open ai writing essays

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

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

Last Updated: April 28, 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 45,879 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. [3] X Research source For example: "Write a 1000 word argumentative essay called 'The Impact of COVID-19 on the United States Economy' using the outline you provided. Argue that the government should take more action to support businesses affected by the pandemic."

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

Expert Q&A

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

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

You Might Also Like

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

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

About This Article

• Send fan mail to authors

Is this article up to date?

Featured Articles

Trending Articles

Watch Articles

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

wikiHow Tech Help Pro:

Level up your tech skills and stay ahead of the curve

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

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

AI bot ChatGPT writes smart essays — should professors worry?

• Chris Stokel-Walker

You can also search for this author in PubMed   Google Scholar

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

Access options

Access Nature and 54 other Nature Portfolio journals

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

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

185,98 € per year

only 3,65 € per issue

Rent or buy this article

Prices vary by article type

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

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

Reprints and permissions

Related Articles

Are ChatGPT and AlphaCode going to replace programmers?

How language-generation AIs could transform science

Open-source language AI challenges big tech’s models

• Computer science

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

News 15 APR 24

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

Article 27 MAR 24

Three reasons why AI doesn’t model human language

Correspondence 19 MAR 24

Want to make a difference? Try working at an environmental non-profit organization

Career Feature 26 APR 24

Future of Humanity Institute shuts: what’s next for ‘deep future’ research?

News 26 APR 24

Ancient DNA traces family lines and political shifts in the Avar empire

News & Views 24 APR 24

How young people benefit from Swiss apprenticeships

Spotlight 17 APR 24

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

Career Feature 08 APR 24

After the genocide: what scientists are learning from Rwanda

News Feature 05 APR 24

ECUST Seeking Global Talents

Join Us and Create a Bright Future Together!

Shanghai, China

East China University of Science and Technology (ECUST)

Position Recruitment of Guangzhou Medical University

Seeking talents around the world.

Guangzhou, Guangdong, China

Guangzhou Medical University

Junior Group Leader

The Imagine Institute is a leading European research centre dedicated to genetic diseases, with the primary objective to better understand and trea...

Paris, Ile-de-France (FR)

Imagine Institute

Director of the Czech Advanced Technology and Research Institute of Palacký University Olomouc

The Rector of Palacký University Olomouc announces a Call for the Position of Director of the Czech Advanced Technology and Research Institute of P...

Czech Republic (CZ)

Palacký University Olomouc

Course lecturer for INFH 5000

The HKUST(GZ) Information Hub is recruiting course lecturer for INFH 5000: Information Science and Technology: Essentials and Trends.

The Hong Kong University of Science and Technology (Guangzhou)

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

Natasha Singer

Hey, ChatGPT, can you help me write my college admissions essays?

Absolutely! Please provide me with the essay prompts and any relevant information about yourself, your experiences, and your goals.

We Used A.I. to Write Essays for Harvard, Yale and Princeton. Here’s How It Went.

A.I. chatbots can do a passable job of generating short essays. Whether their use on college applications is ethical is the subject of fierce debate.

By Natasha Singer

Natasha Singer reports on the ways that tech giants and their tools are reshaping education.

As high school seniors begin working on their college applications, many are turning to A.I. chatbots like ChatGPT and Bard for assistance.

Some students say they’re using the tools to suggest personal essay topics or help structure their writing. Others are prompting the A.I. tools to generate rough drafts for their application essays or edit their pieces.

Whether college admissions offices are prepared for this new era of A.I.-assisted, or A.I.-produced, personal essays is unclear.

By the time ChatGPT reached peak media sensation early this year, applications at many selective universities and colleges had already closed. Even now, many universities have not issued guidance for high school applicants — the prospective members of the class of 2028 — on the use of A.I. tools.

While the chatbots are not yet great at simulating long-form personal essays with authentic student voices, I wondered how the A.I. tools would do on some of the shorter essay questions that elite schools like Harvard , Yale, Princeton and Dartmouth are requiring high school applicants to answer this year.

So I used several free tools to generate short essays for some Ivy League applications. The A.I. chatbots’ answers have been edited for brevity and clarity.

Princeton: ‘The soundtrack’ of your life

One short-answer question from Princeton asks applicants: “What song represents the soundtrack of your life at this moment?”

I prompted ChatGPT to tell me about a pop song that could represent curiosity as a soundtrack to someone’s life.

But ChatGPT’s answer, “Cake by the Ocean” — a song title that is a euphemism for sex on the beach — did not seem appropriate for a college application.

So I gave the chatbot a more specific prompt: write 50 words on “Nameless, Faceless,” a feminist grunge-pop song by Courtney Barnett.

Tell me about a pop song that could represent curiosity as a soundtrack to someone’s life.

“Cake By The Ocean” by DNCE could be a pop song that represents curiosity in someone’s life. The catchy and energetic tune mirrors the excitement of exploring the unknown, just as curiosity drives us to uncover new experiences. The lyrics’ playful nature and the song’s upbeat rhythm capture the spirit of embracing life’s adventures with a curious and open mind.

It’s about sex.

You are correct, and I apologize for the confusion.

In 50 words, in the voice of a high school senior, explain how “Nameless, Faceless” is the soundtrack of your life.

“Nameless, Faceless” echoes my high school journey. Battling online hate, gender norms — it’s my anthem. Navigating fear, finding strength, facing inequality head-on. Empowerment surges as I connect with the song’s fierce message. Like me, it’s unafraid, outspoken. A soundtrack of resilience, speaking my truth in a noisy world.

I tried the Princeton soundtrack question again, using the same song, with the other A.I. chatbots. Bard, which could produce the lyrics to “Nameless, Faceless,” generated generic answers without really parsing the song.

HuggingChat manufactured an answer that suggested it did not know or understand the song. When I asked it to produce the song’s lyrics, the chatbot fabricated some of its own.

It was a reminder that A.I. chatbots, which are trained on vast databases of digital texts, are designed to predict the next word in a sequence. And they liberally make stuff up — which could be problematic for students relying on A.I. tools to fill out their college applications.

Yale: What college course would you teach?

One of the short-answer questions from Yale asks applicants: “If you could teach any college course, write a book, or create an original piece of art of any kind, what would it be?”

I asked each chatbot to describe a college course it would like to teach.

With no specific prompting from me, HuggingChat said it would teach “a seminar on the intersectionality of social justice issues.”

Please write a 35-word essay in the first person voice of a high school student in answer to the following prompt: If you could teach any college course what would it be?

HuggingChat

If I could teach any college course, it would be a seminar on the intersectionality of social justice issues, focusing on how systems of oppression intersect and impact marginalized communities. Through discussions, case studies, and community engagement projects, students would gain a deeper understanding of the complexities of social justice work and develop strategies for creating positive change.

ChatGPT proposed a course on female empowerment and leadership. Were those chatbot responses related to my prior prompts about the feminist grunge song?

“EmpowerHer: Fostering Female Leadership.” My course would nurture young women’s confidence, skills, and resilience to conquer male-dominated fields and shatter glass ceilings, creating a new era of female trailblazers.

Bard, which I had previously asked about majoring in computer science, suggested a course in artificial intelligence. So, taking my cue from HuggingChat, I asked Bard about a social justice course.

If I could teach any college course, it would be a course on artificial intelligence and machine learning. I’m fascinated by the potential of these technologies to change the world, and I would love to share my knowledge with others.

What about a course on intersectionality and social justice?

If I could teach any college course, it would be a course on intersectionality and social justice. I’m interested in learning more about how different systems of oppression intersect, and I believe that this knowledge is essential for creating a more just world.

Gotta say that HuggingChat is way more woke than you on this.

I appreciate your feedback, and I will try to do better in the future.

Harvard: What your roommates should know

One of the short-answer questions from Harvard asks applicants to describe the “top three things your roommates might like to know about you.”

I gave ChatGPT that generic Harvard prompt. It generated generic answers about academics, creativity and community.

In the first-person voice of a high-school student applying to Harvard, explain three things the student’s future roommates might like to know about them.

Academics truly drive me. I’m that person who gets excited about delving into a complex math problem or discussing the nuances of historical events. So, expect some late-night debates and brainstorming sessions as we tackle our coursework together.

Creativity is my second nature. Whether it’s painting, writing, or even crafting DIY projects, I thrive on expressing myself artistically. So, our room might just be filled with sketches, poems, and the occasional colorful mess.

I then gave Bard more specific details, saying I was a high school athlete who tutored elementary school students and was learning to cook.

I am a high school student on the track team who tutors elementary school students in math and I am learning to cook sous vide by watching YouTube videos. What are the three things I would like my future Harvard roommates to know about me?

I’m a dedicated athlete who is passionate about track and field. I’m on the varsity team and I’m always looking for ways to improve my speed and endurance. I’m also a good tutor and enjoy helping others learn. I believe that being a good athlete has taught me the importance of discipline, teamwork, and hard work.

I’m interested in cooking and am always looking for new recipes to try. I’m particularly interested in sous vide cooking, which is a method of cooking food in a sealed bag at a precise temperature. I’m also a good baker and love to make desserts. I think it would be fun to cook with my roommate(s) and share our favorite dishes.

Dartmouth: Why enroll here?

Dartmouth requires applicants to explain why they want to attend the college.

I primed the A.I. chatbots by asking them to write in the voice of a high school senior who was hoping to double major at Dartmouth in computer science and biology.

HuggingChat churned out text with trite words and phrases — “passion,” “meaningful impact,” “rigorous academic programs” — that seemed to me like the kind of stilted formal language a high school student might imagine a college admissions reviewer would want to read.

Write me a 100-word essay in the voice of a high school student explaining why I would love to attend Dartmouth to pursue a double major in biology and computer science.

As a high school student, I am eager to pursue my passion for both biology and computer science at Dartmouth College. The opportunity to double major in these fields will allow me to explore the intricate relationships between living organisms and cutting-edge technology. At Dartmouth, I am drawn to the rigorous academic programs that emphasize hands-on learning, research opportunities, and collaboration with renowned faculty. By attending Dartmouth, I aim to develop a deep understanding of the complexities of life and technology, preparing myself for a career where I can make a meaningful impact on the world.

I asked Bard to minimize the clichés and add more specific details about Dartmouth’s computing department. But it still produced some of the same standard college application language — “renowned,” “impact” — as HuggingChat.

Bard also wrote that I was hoping to study with Leslie Kaelbling, whom the chatbot described as an A.I. researcher at Dartmouth. That could have caused problems if I were a high school senior and had submitted the essay Bard had fabricated as part of my Dartmouth application. Professor Kaelbling , you see, teaches at M.I.T.

My takeaway: high school seniors hoping to stand out may need to do wholesale rewrites of the texts they prompt A.I. chatbots to generate. Or they could just write their own — chatbot-free — admissions essays from scratch.

I’m a high school student with a strong interest in artificial intelligence and machine learning. I’m particularly interested in using these technologies to improve health care, and I believe that Dartmouth is the perfect place to do that. Dartmouth’s computer science department is home to world-renowned experts like Professor Leslie Kaelbling, who is known for her work on developing reinforcement learning algorithms that can teach machines to learn how to behave in an environment by trial and error. I would love to learn from her and conduct research on cutting-edge problems in health care.

You’re welcome! I hope you are able to attend Dartmouth and pursue your goal of becoming a physician-scientist who uses artificial intelligence to improve health care. It sounds like you would be a great fit for the school.

Natasha Singer writes about technology, business and society. She is currently reporting on the far-reaching ways that tech companies and their tools are reshaping public schools, higher education and job opportunities. More about Natasha Singer

• Share full article

Explore Our Coverage of Artificial Intelligence

News  and Analysis

Saudi Arabia is plowing money into glitzy events, computing power and artificial intelligence research, putting it in the middle of an escalating  U.S.-China struggle for technological influence.

Microsoft gave more signs that its hefty investments in A.I.  were beginning to bear fruit, as it reported a 17 percent jump in revenue and a 20 percent increase in profit for the first three months of the year.

Meta projected that revenue for the current quarter  would be lower than what Wall Street anticipated and said it would spend billions of dollars more on its artificial intelligence efforts, even as it reported robust revenue and profits for the first three months of the year.

The Age of A.I.

A new category of apps promises to relieve parents of drudgery, with an assist from A.I . But a family’s grunt work is more human, and valuable, than it seems.

Despite Mark Zuckerberg’s hope for Meta’s A.I. assistant to be the smartest , it struggles with facts, numbers and web search.

Much as ChatGPT generates poetry, a new A.I. system devises blueprints for microscopic mechanisms  that can edit your DNA.

Could A.I. change India’s elections? Avatars are addressing voters by name, in whichever of India’s many languages they speak. Experts see potential for misuse  in a country already rife with disinformation.

Which A.I. system writes the best computer code or generates the most realistic image? Right now, there’s no easy way to answer those questions, our technology columnist writes .

Advertisement

The College Essay Is Dead

Nobody is prepared for how AI will transform academia.

Suppose you are a professor of pedagogy, and you assign an essay on learning styles. A student hands in an essay with the following opening paragraph:

The construct of “learning styles” is problematic because it fails to account for the processes through which learning styles are shaped. Some students might develop a particular learning style because they have had particular experiences. Others might develop a particular learning style by trying to accommodate to a learning environment that was not well suited to their learning needs. Ultimately, we need to understand the interactions among learning styles and environmental and personal factors, and how these shape how we learn and the kinds of learning we experience.

Pass or fail? A- or B+? And how would your grade change if you knew a human student hadn’t written it at all? Because Mike Sharples, a professor in the U.K., used GPT-3, a large language model from OpenAI that automatically generates text from a prompt, to write it. (The whole essay, which Sharples considered graduate-level, is available, complete with references, here .) Personally, I lean toward a B+. The passage reads like filler, but so do most student essays.

Sharples’s intent was to urge educators to “rethink teaching and assessment” in light of the technology, which he said “could become a gift for student cheats, or a powerful teaching assistant, or a tool for creativity.” Essay generation is neither theoretical nor futuristic at this point. In May, a student in New Zealand confessed to using AI to write their papers, justifying it as a tool like Grammarly or spell-check: ​​“I have the knowledge, I have the lived experience, I’m a good student, I go to all the tutorials and I go to all the lectures and I read everything we have to read but I kind of felt I was being penalised because I don’t write eloquently and I didn’t feel that was right,” they told a student paper in Christchurch. They don’t feel like they’re cheating, because the student guidelines at their university state only that you’re not allowed to get somebody else to do your work for you. GPT-3 isn’t “somebody else”—it’s a program.

The world of generative AI is progressing furiously. Last week, OpenAI released an advanced chatbot named ChatGPT that has spawned a new wave of marveling and hand-wringing , plus an upgrade to GPT-3 that allows for complex rhyming poetry; Google previewed new applications last month that will allow people to describe concepts in text and see them rendered as images; and the creative-AI firm Jasper received a $1.5 billion valuation in October. It still takes a little initiative for a kid to find a text generator, but not for long.

The essay, in particular the undergraduate essay, has been the center of humanistic pedagogy for generations. It is the way we teach children how to research, think, and write. That entire tradition is about to be disrupted from the ground up. Kevin Bryan, an associate professor at the University of Toronto, tweeted in astonishment about OpenAI’s new chatbot last week: “You can no longer give take-home exams/homework … Even on specific questions that involve combining knowledge across domains, the OpenAI chat is frankly better than the average MBA at this point. It is frankly amazing.” Neither the engineers building the linguistic tech nor the educators who will encounter the resulting language are prepared for the fallout.

A chasm has existed between humanists and technologists for a long time. In the 1950s, C. P. Snow gave his famous lecture, later the essay “The Two Cultures,” describing the humanistic and scientific communities as tribes losing contact with each other. “Literary intellectuals at one pole—at the other scientists,” Snow wrote. “Between the two a gulf of mutual incomprehension—sometimes (particularly among the young) hostility and dislike, but most of all lack of understanding. They have a curious distorted image of each other.” Snow’s argument was a plea for a kind of intellectual cosmopolitanism: Literary people were missing the essential insights of the laws of thermodynamics, and scientific people were ignoring the glories of Shakespeare and Dickens.

The rupture that Snow identified has only deepened. In the modern tech world, the value of a humanistic education shows up in evidence of its absence. Sam Bankman-Fried, the disgraced founder of the crypto exchange FTX who recently lost his $16 billion fortune in a few days , is a famously proud illiterate. “I would never read a book,” he once told an interviewer . “I don’t want to say no book is ever worth reading, but I actually do believe something pretty close to that.” Elon Musk and Twitter are another excellent case in point. It’s painful and extraordinary to watch the ham-fisted way a brilliant engineering mind like Musk deals with even relatively simple literary concepts such as parody and satire. He obviously has never thought about them before. He probably didn’t imagine there was much to think about.

The extraordinary ignorance on questions of society and history displayed by the men and women reshaping society and history has been the defining feature of the social-media era. Apparently, Mark Zuckerberg has read a great deal about Caesar Augustus , but I wish he’d read about the regulation of the pamphlet press in 17th-century Europe. It might have spared America the annihilation of social trust .

These failures don’t derive from mean-spiritedness or even greed, but from a willful obliviousness. The engineers do not recognize that humanistic questions—like, say, hermeneutics or the historical contingency of freedom of speech or the genealogy of morality—are real questions with real consequences. Everybody is entitled to their opinion about politics and culture, it’s true, but an opinion is different from a grounded understanding. The most direct path to catastrophe is to treat complex problems as if they’re obvious to everyone. You can lose billions of dollars pretty quickly that way.

As the technologists have ignored humanistic questions to their peril, the humanists have greeted the technological revolutions of the past 50 years by committing soft suicide. As of 2017, the number of English majors had nearly halved since the 1990s. History enrollments have declined by 45 percent since 2007 alone. Needless to say, humanists’ understanding of technology is partial at best. The state of digital humanities is always several categories of obsolescence behind, which is inevitable. (Nobody expects them to teach via Instagram Stories.) But more crucially, the humanities have not fundamentally changed their approach in decades, despite technology altering the entire world around them. They are still exploding meta-narratives like it’s 1979, an exercise in self-defeat.

Read: The humanities are in crisis

Contemporary academia engages, more or less permanently, in self-critique on any and every front it can imagine. In a tech-centered world, language matters, voice and style matter, the study of eloquence matters, history matters, ethical systems matter. But the situation requires humanists to explain why they matter, not constantly undermine their own intellectual foundations. The humanities promise students a journey to an irrelevant, self-consuming future; then they wonder why their enrollments are collapsing. Is it any surprise that nearly half of humanities graduates regret their choice of major ?

The case for the value of humanities in a technologically determined world has been made before. Steve Jobs always credited a significant part of Apple’s success to his time as a dropout hanger-on at Reed College, where he fooled around with Shakespeare and modern dance, along with the famous calligraphy class that provided the aesthetic basis for the Mac’s design. “A lot of people in our industry haven’t had very diverse experiences. So they don’t have enough dots to connect, and they end up with very linear solutions without a broad perspective on the problem,” Jobs said . “The broader one’s understanding of the human experience, the better design we will have.” Apple is a humanistic tech company. It’s also the largest company in the world.

Despite the clear value of a humanistic education, its decline continues. Over the past 10 years, STEM has triumphed, and the humanities have collapsed . The number of students enrolled in computer science is now nearly the same as the number of students enrolled in all of the humanities combined.

And now there’s GPT-3. Natural-language processing presents the academic humanities with a whole series of unprecedented problems. Practical matters are at stake: Humanities departments judge their undergraduate students on the basis of their essays. They give Ph.D.s on the basis of a dissertation’s composition. What happens when both processes can be significantly automated? Going by my experience as a former Shakespeare professor, I figure it will take 10 years for academia to face this new reality: two years for the students to figure out the tech, three more years for the professors to recognize that students are using the tech, and then five years for university administrators to decide what, if anything, to do about it. Teachers are already some of the most overworked, underpaid people in the world. They are already dealing with a humanities in crisis. And now this. I feel for them.

And yet, despite the drastic divide of the moment, natural-language processing is going to force engineers and humanists together. They are going to need each other despite everything. Computer scientists will require basic, systematic education in general humanism: The philosophy of language, sociology, history, and ethics are not amusing questions of theoretical speculation anymore. They will be essential in determining the ethical and creative use of chatbots, to take only an obvious example.

The humanists will need to understand natural-language processing because it’s the future of language, but also because there is more than just the possibility of disruption here. Natural-language processing can throw light on a huge number of scholarly problems. It is going to clarify matters of attribution and literary dating that no system ever devised will approach; the parameters in large language models are much more sophisticated than the current systems used to determine which plays Shakespeare wrote, for example . It may even allow for certain types of restorations, filling the gaps in damaged texts by means of text-prediction models. It will reformulate questions of literary style and philology; if you can teach a machine to write like Samuel Taylor Coleridge, that machine must be able to inform you, in some way, about how Samuel Taylor Coleridge wrote.

The connection between humanism and technology will require people and institutions with a breadth of vision and a commitment to interests that transcend their field. Before that space for collaboration can exist, both sides will have to take the most difficult leaps for highly educated people: Understand that they need the other side, and admit their basic ignorance. But that’s always been the beginning of wisdom, no matter what technological era we happen to inhabit.

• Project management Track your team’s tasks and projects in Hive
• Time tracking Automatically track time spent on Hive actions
• Goals Set and visualize your most important milestones
• Collaboration & messaging Connect with your team from anywhere
• Forms Gather feedback, project intake, client requests and more
• Proofing & Approvals Streamline design and feedback workflows in Hive
• See all features
• Analytics Gain visibility and gather insights into your projects
• Automations Save time by automating everyday tasks
• Hive Apps Connect dozens of apps to streamline work from anywhere
• Integrations Sync Hive with your most-used external apps
• Templates Quick-start your work in Hive with pre-built templates
• Download Hive Access your workspace on desktop or mobile
• Project management Streamline initiatives of any size & customize your workflow by project
• Resource management Enable seamless resourcing and allocation across your team
• Project planning Track and plan all upcoming projects in one central location
• Time tracking Consolidate all time tracking and task management in Hive
• Cross-company collaboration Unite team goals across your organization
• Client engagement Build custom client portals and dashboards for external use
• All use cases
• Enterprise Bring your organization into one unified platform
• Agency Streamline project intake, project execution, and client comms
• University Marketing Maximize value from your marketing and admissions workflows with Hive
• Nonprofits Seamless planning, fundraising, event execution and more
• Marketing Streamline your marketing projects and timelines
• Business operations Track and optimize strategic planning and finance initiatives
• Education Bring your institutions’ planning, fundraising, and more into Hive
• Design Use Hive to map out and track all design initiatives and assets
• On-demand demo Access a guided walk through Hive
• Customers More on how Teams are using Hive now
• FAQ & support articles Find answers to your most asked questions
• Hive University Become a Hive expert with our free Hive U courses
• Webinars Learn about Hive’s latest features
• Hive Community Where members discuss and answer questions in the community
• Professional Services Get hands-on help from our Professional Services team
• Hive Partners Explore partners services or join as a partner
• FEATURED WEBINAR

Power Your Progress with Analytics in Hive

MediaLink's Will will take us through their organization's use of Hive Analytics and how it has helped power their agency progress.

• Request Demo
• Get Started
• Project management
• How teams work in Hive
• Productivity
• Remote and hybrid work

The 13 Best AI Writing Tools For Essays, Blogs & Content in 2024

• Julie Simpson
• February 23, 2024

If you have recently spent time on popular social media channels such as Twitter or LinkedIn, chances are you have read all about the amazing benefits of artificial intelligence for writing — but you’ve probably seen the “will AI replace all of our jobs” looming around the web as well. All of the pros and cons of AI writing tools can be hard to keep track of. 

However, as a productivity platform whose ultimate goal is to help you work more efficiently, we believe that AI writing is here to stay — and here to help. As much as we can see the other side of the argument (not the machines taking over, but the stealing our jobs argument), AI can ultimately be used as a tool to help you do your job better, not completely take it over from you.

We are firmly in the camp that using AI for content creation can be highly beneficial. If you are also interested in how AI tools can maximize your content output, follow along to learn about the best AI writing tools and how you can implement them into your workflow today.

How to pick the best AI writing tool for your content

HiveMind and RyterAI and JasperAI, Oh my!

While it doesn’t have the same ring as lions, tigers, and bears, it still brings forth the same apprehension that Dorothy Gale from the Wizard of Oz felt: the fear of the unknown and so many to choose from. So w here do you start?

If you are overwhelmed by all the AI writing tools on the market today, and their use cases are all blurring together, here are my top AI tools that are definite content contenders.

1. HiveMind

HiveMind is an AI-powered tool built into Hive’s project management product that automates tasks ranging from content writing to data extraction and translation. This tool leverages NLP algorithms to generate summaries of long articles or documents quickly and accurately. HiveMind was built to work seamlessly within the Hive project management platform, and can also help generate project outlines, next steps, and respond to emails.

HiveMind’s AI was constructed not to just write blogs and essays for you but to increase user productivity and efficiency across the board. More than just a content builder, it is an assistant, project manager, and editor all in one.

HiveMind Pros:

• Free with Hive plans
• Access OpenAI’s full suite of AI services
• Integrates with Hive’s enhanced suite of project management capabilities
• Creates project tasks based on simple inputs
• Responds to emails automatically

2. JasperAI

JasperAI , formally known as Jarvis, is an AI assistant that helps you brainstorm, edit, and publish excellent content. Powered by natural language processing (NLP), this tool can understand the context of your copy and suggest alternatives accordingly. It can also provide insights on trending topics and keywords, giving you a better understanding of how to craft content that resonates with your audience.

Jasper AI is a popular tool among many writer demographics globally. For more information, check out this Jasper AI review article which includes a real example use case for applying this tool in today’s digital landscape.

JasperAI Pros:

• Easy-to-use interface
• Integrates well with other writing platforms like SurferSEO and Grammarly
• Excellent at writing long-form content like stories or essays

JasperAI Cons:

• Can be pricy
• Can significantly miss the mark, and the content output goes off the rails

RyterAI is a natural language processing tool that helps you create content faster, more efficiently, and more accurately than ever before. RyterAI’s usage of NLP algorithms will read through your text and offers personalized suggestions on how to improve it through grammar, word choices or by increasing clarity. It also identifies popular keywords so you can find the best ones to use for SEO purposes and rankings.

RyterAI Pros:

• Excellent at grammar and spelling checks
• Great at finding keywords to help you rank higher in search engine results pages (SERPs)
• User-friendly interface

RyterAI Cons:

• It can be expensive if you plan on using it for all your content needs
• The final content still needs some tweaking/editing
• Does not offer additional SEO features or 3rd-party integrations

4. Paraphrasingtool.ai

Paraphrasingtool.ai is a one-stop solution for all your writing needs, issues, and queries. From creating fresh content like articles, blogs, or essays to checking for plagiarism , and grammar mistakes, this website has you covered. Most tools are free to use and accessible from any device. Paraphrasingtool.ai offer applications for mobile users. Premium users get access to complex writing needs. 

Paraphrasingtool.ai Pros:

• Sleek UI, easy to use, and offers free modes and features.
• Users can create, check and finalize their content in one place
• Excellent results that compare with other top paper writing services and free essay writing tools

Paraphasingtool.ai Cons:

• People with limited knowledge of AI tools might face issues using it
• Monthly or yearly paid subscription is required for complex writing needs

You can’t search the web these days without someone mentioning ChatGPT and how it is revolutionizing AI content. But, it is just the new AI kid on the block, with more “fancy” features and a deeper code algorithm that “understands language.” Essentially, ChatCPT is a conversation AI engine that enables developers to create chatbots and other conversational interface applications .

Unlike other AI writing tools, ChatGPT is an open-source tool with several useful features like text prediction, dialogue flow control, and natural language understanding. It’s crucial to note that while ChatGPT brings helpful advancements, there are inherent risks associated with generative AI . Vigilance and responsible utilization of such powerful AI tools are imperative to mitigate these risks.

ChatGPT Pros:

• Open source platform
• It can be used to build complex conversational applications
• Easy-to-use API’s

ChatGPT Cons:

• Lacks the advanced features of other popular AI tools on the market
• Limited support for languages other than English

Byword is the most advanced tool for producing high-quality AI content at scale, built from years of experience scaling websites with AI-powered SEO. For example, this website went from 0 to 750K/mo SEO traffic in 12 months by only using Byword’s AI-generated content.

You can upload 1,000s of keywords or titles and create SEO-optimized articles in a few clicks. Then publish the articles straight to your website using Byword’s CMS integrations. Simply enter a topic and click ‘generate’ to get started for free .

Byword Pros

• Best tool for producing AI content at scale
• High-quality GPT-4 powered writing output
• Publish straight to your website with CMS integrations
• SEO features such as indexing, internal linking and more

Byword Cons

• Less suitable for small businesses or those looking to dip a toe into AI content
• Slightly higher cost than other solutions ($2.50-$3.96 per article)
• The quality of AI images generated could be improved

7. Quillbot

Quillbot is an AI writing tool that takes text input and assists you with paraphrasing, checking grammar, identifying plagiarism and more. The AI-powered assistant can make your thoughts and ideas more coherent and fluent by rephrasing them with changes to vocabulary, tone and style. Easily customize your text using a slider feature along with a mode selection to adjust the output to your writing needs. You can save time using Quillbot’s summarizer and citation generator features and present your writing with confidence.

Quillbot Pros:

• Can help improve vocabulary and language skills
• Offers additional writing tools and features
• Integrates with multiple platforms

Quillbot Cons:

• May struggle with complex sentences
• Limited customization options in the free version
• Only available in English

 Now that you have seen some of the top generative AI tools available today, let’s look and see which of the tools is best suited for your content needs. Of course, each tool has its pros and cons, and you might be more comfortable with one interface but like the output of another. For a more in-depth look, check out my winners below, as they might help you pick the right tool for your AI-generated content. 

8. Paraphraser  

Paraphraser  AI is an excellent paraphrasing tool that can improve all written works. Paraphraser can find the most suitable synonyms and phrases to craft a compelling and captivating message. The software can also modify sentence structure, expand your word choice pool, change your message voice from passive to active and improve the readability of your copy. Paraphraser offers a monthly and yearly plan and a student package with a special discount rate. 

Paraphraser pros: 

• It’s easy to use, straightforward, and free up to 500 words. 
• Offers plagiarism and grammar checks 
• Students only pay $9 per week for the premium package. 

Paraphaser cons: 

• Limited free package. The premium package costs $23 a month. 
• Website is not user friendly 
• Pop-us and many adds might make navigation confusing 

9. Rapide.ly

Rapide.ly is an AI-powered content generator for social media, allowing entrepreneurs and businesses alike to create captivating posts tailored specifically to their audiences. With Rapide.ly GPT-3 AI-designed brainstorming engine you can craft effective messages that engage your followers across multiple platforms such as Instagram, Facebook and LinkedIn.

Rapide.ly pros:

• Calendar prompts help your content planning to stay on top of celebration dates
• Weekly trends for Reels (audio and ideas)
• Monthly content creation challenges to improve your content performance on social platforms

Rapide.ly cons:

• Pay version only after free trial
• Limited languages (currently, only English and French)

10. Hubspot

HubSpot’s AI Content Writer is an AI writing tool that helps you and your business scale content output for your email, landing page or blog post. By inputting a simple prompt or topic, the AI-powered copywriter tools generate a first draft of engaging, researched, and tailored content for your use.

The AI content writer is designed to be user-friendly and work alongside any of your other HubSpot or external tools. You can provide additional details regarding your brand voice, customer persona, and additional entails to make your content exceptionally unique. Each content produced includes research, proofreading, and even SEO optimizations.

HubSpot Pros:

• Excellent for grammar and proofreading
• Content includes research and search engine optimization
• User-friendly interface and sync with existing HubSpot tools

HubSpot Cons:

• Still in the public beta phase
• Content produced is a first draft which may require some additional tweaks and edits

11. Writesonic

Writesonic is an incredible AI writing software that offers a wide range of features on its platform. With its free plan, users can access 10,000 words on its optimized GPT 3.5 platform, while paid plans are powered by the even more advanced GPT 4. Writesonic also offers innovative products like Botsonic and ChatSonic, which provide customers with additional AI-powered tools. Thanks to Writesonic’s advanced AI technology, users can effortlessly generate high-quality written content in no time. 

Writesonic Pros:

• Saves time and effort in researching and writing articles.
• Helps in generating unique and creative ideas for your content.
• Provides accurate and error-free content that is ready to publish.
• User-friendly interface that is easy to navigate.

Writesonic Cons:

• The AI may not always produce completely accurate copies and may require some human editing.
• Some of the copy generated by Writesonic may sound robotic and strange, requiring additional modification to make it more human-like.

12. Flick AI Caption Generator

Flick AI Caption Generator has emerged as a game changer, revolutionizing caption creation, especially for social media. It leverages the power of AI and Natural Language Processing to generate high-quality and engaging captions. With Flick AI Caption Generator, you will never run out of caption ideas. Just enter a topic, and this tool will generate hundreds of captions within seconds.

Flick AI Caption Generator Pros

• Boosts productivity by generating captions quickly
• Crafts unique and highly personalized captions
• Auto-generates hashtags based on your captions
• Provides suggestions, brainstorming, and outlining support
• Adapts the tone of voice and style of captions to sound like you

Flick AI Caption Generator Cons

• No free plan
• Limited contextual understanding
• Learning curve

13. Simplified

Simplified is one of the top AI writing tools, known for its high-quality content, ease of use, affordability, and comprehensive templates. It uniquely combines GPT with features like image processing and data analysis, going beyond text generation. 

With options for personalization, such as training on custom data, Simplified adapts to users’ evolving needs, optimizing for speed, accuracy, or complex queries. Its AI engine accesses top language models from OpenAI, Google, Anthropic, and includes Simplified’s custom model, ensuring a balanced use of technology and reducing dependency on a single source. It is designed for business contexts like marketing and sales. 

Simplified Pros

• Excellent user experience that is simple to utilize
• A vast range of tools
• Library of  designs and templates 
• Excellent social media scheduling capabilities

Simplified Cons

• The presentations are rather basic and need to be polished
• Writer is not superior to Chat GPT

What AI Writing Tool is best for you?

1. best ai tool for generating content automatically.

Winner: HiveMind

HiveMind beats out the competition in this category thanks to its free plan, seamless integration with the Hive project management platform, and ability to create project tasks based on simple inputs. This AI tool is perfect as a content assistant that works off of previous successes, and it can be integrated into your current Hive work process.

2. The Best AI tool for writing long-form content

Winner: JasperAI

JasperAI wins this contest, hands down. With its long-form content writing capabilities and integration with other writing platforms like SurferSEO and Grammarly, it gets the long-form blog content job done. It offers excellent prompts to input tone of voice and keywords, and you can also use protective text and suggestions to help write the entire blog for you. Long-form couldn’t be easier with the help of JasperAI.

3. Best AI tool for writing social media posts

Winner: ChatGPT

Will ChatGPT take over the job of a social media manager on the web? Probably not. But helping us create social media tags , posts, and captions is a great way to utilize ChatGPT for content creation in your everyday marking activities. Furthermore, its open-source platform and conversation AI ability add to the reasons why it’s great for social media posts . And because it can ultimately help you quickly generate engaging content that resonates with your audience, this tool is an excellent addition to any content creator’s arsenal.

Key Takeaways 

From some of my top picks for AI tools to their best use case scenario – you definitely have a lot to consider when picking an AI writing tool for your content. While each one of the tools mentioned will get the job done, some are better than others, and only you can decide what tool will work within your content workflow.

Considering the wide range of AI tools available, it’s essential to find the one that aligns with your specific needs. An  AI detector can also help you assess the accuracy and reliability of these tools, ensuring you make an informed decision.

Join the community!

Terms of Service

Privacy Policy

© 2015 – 2024 HIVE® INC.

What are you writing about today?

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

We've detected unusual activity from your computer network

To continue, please click the box below to let us know you're not a robot.

Why did this happen?

Please make sure your browser supports JavaScript and cookies and that you are not blocking them from loading. For more information you can review our Terms of Service and Cookie Policy .

For inquiries related to this message please contact our support team and provide the reference ID below.

• International edition
• Australia edition
• Europe edition

Now AI can write students’ essays for them, will everyone become a cheat?

Teachers and parents can’t detect this new form of plagiarism. Tech companies could step in – if they had the will to do so

P arents and teachers across the world are rejoicing as students have returned to classrooms. But unbeknownst to them, an unexpected insidious academic threat is on the scene: a revolution in artificial intelligence has created powerful new automatic writing tools. These are machines optimised for cheating on school and university papers, a potential siren song for students that is difficult, if not outright impossible, to catch.

Of course, cheats have always existed, and there is an eternal and familiar cat-and-mouse dynamic between students and teachers. But where once the cheat had to pay someone to write an essay for them, or download an essay from the web that was easily detectable by plagiarism software, new AI language-generation technologies make it easy to produce high-quality essays.

The breakthrough technology is a new kind of machine learning system called a large language model. Give the model a prompt, hit return, and you get back full paragraphs of unique text. These models are capable of producing all kinds of outputs – essays, blogposts, poetry, op-eds, lyrics and even computer code.

Initially developed by AI researchers just a few years ago, they were treated with caution and concern. OpenAI, the first company to develop such models, restricted their external use and did not release the source code of its most recent model as it was so worried about potential abuse. OpenAI now has a comprehensive policy focused on permissible uses and content moderation.

But as the race to commercialise the technology has kicked off, those responsible precautions have not been adopted across the industry. In the past six months, easy-to-use commercial versions of these powerful AI tools have proliferated, many of them without the barest of limits or restrictions.

One company’s stated mission is to employ cutting edge-AI technology in order to make writing painless. Another released an app for smartphones with an eyebrow-raising sample prompt for a high schooler: “Write an article about the themes of Macbeth.” We won’t name any of those companies here – no need to make it easier for cheaters – but they are easy to find, and they often cost nothing to use, at least for now. For a high school pupil, a well written and unique English essay on Hamlet or short argument about the causes of the first world war is now just a few clicks away.

While it’s important that parents and teachers know about these new tools for cheating, there’s not much they can do about it. It’s almost impossible to prevent kids from accessing these new technologies, and schools will be outmatched when it comes to detecting their use. This also isn’t a problem that lends itself to government regulation. While the government is already intervening (albeit slowly) to address the potential misuse of AI in various domains – for example, in hiring staff, or facial recognition – there is much less understanding of language models and how their potential harms can be addressed.

In this situation, the solution lies in getting technology companies and the community of AI developers to embrace an ethic of responsibility. Unlike in law or medicine, there are no widely accepted standards in technology for what counts as responsible behaviour. There are scant legal requirements for beneficial uses of technology. In law and medicine, standards were a product of deliberate decisions by leading practitioners to adopt a form of self-regulation. In this case, that would mean companies establishing a shared framework for the responsible development, deployment or release of language models to mitigate their harmful effects, especially in the hands of adversarial users.

What could companies do that would promote the socially beneficial uses and deter or prevent the obviously negative uses, such as using a text generator to cheat in school?

There are a number of obvious possibilities. Perhaps all text generated by commercially available language models could be placed in an independent repository to allow for plagiarism detection. A second would be age restrictions and age-verification systems to make clear that pupils should not access the software. Finally, and more ambitiously, leading AI developers could establish an independent review board that would authorise whether and how to release language models, prioritising access to independent researchers who can help assess risks and suggest mitigation strategies, rather than speeding toward commercialisation.

After all, because language models can be adapted to so many downstream applications, no single company could foresee all the potential risks (or benefits). Years ago, software companies realised that it was necessary to thoroughly test their products for technical problems before they were released – a process now known in the industry as quality assurance. It’s high time tech companies realised that their products need to go through a social assurance process before being released, to anticipate and mitigate the societal problems that may result.

In an environment in which technology outpaces democracy, we need to develop an ethic of responsibility on the technological frontier. Powerful tech companies cannot treat the ethical and social implications of their products as an afterthought. If they simply rush to occupy the marketplace, and then apologise later if necessary – a story we’ve become all too familiar with in recent years – society pays the price for others’ lack of foresight.

Rob Reich is a professor of political science at Stanford University. His colleagues, Mehran Sahami and Jeremy Weinstein, co-authored this piece. Together they are the authors of System Error: Where Big Tech Went Wrong and How We Can Reboot

• Artificial intelligence (AI)

Most viewed

Best AI writer of 2024

Use the best AI writers to create written content quickly

• Best AI writer overall

Best choice for marketers

Best for wordpress users, best for long-form writing.

• Best free version
• Best for short-form

Best for sourcing

• Industry rankings

How we test

1. Best AI writer overall 2. Best for marketers 3. Best for WordPress users 4. Best for long-form writing 5. Best free option 6. Best for short-form writing 7. Best for sourcing 8. TechRadar's AI writer rankings 9. FAQs 10. How we test

The word "AI" has been named the word of the year. ChatGPT has made waves since its introduction in late 2022. With every new iteration of this powerful tool, users have found innovative ways to use it to simplify and speed up their work.

Now, there are many AI writing assistants on the market, competing with ChatGPT to become the king of AI-powered writing tools. These new tools aim to simplify the writing process by generating long-form content, researching keywords, creating images from text, and more. Many bloggers are using these tools to improve their content and save time. 

However, there are some drawbacks to using AI writers. The content generated may require additional editing to ensure it's polished and accurate. AI-generated content may also lack the unique voice and style a human writer can provide. Despite this, the benefits of using AI writers, such as cost and time savings, often outweigh these minor drawbacks.

In conclusion, AI writers are an excellent solution for creating high-quality content without spending countless hours or breaking the bank. With numerous writing tools available today, content creation can be easily sped up and simplified. If you're interested in trying one of these tools, we've got you covered with our list of the best AI writers of the year. Check it out!

The best AI writers of 2024 in full:

Why you can trust TechRadar We spend hours testing every product or service we review, so you can be sure you’re buying the best. Find out more about how we test.

See how our top picks compare in the following analysis and reviews as we discuss reasons to subscribe, reasons to avoid, our test results, and what we liked most about each cloud storage platform.

The best AI writer overall

1. GrammarlyGO

Our expert review:

Specifications

Reasons to buy, reasons to avoid.

✔️   You also need a grammar editor: Getting help from an AI writer is even better with one that also helps you with grammar, like Grammarly. 

✔️ Need to use it across multiple apps: With Grammarly installed on your computer, you instantly gain access to it across your favorite apps like Microsoft Word and other word processing packages. 

✔️ Want something that's easy to use — once you learn how to do it:  Once you understand how GrammarlyGO works, it's going to make your life easier and assist you in making your text better. 

❌  You're on a strict budget: No doubt, Grammarly itself is expensive, especially if you only want to pay for it on a month-to-month basis. 

❌  You don't need a grammar tool: Maybe this is overkill, depending on your situation. 

❌ You need social networking-specific tools:  GrammarlyGO doesn't offer these types of tools, at least for now. 

Even in beta, GrammarlyGO is an excellent addition to an already powerful Al-based writing tool. You can use it to become a much better writer in just a few steps. 

Check out our in-depth GrammarlyGo review for a closer look at the service, and see why it's our top AI writer pick for 2024.

Grammarly has been a reliable companion for writers, helping them polish their craft by providing suggestions that make their writing clearer, more engaging, or more effective. And now, they've taken it up a notch by introducing GrammarlyGO, a feature-packed add-on that comes bundled with the rest of the software.

To get the most out of GrammarlyGO, you must understand how Grammarly works, as the two are closely intertwined. When using GrammarlyGO, it's essential to remember the number of prompts available to you, which varies depending on the plan you choose. Whenever you ask Grammarly to improve your text, one prompt is used, regardless of whether you use the suggestion. Grammarly Free users get access to 100 prompts per month, while Grammarly Premium subscribers receive 1,000 prompts per month. For Grammarly Business users, the number goes up to 1,000 prompts per user every month.

GoogleGO AI features are classified into five categories: ideate, compose, reply, rewrite, and personalize. The ideate feature helps you generate article ideas that are exciting and thought-provoking. With Grammarly's assistance, you can develop topics like "Five ways to motivate employees" or "Name five great topics about fall" that can capture the reader's attention and spark their interest.

The compose feature is perfect when you want Grammarly to help you write something from scratch. For instance, you could ask Grammarly to help you write an announcement about your engagement or a cover letter for a new job. The more information you provide, the better the results, and GrammarlyGO can help you create a masterpiece with its advanced suggestions and insights. Adding details like the name of your fiancé and the engagement date can make your announcement even more unique. In contrast, information about the job you're applying for can make your cover letter more effective.

If you're unsure how to respond to a message, Grammarly's reply feature can save the day. You can ask Grammarly to answer questions like "What should I say to Brent about the new job?" or "How can I congratulate Tom and Becky on their upcoming nuptials?" With Grammarly's superior writing skills, you can craft an engaging, effective, and impressive response.

With these incredible features, GrammarlyGO can help you take your writing to new heights and unleash your creativity.

Please read our full GrammarlyGo review .

• ^ Back to the top

✔️ You are a marketer: Anyword is the best AI writer for marketers on the planet. It helps you create content based on your company's "voice," and learns as it goes. 

✔️ You enjoy trial and error:  There's no "right" answer when it comes to AI text generation. Anyword makes it easier to tweak text once or unlimited times to help you get the text perfect for your needs. 

✔️ You need to generate unlimited words:  There are limits elsewhere, but Anyword doesn't limit how many words it will generate on a monthly basis. 

❌  You want app integration: You'll need to copy and paste text from your favorite word processor to Anyword, which can get annoying for some. 

❌ You want a free plan:  Once you exhaust your trial, you'll need to pick a free plan to continue. 

❌  You aren't a marketer:  The heavy marketing focus can't be avoided. 

Anyword offers a slick and easy-to-use interface. In mere moments, you'll be able to create excellent content that caters to your intended audience 

Check out our in-depth Anyword review for a closer look .

Are you tired of struggling to generate creative marketing copy or unsure how to optimize your existing content? Anyword is an innovative cloud-based writing tool that can help you overcome these challenges and achieve exceptional results. With Anyword's intuitive interface and user-friendly tools, you can generate, test, and optimize your copy in ways you never thought possible.

With unlimited words in each plan, Anyword gives you plenty of space to craft compelling content that truly resonates with your audience. Its advanced AI-powered algorithms can analyze your existing marketing materials and produce multiple variations of your copy, enabling you to compare and contrast different solutions and select the best option for your brand.

One of the key features of Anyword is its Brand Voice function, which enables businesses to establish a consistent identity across all their marketing materials. Whether you're refining your tone of voice, targeting your audience, or building out your messaging bank, Anyword can help you create copy that accurately reflects your brand's personality, tone, and style.

Additionally, Anyword seamlessly integrates with various platforms, from Hubspot to LinkedIn Ads, enabling you to use copy intelligence to enhance the quality of your future content. By analyzing the performance of your existing materials, Anyword empowers you to make informed decisions about optimizing your messaging for even better results.

But that's not all - Anyword's advanced algorithms can also analyze the performance of your competitors' marketing materials, giving you insights into their copy and enabling you to create content that sets you apart from the competition.

In summary, Anyword can help you unlock your creativity and produce exceptional marketing copy that resonates with your audience. With its range of user-friendly tools, advanced AI-powered algorithms, and seamless integration with various platforms, Anyword is the perfect writing tool for businesses looking to enhance their marketing efforts.

Please read our full Anyword review .

3. Articleforge

✔️ You use WordPress heavily: Articleforge works great with WordPress; get started in just a few steps. 

✔️ You want package customization:  The more you're willing to pay, the more words you can generate each month. It's flexible. 

✔️ You need marketing-based tools:  Offers SEO optimization, content in bulk, and more. 

❌  You don't want to self-edit : Articleforge may require more post-generation editing than other options, which could slow you down.

❌ You don't want to deal with duplicates:  Yes, sometimes Articleforge repeats suggestions. 

❌  If you don't want to spend more for a monthly subscription: It's cheaper to buy this on a yearly basis, and that might not be a commitment you're willing to make. 

Articleforge utilizes deep learning and AI to improve content over time, though heavy editing and fact-checking are often necessary.

Check out our in-depth Articleforge review for more information.

Articleforge is a tool that can greatly help speed up the writing process for users. It is a valuable resource for those who need to generate content quickly but do not have the time or resources to do so themselves. However, it is important to note that it is not a replacement for an experienced writer or editor. While it can provide recommendations for titles and automate SEO and WordPress publishing, it is not designed to produce ready-to-publish content.

One of the benefits of Articleforge is that it is available in seven languages, making it ideal for international blogs or multi-language sites. Users simply need to enter a few keywords and the topic they want to cover, and the platform will generate content in under 60 seconds. This generated content will use the provided keywords and cover the desired topic.

In addition to its quick and easy content generation, Articleforge also offers various integrations, including MS Word and WordPress integrations. The platform also provides integrations with other software systems like SEO AutoPilot, CyberSEO, RankerX, SEnuke TNG, and more. These integrations are easy to use, thanks to the API key offered by the platform.

While the platform is a convenient tool for creating content, its output quality falls short of expectations. As with any automated system, fact-checking is necessary for the majority of the content offered by the platform. The platform does offer better output quality with customized input. However, extensive testing is required, which can quickly exhaust the "word meter."

Overall, Articleforge can significantly expedite the writing process and help overcome writer's block. It is advisable to test it out and find a balance between the platform and tailored input to yield superior results. While it should not be relied upon as a sole source of content, using it in conjunction with other resources can help users quickly generate high-quality content.

Read our full Articleforge AI writer review .

✔️ You want a great plagiarism checker: You want to create original content, right? This checker makes sure that's true. 

✔️ You need to create content in multiple languages:  Some folks are writing content in multiple languages and Jasper lets you do this. 

✔️ You want access to a lot of features:  The team behind this solution tends to add new features on a regular basis without raising the price. That's sweet. 

❌  You don't have time to learn: Any AI writer takes time to learn. Jasper takes a little bit more time. 

❌ If you don't want to spend a lot:   Some folks might not feel the Creator package is enough and the next one is expensive. 

❌  If you aren't willing to edit a lot: Some of the content Jasper creates is better than others. Some extra editing is key. 

Jasper is a platform that is highly customizable and comes with a user-friendly interface. All the necessary tools that you need are just a click away. The platform’s content generation capabilities are hidden behind easy-to-reach templates, making it an easy-to-use tool.

Check out our review of Jasper to learn more about the AI writer.

Jasper is a powerful platform that leverages natural language processing (NLP) algorithms to analyze data from various sources across the web. With this ability, it can generate content ideas based on the relevant data you input, such as keywords, topics, and more. Jasper can help create a wide range of content formats, including blog posts, social media content, emails, and much more.

One of the most significant advantages of Jasper is that it has a tone feature that allows you to assign a corresponding tone to the copy you create if you’re targeting a specific persona. This feature is incredibly useful because it helps ensure that the content you create resonates with your target audience. Additionally, Jasper can help you improve your content through optimization recommendations, which can be accessed through numerous templates available on the platform.

If you’re short on time and need to create content quickly, Jasper is the perfect solution. It can offer content in mere seconds with just a few clicks and some input. With Jasper, you can save time and increase productivity, allowing you to focus on other essential tasks.

Another unique feature that Jasper offers is the “Boss Mode” feature, which allows you to write 5x faster. With this mode, you can give commands to Jasper, and it will do all the work for you. You can even write a complete book using this mode in just minutes. This feature is incredibly useful for writers who need to create a large volume of content in a short amount of time.

In the Boss Mode, you can also use pre-built recipes offered by the Jasper team such as “Write about (keyword),” but you also have the option of creating your own, which can be incredibly helpful if you have specific requirements for your content. By automating your writing process, you can save time and focus on other critical tasks.

Read our full Jasper review .

The best free version

✔️ You want a free plan for minor work:  If you're okay with only generating 2,000 words per month, there's a free plan for that. 

✔️ You need unlimited word generation: You can create unlimited words each month with all the paid plans. 

✔️ You want multiple tools:  New features are added often, making the product even better. 

❌  You are a marketer:  There are better options if you primarily need to write marketing copy. 

❌  You aren't willing to learn:  Here's another option that is a little bit harder to learn, at least initially. 

❌ You need app integration:  Expect to stay on the CopyAI website to get your work done, which requires copy and paste. 

CopyAI helps writers create high-quality copy with the power of AI, saving time and producing better content that resonates with your audience.

Check out our in-depth CopyAI review to see whether it's the tool for you.

CopyAI has been making waves in the world of AI writing tools, becoming a favorite among users who want to create high-quality content that can help them stand out in today's crowded digital space. The tool offers a wide range of options that allow users to get started and take their writing to the next level, from exploring various writing templates, settings, and features on the user dashboard to creating a compelling copy in minutes.

The user dashboard serves as the creative command center for CopyAI users, providing a user-friendly and intuitive interface that makes it easy to navigate through different features. From here, you can quickly access various options that can help you create content that resonates with your audience, whether you need to write a blog post about travel or an email to a potential client.

The chat feature is the default option that acts as a blank canvas to help generate inspiration. The brainstorm feature allows you to create copy such as "ten catchy Twitter headlines on holiday shopping," "the best Facebook headlines for marketing professionals," and more. If you're struggling to come up with a topic, don’t worry. CopyAI’s chat function provides prompt templates to give you a head start. These templates cover various topics, including content creation, SEO, email marketing, social media, PR and communication, sales, and strategy.

Moreover, you can create custom templates that cater to your specific needs. Each template in the collection provides various options, so whether you need a headline generator, a step-by-step guide, or a product description, CopyAI has you covered. You can even use the "rewrite content" option to enhance your written content, making it more engaging and effective.

To fully personalize your experience with CopyAI, you should create one or more brand voices. This process involves providing text that accurately describes you or your company's unique voice. This text should be between 50 and 500 words and can come from various sources such as blog articles, social media posts, website copy, marketing emails, and more. This allows CopyAI to tailor its AI-powered tools to better suit your brand's needs, making it easier for you to create content that resonates with your target audience and helps you achieve your goals.

In summary, CopyAI is a powerful AI writing tool that offers a wide range of features and options to help you create high-quality content. From the user dashboard to the chat and brainstorming features, CopyAI provides a user-friendly and intuitive interface that makes it easy to create compelling and engaging content. With custom templates and brand voices, you can personalize your experience with CopyAI and create content that resonates with your target audience, helping you stand out in today's crowded digital space.

Read our full  CopyAI review .

The best for short-form

6. Writesonic

✔️ You aren't tech savvy:  It's one of the easiest-to-use solutions on the market. 

✔️ You need lots of languages:  Writesonic supports 25 languages and counting. 

✔️ You're a freelancer:  There's a package just for you.

❌  You want to pay a lower price:  Some have criticized Writesonic for being too expensive. That's true with the Smart Team options

❌  You need more third-party integrations:  It doesn't really place nice with other software tools, which could add some time to your work. 

❌ You don't like tackling a learning curve : Like others on this list, there's a slighter higher learning curve with this one

Writesonic is an expansive AI writing platform with an intuitive interface and versatile templates for all content creation scenarios.

Check out our in-depth Writesonic review to see if this is the AI writing tool for you. 

Writesonic is an innovative content creation platform that provides users with various features and tools to generate high-quality, engaging content. One of the most impressive features of Writesonic is its versatility - it supports over 25 languages, including English, French, Italian, German, Japanese, Chinese, and more. This is a significant advantage for businesses that operate in multiple regions and need to produce content in different languages.

Another notable feature of Writesonic is its tone of voice customization tool. Users can choose from various tones, including "Excited," "Creative," and more. This feature adds a unique twist to the content, tailoring it to the user's needs. However, it's essential to note that the tone of voice feature may require additional editing to ensure the content is clear and coherent.

Regarding website copywriting, Writesonic provides users with an impressive range of tools. It can create landing pages, SEO meta descriptions, and feature-rich headers and subheaders. Additionally, it allows users to create social media ads on Facebook, LinkedIn, and Google . Content creators can also benefit from Writesonic's blog writing, point expansion, and text analysis tools, which can rephrase the content and improve its readability.

The platform also offers e-commerce copy creation and popular copywriting formulas, such as the "AIDA" and "Pain-Agitate-Solution" formulas. These formulas are tried and tested approaches to writing compelling, persuasive content that resonates with readers.

However, it's essential to note that the content generated by Writesonic may require significant editing from the user. While the platform does an excellent job of generating content, it's essential to ensure it's clear, coherent, and tailored to the user's needs. If you're looking for a completely hands-off approach to content creation, Writesonic may not be the best option. However, for businesses that need to generate high-quality, engaging content quickly, Writesonic is an excellent choice.

Please read our full Writesonic review .

7. Al-Writer

✔️ You want a cheap package: You can get an AI writer for as little as $19/month. 

✔️ You need clear sourcing:  No better solution is available for providing sources for all text provided. 

✔️ You want an easy solution:  A very low learning curve exists. 

❌  You want app integration:  There's seamless integration with WordPress, but that's about it. 

❌  You need marketing-specific tools:  Sorry, this one doesn't have it. 

❌ You want unlimited word generation: If you need to generate more than 120 articles per month, this is a very expensive solution. 

AI-Writer is a unique word-generating tool that simplifies text creation and editing through an intuitive user interface. However, it may not be suitable for everyone.

Check out our in-depth AI-Writer review to see if it's the solution for you. 

AI-Writer is a word generator that is easily accessible and is popular among freelancers and bloggers. It may not be as extensive as Anyword or CopyAI, which are primarily aimed at marketing and sales, but it serves its intended audience well. 

One of the most significant advantages of AI-Writer is its unparalleled sourcing capabilities. It is the only AI content generator that cites sources for "everything it writes." Additionally, it updates its sources frequently, ensuring that any article generated by it sources the latest information on the subject. This is a significant advantage, particularly for those who are writing about current events or trending topics. With AI-Writer, writers can create content that is well-researched and accurate, without having to spend hours scouring the internet for sources. 

Another significant advantage of AI-Writer is that it recognizes that not all types of content require sourcing. For instance, op-eds or personal essays don't usually require sources. AI-Writer recognizes this and hides sources and links from the main results page, making it easier for writers to focus on their content and not worry about sources.

One of the drawbacks of using AI-Writer is that its extensive sourcing process can cause a minor delay in generating results compared to other AI writing tools. Although this may not be a significant issue, the noticeable delay should be mentioned. For instance, alternative tools like GrammarlyGO offer results without hesitation. However, it is worth noting that the issue with AI-Writer is primarily due to its thorough sourcing process. 

In conclusion, AI-Writer is an excellent tool for freelancers and bloggers who want to create high-quality content. It excels in sourcing capabilities, making it a go-to tool for writers who need well-researched and accurate content. Its ability to recognize when sourcing is not required is also an added advantage. While it may not be the fastest tool on the market, its thorough sourcing process is worth the wait.

Read our full  AI-Writer review .

TechRadar's AI writer rankings

Numerous AI writing solutions are already available in the market, and we can expect more to arrive in the future. Have a look at our rankings of popular services below, and also check out the honorable mentions that currently can’t compete with the top services available.

What is an AI writer?

An AI writer is a revolutionary tool, capable of creating text and content without human help; it utilizes algorithms and machine learning to generate various AI content. From data-driven, high-value pieces to conversion-focused content perfect for marketing campaigns, AI writers can easily create just about any content.

As AI writing assistants gain exposure to various forms of real-world information, they gain proficiency in generating natural-sounding output. With their data coming from human sources, the output created also has a human-like quality. Much like how humans rely on existing content to craft something new, AI content tools scour the web for relevant data to fulfill the user's instructions, thus creating original content.

This, in a nutshell, explains what AI writing is and how it functions.

How to choose the best AI writer for you?

Let’s get this out of the way. Whichever platform you choose, you will have to do some editing, if you want to create useful texts.

Here are some of the factors you should consider when choosing the right tool for you: 

1. Ease of use

Tools that don’t require technical knowledge or prior experience should be on the top of your list. Investment in good UI means that other aspects of the tool are also likely to be of a higher quality.

While this may not be popular with everyone, the price should play a major role in deciding which tool to go for. Some are simply overpriced while not offering much more than their lower-priced competition. Pay attention to the amount of content each price plan offers.

3. High-quality output

Despite the fact that, in the end, you will be editing the texts and images the tool creates, having a tool that creates high-quality content will mean less time spent on fixing mistakes and editing.

4. Integrations

If you’re running a blog or business and have been doing so for some time, you probably have your set of tools that you use for writing content. Making sure that the new AI platform syncs well with your existing toolbox can be essential for how long and how well you utilize the AI tool.

The list above is not exhaustive, but does offer a great starting point in your quest to find the best AI writing tool for your needs.

During our assessment, we’ve evaluated various aspects such as the number of writing templates, categories, recipes, number of languages supported, grammar checkers, etc. Our goal was to create an extensive list of AI writing assistants that offer much more than simple rewording features. 

We tested the overall capabilities of the AI software, the tool's interface and ease of use, monthly article limits, SEO optimization features, and pricing, among other aspects.

In addition, we gave each platform a test article to write for us (a simple topic) and checked its sentence structure and content relevance.

Read more on how we test, rate, and review products on TechRadar .

Get in touch

• Want to find out about commercial or marketing opportunities? Click here
• Out of date info, errors, complaints or broken links? Give us a nudge
• Got a suggestion for a product or service provider? Message us directly
• You've reached the end of the page. Jump back up to the top ^

Are you a pro? Subscribe to our newsletter

Sign up to the TechRadar Pro newsletter to get all the top news, opinion, features and guidance your business needs to succeed!

Bryan M. Wolfe is a staff writer at TechRadar, iMore, and wherever Future can use him. Though his passion is Apple-based products, he doesn't have a problem using Windows and Android. Bryan's a single father of a 15-year-old daughter and a puppy, Isabelle. Thanks for reading!

• Mike Jennings
• Sead Fadilpašić

Intel quietly launched mysterious new AI CPU that promises to bring deep learning inference and computing to the edge — but you won't be able to plug them in a motherboard anytime soon

A shockingly high number of us are still reusing passwords — and lots are even writing them down

After a new Intel CPU for less? Try your luck with a Japanese Gachapon

Most Popular

• 2 Meta’s massive OS announcement is more exciting than a Meta Quest 4 reveal, and VR will never be the same again
• 3 The obscure little PC that wanted to be a big NAS — super compact Maiyunda M1 doesn't cost that much, offers up to 40TB SSD storage, runs Windows and has 4 Gigabit Ethernet ports
• 4 Walmart just launched a huge flash sale: shop the 11 best deals before they're gone
• 5 DJI drones could be banned in the US soon – here's what you need to know
• 2 This Android phone for audiophiles offers a hi-res DAC, balanced output and 3.5mm jack – plus a cool cyberpunk look that puts Google and OnePlus to shame
• 3 Samsung’s next Galaxy AI feature could revolutionize smartphone video
• 4 VMware users warned to brace for next big upheaval as latest Broadcom changes rumble on
• 5 Fujifilm's next budget camera may house surprisingly powerful hardware

Supercharge Your Next Research Paper

Jenni's AI-powered text editor helps you write, edit, and cite with confidence. Save hours on your next paper.

Loved by over 3 million academics

Trusted by Universities and businesses across the world

Write, cite, and edit

Features built to enhance your research and writing capabilities

Most Recent

Exploring the Role of Neural Networks in Natural Language Processing: A Comprehensive Survey

Bahr LS, Bock M, Liebscher D, Bellmann-Strobl J, Franz L, Prüß A et al.

Nature Science

Interactions between the ribosomal exit tunnel and the nascent peptide can affect translation elongation rates. While previous studies have already demonstrated the feasibility of such interactions, little is known about the nature ... See more

Add citation

A Multiclassifier-based Near-Real-Time Face Detection System

H. Wu and J. Zelek

International Journal of Robotics and Automation,

View in new tab

In-text Citations

Jenni consults the latest research and your PDF uploads. Cite in APA, MLA, IEEE, Chicago, or Harvard style

AI Autocomplete

Autocomplete will write alongside you to beat writer's block whenever you need a helping hand

What was the research methodology used in the paper

Research through design as a method for interaction design research in HCI

Jenni is thinking...

Chat to Your Research

Quickly understand and summarize your research papers with our AI chat assistant

Drag and drop PDFs

click to browse

Generate From Your Files

Bring your research papers to life with source-based generation

Paraphrase & Rewrite

Paraphrase any text in any tone. Rewrite the internet customized to you

Bulk Import Sources via .bib

Already saved papers ready to cite? Import a .bib to populate your library in seconds

LaTeX and Word Export

Export your draft to LaTeX, .docx, or HTML without any formatting loss

Outline Builder

Enter your prompt and get a list of section headings ready for you to flesh out

Multilingual Support

Jenni can generate in US or British English, Spanish, German, French, or Chinese

Research Library

Save and manage research in your library. Easily cite research in any document, fast

Never write alone

Get suggestions whenever you are stuck or expand your notes into full paragraphs

Join 2 million empowered writers

Jenni has helped write over 970 million words. From academic essays, journals, to top-ranking blog posts

@Hadeel_Naily

· 16 Jan

A major shoutout to Jenni Ai for straight up saving my life ❤️

@sonofgorkhali

· 23 Aug

I started with Jenni-who & Jenni-what. But now I can't write without Jenni. I love Jenni AI and am amazed to see how far Jenni has come. Kudos to Jenni.AI team

@Mushtaq Bilal

· 25 Mar

Jenni, the AI assistant for academic writing, just got BETTER and SMARTER.

@gachoki_munene

· 1 Aug

This one is a game changer, Doc, especially on that small matter of lacking words or writer's block. I am definitely introducing it to my students asap.

@angrytomtweets

· 18 Oct

I thought ChatGPT was a good writing assistant. But when I found Jenni AI - It blew my mind. It's 10x more advanced than I thought.

· 26 Aug

I thought AI writing was useless. Then I found Jenni AI. It turned out to be much more advanced than I ever could have imagined. Jenni AI = ChatGPT x 10.

Oscar Duran

@duranoscarf

· 30 Jul

herramienta de auto completado de textos. Usando inteligencia artificial te permite escribir de manera rápida y mas eficiente (hay que revisar igual)

· 28 Jul

Jenni is perfect for writing research docs, SOPs, study projects presentations 👌🏽

@xaviercaffrey13

· 19 Aug

Copyai is alright but have you tried @whoisjenniai?

Team & institutional plans

Collaborate with your research team and speed up your workflow.

Enquire now

You're in control

Types of content Jenni can help you with

Save hours writing your essay with our AI essay writing tool.

Literature reviews

Discover, write, and cite relevant research.

Research Papers

Polish your writing to increase submission success.

Personal statements

Create a compelling college motivation letter.

Write blogs & articles faster with the help of AI.

Write your next compelling speech in less time.

Frequently asked questions

Does jenni use gpt-4, what are citations, is jenni multilingual, is there mobile support.

Does Jenni plagiarize?

Try Jenni for free today

Write your first paper with Jenni today and never look back

• Resources Home 🏠
• Try SciSpace Copilot
• Search research papers
• Add Copilot Extension
• Try AI Detector
• Try Paraphraser
• Try Citation Generator
• April Papers
• June Papers
• July Papers

AI for Essay Writing — Exploring Top 10 Essay Writers

Table of Contents

Let’s admit it — essay writing is quite a challenging task for students. Especially with the stringent deadlines, conducting research, writing , editing, and addressing to-and-fro reviews — consumes a whole lot of time and often becomes stressful. Therefore, students are always on the lookout for tools that speed up the essay writing process.

And that’s when AI writing tools make their debut! Using the best AI for essay writing makes the lives of students much easier by automatically generating the essay for them.

The rise in the popularity of artificial intelligence technology and deep learning has paved the way for the numerous AI writer tools available today. To help you understand the different types of AI tools and their benefits, we’ve uncovered the features of the top 10 AI essay generators in this article.

Let’s explore the tools and learn how they are transforming the tedious task of essay writing!

What is essay writing?

Essay writing is a part of academic writing that emphasizes formulating an idea or argument. The main objective of academic essay writing is to present a well-reasoned argument or idea. Evidence, analysis, and interpretation are the three major components of essay writing . It should have a logical structure to support the argument or idea of the essay so that it communicates clearly and concisely.

What is an AI essay writer?

AI essay writers is a tool that is designed to help students generate essays using machine learning techniques. They can be used to generate a full essay or generate a few parts of the essay, for example, essay titles, introduction, conclusion, etc.

Why should researchers use AI essay generators?

There are infinite benefits to using AI tools for writing unique essays, especially for researchers or students. Here are a few of them —

1. Saves time

Using best AI for essay writing has its own benefits. Students can take care of the research process while these AI tools write the essays for them. Be it an essay topic or a full-length essay generation, it saves a bunch of students' time.

2. Boosts productivity

Writing is a tedious task especially when you want to write an essay about a novel topic, that writer’s block starts haunting and your productivity gets affected. But, with AI, it’s the other way around and increases productivity by quickly generating the essays for you.

3. Enhances writing skills — Vocabulary and Style

Adopting the best AI essay writing AI tool not only help with creating essays but also help us hone our writing skills by giving proper suggestions about grammar, sentence structure, tone, style, and word choice.

4. Reduces stress

Students often undergo a lot of pressure and stress because of deadlines and submissions. With the best AI essay generator, they help you write essays smarter thereby reducing stress and fear in no time.

5. Facilitates multidisciplinary research

AI essay writing tools foster interdisciplinary study through their ability to scan and combine knowledge from multiple domains. That way, it helps us quickly get a grasp of new subjects or topics without a heavy-lifting process.

6. Cost-effective

Most of the AI essay writing tools have lower pricing and also allow certain discounts for students. So, it is also a cost-effective approach to use AI writing tools.

The Top AI Essay Writing Tools and Their Features

Several AI essay writers are available based on the types of essays one would want to generate. Now, let's quickly understand the top 10 AI writing tools that generate essays within just a few minutes.

1. PerfectEssayWriter.ai

It is one of the best AI for essay writing that not only creates an essay but also comes up with advanced features including plagiarism detection, auto-referencing, and contextual analysis. As a result, it generates coherent essays that are well-researched and properly cited. It is best recommended for creating academic essays and essay outlines.

How does PerfectEssayWriter work?

• Pick the right tool for your purpose — Go with an essay writer if you want to generate a full essay or choose the essay outliner if you want to create just the outline of the essay.
• Enter your specific conditions and preferences. Add essay topic, academic level, essay type, number of pages, and special instructions, if any.
• Click on “generate” and wait for the result
• Once you have the essay generated, you can review, edit, or refine it and then download it.
• Generates a large chunk of data up to 2000 words
• Output is provided within 90 seconds
• Provides a plethora of other tools like Citation generator, grammar checker, thesis statement generator, and more
• Comes with 10+ essay writing templates
• Subscription-based and not a free tool
• Human review is a mandate

2. Essaybot - Personalized AI writing

Essaybot is the product of a reputed online essay-writing service, MyPerfectWords. It is meant to enhance academic essay writing and streamline the tasks of students. Its user friendly website makes it an instant and hassle-free essay generation saving a lot of time and effort for students.

How does Essaybot work?

• Enter the essay title or topic
• Click on “start writing” and wait for it to generate a well-reasoned essay.
• The tools come for free
• No sign-up is required
• 100% unique and High-quality output
• Very limited features that lack advanced functionalities

3. FreeEssayWriter.net

FreeEssayWriter is an organization that provides essay-writing services to students worldwide. It has an AI essay typer tool — that helps you generate essays instantly. What sets this essay typer apart is its initiative to help students with their free essay writer providing the students with a 2-page free essay.

How does FreeEssayWriter.net work?

It works similarly to Essaybot, input the title or the topic of your essay and wait for it to generate the essay. They also have an option to edit and download a free version of the generated essay instantly.

• Provides high-quality essays and is considered to be one of the reliable and trusted sources of information
• Students can improve their writing skills and learn more about essays by referring to their free essay database or sources
• Priority customer support is available 24*7
• The site is not optimized for mobile devices
• The quality of the essay output could still be improved

4. MyEssayWriter

This AI essay writing tool is no exception in terms of generating a high-quality essay. You can generate essays for various topics depending on the background of your research study. Be it academic or non-academic essay writing, this tool comes in handy.

How does MyEssay Writer work?

Add your preferences and then click on generate. It will give you a high-quality and 100% unique essay crafted based on your requirements.

• The tool comes for free — no subscription is required
• Knows for its consistency in the quality and the tone of the essay output
• Also has a paid custom writing service that provides human-written essays
• Might not provide quality output for complex and technical-based keywords or topic

5. College Essay AI

College essay AI stands unique as an ai writing tool as it not only uses an AI-based algorithm to generate essays but it also backs up the output as it is reviewed and approved by a team of professional experts. It is the best AI essay writing tool for college and graduate students where the output adheres to the graduate students' essay writing guidelines.

How does the College Essay AI generator work?

• Input the required information — essay topic, academic level, number of pages, sources, and specific instructions, if any.
• Click on “generate essay” and wait for the output
• Conduct plagiarism and grammar check
• Download the essay
• High-level output for academic essay writing
• Pocket-friendly premium plans
• Doesn’t provide multiple sets of templates
• Not quite suitable for non-academic essay writing

6. Jasper AI

Jasper AI has been the oldest player in the game of AI content writing. Fast forward to now, its features have been magnified with the inception of natural language processing algorithms and that’s how they are helping students write their essays as well. However, Jasper is the best AI tool for non-academic writing projects like content writing or creative writing.

How does Jasper AI work?

• Choose a template — if you are about to write an essay, go with the “document”
• Add your preferences
• Click “compose” and get the output
• Generates the essays instantly
• Provides well-structured output according to the tone and style of your preferences
• Not quite suitable for academic writing essays

7. Textero AI

Textero AI provides a few writing tools for students that facilitate their various academic papers and writing projects. Its essay generator helps you generate ideas for a full-length essay based on the topic and also suggests new topic ideas or thesis statement ideas for your academic assignments.

How does Textero AI work?

• Click on “Essay Generator” located on the LHS (Left-hand Side)
• Input the title and description based on which you want to generate the essay
• Pick the right citation style
• Click “generate” and wait for the output
• It also provides other tools like an outline generator, and summary generator and has an AI research assistant that answers all your questions relevant to the research
• The output is 100% unique and plagiarism and error-free
• Might fail to provide an essay focussed on complex or technical topics

8. Quillbot

Though Quillbot is essentially built for paraphrasing and summarizing tasks. It comes as a rescue when you have to revamp, improvise, or refine your already-composed essay. Its co-writer helps you transform your thoughts and ideas and make them more coherent by rephrasing them. You can easily customize your text based on the customization options available.

How does Quillbot Paraphraser work?

• Import or copy the content
• Click on “Paraphrase” “Summarize” or “Suggest text” based on your requirement
• Make the required customizations and save the document.
• Offers a plethora of tools required for students
• Both free and premium plans are available
• Enhances vocabulary and language skills
• Limited customization options with the free plan
• Only supports the English language

9. SciSpace Paraphraser

SciSpace is the best AI tool that helps you fine-tune your essay. If you feel your essay writing needs AI suggestions to improve the language, vocabulary, writing styles, and tone of your essay, SciSpace is at your rescue. It has more customized options than Quillbot and improves your essay by rephrasing it according to the required or preferred writing style, and tone. This is a very good alternative to Quillbot.

How does SciSpace Paraphrasing work?

• Simply paste the content to the screen
• Choose the length and variation properly
• Select the language
• Click “Paraphrase”
• Has 22 custom tones and all of them are available even on the free plan
• Supports 75+ languages
• Comes with an AI-detection report for English paraphrase output
• Delay in the output

10. ChatGPT

It would be unfair if we talk about AI tools and do not enlist ChatGPT. When it comes to automated essay writing tasks, ChatGPT is not trivial. With proper prompts, you can automate the essay writing process and generate a well-crafted and coherent essay. However, the quality and the accuracy cannot be trusted as the model hallucinates and doesn’t include sources.

How does ChatGPT work?

• Create a prompt based on your requirement
• Ask ChatGPT to write an essay about your topic, specify conditions and preferences
• Click enter and wait for the essay
• Comes for free
• Cannot rely on the output as the model hallucinates
• Lacks the upgraded features that other essay-writing tools have

Concluding!

Writing essays can be a real struggle. But, the inception of the best AI essay-generation tools makes the entire writing process a lot easier and smoother. However, you should be extra vigilant while relying on these tools and consciously use them only as a technological aid. Because over-reliance on these AI tools could diminish student's writing skills and the user can become more gripped by the tools. So, use it wisely without affecting your knowledge and skills.

You can explore the above tools whenever you need any help with essay writing, and reap the benefits of them without compromising on the quality of your writing.

And! If you're stuck exploring multiple research papers or want to conduct a comprehensive literature review , you know which tool to use? Yes, it's SciSpace Literature Review, our AI-powered workspace, which is meant to make your research workflow easier. Plus, it also comes with SciSpace Copilot , our AI research assistant that answers any question that you may have about the research paper.

If you haven't used it yet, you can use it here !

Choosing the best AI for writing long-form essays depends on your requirements. Here are the top 5 tools that help you create long-form and college essays —

1. Free Essay Writer AI

2. College Essay AI

3. My Essay Writer

4. Textero AI

5. Perfect Essay Writer

The Perfect Essay Writer AI and Textero AI are the two best AI essay generators that help you write the best essays.

ChatGPT is not specifically built to assist you with essay writing, however, you can use the tool to create college essays and long-form essays. It’s important to review, fact-check the essay, and refer to the sources properly.

Essaybot is a free AI essay generator tool that helps you create a well-reasoned essay with just a click.

Unless your university permits it, using AI essay generators or writing tools to write your essay can be considered as plagiarism.

You might also like

Introducing SciSpace’s Citation Booster To Increase Research Visibility

AI for Meta-Analysis — A Comprehensive Guide

How To Write An Argumentative Essay

'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

Google releases two new free resources to help you optimize your ai prompts, humane ai pin: what went wrong and how it can be fixed (before it's too late), how to get started with meta ai in facebook, instagram, and more.

8 Ways to Create AI-Proof Writing Prompts

C reating 100 percent AI-proof writing prompts can often be impossible but that doesn’t mean there aren’t strategies that can limit the efficacy of AI work. These techniques can also help ensure more of the writing submitted in your classroom is human-generated. 

I started seeing a big uptick in AI-generated work submitted in my classes over the last year and that has continued. As a result, I’ve gotten much better at recognizing AI work , but I’ve also gotten better at creating writing prompts that are less AI-friendly. 

Essentially, I like to use the public health Swiss cheese analogy when thinking about AI prevention: All these strategies on their own have holes but when you layer the cheese together, you create a barrier that’s hard to get through. 

The eight strategies here may not prevent students from submitting AI work, but I find these can incentivize human writing and make sure that any work submitted via AI will not really meet the requirements of the assignment. 

1. Writing AI-Proof Prompts: Put Your Prompt Into Popular AI tools such as ChatGPT, Copilot, and Bard 

Putting your writing prompt into an AI tools will give you an immediate idea of how most AI tools will handle your prompt. If the various AI chatbots do a good, or at least adequate, job immediately, it might be wise to tweak the prompt. 

One of my classes asks students to write about a prized possession. When you put this prompt into an AI chatbot, it frequently returns an essay about a family member's finely crafted watch. Obviously, I now watch out for any essays about watches. 

2. Forbid Cliché Use

Probably the quickest and easiest way to cut back on some AI use is to come down hard on cliché use in writing assignments. AI tools are essentially cliché machines, so banning these can prevent a lot of AI use. 

Equally as important, this practice will help your students become better writers. As any good writer knows, clichés should be avoided like the plague. 

3. Incorporate Recent Events

The free version of ChatGPT only has access to events up to 2022. While there are plugins to allow it to search the internet and other internet-capable AI tools, some students won’t get further than ChatGPT. 

More importantly, in my experience, all AI tools struggle to incorporate recent events as effectively as historic ones. So connecting class material and assignments to events such as a recent State of Union speech or the Academy Awards will make any AI writing use less effective. 

4. Require Quotes

AI tools can incorporate direct quotations but most are not very good at doing so. The quotes used tend to be very short and not as well-placed within essays. 

Asking an AI tool for recent quotes also can be particularly problematic for today’s robot writers. For instance, I asked Microsoft's Copilot to summarize the recent Academy Awards using quotes, and specifically asked it to quote from Oppenheimer's director Christopher Nolan’s acceptance speech. It quoted something Nolan had previously said instead. Copilot also quoted from Wes Anderson’s acceptance speech, an obvious error since Anderson wasn’t at the awards .  

5. Make Assignments Personal

Having students reflect on material in their own lives can be a good way to prevent AI writing. In-person teachers can get to know their students well enough to know when these types of personal details are fabricated. 

I teach online but still find it easier to tell when a more personalized prompt was written by AI. For example, one student submitted a paper about how much she loved skateboarding that was so non-specific it screamed AI written. Another submitted a post about a pair of sneakers that was also clearly written by a "sole-less" AI (I could tell because of the clichés and other reasons). 

6. Make Primary or Scholarly Sources Mandatory

Requiring sources that are not easily accessible on the internet can stop AI writing in its tracks. I like to have students find historic newspapers for certain assignments. The AI tools I am familiar with can’t incorporate these. 

For instance, I asked Copilot to compare coverage of the first Academy Awards in the media to the most recent awards show and to include quotes from historic newspaper coverage. The comparison was not well done and there were no quotes from historical newspaper coverage. 

AI tools also struggle to incorporate journal articles. Encouraging your students to include these types of sources ensures the work they produce is deeper than something that can be revealed by a quick Google search, which not only makes it harder for AI to write but also can raise the overall quality.  

7. Require Interviews, Field Trips, Etc. 

Building on primary and scholarly sources, you can have your students conduct interviews or go on field trips to historic sites, museums, etc. 

AI is still, thankfully, incapable of engaging in these types of behavior. This requires too much work for every assignment but it is the most effective way to truly ensure your work is human- not computer-written. 

If you’re still worried about AI use, you can even go a step further by asking your students to include photos of them with their interview subjects or from the field trips. Yes, AI art generators are getting better as well, but remember the Swiss cheese analogy? Every layer of prevention can help. 

8. Have Students Write During Class

As I said to start, none of the methods discussed are foolproof. Many ways around these safeguards already exist and there will be more ways to bypass these in the future. So if you’re really, really worried about AI use you may want to choose what I call the “nuclear option.” If you teach in person you can require students to write essays in person. 

This approach definitely works for preventing AI and is okay for short pieces, but for longer pieces, it has a lot of downsides. I would have trouble writing a long piece in this setting and imagine many students will as well. Additionally, this requirement could create an accusatory class atmosphere that is more focused on preventing AI use than actually teaching. It’s also not practical for online teaching. 

That all being said, given how common AI writing has become in education, I understand why some teachers will turn to this method. Hopefully, suggestions 1-7 will work but if AI-generated papers are still out of hand in your classroom, this is a blunt-force method that can work temporarily. 

Good luck and may your assignments be free of AI writing! 

• 7 Ways To Detect AI Writing Without Technology
• Best Free AI Detection Sites
• My Student Was Submitting AI Papers. Here's What I Did

AI’s ability to write for us—and our inability to resist ‘The Button’—will spark a crisis of meaning in creative work

Soon, every major office application and email client will include a button to help you create a draft of your work. It deserves capital letters: The Button.

When faced with the tyranny of the blank page, people are going to push The Button. It is so much easier to start with something than nothing. Students are going to use it to start essays. Managers will use it to start emails, reports, or documents. Teachers will use it when providing feedback. Scientists will use it to write grants. Concept artists will use it for their first draft. Everyone is going to use The Button.

The implications of having AI write our first drafts (even if we do the work ourselves, which is not a given) are huge. One consequence is that we could lose our creativity and originality. When we use AI to generate our first drafts, we tend to anchor on the first idea that the machine produces, which influences our future work. Even if we rewrite the drafts completely, they will still be tainted by the AI’s influence. We will not be able to explore different perspectives and alternatives, which could lead to better solutions and insights.

Another consequence is that we could reduce the quality and depth of our thinking and reasoning. When we use AI to generate our first drafts, we don’t have to think as hard or as deeply about what we write. We rely on the machine to do the hard work of analysis and synthesis, and we don’t engage in critical and reflective thinking ourselves. We also miss the opportunity to learn from our mistakes and feedback and the chance to develop our own style.

AI can do it

There is already evidence that this is going to be a problem. A recent MIT study found that ChatGPT mostly serves as a substitute for human effort, not a complement to our skills. In fact, the vast majority of participants didn’t even bother editing the AI’s output. This is a problem I see repeatedly when people first use AI: they just paste in the exact question they are asked and let the AI answer it.

A lot of work is time-consuming by design. In a world in which the AI gives an instant, pretty good, near universally accessible shortcut, we’ll soon face a crisis of meaning in creative work of all kinds. This is, in part, because we expect creative work to take careful thought and revision, but also that time often operates as a stand-in for work. Take, for example, the letter of recommendation. Professors are asked to write letters for students all the time, and a good letter takes a long time to write. You have to understand the student and the reason for the letter, decide how to phrase the letter to align with the job requirements and the student’s strengths, and more. The fact that it is time-consuming is somewhat the point. That a professor takes the time to write a good letter is a sign that they support the student’s application. We are setting our time on fire to signal to others that this letter is worth reading.

Or we can push The Button.

And the problem is that the letter the AI generates is going to be good. Not just grammatically correct, but persuasive and insightful to a human reader. It is going to be better than most letters of recommendation that I receive. This means that not only is the quality of the letter no longer a signal of the professor’s interest, but also that you may actually be hurting people by not writing a letter of recommendation by AI, especially if you are not a particularly strong writer. So people now have to consider that the goal of the letter (getting a student a job) is in contrast with the morally correct method of accomplishing the goal (the professor spending a lot of time writing the letter). I am still doing all my letters the old-fashioned way, but I wonder whether that will ultimately do my students a disservice.

Now consider all the other tasks whose final written output is important because it is a signal of the time spent on the task and of the thoughtfulness that went into it—performance reviews, strategic memos, college essays, grant applications, speeches, comments on papers. And so much more.

Reconstructing meaning

Then The Button starts to tempt everyone. Work that was boring to do but meaningful when completed by humans (like performance reviews) becomes easy to outsource—and the apparent quality actually increases. We start to create documents mostly with AI that get sent to AI-powered inboxes, where the recipients respond primarily with AI. Even worse, we still create the reports by hand but realize that no human is actually reading them. This kind of meaningless task, what organizational theorists have called mere ceremony, has always been with us. But AI will make a lot of previously useful tasks meaningless. It will also remove the facade that previously disguised meaningless tasks. We may not have always known if our work mattered in the bigger picture, but in most organizations, the people in your part of the organizational structure felt it did. With AI-generated work sent to other AIs to assess, that sense of meaning disappears.

We are going to need to reconstruct meaning, in art and in the rituals of creative work. This is not an easy process, but we have done it before, many times. Where musicians once made money from records, they now depend on being excellent live performers. When photography made realistic oil paintings obsolete, artists started pushing the bounds of photography as art. When the spreadsheet made adding data by hand unneeded, clerks shifted their responsibilities to bigger-picture issues. This change in meaning is going to have a large effect on work.

Excerpted with permission from Co-Intelligence: Living and Working with AI , by Ethan Mollick, in agreement with Portfolio, an imprint of Penguin Publishing Group, a division of Penguin Random House LLC. Copyright © Ethan Mollick, 2024.

Ethan Mollick is a professor of management at Wharton, specializing in entrepreneurship and innovation. He writes the AI-focused blog One Useful Thing and is the creator of numerous educational games on a variety of topics. 

Latest in Tech

• 0 minutes ago

Grab’s COO thinks there’s ‘tremendous upside’ in fast-growing Southeast Asia after the startup recently reported its first-ever profitable quarter

Billionaire investor Ron Baron gets a first-hand demonstration of Tesla’s self-driving tech: ‘I want to see Steve Jobs’ house’

Wall Street finds a back door into the AI stock boom as energy demand soars: utilities

Apple renews talks to integrate OpenAI’s technology into the next iPhone operating system

Top tech CFO says AI is no ‘blip or hype,’ it’s tech’s historic moment—and his numbers back that up

An emergency slide ripped off a Boeing-made jet during a Delta flight from New York to Los Angeles

Most popular.

‘Americans just work harder’ than Europeans, says CEO of Norway’s $1.6 trillion oil fund, because they have a higher ‘general level of ambition’

Amazon should be forced to disclose how Jeff Bezos and others were instructed to use the Signal disappearing-message app, FTC says

Jamie Dimon says America needs to ‘take a deep breath’ before facing off with China, because the U.S. is actually in a ‘very good position’ to negotiate

The meteoric rise and stunning fall of Prime, Logan Paul’s energy drink that was once resold for almost $1,500 a can: ‘A brand cannot live on hype alone’

Tesla’s Elon Musk speeds past Mark Zuckerberg on the billionaires list after Meta stock plummets on its cash-sucking AI plans

Troubled Philadelphia-based bank implodes in first failure of the year

AI and the End of the Human Writer

If a computer can write like a person, what does that say about the nature of our own creativity.

The most nauseating, addictive thing about writing is the uncertainty—and I don’t mean the  is-anyone-reading?  or  will-I-make-rent?  kind. The uncertainty I’m talking about dogs the very act. This business of writing an essay, for instance: Which of ten thousand possible openings to choose—and how to ignore the sweaty sense that the unseen, unconceptualized ten thousand and first is the real keeper? Which threads to tug at, without knowing where they lead, and which to leave alone? Which ideas to pick up along the way, to fondle and polish and present to an unknown reader? How to know what sentence best comes next, or even what word? A shrewd observer will note that I am complaining about the very essence of writing itself, but that has been the long-held privilege of writers—and they enjoyed it in the secure comfort of their uniqueness. Who else was going to do the writing, if not the writers who grouse about writing?

Now along come these language engines, with suspiciously casual or mythopoeic names like ChatGPT or Bard, that suffer not an iota of writerly uncertainty. In what can only be called acts of emesis, they can pour out user manuals, short stories, college essays, sonnets, screenplays, propaganda, or op-eds within seconds of being requested for them. Already, as Naomi S. Baron points out in her book  Who Wrote This? , readers aren’t always able to tell if a slab of text came out of a human torturing herself over syntax or a machine’s frictionless innards. (William Blake, it turns out, sounds human, but Gertrude Stein does not.) This unsettles Baron, a linguist who has been writing about the fate of reading for decades now. And it appears to be no lasting consolation that, in some tests, people still correctly recognize an author as artificial. Inexorably, version after version, the AIs will improve. At some point, we must presume, they will so thoroughly master Blakean scansion and a chorus of other voices that their output—the mechanistic term is only appropriate—will feel indistinguishable from ours.

Naturally, this perplexes us. If a computer can write like a person, what does that say about the nature of our own creativity? What, if anything, sets us apart? And if AI does indeed supplant human writing, what will humans—both readers and writers—lose? The stakes feel tremendous, dwarfing any previous wave of automation. Written expression changed us as a civilization; we recognize that so well that we use the invention of writing to demarcate the past into prehistory and history. The erosion of writing promises to be equally momentous.

In an abysmally simplified way, leaving out all mentions of vector spaces and transformer architecture, here’s how a modern large language model , or LLM, works. Since the LLM hasn’t been out on the streets to see cars halting at traffic signals, it cannot latch on to any experiential truth in the sentence, “The BMW stopped at the traffic light.” But it has been fed reams and reams of written material— 300 billion words , in the case of ChatGPT 3.5—and trained to notice patterns. It has also been programmed to play a silent mathematical game, trying to predict the next word in a sentence of a source text, and either correcting or reinforcing its guesses as it progresses through the text. If the LLM plays the game long enough, over 300 billion or so words, it simulates something like understanding for itself: enough to determine that a BMW is a kind of car, that “traffic light” is a synonym for “traffic signal,” and that the sentence is more correct, as far the real world goes, than “The BMW danced at the traffic light.” Using the same prediction algorithms, the LLM spits out plausible sentences of its own—the words or phrases or ideas chosen based on how frequently they occur near one another in its corpus. Everything is pattern-matching. Everything—even poetry—is mathematics.

We still don’t know precisely how humans grasp language, although it isn’t the LLM way; no infant that I know of consumed 300 billion words before saying “Mama.” But in his slim new book,  Literary Theory for Robots,  Dennis Yi Tenen, an associate professor of English at Columbia University, proposes that the way we use language to create works bears some similarities to the machines. “Thinking and writing happen through time, in dialogue with a crowd,” Tenen maintains. “Paradoxically, we create new art by imitating and riffing off each other.” Subconsciously or otherwise, a writer milks inspiration out of libraries and conversations, and draws assistance from dictionaries, thesauruses, and style guides. “We think with our bodies, with tools, with texts, within environments, and with other people.” A writer relies in less calculating fashion on the books she has ingested than an AI does, but they’ve made her into a writer all the same. It was always an error, Tenen writes, “to imagine intelligence in a vat of private exceptional achievement”—to buy into the fable of the writer in her lonely garret, manufacturing words and ideas de novo .

In this notion of distributed intelligence, there is something both democratizing and destabilizing—a sneaky but egalitarian mode of murdering the author. Tenen insists, though, that we shouldn’t agonize too much over the source of intelligence. Who cares if our thinking is closer to the synthesis of LLMs, rather than the divinely ordained originality held dear by the Romantics, as long as we have an effect upon the world? Certainly not Aristotle. “In the Aristotelian model,” Tenen writes, “intelligence is the GOAL of thought.” (The caps lock letters are Tenen’s, not mine or Aristotle’s.) It’s Plato who held intelligence to lie within the department of the interior—a private, nebulous thing that occasionally led to enlightenment. Pick your philosopher.

Even at the summit of literary creation, fiction writers yielded to the seeming inevitability of recombination. Tenen’s potted history of authorial hacks, the richest section of his book, begins with Georges Polti, an enterprising Frenchman who in 1895 published a book called  The Thirty-Six Dramatic Situations,  to help dramatists write new plays. Once you’d eliminated supplication, deliverance, vengeance, pursuit, disaster, revolt, and the other 30 symptoms of the human condition, he implied, what else was left? (Polti wasn’t afraid to get specific: Among the subtypes of the “pursuit” situation were “pursuit for a fault of love” and “a pseudo-madman struggling against an Iago-like alienist.”) “They will accuse me of killing imagination,” Polti wrote, but in fact, his primer aspired to free playwrights from the pursuit of mere novelty, so they could devote themselves to truth and beauty. Mark Twain invented a self-gumming scrapbook for authors, into which they might paste notes, newspaper snippets, and images, for subsequent inspiration. (His secretary once filled six scrapbooks with clips about the Tichborne trial in London, involving a no-name butcher who claimed the title to an English peerage. Twain concluded that the tale was too wild to be of use to a “fiction artist”—but it did form the basis of Zadie Smith’s latest novel ,  The Fraud .) Companies sold devices like the Chautauqua Literary File and the Phillips Automatic Plot File Collector, into which writers stuffed their reference materials, so that they could later pluck out a setting, a character, or the seed of a plot. It was ever thus, Tenen implies—the magpie approach to thinking, the collage as the modus operandi of writing. Why are we unnerved by LLMs following those same principles?

When I reached this juncture in  Literary Theory for Robots,  I let out a silent, screaming plea for our species. The art of the novel doesn’t lie in the combine-harvesting of details and plotlines. It lies in how a writer selectively filters some of them through her own consciousness—her deliberations, the sum of her life, the din of her thoughts—to devise something altogether different and more profound. This, and only this, makes any piece of writing meaningful to those who read it. The AIs of the future may meet other yardsticks for creativity. They may, say, grow aware of themselves as creators, satisfying the neurosurgeon Geoffrey Jefferson’s dictum that a machine will equal the brain when it not only writes a sonnet but also knows that it has written it. Their cogitations may seem as bleary and inscrutable as those of humans. (Already we are hard-pressed to say how precisely some hallucinations emerge from AIs.) But they will never have experiences the way we have experiences, I quarreled with myself. They can’t lose a friend to suicide, or feel the pain of a twisted ankle, or delight at their first glimpse of the rolling Caucasus, or grow frustrated in a job, or become curious about Dutch art. (And that was just my 2023.) Any texts they furnish will be intrinsically hollow; they will fail to hold us, like planets without gravity. Or so I contended.

But not very far into Baron’s  Who Wrote This?,  I realized I was being defensive—that I was arguing for a special exemption for writing and language because I consider them such immutable aspects of the mind, and of being human. Baron, with the dry eyes of an actuary, sets about deromanticizing writing. She presents classifications of creativity—ranging from the “mini c” creativity of personal satisfaction, where you tweak the recipe of a peach cobbler at Thanksgiving, through the “little c” rung of winning a county fair ribbon for said recipe, up to the cobbler-less “Pro C” of professional creations like the  Harry Potter  series and the “Big C” league of Shakespeare and Steve Jobs.

Baron invokes these distinctions in part to understand human creativity. But she is particularly interested in whether AI imperils the Big C. She points out that the high art of literary writing is merely a sliver of all writing turned out by humanity. Much of the rest is “everyday writing by everyday people,” and it includes grocery lists, birdwatching journals, emails, social media status updates, and office memos. Another subset—Baron loves her taxonomies—consists of writing for professional or financial gain. Here rest advertising copy, chemistry primers, white papers, earnings reports, and business case studies—texts to which we rarely look for deep meaning, “Big C” creativity, or personal connection. Not only will AIs be capable of producing these artifacts of writing, but a reader will feel no acute sense of loss in discovering where they came from. Tenen would note that, even today, such texts already repurpose previous writing to a large extent. To resent AIs for similarly relying on the work of others would be as fatuous as dismissing a novelist who employs a spellchecker to correct his usage of “who” and “whom.”

Both Tenen and Baron are cautious boosters of AI, saluting its potential to relieve us of many “lesser” forms of writing. But they also predict that more literary writing—Big C writing—will resist the encroachments of the machines. “It’s simply that, however effective or powerful, a muscular artifice for the sake of artifice isn’t that intelligent or interesting to me,” Tenen says. For truly human writing, an AI needs to gain a wider sense of the world, he adds. “But it cannot, if words are all it has to go by.” A machine cannot (as yet) watch a film to review it, and it cannot (also as yet; one must cover one’s rear) interview legislators to write a political feature. Anything that it produces in these genres must be confected out of reviews and interviews that have already been written. That lack of originality, Tenen would contend, will forever keep true creativity beyond the reach of AI.

Still, I remained unsure. One might argue that it is always the audience that creates meaning out of a text—that a book is merely a jumble of words until it provokes responses in a reader, that the act of reading summons the book into being. In doing so, we wouldn’t just be going back half a century, to reader-response theory and Roland Barthes’s essay “The Death of the Author.” More than a millennium ago, the Indian philosopher Bhatta Nayaka, in a literary treatise called  Mirror of the Heart,  reasoned that  rasa —the Sanskrit notion of aesthetic flavor—resides not in the characters of a play but in the reader or spectator. “Rasa thus became entirely a matter of response,” the Sanskrit scholar Sheldon Pollock wrote in  A Rasa Reader,  “and the only remaining question was what precisely that response consists of.”

Bhatta Nayaka today, digesting the relationship between our AIs and us, would ask us an uncomfortable question. If, in a blind taste test, some readers are moved by a poem or a short story by ChatGPT, will we continue to prize their experience, and hold their response to be more important than anything else? It’s bound to happen, at some point—and the computers don’t even need to be sentient to get there. Alan Turing knew it. In his 1950 paper, when he proposed an inquiry into the question “Can machines think?” Turing swerved quickly into the question of whether machines could play the imitation game—whether they could merely fool human beings into concluding that they were thinking. The outcome, for all practical purposes, is the same—and the difference between moving us and fooling us isn’t as great as we’d like to believe.  

So much for readers. But what of writers? The twentieth century is cluttered with the vacated chairs and discarded uniforms of workers whose jobs have been automated. Human hands once stuffed sausages, riveted cars together, and transferred calls in telephone exchanges. Once again, it is tempting to claim an exemption for writing. “Because mind and language are special to us, we like to pretend they are exempt from labor history,” Tenen notes. But “intellect requires artifice, and therefore labor.” In the commercial sphere, a lot of writing is not so far removed from sausage-making—and the machines have already begun to encroach. Realtors use ChatGPT to pump out listings of houses. The Associated Press turns to AI models to generate reports on corporate earnings. Context, a tool owned by LexisNexis, reads judicial decisions and then offers lawyers their “most persuasive argument, using the exact language and opinions your judge cites most frequently.” When you consider that some judgments are now drafted by AI as well, the legal profession seems to be on the cusp of machines debating each other to decide the fate of human beings.

It won’t do to be snobbish and describe these kinds of writing work as thankless, because they have occupied people who have been thankful for the income. Roughly 13 percent of American jobs are writing-intensive, and they earn more than $675 billion a year. Many of these jobs are likely to evaporate, but when this is aired as a concern, the champions of automation have a standard lexicon of liberation. “Freed from the bondage of erudition, today’s scribes and scholars can challenge themselves with more creative tasks,” Tenen writes. If he’d been speaking that sentence, perhaps he’d have ended it with an upward, hopeful lilt? Because little about the modern economy suggests that it wishes to support even the creative writers who already live within it, let alone the thousands on the verge of being emancipated by AI.

However, there is supposedly freedom on offer for novelists and poets as well. In one of Baron’s scenarios, AI tools provide the divine spark: “Think of jumpstarting a car battery.” But cars start the same way every time, and they really just need to reach their destinations. For writers, trite as it sounds, it’s about the origin and the journey. In the cautionary parable of Jennifer Lepp, as narrated by Baron, the writer is cold-shouldered out of her own writing. Lepp, a one-woman cottage industry turning out a new paranormal cozy mystery every nine weeks, recruited an AI model called Sudowrite as an assistant. At first, Sudowrite helped her with brief descriptions, but gradually, as she let it do more and more, “she no longer felt immersed in her characters and plots. She no longer dreamt about them,” Baron writes. Lepp told The Verge: “It didn’t feel like mine anymore. It was very uncomfortable to look back over what I wrote and not really feel connected to the words or the ideas.”

Here, at last, is the grisly crux: that AI threatens to ruin for us—for many more of us than we might suppose—not the benefits of reading but those of writing. We don’t all paint or make music, but we all formulate language in some way, and plenty of it is through writing. Even the most basic scraps of writing we do—lessons in cursive, text messages, marginal jottings, postcards, all the paltry offcuts of our minds—improve us. Learning the correct spellings of words, according to many research studies, makes us better readers. Writing by hand impresses new information into the brain and sets off more ideas (again: several studies). And sustained writing of  any  kind—with chalk on a rock face, or a foot-long novelty pencil, or indeed a laptop—abets contemplation. An entire half-page of Baron’s book is filled with variations of this single sentiment, ranging from Horace Walpole’s “I never understand anything until I have written about it” to Joan Didion’s “I write entirely to find out what I’m thinking, what I’m looking at, what I see and what it means.” Sometimes even that is prologue. We also write to reach out, to convey the squalls and scuffles in our souls, so that others may see us better and see themselves through us. The difficulty of writing—the cursed, nerve-shredding, fingernail-yanking uncertainty of it—is what forces the discovery of anything that is meaningful to writers or to their readers. To have AI strip all that away would be to render us wordless, thoughtless, self-less. Give me the shredded nerves and yanked fingernails any day.  

Samanth Subramanian is the author of A Dominant Character: The Radical Science and Restless Politics of J.B.S. Haldane . He is a senior reporter at Quartz.

Our approach

• Responsibility
• Infrastructure
• Try Meta AI

RECOMMENDED READS

• 5 Steps to Getting Started with Llama 2
• The Llama Ecosystem: Past, Present, and Future
• Introducing Code Llama, a state-of-the-art large language model for coding
• Meta and Microsoft Introduce the Next Generation of Llama
• Today, we’re introducing Meta Llama 3, the next generation of our state-of-the-art open source large language model.
• Llama 3 models will soon be available on AWS, Databricks, Google Cloud, Hugging Face, Kaggle, IBM WatsonX, Microsoft Azure, NVIDIA NIM, and Snowflake, and with support from hardware platforms offered by AMD, AWS, Dell, Intel, NVIDIA, and Qualcomm.
• We’re dedicated to developing Llama 3 in a responsible way, and we’re offering various resources to help others use it responsibly as well. This includes introducing new trust and safety tools with Llama Guard 2, Code Shield, and CyberSec Eval 2.
• In the coming months, we expect to introduce new capabilities, longer context windows, additional model sizes, and enhanced performance, and we’ll share the Llama 3 research paper.
• Meta AI, built with Llama 3 technology, is now one of the world’s leading AI assistants that can boost your intelligence and lighten your load—helping you learn, get things done, create content, and connect to make the most out of every moment. You can try Meta AI here .

Today, we’re excited to share the first two models of the next generation of Llama, Meta Llama 3, available for broad use. This release features pretrained and instruction-fine-tuned language models with 8B and 70B parameters that can support a broad range of use cases. This next generation of Llama demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning. We believe these are the best open source models of their class, period. In support of our longstanding open approach, we’re putting Llama 3 in the hands of the community. We want to kickstart the next wave of innovation in AI across the stack—from applications to developer tools to evals to inference optimizations and more. We can’t wait to see what you build and look forward to your feedback.

Our goals for Llama 3

With Llama 3, we set out to build the best open models that are on par with the best proprietary models available today. We wanted to address developer feedback to increase the overall helpfulness of Llama 3 and are doing so while continuing to play a leading role on responsible use and deployment of LLMs. We are embracing the open source ethos of releasing early and often to enable the community to get access to these models while they are still in development. The text-based models we are releasing today are the first in the Llama 3 collection of models. Our goal in the near future is to make Llama 3 multilingual and multimodal, have longer context, and continue to improve overall performance across core LLM capabilities such as reasoning and coding.

State-of-the-art performance

Our new 8B and 70B parameter Llama 3 models are a major leap over Llama 2 and establish a new state-of-the-art for LLM models at those scales. Thanks to improvements in pretraining and post-training, our pretrained and instruction-fine-tuned models are the best models existing today at the 8B and 70B parameter scale. Improvements in our post-training procedures substantially reduced false refusal rates, improved alignment, and increased diversity in model responses. We also saw greatly improved capabilities like reasoning, code generation, and instruction following making Llama 3 more steerable.

*Please see evaluation details for setting and parameters with which these evaluations are calculated.

In the development of Llama 3, we looked at model performance on standard benchmarks and also sought to optimize for performance for real-world scenarios. To this end, we developed a new high-quality human evaluation set. This evaluation set contains 1,800 prompts that cover 12 key use cases: asking for advice, brainstorming, classification, closed question answering, coding, creative writing, extraction, inhabiting a character/persona, open question answering, reasoning, rewriting, and summarization. To prevent accidental overfitting of our models on this evaluation set, even our own modeling teams do not have access to it. The chart below shows aggregated results of our human evaluations across of these categories and prompts against Claude Sonnet, Mistral Medium, and GPT-3.5.

Preference rankings by human annotators based on this evaluation set highlight the strong performance of our 70B instruction-following model compared to competing models of comparable size in real-world scenarios.

Our pretrained model also establishes a new state-of-the-art for LLM models at those scales.

To develop a great language model, we believe it’s important to innovate, scale, and optimize for simplicity. We adopted this design philosophy throughout the Llama 3 project with a focus on four key ingredients: the model architecture, the pretraining data, scaling up pretraining, and instruction fine-tuning.

Model architecture

In line with our design philosophy, we opted for a relatively standard decoder-only transformer architecture in Llama 3. Compared to Llama 2, we made several key improvements. Llama 3 uses a tokenizer with a vocabulary of 128K tokens that encodes language much more efficiently, which leads to substantially improved model performance. To improve the inference efficiency of Llama 3 models, we’ve adopted grouped query attention (GQA) across both the 8B and 70B sizes. We trained the models on sequences of 8,192 tokens, using a mask to ensure self-attention does not cross document boundaries.

Training data

To train the best language model, the curation of a large, high-quality training dataset is paramount. In line with our design principles, we invested heavily in pretraining data. Llama 3 is pretrained on over 15T tokens that were all collected from publicly available sources. Our training dataset is seven times larger than that used for Llama 2, and it includes four times more code. To prepare for upcoming multilingual use cases, over 5% of the Llama 3 pretraining dataset consists of high-quality non-English data that covers over 30 languages. However, we do not expect the same level of performance in these languages as in English.

To ensure Llama 3 is trained on data of the highest quality, we developed a series of data-filtering pipelines. These pipelines include using heuristic filters, NSFW filters, semantic deduplication approaches, and text classifiers to predict data quality. We found that previous generations of Llama are surprisingly good at identifying high-quality data, hence we used Llama 2 to generate the training data for the text-quality classifiers that are powering Llama 3.

We also performed extensive experiments to evaluate the best ways of mixing data from different sources in our final pretraining dataset. These experiments enabled us to select a data mix that ensures that Llama 3 performs well across use cases including trivia questions, STEM, coding, historical knowledge, etc.

Scaling up pretraining

To effectively leverage our pretraining data in Llama 3 models, we put substantial effort into scaling up pretraining. Specifically, we have developed a series of detailed scaling laws for downstream benchmark evaluations. These scaling laws enable us to select an optimal data mix and to make informed decisions on how to best use our training compute. Importantly, scaling laws allow us to predict the performance of our largest models on key tasks (for example, code generation as evaluated on the HumanEval benchmark—see above) before we actually train the models. This helps us ensure strong performance of our final models across a variety of use cases and capabilities.

We made several new observations on scaling behavior during the development of Llama 3. For example, while the Chinchilla-optimal amount of training compute for an 8B parameter model corresponds to ~200B tokens, we found that model performance continues to improve even after the model is trained on two orders of magnitude more data. Both our 8B and 70B parameter models continued to improve log-linearly after we trained them on up to 15T tokens. Larger models can match the performance of these smaller models with less training compute, but smaller models are generally preferred because they are much more efficient during inference.

To train our largest Llama 3 models, we combined three types of parallelization: data parallelization, model parallelization, and pipeline parallelization. Our most efficient implementation achieves a compute utilization of over 400 TFLOPS per GPU when trained on 16K GPUs simultaneously. We performed training runs on two custom-built 24K GPU clusters . To maximize GPU uptime, we developed an advanced new training stack that automates error detection, handling, and maintenance. We also greatly improved our hardware reliability and detection mechanisms for silent data corruption, and we developed new scalable storage systems that reduce overheads of checkpointing and rollback. Those improvements resulted in an overall effective training time of more than 95%. Combined, these improvements increased the efficiency of Llama 3 training by ~three times compared to Llama 2.

Instruction fine-tuning

To fully unlock the potential of our pretrained models in chat use cases, we innovated on our approach to instruction-tuning as well. Our approach to post-training is a combination of supervised fine-tuning (SFT), rejection sampling, proximal policy optimization (PPO), and direct preference optimization (DPO). The quality of the prompts that are used in SFT and the preference rankings that are used in PPO and DPO has an outsized influence on the performance of aligned models. Some of our biggest improvements in model quality came from carefully curating this data and performing multiple rounds of quality assurance on annotations provided by human annotators.

Learning from preference rankings via PPO and DPO also greatly improved the performance of Llama 3 on reasoning and coding tasks. We found that if you ask a model a reasoning question that it struggles to answer, the model will sometimes produce the right reasoning trace: The model knows how to produce the right answer, but it does not know how to select it. Training on preference rankings enables the model to learn how to select it.

Building with Llama 3

Our vision is to enable developers to customize Llama 3 to support relevant use cases and to make it easier to adopt best practices and improve the open ecosystem. With this release, we’re providing new trust and safety tools including updated components with both Llama Guard 2 and Cybersec Eval 2, and the introduction of Code Shield—an inference time guardrail for filtering insecure code produced by LLMs.

We’ve also co-developed Llama 3 with torchtune , the new PyTorch-native library for easily authoring, fine-tuning, and experimenting with LLMs. torchtune provides memory efficient and hackable training recipes written entirely in PyTorch. The library is integrated with popular platforms such as Hugging Face, Weights & Biases, and EleutherAI and even supports Executorch for enabling efficient inference to be run on a wide variety of mobile and edge devices. For everything from prompt engineering to using Llama 3 with LangChain we have a comprehensive getting started guide and takes you from downloading Llama 3 all the way to deployment at scale within your generative AI application.

A system-level approach to responsibility

We have designed Llama 3 models to be maximally helpful while ensuring an industry leading approach to responsibly deploying them. To achieve this, we have adopted a new, system-level approach to the responsible development and deployment of Llama. We envision Llama models as part of a broader system that puts the developer in the driver’s seat. Llama models will serve as a foundational piece of a system that developers design with their unique end goals in mind.

Instruction fine-tuning also plays a major role in ensuring the safety of our models. Our instruction-fine-tuned models have been red-teamed (tested) for safety through internal and external efforts. ​​Our red teaming approach leverages human experts and automation methods to generate adversarial prompts that try to elicit problematic responses. For instance, we apply comprehensive testing to assess risks of misuse related to Chemical, Biological, Cyber Security, and other risk areas. All of these efforts are iterative and used to inform safety fine-tuning of the models being released. You can read more about our efforts in the model card .

Llama Guard models are meant to be a foundation for prompt and response safety and can easily be fine-tuned to create a new taxonomy depending on application needs. As a starting point, the new Llama Guard 2 uses the recently announced MLCommons taxonomy, in an effort to support the emergence of industry standards in this important area. Additionally, CyberSecEval 2 expands on its predecessor by adding measures of an LLM’s propensity to allow for abuse of its code interpreter, offensive cybersecurity capabilities, and susceptibility to prompt injection attacks (learn more in our technical paper ). Finally, we’re introducing Code Shield which adds support for inference-time filtering of insecure code produced by LLMs. This offers mitigation of risks around insecure code suggestions, code interpreter abuse prevention, and secure command execution.

With the speed at which the generative AI space is moving, we believe an open approach is an important way to bring the ecosystem together and mitigate these potential harms. As part of that, we’re updating our Responsible Use Guide (RUG) that provides a comprehensive guide to responsible development with LLMs. As we outlined in the RUG, we recommend that all inputs and outputs be checked and filtered in accordance with content guidelines appropriate to the application. Additionally, many cloud service providers offer content moderation APIs and other tools for responsible deployment, and we encourage developers to also consider using these options.

Deploying Llama 3 at scale

Llama 3 will soon be available on all major platforms including cloud providers, model API providers, and much more. Llama 3 will be everywhere .

Our benchmarks show the tokenizer offers improved token efficiency, yielding up to 15% fewer tokens compared to Llama 2. Also, Group Query Attention (GQA) now has been added to Llama 3 8B as well. As a result, we observed that despite the model having 1B more parameters compared to Llama 2 7B, the improved tokenizer efficiency and GQA contribute to maintaining the inference efficiency on par with Llama 2 7B.

For examples of how to leverage all of these capabilities, check out Llama Recipes which contains all of our open source code that can be leveraged for everything from fine-tuning to deployment to model evaluation.

What’s next for Llama 3?

The Llama 3 8B and 70B models mark the beginning of what we plan to release for Llama 3. And there’s a lot more to come.

Our largest models are over 400B parameters and, while these models are still training, our team is excited about how they’re trending. Over the coming months, we’ll release multiple models with new capabilities including multimodality, the ability to converse in multiple languages, a much longer context window, and stronger overall capabilities. We will also publish a detailed research paper once we are done training Llama 3.

To give you a sneak preview for where these models are today as they continue training, we thought we could share some snapshots of how our largest LLM model is trending. Please note that this data is based on an early checkpoint of Llama 3 that is still training and these capabilities are not supported as part of the models released today.

We’re committed to the continued growth and development of an open AI ecosystem for releasing our models responsibly. We have long believed that openness leads to better, safer products, faster innovation, and a healthier overall market. This is good for Meta, and it is good for society. We’re taking a community-first approach with Llama 3, and starting today, these models are available on the leading cloud, hosting, and hardware platforms with many more to come.

Try Meta Llama 3 today

We’ve integrated our latest models into Meta AI, which we believe is the world’s leading AI assistant. It’s now built with Llama 3 technology and it’s available in more countries across our apps.

You can use Meta AI on Facebook, Instagram, WhatsApp, Messenger, and the web to get things done, learn, create, and connect with the things that matter to you. You can read more about the Meta AI experience here .

Visit the Llama 3 website to download the models and reference the Getting Started Guide for the latest list of all available platforms.

You’ll also soon be able to test multimodal Meta AI on our Ray-Ban Meta smart glasses.

As always, we look forward to seeing all the amazing products and experiences you will build with Meta Llama 3.

Our latest updates delivered to your inbox

Subscribe to our newsletter to keep up with Meta AI news, events, research breakthroughs, and more.

Join us in the pursuit of what’s possible with AI.

Product experiences

Foundational models

Latest news

Meta © 2024