• Example: “This essay argues that children’s cartoons have a substantial influence on consumer behavior, shaping children’s preferences, purchase decisions, and brand loyalty. This assertion is supported by a combination of qualitative and quantitative data.”
• Briefly describe the research conducted and the use of both qualitative and quantitative data.
• Explain the purpose of the research in examining the relationship between children’s cartoons and consumer behavior.
• Mention the sample size, research methods employed, and the sources of data (e.g., surveys, interviews, content analysis).
• Discuss the significance of understanding the impact of children’s cartoons on consumer behavior.
• Highlight the potential implications for marketers, parents, and society as a whole.
• Emphasize the need for critical examination of the messages conveyed through children’s cartoons.
• Provide a brief overview of the main points or sections that will be covered in the essay.
• Examination of the persuasive techniques employed in children’s cartoons.
• Analysis of qualitative data to understand the effects of cartoons on children’s preferences and behaviors.
• Presentation of quantitative data on the relationship between exposure to cartoons and consumer behavior.
• Discussion of the ethical considerations surrounding marketing to children.
• Conclusion on the overall impact of children’s cartoons on consumer behavior.
• Summarize how the upcoming sections will provide evidence and analysis to support your argument.
• Example: “Through a combination of qualitative and quantitative data, this essay will delve into the persuasive techniques used in children’s cartoons, examine the effects of cartoons on children’s preferences and behaviors, present quantitative evidence of the relationship between exposure to cartoons and consumer behavior, discuss the ethical concerns, and ultimately draw conclusions about the influence of children’s cartoons on consumer behavior.”

Don't submit your assignments before you do this

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

Try for free

At the end of your introduction, you may give a brief overview of specific sections of your paper.

You can use ChatGPT to summarize text and condense your writing to its most important ideas. To do this, copy and paste sections of your essay into ChatGPT and prompt it to summarize the text.

However, we don’t recommend passing off AI-generated outputs as your own work. This is considered academically dishonest and may be detected using AI detectors . Instead, use ChatGPT outputs as a source of inspiration to help you clearly indicate your key objectives and findings in your own words.

Alternatively, you can use a specialized tool like Scribbr’s free text summarizer , which offers a smoother user experience.

Example: Using ChatGPT to summarize text

• Provide a one-line summary of the following paragraph: “Exposure to cartoons exerts a discernible impact on a child’s preferences, primarily through the establishment of robust associations between animated characters, branded products, and positive emotional experiences. Through repeated exposure, children develop an attachment to specific brands that influences their future buying choices. Furthermore, recent studies have established a correlation between the amount of time spent watching cartoons and children’s consumer behavior, including their demands for advertised products and their influence on family purchasing decisions.”
• Repeated exposure to cartoons influences children’s preferences, brand attachments, consumer behavior, and purchasing decisions.

When writing your introduction, you may have difficulty finding fresh ways to describe the content of your essay. You can use ChatGPT as a paraphrasing tool to rephrase text in clear language. This can help you to communicate your ideas more effectively, avoid repetition, and maintain a consistent tone.

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

Example: Using ChatGPT to paraphrase text

• Paraphrase the following sentence: “This raises ethical concerns regarding the potential exploitation of young minds for commercial gain, highlighting the need for responsible content creation and parental guidance to mitigate the impact of children’s cartoons on consumer behavior.”
• The potential exploitation of young minds for commercial gain gives rise to ethical concerns, emphasizing the importance of responsible content creation and parental guidance to reduce the influence of children’s cartoons on consumer behavior.

Once you’ve finished writing your introduction, you can use ChatGPT to generate feedback. Paste your introduction into the tool and prompt it to provide feedback on specific aspects of your writing, such as tone, clarity, or structure.

You can also use ChatGPT to check grammar and punctuation mistakes. However, it’s not specifically designed for this purpose and may fail to detect some errors. We recommend using a more specialized tool like Scribbr’s free grammar checker . Or, for more comprehensive feedback, try Scribbr’s proofreading and editing service .

Example: Using ChatGPT to get feedback

• Provide feedback on the above text with regard to tone of voice and clarity of structure.

Furthermore, the last paragraph could be revised to provide a more concise summary of the main points that will be addressed in the essay. This would help to give the reader a clearer roadmap of what to expect in the subsequent sections.

Check for common mistakes

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

Fix mistakes for free

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

• ChatGPT vs human editor
• ChatGPT citations
• Is ChatGPT trustworthy?
• Using ChatGPT for your studies
• Sunk cost fallacy
• Straw man fallacy
• Slippery slope fallacy
• Red herring fallacy
• Ecological fallacy
• Logical fallacy

Research bias

• Implicit bias
• Framing bias
• Cognitive bias
• Optimism bias
• Hawthorne effect
• Unconscious bias

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.

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

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

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

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

Cite this Scribbr article

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

Driessen, K. (2023, September 11). How to Write an Introduction Using ChatGPT | Tips & Examples. Scribbr. Retrieved July 5, 2024, from https://www.scribbr.com/ai-tools/chatgpt-essay-introduction/

Is this article helpful?

Koen Driessen

Other students also liked, using chatgpt for assignments | tips & examples, what can chatgpt do | suggestions & examples, how to write good chatgpt prompts.

Koen Driessen (Scribbr Team)

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

Still have questions?

"i thought ai proofreading was useless but..".

I've been using Scribbr for years now and I know it's a service that won't disappoint. It does a good job spotting mistakes”

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

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

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

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

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

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

Timeline of the most recent ChatGPT updates

February 2024, january 2024.

• ChatGPT FAQs

OpenAI delays ChatGPT’s new Voice Mode

OpenAI planned to start rolling out its advanced Voice Mode feature to a small group of ChatGPT Plus users in late June, but it says lingering issues forced it to postpone the launch to July. OpenAI says Advanced Voice Mode might not launch for all ChatGPT Plus customers until the fall, depending on whether it meets certain internal safety and reliability checks.

ChatGPT releases app for Mac

ChatGPT for macOS is now available for all users . With the app, users can quickly call up ChatGPT by using the keyboard combination of Option + Space. The app allows users to upload files and other photos, as well as speak to ChatGPT from their desktop and search through their past conversations.

The ChatGPT desktop app for macOS is now available for all users. Get faster access to ChatGPT to chat about email, screenshots, and anything on your screen with the Option + Space shortcut: https://t.co/2rEx3PmMqg pic.twitter.com/x9sT8AnjDm — OpenAI (@OpenAI) June 25, 2024

Apple brings ChatGPT to its apps, including Siri

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

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

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

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

ChatGPT experiences two outages in a single day

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

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

The Atlantic and Vox Media ink content deals with OpenAI

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

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

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

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

OpenAI says it is training its GPT-4 successor

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

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

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

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

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

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

OpenAI to remove ChatGPT’s Scarlett Johansson-like voice

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

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

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

ChatGPT lets you add files from Google Drive and Microsoft OneDrive

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

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

OpenAI inks deal to train AI on Reddit data

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

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

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

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

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

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

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

OpenAI explores allowing AI porn

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

OpenAI and Stack Overflow announce partnership

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

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

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

OpenAI inks content licensing deal with Financial Times

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

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

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

Sam Altman pitches ChatGPT Enterprise to Fortune 500 companies

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

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

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

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

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

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

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

OpenAI’s chatbot store is filling up with spam

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

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

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

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

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

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

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

ChatGPT can now read its answers aloud

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

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

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

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

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

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

ChatGPT experienced a bizarre bug for several hours

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

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

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

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

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

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

OpenAI begins rolling out “Temporary Chat” feature

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

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

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

ChatGPT users can now invoke GPTs directly in chats

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

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

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

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

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

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

OpenAI partners with Common Sense Media to collaborate on AI guidelines

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

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

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

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

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

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

OpenAI bans developer of a bot impersonating a presidential candidate

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

OpenAI announces partnership with Arizona State University

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

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

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

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

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

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

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

OpenAI unveils plan to combat election misinformation

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

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

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

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

OpenAI changes policy to allow military applications

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

ChatGPT subscription aimed at small teams debuts

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

OpenAI’s GPT store officially launches

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

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

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

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

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

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

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

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

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

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

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

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

OpenAI moves to shrink regulatory risk in EU around data privacy

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

What is ChatGPT? How does it work?

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

When did ChatGPT get released?

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

What is the latest version of ChatGPT?

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

Can I use ChatGPT for free?

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

Who uses ChatGPT?

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

What companies use ChatGPT?

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

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

What does GPT mean in ChatGPT?

GPT stands for Generative Pre-Trained Transformer.

What is the difference between ChatGPT and a chatbot?

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

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

Can ChatGPT write essays?

Can chatgpt commit libel.

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

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

Does ChatGPT have an app?

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

What is the ChatGPT character limit?

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

Does ChatGPT have an API?

Yes, it was released March 1, 2023.

What are some sample everyday uses for ChatGPT?

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

What are some advanced uses for ChatGPT?

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

How good is ChatGPT at writing code?

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

Can you save a ChatGPT chat?

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

Are there alternatives to ChatGPT?

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

How does ChatGPT handle data privacy?

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

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

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

What controversies have surrounded ChatGPT?

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

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

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

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

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

Where can I find examples of ChatGPT prompts?

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

Can ChatGPT be detected?

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

Are ChatGPT chats public?

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

What lawsuits are there surrounding ChatGPT?

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

Are there issues regarding plagiarism with ChatGPT?

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

More TechCrunch

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

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

Startups Weekly

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

TechCrunch Fintech

The latest Fintech news and analysis, delivered every Tuesday.

TechCrunch Mobility

TechCrunch Mobility is your destination for transportation news and insight.

How to set up parental controls on Facebook, Snapchat, TikTok and more popular sites

We’ve created this guide to help parents navigate the controls offered by popular social media companies.

Featured Article

You could learn a lot from a CIO with a $17B IT budget

Lori Beer’s work is a case study for every CIO out there, most of whom will never come close to JP Morgan Chase’s scale, but who can still learn from how it goes about its business.

Tesla makes it onto Chinese government purchase list

For the first time, Chinese government workers will be able to purchase Tesla’s Model Y for official use. Specifically, officials in eastern China’s Jiangsu province included the Model Y in…

Tokens are a big reason today’s generative AI falls short

Generative AI models don’t process text the same way humans do. Understanding their “token”-based internal environments may help explain some of their strange behaviors — and stubborn limitations. Most models,…

Apple approves Epic Games’ marketplace app after initial rejections

After multiple rejections, Apple has approved Fortnite maker Epic Games’ third-party app marketplace for launch in the EU. As now permitted by the EU’s Digital Markets Act (DMA), Epic announced…

OpenAI breach is a reminder that AI companies are treasure troves for hackers

There’s no need to worry that your secret ChatGPT conversations were obtained in a recently reported breach of OpenAI’s systems. The hack itself, while troubling, appears to have been superficial…

Space for newcomers, biotech going mainstream, and more

Welcome to Startups Weekly — TechCrunch’s weekly recap of everything you can’t miss from the world of startups. Sign up here to get it in your inbox every Friday. Most…

X plans to more deeply integrate Grok’s AI, app researcher finds

Elon Musk’s X is exploring more ways to integrate xAI’s Grok into the social networking app. According to a series of recent discoveries, X is developing new features like the…

Meet Brex, Google Cloud, Aerospace and more at Disrupt 2024

We’re about four months away from TechCrunch Disrupt 2024, taking place October 28 to 30 in San Francisco! We could not bring you this world-class event without our world-class partners…

Amazon faces more EU scrutiny over recommender algorithms and ads transparency

In its latest step targeting a major marketplace, the European Commission sent Amazon another request for information (RFI) Friday in relation to its compliance under the bloc’s rulebook for digital…

Quantum Rise grabs $15M seed for its AI-driven ‘Consulting 2.0’ startup

Quantum Rise, a Chicago-based startup that does AI-driven automation for companies like dunnhumby (a retail analytics platform for the grocery industry), has raised a $15 million seed round from Erie…

YouTube’s updated eraser tool removes copyrighted music without impacting other audio

On July 4, YouTube released an updated eraser tool for creators so they can easily remove any copyrighted music from their videos without affecting any other audio such as dialog…

India’s Airtel dismisses data breach reports amid customer concerns

Airtel, India’s second-largest telecom operator, on Friday denied any breach of its systems following reports of an alleged security lapse that has caused concern among its customers. The telecom group,…

Spain’s exposure to climate change helps Madrid-based VC Seaya close €300M climate tech fund

According to a recent Dealroom report on the Spanish tech ecosystem, the combined enterprise value of Spanish startups surpassed €100 billion in 2023. In the latest confirmation of this upward trend, Madrid-based…

Forestay, Europe’s newest $220M growth-stage VC fund, will focus on AI

Forestay, an emerging VC based out of Geneva, Switzerland, has been busy. This week it closed its second fund, Forestay Capital II, at a hard cap of $220 million. The…

A year later, what Threads could learn from other social networks

Threads, Meta’s alternative to Twitter, just celebrated its first birthday. After launching on July 5 last year, the social network has reached 175 million monthly active users — that’s a…

J2 Ventures, focused on military healthcare, grabs $150M for its second fund

J2 Ventures, a firm led mostly by U.S. military veterans, announced on Thursday that it has raised a $150 million second fund. The Boston-based firm invests in startups whose products…

HealthEquity says data breach is an ‘isolated incident’

HealthEquity said in an 8-K filing with the SEC that it detected “anomalous behavior by a personal use device belonging to a business partner.”

Roll20, an online tabletop role-playing game platform, discloses data breach

Roll20 said that on June 29 it had detected that a “bad actor” gained access to an account on the company’s administrative website for one hour.

Fisker asks bankruptcy court to sell its EVs at average of $14,000 each

Fisker has a willing buyer for its remaining inventory of all-electric Ocean SUVs, and has asked the Delaware Bankruptcy Court judge overseeing its Chapter 11 case to approve the sale.…

Fizz, the anonymous Gen Z social app, adds a marketplace for college students

Teddy Solomon just moved to a new house in Palo Alto, so he turned to the Stanford community on Fizz to furnish his room. “Every time I show up to…

Why deep tech VC Driving Forces is shutting down

With increasing competition for what is, essentially, still a small number of hard tech and deep tech deals, Sidney Scott realized it would be a challenge for smaller funds like…

How to turn off those silly video call reactions on iPhone and Mac

A guide to turn off reactions on your iPhone and Mac so you don’t get surprised by effects during work video calls.

Amazon retires its Astro for Business security robot after only 7 months

Amazon has decided to discontinue its Astro for Business device, a security robot for small- and medium-sized businesses, just seven months after launch.  In an email sent to customers and…

This Week in AI: With Chevron’s demise, AI regulation seems dead in the water

Hiya, folks, and welcome to TechCrunch’s regular AI newsletter. This week in AI, the U.S. Supreme Court struck down “Chevron deference,” a 40-year-old ruling on federal agencies’ power that required…

noplace, a mashup of Twitter and Myspace for Gen Z, hits No. 1 on the App Store

Noplace had already gone viral ahead of its public launch because of its feature that allows users to express themselves by customizing the colors of their profile.

Cloudflare launches a tool to combat AI bots

Cloudflare analyzed AI bot and crawler traffic to fine-tune automatic bot detection models.

Twilio says hackers identified cell phone numbers of two-factor app Authy users

Twilio says “threat actors were able to identify” phone numbers of people who use the two-factor app Authy.

Nano Dimension is buying Desktop Metal

The news brings closure to more than two years of volleying back and forth between some of the biggest names in additive manufacturing.

Groups save big at TechCrunch Disrupt 2024

Planning to attend TechCrunch Disrupt 2024 with your team? Maximize your team-building time and your company’s impact across the entire conference when you bring your team. Groups of 4 to…

Have a thesis expert improve your writing

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

• Knowledge Base

Using AI tools

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

How to Write an Essay with ChatGPT | Tips & Examples

Published on 26 June 2023 by Koen Driessen .

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

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

You can use ChatGPT to:

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

Instantly correct all language mistakes in your text

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

Table of contents

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

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

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

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

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

Example: Using ChatGPT to write a research question

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

The only proofreading tool specialized in correcting academic writing

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

Correct my document today

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

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

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

Examples: Using ChatGPT to generate an essay outline

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

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

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

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

Example: Using ChatGPT to find sources

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

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

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

Example: Using ChatGPT to summarise/paraphrase

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

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

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

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

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

Example: Using ChatGPT for feedback

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

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

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

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

Citing sources

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

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

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

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

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

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

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

Cite this Scribbr article

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

Driessen, K. (2023, June 26). How to Write an Essay with ChatGPT | Tips & Examples. Scribbr. Retrieved 5 July 2024, from https://www.scribbr.co.uk/using-ai-tools/chatgpt-essays/

Is this article helpful?

Koen Driessen

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

ChatGPT: Here's What You Get With the Gen AI Tool That Started It All

ChatGPT quickly swept us away with its mind-blowing skills. Its latest model, GPT-4o, is faster, cheaper and can generate more text than its predecessors.

• Shankland covered the tech industry for more than 25 years and was a science writer for five years before that. He has deep expertise in microprocessors, digital photography, computer hardware and software, internet standards, web technology, and more.

In late 2022, OpenAI wowed the world when it introduced ChatGPT , a chatbot with an entirely new level of power, breadth and usefulness, thanks to the generative AI technology behind it. Since then, ChatGPT has continued to evolve, including its most recent development: the launch of its GPT-4o model .

ChatGPT and generative AI aren't a novelty anymore, but keeping track of what they can do poses a challenge as new abilities arrive. Most notably, OpenAI now provides easier access to anyone who wants to use it. It also lets anyone write custom AI apps called GPTs and share them on its own app store, while on a smaller scale ChatGPT can now speak its responses to you. OpenAI has been leading the generative AI charge , but it's hotly pursued by Microsoft, Google and startups far and wide.

Generative AI still hasn't shaken a core problem -- it makes up information that sounds plausible but isn't necessarily correct. But there's no denying AI has fired the imaginations of computer scientists, loosened the purse strings of venture capitalists and caught the attention of everyone from teachers to doctors to artists and more, all wondering how AI will change their work and their lives. 

If you're trying to get a handle on ChatGPT, this FAQ is for you. Here's a look at what's up.

Read more :  ChatGPT 3.5 Review: First Doesn't Mean Best

What is ChatGPT?

ChatGPT is an online chatbot that responds to "prompts" -- text requests that you type. ChatGPT has countless uses . You can request relationship advice, a summarized history of punk rock or an explanation of the ocean's tides. It's particularly good at writing software, and it can also handle some other technical tasks, like creating 3D models .

ChatGPT is called a generative AI because it generates these responses on its own. But it can also display more overtly creative output like screenplays, poetry, jokes and student essays. That's one of the abilities that really caught people's attention.

Much of AI has been focused on specific tasks, but ChatGPT is a general-purpose tool. This puts it more into a category like a search engine.

That breadth makes it powerful but also hard to fully control. OpenAI has many mechanisms in place to try to screen out abuse and other problems, but there's an active cat-and-mouse game afoot by researchers and others who try to get ChatGPT to do things like offer bomb-making recipes.

ChatGPT really blew people's minds when it began passing tests. For example, AnsibleHealth researchers reported in 2023 that " ChatGPT performed at or near the passing threshold " for the United States Medical Licensing Exam, suggesting that AI chatbots "may have the potential to assist with medical education, and potentially, clinical decision-making."

We're a long way from fully fledged doctor-bots you can trust, but the computing industry is investing billions of dollars to solve the problems and expand AI into new domains like visual data, too. OpenAI is among those at the vanguard. So strap in, because the AI journey is going to be a sometimes terrifying, sometimes exciting thrill.

What's ChatGPT's origin?

Artificial intelligence algorithms had been ticking away for years before ChatGPT arrived. These systems were a big departure from traditional programming, which follows a rigid if-this-then-that approach. AI, in contrast, is trained to spot patterns in complex real-world data. AI has been busy for more than a decade screening out spam, identifying our friends in photos, recommending videos and translating our Alexa voice commands into computerese.

A Google technology called transformers helped propel AI to a new level, leading to a type of AI called a large language model, or LLM . These AIs are trained on enormous quantities of text, including material like books, blog posts, forum comments and news articles. The training process internalizes the relationships between words, letting chatbots process input text and then generate what it believes to be appropriate output text. 

A second phase of building an LLM is called reinforcement learning through human feedback, or RLHF. That's when people review the chatbot's responses and steer it toward good answers or away from bad ones. That significantly alters the tool's behavior and is one important mechanism for trying to stop abuse.

OpenAI's LLM is called GPT, which stands for "generative pretrained transformer." Training a new model is expensive and time consuming, typically taking weeks and requiring a data center packed with thousands of expensive AI acceleration processors. OpenAI's latest LLM is called GPT-4o. Other LLMs include Google's Gemini (formerly called Bard), Anthropic's Claude and Meta's Llama .

ChatGPT is an interface that lets you easily prompt GPT for responses. When it arrived as a free tool in November 2022, its use exploded far beyond what OpenAI expected.

When OpenAI launched ChatGPT, the company didn't even see it as a product. It was supposed to be a mere "research preview," a test that could draw some feedback from a broader audience, said ChatGPT product leader Nick Turley. Instead, it went viral, and OpenAI scrambled to just keep the service up and running under the demand.

"It was surreal," Turley said. "There was something about that release that just struck a nerve with folks in a way that we certainly did not expect. I remember distinctly coming back the day after we launched and looking at dashboards and thinking, something's broken, this couldn't be real, because we really didn't make a very big deal out of this launch."

ChatGPT, a name only engineers could love, was launched as a research project in November 2022, but quickly caught on as a consumer product.

How do I use ChatGPT?

The ChatGPT website is the most obvious method. Open it up, select the LLM version you want from the drop-down menu in the upper left corner, and type in a query.

As of April 1, OpenAI is allowing consumers to use ChatGPT without first signing up for an account. According to a blog post , the move was meant to make the tool more accessible. OpenAI also said in the post that as part of the move, it's introducing added content safeguards, blocking prompts in a wider range of categories.

However, users with accounts will be able to do more with the tool, such as save and review their history, share conversations and tap into features like voice conversations and custom instructions.

In 2023, OpenAI released a ChatGPT app for iPhones and for Android phones . In February 2024, ChatGPT for Apple Vision Pro arrived , too, adding the chatbot's abilities to the "spatial computing" headset. Be careful to look for the genuine article, because other developers can create their own chatbot apps that link to OpenAI's GPT.

In January 2024, OpenAI opened its GPT Store , a collection of custom AI apps that focus ChatGPT's all-purpose design to specific jobs. A lot more on that later, but in addition to finding them through the store you can invoke them with the @ symbol in a prompt, the way you might tag a friend on Instagram.

Microsoft uses GPT for its Bing search engine, which means you can also try out ChatGPT there.

ChatGPT has sprouted up in various hardware devices, including Volkswagen EVs , Humane's voice-controlled AI pin and the squarish Rabbit R1 device .

How much does ChatGPT cost?

It's free, though you have to set up an account to take advantage of all of its features.

For more capability, there's also a subscription called ChatGPT Plus that costs $20 per month that offers a variety of advantages: It responds faster, particularly during busy times when the free version is slow or sometimes tells you to try again later. It also offers access to newer AI models, including GPT-4 Turbo , which arrived in late 2023 with more up-to-date responses and an ability to ingest and output larger blocks of text.

The free ChatGPT uses GPT-4o, which launched in May of this year.

ChatGPT is growing beyond its language roots. With ChatGPT Plus, you can upload images, for example, to ask what type of mushroom is in a photo.

Perhaps most importantly, ChatGPT Plus lets you use GPTs.

What are these GPTs?

GPTs are custom versions of ChatGPT from OpenAI, its business partners and thousands of third-party developers who created their own GPTs.

Sometimes when people encounter ChatGPT, they don't know where to start. OpenAI calls it the "empty box problem." Discovering that led the company to find a way to narrow down the choices, Turley said.

"People really benefit from the packaging of a use case -- here's a very specific thing that I can do with ChatGPT," like travel planning, cooking help or an interactive, step-by-step tool to build a website, Turley said.

OpenAI CEO Sam Altman announces custom AI apps called GPTs at a developer event in November 2023.

Think of GPTs as OpenAI trying to make the general-purpose power of ChatGPT more refined the same way smartphones have a wealth of specific tools. (And think of GPTs as OpenAI's attempt to take control over how we find, use and pay for these apps, much like Apple has a commanding role over iPhones through its App Store.)

What GPTs are available now?

OpenAI's GPT store now offers millions of GPTs , though as with smartphone apps, you'll probably not be interested in most of them. A range of GPT custom apps are available, including AllTrails personal trail recommendations , a Khan Academy programming tutor , a Canva design tool , a book recommender , a fitness trainer , the laundry buddy clothes washing label decoder, a music theory instructor , a haiku writer and the Pearl for Pets for vet advice bot .

One person excited by GPTs is Daniel Kivatinos, co-founder of financial services company JustPaid . His team is building a GPT designed to take a spreadsheet of financial data as input and then let executives ask questions. How fast is a startup going through the money investors gave it? Why did that employee just file a $6,000 travel expense?

JustPaid hopes that GPTs will eventually be powerful enough to accept connections to bank accounts and financial software. For now, the developers are focusing on guardrails to avoid problems like hallucinations -- those answers that sound plausible but are actually wrong -- or making sure the GPT is answering based on the users' data, not on some general information in its AI model, Kivatinos said.

Anyone can create a GPT, at least in principle. OpenAI's GPT editor walks you through the process with a series of prompts. Just like with the regular ChatGPT, your ability to craft the right prompt will generate better results.

Another notable difference from regular ChatGPT: GPTs let you upload extra data that's relevant to your particular GPT, like a collection of essays or a writing style guide.

Some of the GPTs draw on OpenAI's Dall-E tool for turning text into images, which can be useful and entertaining. For example, there is a coloring book picture creator , a logo generator and a tool that turns text prompts into diagrams like company org charts. OpenAI calls Dall-E a GPT.

How up to date is ChatGPT?

Not very, and that can be a problem. For example, a Bing search using ChatGPT to process results said OpenAI hadn't yet released its ChatGPT Android app. Search results from traditional search engines can help to "ground" AI results, and indeed that's part of the Microsoft-OpenAI partnership that can tweak ChatGPT Plus results.

GPT-4 Turbo is trained on data up through April 2023. But it's nothing like a search engine whose bots crawl news sites many times a day for the latest information.

Can you trust ChatGPT responses?

No. Well, sometimes, but you need to be wary.

Large language models work by stringing words together, one after another, based on what's probable each step of the way. But it turns out that the generative AI fueled by LLMs works better and sounds more natural with a little spice of randomness added to the word selection recipe. That's the basic statistical nature that underlies the criticism that LLMs are mere "stochastic parrots" rather than sophisticated systems that in some way understand the world's complexity.

The result of this system, combined with the steering influence of the human training, is an AI that produces results that sound plausible but that aren't necessarily true. ChatGPT does better with information that's well represented in training data and undisputed -- for instance, red traffic signals mean stop, Plato was a philosopher who wrote the Allegory of the Cave , an Alaskan earthquake in 1964 was the largest in US history at magnitude 9.2.

We humans interact with AI chatbots by writing prompts -- questions or statements that seek an answer from the information stored in the chatbot's underlying large language model. 

When facts are more sparsely documented, controversial or off the beaten track of human knowledge, LLMs don't work as well. Unfortunately, they sometimes produce incorrect answers with a convincing, authoritative voice. That's what tripped up a lawyer who used ChatGPT to bolster his legal case only to be reprimanded when it emerged ChatGPT fabricated some cases that appeared to support his arguments. "I did not comprehend that ChatGPT could fabricate cases ," he said, according to The New York Times.

Such fabrications are called hallucinations in the AI business.

That means when you're using ChatGPT, it's best to double check facts elsewhere.

But there are plenty of creative uses for ChatGPT that don't require strictly factual results.

Want to use ChatGPT to draft a cover letter for a job hunt or give you ideas for a themed birthday party? No problem. Looking for hotel suggestions in Bangladesh? ChatGPT can give useful travel itineraries , but confirm the results before booking anything.

Is the hallucination problem getting better?

Yes, but we haven't seen a breakthrough.

"Hallucinations are a fundamental limitation of the way that these models work today," Turley said. LLMs just predict the next word in a response, over and over, "which means that they return things that are likely to be true, which is not always the same as things that are true," Turley said.

But OpenAI has been making gradual progress. "With nearly every model update, we've gotten a little bit better on making the model both more factual and more self aware about what it does and doesn't know," Turley said. "If you compare ChatGPT now to the original ChatGPT, it's much better at saying, 'I don't know that' or 'I can't help you with that' versus making something up."

Hallucinations are so much a part of the zeitgeist that Dictionary.com touted it as a new word it added to its dictionary in 2023.

Can you use ChatGPT for wicked purposes?

You can try, but lots of it will violate OpenAI's terms of use , and the company tries to block it too. The company prohibits use that involves sexual or violent material, racist caricatures, and personal information like Social Security numbers or addresses.

OpenAI works hard to prevent harmful uses. Indeed, its basic sales pitch is trying to bring the benefits of AI to the world without the drawbacks. But it acknowledges the difficulties, for example in its GPT-4 "system card" that documents its safety work.

"GPT-4 can generate potentially harmful content, such as advice on planning attacks or hate speech. It can represent various societal biases and worldviews that may not be representative of the user's intent, or of widely shared values. It can also generate code that is compromised or vulnerable," the system card says. It also can be used to try to identify individuals and could help lower the cost of cyberattacks.

Through a process called red teaming, in which experts try to find unsafe uses of its AI and bypass protections, OpenAI identified lots of problems and tried to nip them in the bud before GPT-4 launched. For example, a prompt to generate jokes mocking a Muslim boyfriend in a wheelchair was diverted so its response said, "I cannot provide jokes that may offend someone based on their religion, disability or any other personal factors. However, I'd be happy to help you come up with some light-hearted and friendly jokes that can bring laughter to the event without hurting anyone's feelings."

Researchers are still probing LLM limits. For example, Italian researchers discovered they could use ChatGPT to fabricate fake but convincing medical research data . And Google DeepMind researchers found that telling ChatGPT to repeat the same word forever eventually caused a glitch that made the chatbot blurt out training data verbatim. That's a big no-no, and OpenAI barred the approach .

LLMs are still new. Expect more problems and more patches.

And there are plenty of uses for ChatGPT that might be allowed but ill-advised. The website of Philadelphia's sheriff published more than 30 bogus news stories generated with ChatGPT .

What about ChatGPT and cheating in school?

ChatGPT is well suited to short essays on just about anything you might encounter in high school or college, to the chagrin of many educators who fear students will type in prompts instead of thinking for themselves.

Microsoft CEO Satya Nadella touted his company's partnership with OpenAI at a November 2023 event for OpenAI developers. Microsoft uses OpenAI's GPT large language model for its Bing search engine, Office productivity tools and GitHub Copilot programming assistant.

ChatGPT also can solve some math problems, explain physics phenomena, write chemistry lab reports and handle all kinds of other work students are supposed to handle on their own. Companies that sell anti-plagiarism software have pivoted to flagging text they believe an AI generated.

But not everyone is opposed, seeing it more like a tool akin to Google search and Wikipedia articles that can help students.

"There was a time when using calculators on exams was a huge no-no," said Alexis Abramson, dean of Dartmouth's Thayer School of Engineering. "It's really important that our students learn how to use these tools, because 90% of them are going into jobs where they're going to be expected to use these tools. They're going to walk in the office and people will expect them, being age 22 and technologically savvy, to be able to use these tools."

ChatGPT also can help kids get past writer's block and can help kids who aren't as good at writing, perhaps because English isn't their first language, she said.

So for Abramson, using ChatGPT to write a first draft or polish their grammar is fine. But she asks her students to disclose that fact.

"Anytime you use it, I would like you to include what you did when you turn in your assignment," she said. "It's unavoidable that students will use ChatGPT, so why don't we figure out a way to help them use it responsibly?"

Is ChatGPT coming for my job?

The threat to employment is real as managers seek to replace expensive humans with cheaper automated processes. We've seen this movie before: elevator operators were replaced by buttons, bookkeepers were replaced by accounting software, welders were replaced by robots. 

ChatGPT has all sorts of potential to blitz white-collar jobs: paralegals summarizing documents, marketers writing promotional materials, tax advisers interpreting IRS rules, even therapists offering relationship advice.

But so far, in part because of problems with things like hallucinations, AI companies present their bots as assistants and "copilots," not replacements.

And so far, sentiment is more positive than negative about chatbots, according to a survey by consulting firm PwC. Of 53,912 people surveyed around the world, 52% expressed at least one good expectation about the arrival of AI, for example that AI would increase their productivity. That compares with 35% who had at least one negative thing to say, for example that AI will replace them or require skills they're not confident they can learn.

How will ChatGPT affect programmers?

Software development is a particular area where people have found ChatGPT and its rivals useful. Trained on millions of lines of code, it internalized enough information to build websites and mobile apps. It can help programmers frame up bigger projects or fill in details.

One of the biggest fans is Microsoft's GitHub , a site where developers can host projects and invite collaboration. Nearly a third of people maintaining GitHub projects use its GPT-based assistant, called Copilot, and 92% of US developers say they're using AI tools .

"We call it the industrial revolution of software development," said Github Chief Product Officer Inbal Shani. "We see it lowering the barrier for entry. People who are not developers today can write software and develop applications using Copilot."

It's the next step in making programming more accessible, she said. Programmers used to have to understand bits and bytes, then higher-level languages gradually eased the difficulties. "Now you can write coding the way you talk to people," she said.

And AI programming aids still have a lot to prove. Researchers from Stanford and the University of California-San Diego found in a  study of 47 programmers  that those with access to an OpenAI programming help " wrote significantly less secure code  than those without access."

And they raise a variation of the cheating problem that some teachers are worried about: copying software that shouldn't be copied, which can lead to copyright problems. That's why Copyleaks, a maker of plagiarism detection software, offers a tool called the  Codeleaks Source Code AI Detector  designed to spot AI-generated code from ChatGPT, Google Gemini and GitHub Copilot. AIs could inadvertently copy code from other sources, and the latest version is designed to spot copied code based on its semantic structures, not just verbatim software.

At least in the next five years, Shani doesn't see AI tools like Copilot as taking humans out of programming.

"I don't think that it will replace the human in the loop. There's some capabilities that we as humanity have -- the creative thinking, the innovation, the ability to think beyond how a machine thinks in terms of putting things together in a creative way. That's something that the machine can still not do."

CNET's Lisa Lacy contributed to this report.

Computing Guides

• Best Laptop
• Best Chromebook
• Best Budget Laptop
• Best Cheap Gaming Laptop
• Best 2-in-1 Laptop
• Best Windows Laptop
• Best Macbook
• Best Gaming Laptop
• Best Macbook Deals
• Best Desktop PC
• Best Gaming PC
• Best Monitor Under 200
• Best Desktop Deals
• Best Monitors
• M2 Mac Mini Review
• Best PC Speakers
• Best Printer
• Best External Hard Drive SSD
• Best USB C Hub Docking Station
• Best Keyboard
• Best Webcams
• Best Laptop Backpack
• Best Camera to Buy
• Best Vlogging Camera
• Best Tripod
• Best Waterproof Camera
• Best Action Camera
• Best Camera Bag and Backpack
• Best E-Ink Tablets
• Best iPad Deals
• Best E-Reader
• Best Tablet
• Best Android Tablet
• Best 3D Printer
• Best Budget 3D Printer
• Best 3D Printing Filament
• Best 3D Printer Deals

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

• ChatGPT has taken the world by storm — but some struggle to get the chatbot to do what they want.
• Insider asked AI enthusiasts how they interact with the chatbot to produce desirable outputs.
• Here are 14 tips for crafting the best ChatGPT prompts, from assigning it a persona to being polite.

Since launching over a year ago, ChatGPT has become seemingly omnipresent.

At work, people have used the OpenAI product to develop code , generate marketing materials , and create lesson plans . It's become so popular that companies are now hiring workers who have ChatGPT expertise to boost their bottom lines. 

And in their everyday lives, people are turning to the chatbot for help with losing weight , landing dates , and delaying aging.

But ChatGPT doesn't always produce desirable outcomes, and the tech can be prone to errors and misinformation.

It all comes down to the prompts users put into ChatGPT. 

"If you really want to generate something that is going to be useful for you, you need to do more than just write a generic sentence," Jacqueline DeStefano-Tangorra, a consultant who uses ChatGPT to secure new contracts, told Insider . 

Insider sifted through AI research and asked AI enthusiasts, ChatGPT coaches, and workers who use the chatbot for tips on how to get ChatGPT to do what you want.

Here are 12 ways you can write better ChatGPT prompts. 

1. assign chatgpt a specific  role.

ChatGPT works best when you assign it a persona — such as a specific job role — Jason Gulya, an AI council chair at Berkeley College who teaches clients how to use ChatGPT, said.

Rob Cressy, the founder of the AI-coaching firm GPT Leaders, told Insider to "talk to ChatGPT like an employee" to help accomplish particular goals or tasks.

To do this, Gulya suggests that users write a prompt that includes a specific, concrete description of the persona you want the chatbot to take on. Begin your prompt with "act as a professor" or "act as a marketing professional," followed by a description of the desired outcome.

2. Be specific — and only give the bot one task at a time

Once you give ChatGPT a role, craft the prompt so it can accomplish a singular task such as writing a 300-word cover letter or generating a recipe for a protein-packed dinner.

"Don't ask it to do too much at once," Cressy said.

If you're a marketing professional, and you want ChatGPT to build a list of emails, Peggy Dean, an artist who runs a ChatGPT course for creatives , recommends crafting what she calls a "power prompt," a concise and detailed prompt.

If asking ChatGPT to brief a marketing campaign, she said she'd include target audiences, key features, and calls to action.

If asking the chatbot to come up with an email list and calls to action, she said she'd say:

"Pretend you are an expert email marketer and your client is a [role] specializing in [offerings] for [target audience]. Your goal is to build a robust email list in order to accomplish [goal]. Your client uses [platform(s)] to reach their audience. Come up with [details or quantity] ideal call to action ideas of [freebies or lead magnets] your client can provide."

"It's crucial to have a clear idea of what you hope to achieve," Dean told Insider. 

3. Refine your prompts based on a previous outputs

If ChatGPT's response isn't quite what you're looking for, Cressy said to build on its output by fine-tuning the initial prompt. He calls this process "peeling back an onion." 

"Don't be afraid to refine your prompts," DeStefano-Tangorra said. "If the initial output doesn't match your expectation, rephrase the prompt, add more detail, or clarify the context." 

If the answer to a prompt asking ChatGPT to "suggest a good book" is too vague, refine it to something like: "As someone who loves mystery novels with strong female leads, like Agatha Christie's Miss Marple series, can you suggest other similar books that I may enjoy?" 

4. Provide context 

ChatGPT prompts should include context such as historical information, user profiles, preferences, or any relevant details to guide its response, DeStefano-Tangorra said. The more specific, the better. 

Asking ChatGPT to "suggest dinner recipes," will lead to a generic output. Instead, DeStefano-Tangorra suggests tweaking that prompt to say: "As someone who loves trying out new cuisines and has a particular fondness of spicy food, can you suggest an exciting dinner menu for my next weekend get-together with my friends?"

If you want to apply ChatGPT to your business, Cressy suggests creating a "best-practices document" that includes details on who you are, what you do, and what your brand voice sounds like. That way, users can copy and paste the information into the chatbot whenever they start a new conversation. 

Instead of asking ChatGPT to "create me a marketing strategy" the prompt should say "I am a world-class [role] who helps [target audience] for business growth. Our brand voice is friendly, positive, inspiring, brand-safe, conversational. Create me a marketing strategy to help build my brand on Facebook and Instagram by leveraging my podcast." 

5. Break down the desired output into a series of steps

While it's best for prompts to be specific and include context, writing a long prompt can be counterproductive, Gulya said. 

"More often than not, a long mega-prompt does not give the desirable output," he said. 

Related stories

To avoid this, Gulya suggests breaking down the desired output into a series of steps. That way, if the chatbot generates errors, the user can pinpoint what exactly the chatbot may not understand. 

" This allows you to validate each step before proceeding, course-correcting when necessary," Gulya said. 

If the goal is to use ChatGPT to generate a widely read blog post, the user should ask the chatbot to first research which SEO terms will most likely make the article appear at the top of search-engine results. In a separate prompt, ask it to apply what it learned to the blog post.

6. Ask ChatGPT for advice on how to prompt it better 

To ensure your prompt is as thorough as it can be, Dean suggested asking ChatGPT what other details it needs from the user to produce the best output.

To do this, Dean suggests adding a line to your prompt that follows this template: "If I want to [desired outcome], what prompts should I share with ChatGPT in order to get the best results?" 

Once ChatGPT has generated an output, tell the chatbot what you like and dislike about the output and ask it to "request additional results, edits, or tweaks," she said.

7. Prioritize clarity and precision 

DeStefano-Tangorra suggests that ChatGPT users "explicitly outline your expectations within the prompt" by adding precise words. 

"Clear and specific prompts lead to more relevant and useful responses," she said. 

The prompt "compare and contrast using an oven versus a microwave for preparing dinner," should be tweaked to "can you compare and contrast the advantages and disadvantages of using a traditional oven versus a microwave for preparing a family dinner?" 

8. Use a thesaurus

To write your prompt with precision, Anna Bernstein, a prompt engineer at the generative-AI writing tool Copy.ai, suggests using a thesaurus to find the words that can increase your chances of getting what you want out of the chatbot. 

"Don't give up on a concept just because your first prompt didn't get the result you wanted," Bernstein previously told Insider . "Often, finding the right word or phrasing can unlock what you're doing."

9. Pay attention to verbs  

A thesaurus can help you find verbs that clearly express your intent. That way, the AI has a better chance of fully understanding your request, Bernstein said. 

She said that a prompt including the phrase "condense this" is stronger than "rewrite this to be shorter."

10. Be polite, but direct 

While ChatGPT users may have different conversational styles, Gulya said he finds that talking to the AI using polite, direct language — as if he's writing to a friend — yields the best results.

"Doing so puts me in a more collaborative, more flexible mindset," he said. 

When interacting with the chatbot for, say, advice on how college professors can enhance their skillsets, Gulya suggests writing flattering comments such as, "You're magnificent at seeing the root causes in faculty member's anxieties about artificial intelligence."

After the chatbot spits out a response you like, express gratitude by saying something like, "This is great. Thank you so much!" followed by a request to make revisions to its output.

11.Talk to ChatGPT with emotional language

If talking to ChatGPT like a friend doesn't produce desirable results, try adding some emotion to your prompts.  

A study conducted by a team of researchers from Microsoft, William & Mary, and research centers across Asia found that adding phrases like "This is very important to my career" and "You'd better be sure" to ChatGPT prompts yield better responses. 

ChatGPT users can also try writing prompts with phrases like "You'd better be sure," "Take pride in your work and give it your best," and "Remember that progress is made one step at a time. Stay determined and keep moving forward." 

12. Check and tweak the copy's tone and reading level 

If you're using ChatGPT to generate copy or captions for social media posts, make sure to tweak its tone so the content resonates with your target audience, Ashley Couto, a marketing professional who uses the chatbot to reduce her workload, told Business Insider.  

Couto finds that the best marketing copy reads at a fifth- or sixth-grade level, which includes "short sentences and paragraphs, a conversational tone, and simple language." 

To do this, Couto recommends asking ChatGPT to "change the reading level and tone" after it spits out a response. 

13. Feed ChatGPT an outline 

If you want ChatGPT to generate longer posts, Couto suggests giving the AI a specific structure and outline. She said the more specific you can be with your instructions, the better its output will be. 

Here's one prompt Couto uses to generate a company blog post:

"Following this story structure — 1. Capture the heart, 2. Set up a tension, 3. Resolve the tension, 4. Conclude by offering value — write a 1,000-word story at a grade-five reading level in the first person using the following information."

14. Include reference text 

Is ChatGPT making up answers that are factually incorrect? If so, adding bodies of text from trusted sources into the prompt may help eliminate these hallucinations. 

OpenAI's prompt guide suggests copying and pasting articles into ChatGPT, and then asking the chatbot to answer questions based on them.

An example of a prompt OpenAI provides is "Use the provided articles delimited by triple quotes to answer questions. If the answer cannot be found in the articles, write 'I could not find an answer.' After that, insert the text from the article below, followed by the questions you want ChatGPT to answer." 

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

• Main content

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

Digital Trends may earn a commission when you buy through links on our site. Why trust us?

ChatGPT: the latest news and updates on the AI chatbot that changed everything

In the ever-evolving landscape of artificial intelligence , ChatGPT stands out as a groundbreaking development that has captured global attention. From its impressive capabilities and recent advancements to the heated debates surrounding its ethical implications, ChatGPT continues to make headlines.

What is ChatGPT?

When was chatgpt released, how to use chatgpt, how to use the chatgpt iphone, android, and mac apps, is chatgpt free to use, who created chatgpt.

• ChatGPT’s continuous confounding controversies
• Can ChatGPT’s outputs be detected by anti-plagiarism systems?

What are ChatGPT plugins?

Is there a chatgpt api.

• What’s the future of ChatGPT?

ChatGPT alternatives worth trying

Other things to know about chatgpt.

Whether you’re a tech enthusiast or just curious about the future of AI, dive into this comprehensive guide to uncover everything you need to know about this revolutionary AI tool.

ChatGPT is a natural language AI chatbot . At its most basic level, that means you can ask it a question and it will generate an answer. As opposed to a simple voice assistant like Siri or Google Assistant , ChatGPT is built on what is called an LLM (Large Language Model). These neural networks are trained on huge quantities of information from the internet for deep learning — meaning they generate altogether new responses, rather than just regurgitating specific canned responses. They’re not built for a specific purpose like chatbots of the past — and they’re a whole lot smarter.

This is implied in the name of ChatGPT, which stands for Chat Generative Pre-trained Transformer. In the case of the current version of ChatGPT, it’s based on the GPT-4 LLM. The model behind ChatGPT was trained on all sorts of web content including websites, books, social media, news articles, and more — all fine-tuned in the language model by both supervised learning and RLHF (Reinforcement Learning From Human Feedback). OpenAI says this use of human AI trainers is really what makes ChatGPT stand out.

ChatGPT was originally launched to the public in November of 2022 by OpenAI. That initial version was based on the GPT-3.5 model, though the system has undergone a number of iterative advancements since then with the current version of ChatGPT running the GPT-4 model family, with GPT-5 reportedly just around the corner . GPT-3 was first launched in 2020, GPT-2 released the year prior to that.

First, go to chatgpt.com . If you’d like to maintain a history of your previous chats, sign up for a free account. You can use the system anonymously without a login if you prefer. Users can opt to connect their ChatGPT login with that of their Google-, Microsoft- or Apple-backed accounts as well. At the sign up screen, you’ll see some basic rules about ChatGPT, including potential errors in data, how OpenAI collects data, and how users can submit feedback. If you want to get started, we have a roundup of the best ChatGPT tips .

Using ChatGPT itself is simple and straightforward, just type in your text prompt and wait for the system to respond. You can be as creative as you like, and see how your ChatGPT responds to different prompts. If you don’t get the intended result, try tweaking your prompt or giving ChatGPT further instructions The system understands context based on previous responses from the current chat session, so you can refine your requests rather than starting over fresh every time.

For example, starting with “Explain how the solar system was made” will give a more detailed result with more paragraphs than “How was the solar system made,” even though both inquiries will give fairly detailed results. Take it a step further by giving ChatGPT more guidance about style or tone, saying “Explain how the solar system was made as a middle school teacher.”

You also have the option for more specific input requests, for example, an essay with a set number of paragraphs or a link to a specific Wikipedia page. We got an extremely detailed result with the request “write a four-paragraph essay explaining Mary Shelley’s Frankenstein.”

ChatGPT is capable of automating any number of daily work or personal tasks from writing emails and crafting business proposals, to offering suggestions for fun date night ideas or even drafting a best man’s speech for your buddy’s wedding. So long as the request doesn’t violate the site’s rules on explicit or illegal content, the model will do its best to fulfill the commands.

Since its launch, people have been experimenting to discover everything the chatbot can and can’t do — and the results have been impressive, to say the least . Learning the kinds of prompts and follow-up prompts that ChatGPT responds well to requires some experimentation though. Much like we’ve learned to get the information we want from traditional search engines, it can take some time to get the best results from ChatGPT. It really all depends on what you want out of it. To start out, try using it to write a template blog post, for example, or even blocks of code if you’re a programmer.

Our writers experimented with ChatGPT too, attempting to see if it could handle holiday shopping or even properly interpret astrological makeup . In both cases, we found limitations to what it could do while still being thoroughly impressed by the results.

Following an update on August 10, you can now use custom instructions with ChatGPT . This allows you to customize how the AI chatbot responds to your inputs so you can tailor it for your needs. You can’t ask anything, though. OpenAI has safeguards in place in order to “build a safe and beneficial artificial general intelligence.” That means any questions that are hateful, sexist, racist, or discriminatory in any way are generally off-limits.

You shouldn’t take everything that ChatGPT (or any chatbot, for that matter) tells you at face value. When ChatGPT first launched it was highly prone to “ hallucinations .” The system would repeat erroneous data as fact. The issue has become less prevalent as the model is continually fine tuned, though mistakes do still happen . Trust but verify!

What’s more, due to the way that OpenAI trains its underlying large language models — whether that’s GPT-3.5, GPT-4 and GPT-4o , or the upcoming GPT-5 — ChatGPT may not be able to answer your question without help from an internet search if the subject is something that occurred recently. For example, GPT-3.5 and 3.5 Turbo cannot answer questions about events after September 2021 without conducting an internet search to find the information because the data that the model was initially trained on was produced before that “knowledge cutoff date.” Similarly, GPT-4 or GPT-4 Turbo have cutoff dates of December 2023, though GPT-40 (despite being released more recently) has a cutoff of October 2023 .

While ChatGPT might not remember all of recorded history, it will remember what you were discussing with it in previous chat sessions. Logged in users can access their chat history from the navigation sidebar on the left of the screen, and manage these chats, renaming, hiding or deleting them as needed. You can also ask ChatGPT follow up questions based on those previous conversations directly through the chat window. Users also have the option to use ChatGPT in dark mode or light mode.

ChatGPT isn’t just a wordsmith. Those users paying $20/month subscription for ChatGPT Plus or $30/month/user for ChatGPT Business, gain access to the Dall-E image generator, which converts text prompts into lifelike generated images. Unfortunately, this feature is not currently available to the free tier. Regardless of subscription status, all users can use image or voice inputs for their prompt.

ChatGPT is available through the OpenAI web, as well as a mobile app for both iOS and Android devices. The iOS version was an immediate hit when it arrived at the App Store, topping half a million downloads in less than a week.

If you can use chatGPT on the web, you can use it on your phone. Logging on or signing up through the app is nearly identical to the web version and nearly all of the features found on the desktop have been ported to the mobile versions. The app lets you toggle between GPT-3.5, GPT-4, and GPT-4o as well. The clean interface shows your conversation with GPT in a straightforward manner, hiding the chat history and settings behind the menu in the top right.

Some devices go beyond just the app, too. For instance, the Infinix Folax is an Android phone that integrated ChatGPT throughout the device. Instead of just an app, the phone replaces the typical smart assistant (Google Assistant) with ChatGPT.

There’s even an official ChatGPT app released for the Mac that can be used for free . The app is capable of all sorts of new things that bring Mac AI capabilities to new levels — and you don’t even have to wait for macOS Sequoia later this year.

Yes, ChatGPT is completely free to use, though with some restrictions. Even with a free tier account, users will have access to the GPT-3.5 and GPT-40 models, though the number of queries that users can make of the more advanced model are limited. Upgrading to a paid subscription drastically increases that query limit, grants access to other generative AI tools like Dall-E image generation, and the GPT store.

It’s not free for OpenAI to continue running it, of course. Initial estimates are currently that OpenAI spends around $3 million per month to continue running ChatGPT, which is around $100,000 per day. A report from April 2023 indicated that the price of operation is closer to $700,000 per day .

Beyond the cost of the servers themselves, some troubling information and accusations have come to light regarding what else has been done to safeguard the model from producing offensive content.

OpenAI, a San Francisco-based AI research lab, created ChatGPT and released the very first version of the LLM in 2018. The organization started as a non-profit meant for collaboration with other institutions and researchers, funded by high-profile figures like Peter Thiel and Elon Musk, the latter of whom left the company after an internal power struggle to found rival firm, xAI.

OpenAI later transitioned to a for-profit structure in 2019 and is now led by CEO, Sam Altman. It runs on Microsoft’s Azure system infrastructure and is powered by Nvidia’s GPUs, including the new supercomputers just announced this year . Microsoft has invested heavily in OpenAI since 2019 as well, expanding its partnership with the AI startup in 2021 and again in 2023, when Microsoft announced a multi-billion dollar round of investments that included naming its Azure cloud as OpenAI’s exclusive cloud provider.

ChatGPT’s continuous confounding controversies

Although ChatGPT is an extremely capable digital tool, it isn’t foolproof. The AI is known for making mistakes or “hallucinations,” where it makes up an answer to something it doesn’t know. Early on, a simple example of how unreliable it can sometimes be involved misidentifying the prime minister of Japan .

Beyond just making mistakes, many people are concerned about what this human-like generative AI could mean for the future of the internet, so much so that thousands of tech leaders and prominent public figures have signed a petition to slow down the development. It was even banned in Italy due to privacy concerns, alongside complaints from the FTC — although that’s now been reversed. Since then, the FTC has reopened investigations against OpenAI on questions of personal consumer data is being handled.

In addition, JPMorgan Chase has threatened to restrict the use of the AI chatbot for workers, especially for generating emails, which companies like Apple have also prohibited internally. Following Apple’s announcement at WWDC 2024 that it would be integrating OpenAI’s technology into its mobile and desktop products, Tesla CEO and sore loser Elon Musk similarly threatened to ban any device running the software from his businesses — everything from iPhones to Mac Studios. Other high-profile companies have been disallowing the use of ChatGPT internally, including Samsung, Amazon, Verizon, and even the United States Congress .

There’s also the concern that generative AI like ChatGPT could result in the loss of many jobs — as many as 300 million worldwide, according to Goldman Sachs. In particular, it’s taken the spotlight in Hollywood’s writer’s strike , which wants to ensure that AI-written scripts don’t take the jobs of working screenwriters.

In 2023, many people attempting to use ChatGPT received an “at capacity” notice when trying to access the site . It’s likely behind the move to try and use unofficial paid apps, which had already flooded app stores  and scammed thousands into paying for a free service.

Because of how much ChatGPT costs to run, it seems as if OpenAI has been limiting access when its servers are “at capacity.” It can take as long as a few hours to wait out, but if you’re patient, you’ll get through eventually. Of the numerous growing pains ChatGPT has faced , “at capacity” errors had been the biggest hurdle keeping people from using the service more. In some cases, demand had been so high that the entire ChatGPT website has gone down for several hours for maintenance multiple times over the course of months.

Multiple controversies have also emerged from people using ChatGPT to handle tasks that should probably be handled by an actual person. One of the worst cases of this is generating malware, which the FBI recently warned ChatGPT is being used for. More startling, Vanderbilt University’s Peabody School came under fire for generating an email about a mass shooting and the importance of community.

There are also privacy concerns. A recent GDPR complaint says that ChatGPT violates user’s privacy by stealing data from users without their knowledge, and using that data to train the AI model. ChatGPT was even made able to generate Windows 11 keys for free , according to one user. Of course, this is not how ChatGPT was meant to be used, but it’s significant that it was even able to be “tricked” into generating the keys in the first place.

Can ChatGPT’s outputs be detected by anti-plagiarism systems?

Teachers, school administrators, and developers are already finding different ways around this and banning the use of ChatGPT in schools . Others are more optimistic about how ChatGPT might be used for teaching, but plagiarism is undoubtedly going to continue being an issue in terms of education in the future. There are some ideas about how ChatGPT could “watermark” its text and fix this plagiarism problem, but as of now, detecting ChatGPT is still incredibly difficult to do.

ChatGPT launched an updated version of its own plagiarism detection tool in January 2023, with hopes that it would squelch some of the criticism around how people are using the text generation system. It uses a feature called “AI text classifier,” which operates in a way familiar to other plagiarism software. According to OpenAI, however, the tool is a work in progress and remains “imperfect.” Since the advent of GPTs in April 2024, third party developers have also stepped in with their own offerings, such as Plagiarism Checker.

They’re a feature that doesn’t exist anymore. The announcement of ChatGPT plugins caused a great stir in the developer community, with some calling it “the most powerful developer platform ever created.” AI enthusiasts have compared it to the surge of interest in the iOS App Store when it first launched, greatly expanding the capabilities of the iPhone.

Essentially, developers would be able to build plugins directly for ChatGPT, to open it up to have access to the whole of the internet and connect directly to the APIs of specific applications. Some of the examples provided by OpenAI include applications being able to perform actions on behalf of the user, retrieve real-time information, and access knowledge-based information.

However, in 2024, OpenAI reversed course on its plugin plans , sunsetting the feature and replacing them with GPT applets. OpenAI’s GPT applets were released in conjunction with the unveiling of GPT-4o , They’re small, interactive JavaScript applications generated by GPT-4 and available on the ChatGPT website. These applets are various tools designed to perform specific, often singular, tasks such as acting as calculators, planners, widgets, image apps, and text transformation utilities.

Yes. APIs are a way for developers to access ChatGPT and plug its natural language capabilities directly into apps and websites. We’ve seen it used in all sorts of different cases, ranging from suggesting parts in Newegg’s PC builder to building out a travel itinerary with just a few words. Many apps had been announced as partners with OpenAI using the ChatGPT API. Of the initial batch, the most prominent example is Snapchat’s MyAI .

Recently, OpenAI made the ChatGPT API available to everyone, and we’ve seen a surge in tools leveraging the technology, such as Discord’s Clyde chatbot or Wix’s website builder . Most recently, GPT-4 has been made available as an API “for developers to build applications and services.” Some of the companies that have already integrated GPT-4 include Duolingo, Be My Eyes, Stripe, and Khan Academy. 

What’s the future of ChatGPT?

There’s no doubt that the tech world has become obsessed with ChatGPT right now, and it’s not slowing down anytime soon. But the bigger development will be how ChatGPT continues to be integrated into other applications.

GPT-5 is the rumored next significant step up in, which has been teased and talked about ad nauseam over the past year. Some say that it will finish training as early as in December of 2024, paving the way toward AGI (artificial general intelligence) . OpenAI CTO Mira Murati has compared it to having Ph.D.-level intelligence , while others have said it will lead to AI with better memory and reasoning . The timing seems very uncertain though, but it seems like it could launch sometime in 2025.

Beyond GPT-5, plenty of AI enthusiasts and forecasters have predicted where this technology is headed. Last year, Shane Legg, Google DeepMind’s co-founder and chief AGI scientist,  told Time Magazine  that he estimates there to be a 50% chance that AGI will be developed by 2028. Dario Amodei, co-founder and CEO of Anthropic, is even more bullish,  claiming last August  that “human-level” AI could arrive in the next two to three years. For his part, OpenAI CEO Sam Altman argues that AGI could be achieved  within the next half-decade .

All that to say, if you think AI is a big deal now, we’re clearly still in the early days.

ChatGPT remains the most popular AI chatbot, but it’s not without competition. Microsoft’s Copilot is a significant rival, even though Microsoft has invested heavily with the AI startup and Copilot itself leverages the GPT-4 model for its answers.

Google’s Gemini AI (formerly Google Bard ) is another such competitor. Built on Google’s own transformer architecture, this family of multimodal AI models can both understand and generate text, images, audio, videos, and code. First released in March, 2o23, Gemini is available in 46 languages and in 239 countries and territories. One of its big advantages is that Gemini can generate images for free, while you’ll have to upgrade to ChatGPT Plus in OpenAI’s ecosystem.

Anthropic’s Claude family of AI have also emerged as serious challengers to ChatGPT’s dominance. In June 2024, the AI startup announced that its recently released Claude 3.5 Sonnet model outperformed both GPT-4o and Gemini Pro 1.5 at a host of industry benchmarks and significantly outperformed the older Claude 3.0 Opus by double digits while consuming 50 percent less energy.

Meta, the parent company to Facebook, has also spent the last few years developing its own AI chatbot based on its family of Llama large language models. The company finally revealed its chatbot in April 2024, dubbed Meta AI, and revealed that it leverages the company’s latest to date model, Llama 3 . The assistant is available in more than a dozen countries and operates across Meta’s app suite, including Facebook, Instagram, WhatsApp, and Messenger.

Lastly, Apple had long been rumored to be working on an artificial intelligence system of its own, and proved the world right at WWDC 2024 in June, where the company revealed Apple Intelligence . The AI is “comprised of highly capable large language and diffusion models specialized for your everyday tasks” and designed to help iPhone, iPad and Mac users streamline many of their most common everyday tasks across apps.

For example, the system will autonomously prioritize specific system notifications so as to minimize distractions while you focus on a task while writing aides can proofread your work, revise them at your command, and even summarize text for you. Apple’s AI is expected to begin rolling out to users alongside the iOS 18, iPadOS 18 and Mac Sierra software releases in Fall 2024.

Are ChatGPT chats private?

It depends on what you mean by private. All chats with ChatGPT are used by OpenAI to further tune the models, which can actually involve the use of human trainers. No, that doesn’t mean a human is looking through every question you ask ChatGPT, but there’s a reason OpenAI warns against providing any personal information to ChatGPT.

It should be noted that if you don’t delete your chats, the conversations will appear in the left sidebar. Unlike with other chatbots, individual chats within a conversation cannot be deleted, though they can be edited using the pencil icon that appears when you hover over a chat. When you delete the conversations, however, it’s not that ChatGPT forgets they ever happened — it’s just that they disappear from the sidebar chat history.

Fortunately, OpenAI has recently announced a way to make your chats hidden from the sidebar . These “hidden” chats won’t be used to train AI models either. You can also opt out of allowing OpenAI to train its models in the settings.

Will ChatGPT replace Google Search?

Rather than replace it, generative AI features are being integrated directly into search. Microsoft started things off by integrating Copilot right into its own search engine, which puts a “chat” tab right into the menu of Bing search. Google, of course, made its big move with AI Overviews , which uses AI-generated answers in place of traditional search results. It launched first through its Search Generative Experience , but rolled out widely in May 2024.

To be clear, this kind of AI is different than just Gemini or ChatGPT. And yet, it’s also undeniable that AI will play an important role in the future of search in the near future. Despite all the problems with AI Overviews, Google seems committed to making it work.

Is Copilot the same as ChatGPT?

Although Copilot and ChatGPT are capable of similar things, they’re not exactly the same. Copilot, even though it runs the same GPT-4 model as ChatGPT, is an entirely separate product that has been fine-tuned by Microsoft.

Microsoft, as part of its multi-billion dollar investment into OpenAI, originally brought ChatGPT to Bing in the form of Bing Chat . But unlike ChatGPT , Bing Chat required downloading the latest version of Edge at the time.

Bing Chat has since been completely retooled into Copilot, which has seemingly become Microsoft’s most important product. It’s integrated into Microsoft 365 apps through Copilot Pro , while the Copilot+ expands the AI capabilities deep into Windows and laptop hardware.

Can you write essays with ChatGPT?

The use of ChatGPT has been full of controversy, with many onlookers considering how the power of AI will change everything from search engines to novel writing. It’s even demonstrated the ability to earn students surprisingly good grades in essay writing.

Essay writing for students is one of the most obvious examples of where ChatGPT could become a problem. ChatGPT might not write this article all that well, but it feels particularly easy to use for essay writing. Some generative AI tools, such as Caktus AI , are built specifically for this purpose.

Can ChatGPT write and debug code?

Absolutely. It’s one of the most powerful features of ChatGPT. As with everything with AI, you’ll want to double-check everything it produces, because it won’t always get your code right. But it’s certainly powerful at both writing code from scratch and debugging code. Developers have used it to create websites, applications, and games from scratch — all of which are made more powerful with GPT-4, of course.

What is the ChatGPT character limit?

ChatGPT doesn’t have a hard character limit. However, the size of the context window (essentially, how long you can make your prompt), depends on the tier of ChatGPT you’re using. Free tier users receive just 8,000 characters, while Plus and Teams subscribers receive 32k-charcter context windows, and Enterprise users get a whopping 128k characters to play with.

What is Auto-GPT?

Built on GPT-4, Auto-GPT is the latest evolution of AI technology to cause a stir in the industry. It’s not directly related to ChatGPT or OpenAI — instead, it’s an open-source Python application that got into the hands of developers all over the internet when it was published on GitHub .

With ChatGPT or ChatGPT Plus, the capabilities of the AI are limited to a single chat window. Auto-GPT, at its simplest, is making AI autonomous. It can be given a set of goals, and then take the necessary steps towards accomplishing that goal across the internet, including connecting up with applications and software.

According to the official description on GitHub, Auto-GPT is an “experimental open-source application showcasing the capabilities of the GPT-4 language model. This program, driven by GPT-4, chains together LLM ‘thoughts’, to autonomously achieve whatever goal you set. As one of the first examples of GPT-4 running fully autonomously, Auto-GPT pushes the boundaries of what is possible with AI.”

The demo used on the GitHub page is simple — just create a recipe appropriate for Easter and save it to a file. What’s neat is how Auto-GPT breaks down the steps the AI is taking to accomplish the goal, including the “thoughts” and “reasoning” behind its actions. Auto-GPT is already being used in a variety of different applications, with some touting it as the beginning of AGI (Artificial General Intelligence) due to its autonomous nature.

Who owns the copyright to content created by ChatGPT?

This is a question open to debate. Much of the conversation around copyright and AI is ongoing, with some saying generative AI is “stealing” the work of the content it was trained on. This has become increasingly contentious in the world of AI art. Companies like Adobe are finding ways around this by only training models on stock image libraries that already have proper artist credit and legal boundaries.

According to OpenAI, however, you have the right to reprint, sell, and merchandise anything that was created with ChatGPT or ChatGPT Plus. So, you’re not going to get sued by OpenAI.

The larger topic of copyright law regarding generative AI is still to be determined by various lawmakers and interpreters of the law, especially since copyright law as it currently stands technically only protects content created by human beings.

Editors’ Recommendations

• Here’s how Claude 3.5 Sonnet and GPT-4o stack up in a direct comparison
• A dangerous new jailbreak for AI chatbots was just discovered
• OpenAI’s recent acquisition could change PCs forever
• GPT-5 will have ‘Ph.D.-level’ intelligence
• I compared ChatGPT against Google Gemini to see which is the better free AI chatbot
• Artificial Intelligence

While OpenAI continues to add new features to ChatGPT Plus, the free version of ChatGPT has remained relatively stagnant since its release. But not anymore.

One of the best features that's been exclusive to ChatGPT Plus -- custom GPTs -- is now available to use for free. The feature is exactly what it sounds like -- customized versions of ChatGPT that users can create to fulfill a specific task. You can give them extra knowledge and direct their behavior with custom prompts, all without needing to code.

In the ever-growing large language model (LLMs) landscape, two front-runners stand out from the rest of the race: Anthropic's Claude 3.5 Sonnet and OpenAI's GPT-4o (the "o" stands for "Omni"). Both AIs boast impressive capabilities, but which reigns supreme? This guide dives deep into Claude 3.5 Sonnet and GPT-4o, dissecting their strengths and weaknesses across various tasks.

We'll not only explore their relative accuracy and response speeds, but also unpack their pricing structures and service tiers. By the end of this article, you'll be armed with the knowledge to make an informed decision about which LLM best suits your specific needs and budget. Pricing and tiers ChatGPT users can access the GPT-4o model for free, but the number of queries you're allowed to ask it within a three-hour span is limited. Exceeding that limit will move you down to using GPT-3.5, OpenAI's older, less capable model, until the cooldown timer has reset.

You can't always pick from a wide range of home internet providers (depending on your location), but even if your choice is limited, you still want to select the right one. From pricing to speed, support, and contract plans, picking the right broadband provider can make a real difference to the service you receive. Here are our favorites.

Interested in grabbing a short-term internet deal with a discount and bundled extras? Here are the best ones available now. AT&T Fiber

Can ChatGPT Write a Book? We Put It to the Test

Helpful summary.

• Overview: This article examines the process of using ChatGPT to write a book and the limitations that go along with this.
• Why you can trust us: We’ve been using (and later building) AI writing tools like ChatGPT for years. And as writers ourselves, we understand the unique challenges and nuances of writing a book with AI.
• Why is this important: ChatGPT is a popular tool, and lots of writers and authors wonder if it’s a good option for writing books.
• Action Points: Use ChatGPT for ideation, but find an AI tool that was designed for creative writing to handle everything else.
• Further research: Head over to our blog for deep dives, tutorials, and comparisons of AI writing tools.

Can ChatGPT Write a Book?

ChatGPT has taken the world by storm. It’s a versatile chatbot that’s great at giving off the impression that it can do anything. But… can it write a book?

If you do a quick Google search, you’ll see a bunch of articles arguing that it can. And beyond that, many argue that ChatGPT is actually a quick way to write and publish books that are good enough to earn you money .

This is a pretty bold claim, and it’s one we’re skeptical of. So, in this DreamGen guide, we put it to the test.

Why Listen to Us?

At DreamGen, we know how frustrating writer’s block can be. It’s one of the leading reasons why people turn to AI tools like ChatGPT to help them write. Our team has tons of experience using and building AI tools, and we have seen the benefits and pitfalls firsthand.

We are here to share our knowledge and help you make an informed decision about using ChatGPT or other AI tools for your writing needs.

So… Can ChatGPT Write a Book?

We won’t make you read the entire article for the answer. After testing this tool out, our answer to this question is, “Yes, but not a very good one.”

There are just too many limitations standing in the way of ChatGPT for it to be a good tool for end-to-end book writing, including:

• Poor organizational structure for chapters
• Very robotic sounding default tone
• Strict content limitations
• No permanent memory bank

That said, we stand by ChatGPT as a great tool during the ideation stage. It’s a great brainstorming partner since it’s designed to engage in back-and-forth conversations. Want to see how we reached these conclusions?

How to Use ChatGPT to Write a Book

1. ideation.

AI chatbots like ChatGPT were basically tailor-made for ideation. So, as you first start to brainstorm your book, ChatGPT is a powerful tool.

Our recommendation? Start jotting down notes about things you might want to write about, like:

• Character idea
• General vibe

Feel free to get creative here. Then, use the following prompt:

• “Please generate a few story ideas that incorporate the following details: [ insert notes ].”

ChatGPT really impresses us here. The generations are pretty creative, and it does a great job of working within the creative boundaries you set. Our very specific set of instructions yielded a pretty promising set of options, and ChatGPT even went ahead and included details about the premise and plot.

We’ll stick with “The Chameleon Rebellion” for the rest of this guide.

2. Outline Your Book

Another thing ChatGPT is great at? Organizing lots of details into set formats. So, let’s put that to use and get ChatGPT to come up with a potential outline for our story.

Here’s a prompt to try out:

• “Generate a story outline (acts and chapters) for a book about the following: [ previous output ].”

Not bad, ChatGPT.

As you can see, it respected all the details we included in the prompt and managed to spin them into a pretty logical and, dare we say, compelling story outline. With the right characters, this could definitely be a solid sci-fi adventure story.

3. Develop Characters and Settings

Next, we need ChatGPT to make a list of all the characters and settings we want to include in our story.

Use these prompts:

• “Generate a list of all the characters needed to tell the following story: [ previous output ].
• “Generate a list of all the settings needed to tell the following story: [ previous output ].”

ChatGPT will probably attach some basic info about each character and setting to this list. So, if you see anything you’re not happy with, you’ll need to correct this manually.

At this time, you should also look for missing characters or settings. If you think of any that you’d like to include, think of a name (or ask ChatGPT to generate one) and explain to the AI how they fit into the story arc—ChatGPT will then make an addition.

Then, we recommend going through each character individually to add depth.

Here’s a prompt:

• “Please create a character sheet for [ name ]. Include physical description, psychological description, backstory, motivations, relationships, and one line of example dialogue.”

You can do the same for settings with this prompt:

• “Generate a setting sheet for [ location ]. Include physical description, history, and significance to the story.”

4. Generate Chapters

We’ve done the setup work. Now it’s time to write the book… or at least try to.

There are a few ways to go about this, like generating isolated scenes and then asking ChatGPT to weave them into coherent chapters. But the fastest way is to just ask ChatGPT to generate a full chapter based on the information you’ve established so far.

• Generate chapter [ number ] from the following outline:

[ outline ]

Include the following characters and settings:

[ character sheet 1 ]

[ character sheet 2 ]

[ setting sheet 1 ]

Let’s start with the main positive—ChatGPT does a great job of synthesizing the setup information and coming up with a chapter that fits into your story. Beyond that, there are some pretty major flaws with using ChatGPT to write full chapters like this, including:

Writing Quality

ChatGPT isn’t designed for writing prose. In fact, we’d go as far as to say it’s bad at writing prose. There’s always a distinctly robotic, GPT-esque tone present in the outputs it generates. That’s why AI content detectors are very good at picking up on GPT-generated content.

This isn’t a problem in the ideation or planning stages. But it becomes a big problem when it’s actually time to… you know, write. Yes, you can ask ChatGPT to adjust its tone, but these changes are always minimal. Plus, it’s very hard to make them stick over the course of an entire book.

Poor Design

ChatGPT is a chatbot. That means its UI and features are designed like a chatbot. And as any writer will tell you, writing a book tends to happen in something that resembles a word processor (like Google Docs or Microsoft Word) or piece of paper.

With ChatGPT, organizing your book into chapters is almost impossible. You can create separate conversations for each chapter, but then you need to re-explain the entire premise each time.

This brings us to another issue—ChatGPT has no persistent memory system . There’s no way to store information about characters, settings, and items, so ChatGPT always has access. That means whenever your conversations extend past the context window, it’ll instantly forget important details.

With a purpose-built tool like DreamGen? It’s easy —but more on that later.

Content Restrictions

ChatGPT isn’t able to generate any kind of adult content.

That includes:

• Political talk
• Sexual content
• Non-sexual nudity

If you try to add any of these elements to your story, you’ll get a warning like this.

If you keep trying, you risk getting your account banned. And before you try it, if you write these scenes yourself and then paste them into ChatGPT to have it continue around them… it’s still not allowed. Want to see if you can bypass these restrictions? Check out our guide to making ChatGPT NSFW .

Ethical Considerations

ChatGPT is trained on a vast array of sources. That's awesome for variety, but it also means it might pick up some societal prejudices or stereotypes. You don't want your readers feeling offended because the AI didn't quite get it.

To avoid that, you'll need to be an attentive editor, checking for anything that might raise eyebrows. This process involves identifying and removing any potentially problematic elements that may have slipped through the cracks during generation.

After testing this tool out, our answer to this question is, “Yes, but not a very good one.”

That said, we stand by ChatGPT as a great tool during the ideation stage. It’s a great brainstorming partner since it’s designed to engage in back-and-forth conversations.

Best Alternative for Writing a Book: DreamGen

Phew… that’s quite a few limitations. But don’t worry, we have a solution for all the writers and authors out there— DreamGen .

DreamGen is an AI platform that gives writers complete freedom to create long-form stories, books, and fanfics with the help of AI. We developed our own AI models to be completely uncensored, so you can explore any topics or themes you want.

Plus, DreamGen is designed for writing books. Our Story Bible makes it easy to organize items, locations, and characters in a persistent memory bank that our AI can draw from. So you never have to worry about forgetting important details or losing track of your plot.

Core Features

• Role-Play and Story-Writing Modes: Whether you're into creating vibrant stories or immersive role-plays, DreamGen has a mode.
• Open-Source Accessibility: All our models are completely open-source and available on Hugging Face for extra transparency.
• Multi-Character Dynamics: Enjoy complex role-plays with multiple characters interacting with each other independently.
• Scenario Library : Access a library of pre-written scenarios to get a jumpstart on your role-plays and stories.
• Scenario Generator : Do you have a dry spell and need help brainstorming scenario ideas? Do none of the built in scenario strike your fancy? Our scenario generator can help flesh out the plot, characters and more based on your suggestions.
• Deep Settings Menus: Fine-tune AI models, outputs, and more with our in-depth settings menus and customization options.

Bottom Line

AI writing tools like ChatGPT can be a valuable asset for authors struggling with writer's block or world-building. However, this tool isn’t good for writing books—no matter how many articles there are out there claiming it is.

You’re the author, and the AI is there to assist you. With DreamGen, you can harness the power of AI to write your stories without it stealing the show. Get started with a free account today and see what AI creative writing can do for you.

What is Microsoft’s Copilot? Here’s everything you need to know about the AI assistant

Suswati Basu is a multilingual, award-winning editor and the founder of the intersectional literature channel, How To Be Books. She was shortlisted for the Guardian…

Sam Shedden is an experienced journalist and editor with over a decade of experience in online news. A seasoned technology writer and content strategist, he…

• Microsoft's Copilot aims to surpass OpenAI's ChatGPT with advanced features across Microsoft applications.
• Copilot integrates with Windows and Microsoft 365, enhancing productivity through AI-driven functionalities.
• Free and paid versions of Copilot offer various features, with paid versions providing extensive capabilities for business users.

The market for generative AI chatbots is expanding quickly. Although OpenAI’s ChatGPT is currently the most popular, Microsoft’s Copilot is attempting to become the top choice for the general public, creative industries, and anyone interested in exploring how artificial intelligence can make the best of their daily lives.

How is Copilot different to Cortana?

Copilot has replaced Cortana and comes with advanced features. It is able to understand and respond to natural language queries, provide detailed explanations, analyze data, generate content such as code or images, and undertake complex tasks across Microsoft applications.

As a result, Copilot offers far more functionalities than Cortana. For example, it can generate a PowerPoint presentation from the provided information, and craft emails and responses. If you’re dealing with multiple emails from the same colleague on a single subject, Copilot can summarize all those communications.

In addition, Copilot can assist with meeting preparations or provide a summary of missed discussions if you’re late to a Teams meeting.

The tool also supports the creation of budget proposals, project timelines, agendas, and SWOT analyses. Its ability to interpret and execute commands using natural language processing means users don’t require coding skills to use it effectively.

What does Copilot do?

Copilot is integrated within Windows and Microsoft 365 apps like Word, Excel, and PowerPoint, improving productivity:

• Visualizations : Copilot helps users start creative projects by providing first drafts in Word, assisting in creating engaging PowerPoint presentations, and enabling quick data analysis and visualization in Excel.
• Productivity : Copilot reduces busywork by summarizing email threads and drafting responses in Outlook, providing real-time meeting summaries and action items in Teams, and enabling automation and application creation in Power Platform. GitHub data indicates that Copilot significantly increases productivity among developers.
• Chatbot : This new feature allows users to interact with all their Microsoft 365 apps and data (like calendars, emails, and documents) using natural language commands to manage tasks and access information efficiently.
• Upskilling : Copilot simplifies the use of Microsoft 365’s extensive functionality by enabling command execution through natural language, helping users improve their existing skills and learn new ones more quickly.

First launched as Bing Chat on February 7, 2023, as an add-on for Bing and Microsoft’s Edge browser, Copilot is developed on OpenAI’s GPT-4 model.

During its rollout in March, Microsoft CEO Satya Nadella described it as a “major step,” stating, “Today marks the next major step in the evolution of how we interact with computing, which will fundamentally change the way we work and unlock a new wave of productivity growth. With our new copilot for work, we’re giving people more agency and making technology more accessible through the most universal interface — natural language.”

What does chatbot do with Microsoft apps?

Here’s what Copilot brings to your specific Microsoft apps:

• Microsoft Word: Copilot uses AI to compose text, revise existing content , and condense key information into summaries.
• PowerPoint: It transforms basic ideas into comprehensive presentations, complete with detailed speaker notes and citations.
• Excel: The tool helps users uncover insights, recognize patterns, and improve the effectiveness of their spreadsheets.
• Teams: The video conferencing software uses Copilot by creating real-time meeting summaries and identifying actionable items, all while considering the conversation’s context.
• Teams phone: Phone conversations can be summarized and important action items are noted in Teams Phone. It showcases key discussion points and suggests subsequent steps.
• Outlook : It manages and streamlines Outlook inboxes, providing response suggestions and summarizing email threads.
• Power Platform: Copilot supports developers of all skill levels in prototyping and developing low-code applications.
• Business chat: Copilot aggregates and processes data from various sources—documents, calendars, notes, presentations, and contacts—to summarize conversations, pinpoint crucial dates, and draft business plans and emails.
• Microsoft Loop: AI improves any collaborative efforts by aligning data, summarizing information, and providing guidance to team members.

Is Microsoft Copilot free?

Copilot was introduced to Windows 11 as part of the update on September 26, 2023. It is available at no added cost for commercial users of Windows 11. There was speculation that Windows 10 might eventually support Copilot integration, though Microsoft has not officially confirmed this yet.

Microsoft provides a free version of Copilot and also offers a Copilot Pro subscription for $20 per month. The Pro version used to include advanced features such as the Copilot GPT Builder for creating custom chatbots and the capability for higher-resolution image creation. However, this was discontinued in June.

The free version of Copilot has limited features such as image creation in Designer, document and webpage summarization, plugin support, and data protection via Commercial Entra ID. It is accessible through specific platforms:

• Mobile app : Available on Google Play and the Apple App Store, users can interact with Copilot features like conversational search, image creation, and text generation on the go.
• Web app: This is a continuation of Bing Chat, now rebranded as Microsoft Copilot. Users can search, question, and customize of outputs using various Copilot GPTs such as Designer and Fitness Trainer. Accessible via web browsers, it provides a free way to engage with generative AI.
• Copilot for Windows: Integrated into the latest versions of Windows, this version makes it easy to manage PC settings, interact with Copilot via text or voice, and perform tasks like shopping or writing essays for free.
• Copilot for Edge: Built into the Edge browser, this service uses GPT-4 to upgrade online searching and provide generative AI features like image generation and story writing directly within the browser.

What do the paid versions include?

Microsoft 365 Copilot became available for all business users for $30 per user per month, starting January 15, 2024. At first, it was only open to Enterprise users. There is an annual option for $360, though this still requires a qualifying Microsoft 365 plan.

The system works in conjunction with Microsoft 365 apps like Word, Outlook, Teams, PowerPoint, and Excel. Although Copilot is available for free at copilot.microsoft.com, make sure you access it using Microsoft Edge or Google Chrome for it to work smoothly.

The subscription includes all the features of Copilot Pro along with additional gadgets. It also extends Copilot to all Microsoft 365 apps, including Teams, provided you have a Microsoft 365 subscription that includes Teams. It’s important to note that current Office plans do not include Teams, as Microsoft has separated Teams from its Office suite. Users now have the option to purchase plans either with or without the Teams collaboration app.

Is Copilot better than ChatGPT?

Shortly after the launch of ChatGPT, Microsoft unveiled an AI chatbot for its Bing search engine, first named Bing Chat but later rebranded as Copilot. This new tool gave more advanced options over ChatGPT, most notably free internet access which provided a considerable edge.

By May 2024, OpenAI responded by upgrading the free version of ChatGPT to include features that not only matched but in some aspects, surpassed those of Copilot. Despite these improvements, one persistent issue with ChatGPT was its inability to consistently verify the accuracy of its responses, as it does not generally cite sources. The May update allowed ChatGPT to access the internet, although it still provided source links only selectively.

Meanwhile, Copilot automatically embeds footnotes in its responses, directing users to the source material via web links, which helps with transparency and trust. Copilot is much like a search engine, its replies can include links and photos that add context and engage users. The images it generates also usually include additional information, improving the user experience.

However, this changed when OpenAI launched its new GPT-4o model in May 2024. This updated version has all the bells and whistles of GPT-4, which already outshines most AI models for its reasoning and coding, and introduces multimodal capabilities. GPT-4o can process and generate content across multiple formats, including text, audio, and images, recognizing inputs from text, audio, images, and video.

Thanks to the upgrade, free users can now access the advanced system, which was previously limited to paid users.

Featured image: Canva / Microsoft

About ReadWrite’s Editorial Process

The ReadWrite Editorial policy involves closely monitoring the tech industry for major developments, new product launches, AI breakthroughs, video game releases and other newsworthy events. Editors assign relevant stories to staff writers or freelance contributors with expertise in each particular topic area. Before publication, articles go through a rigorous round of editing for accuracy, clarity, and to ensure adherence to ReadWrite's style guidelines.

Suswati Basu Tech journalist

Suswati Basu is a multilingual, award-winning editor and the founder of the intersectional literature channel, How To Be Books. She was shortlisted for the Guardian Mary Stott Prize and longlisted for the Guardian International Development Journalism Award. With 18 years of experience in the media industry, Suswati has held significant roles such as head of audience and deputy editor for NationalWorld news, digital editor for Channel 4 News and ITV News. She has also contributed to the Guardian and received training at the BBC As an audience, trends, and SEO specialist, she has participated in panel events alongside Google. Her…

Related News

YouTube launches improved ‘eraser’ tool to remove music that would get a copyright strike

Figma disables new AI design feature after being called out on social media

AI startup Abnormal Security ‘valued at $5bn’

WhatsApp “Imagine Me” feature leaks – here’s what we know

Most popular tech stories.

• 4 Best Meme Coin Presales to Buy in June 2024 – $PLAY, $WAI, $SEAL, and $DAWGZ
• ChatGPT-5: release date, price, and what we know so far
• Level Up Your Crypto Casino Experience with Mega Dice Token Presale, Featuring Referrals and Airdrop Bonuses – OnlineHustleTV Reviews
• TodayTrader Reviews The Newest Meme Coin Presale with Play-to-Earn Features – Next 10x Crypto Gem?
• 3 Dog Coins with 100x Potential – PlayDoge, Base Dawgz, and WienerAI

Latest News

Best Elden Ring starting class explained

Being a FromSoftware title, Elden Ring has a (well-deserved) reputation for being a hard game. Early on before you've found any weapons, upgraded your gear, or leveled up much, the...

EA Sports FC25 leaks reveal release date, editions, logo, and prices, ahead of official announcement

The First Descendant voice actors - you sound familiar, were you in The Witcher?

Notcoin's Bullish Signs Point to Potential Price Surge as New AI-Powered Project Hits $7 Million Milestone

The first descendant voice actors – you sound familiar, were you in the witcher, notcoin’s bullish signs point to potential price surge as new ai-powered project hits $7 million milestone.

How to respec in Elden Ring to change your build

Popular topics.

Get the biggest tech headlines of the day delivered to your inbox

By signing up, you agree to our Terms and Privacy Policy. Unsubscribe anytime.

Explore the latest in tech with our Tech News. We cut through the noise for concise, relevant updates, keeping you informed about the rapidly evolving tech landscape with curated content that separates signal from noise.

Explore tech impact in In-Depth Stories. Narrative data journalism offers comprehensive analyses, revealing stories behind data. Understand industry trends for a deeper perspective on tech's intricate relationships with society.

Empower decisions with Expert Reviews, merging industry expertise and insightful analysis. Delve into tech intricacies, get the best deals, and stay ahead with our trustworthy guide to navigating the ever-changing tech market.