how to make chatgpt write better essays

Have a language expert improve your writing

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

• Knowledge Base

Using AI tools

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

How to Write an Essay with ChatGPT | Tips & Examples

Published on June 22, 2023 by Koen Driessen . Revised on November 16, 2023.

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

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

You can use ChatGPT to:

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

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

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

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

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

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

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

Example: Using ChatGPT to write a research question

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

Check for common mistakes

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

Fix mistakes for free

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

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

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

Examples: Using ChatGPT to generate an essay outline

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

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

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

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

Example: Using ChatGPT to find sources

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

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

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

Example: Using ChatGPT to summarize/paraphrase

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

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

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

Try for free

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

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

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

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

Example: Using ChatGPT for feedback

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

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

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

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

Citing sources

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

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

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

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

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

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

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

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

Cite this Scribbr article

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

Driessen, K. (2023, November 16). How to Write an Essay with ChatGPT | Tips & Examples. Scribbr. Retrieved April 2, 2024, from https://www.scribbr.com/ai-tools/chatgpt-essay/

Is this article helpful?

Koen Driessen

Other students also liked, how to write good chatgpt prompts, how to use chatgpt in your studies, what are the limitations of chatgpt.

Koen Driessen (Scribbr Team)

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

Still have questions?

Unlimited academic ai-proofreading.

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

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

• Backchannel
• Newsletters
• WIRED Insider
• WIRED Consulting

David Nield

5 Ways ChatGPT Can Improve, Not Replace, Your Writing

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

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

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

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

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

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

Julian Chokkattu

Brenda Stolyar

Adrienne So

ChatGPT is never short of ideas.

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

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

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

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

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

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

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

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

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

Get your names right with ChatGPT.

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

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

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

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

You Might Also Like …

In your inbox: Will Knight's Fast Forward explores advances in AI

This shadowy firm enables businesses to operate in near-total secrecy

Scientists are inching closer to bringing back the woolly mammoth

The first rule of the Extreme Dishwasher Loading Facebook group is …

Phones for every budget: These devices stood up to WIRED’s testing

Boone Ashworth

Estelle Erasmus

Reece Rogers

Michael Calore

WIRED COUPONS

Tax Deadline Promo! Up to 10% off TurboTax

$50 off in-person tax prep when you switch from TurboTax or another tax provider | H&R Block coupon

$25 off your first 3 orders with Exclusive Instacart Promo Code

Dyson promo code: 20% off all purchases + free shipping

GoPro Promo Code: 15% off Cameras and Accessories

Up to +30% Off with your Samsung promo code

'ZDNET Recommends': What exactly does it mean?

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

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

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

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

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

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

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

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

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

How ChatGPT can help you write an essay

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

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

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

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

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

1. Use ChatGPT to generate essay ideas

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

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

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

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

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

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

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

2. Use the chatbot to create an outline

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

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

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

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

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

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

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

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

3. Use ChatGPT to find sources

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

Also: How to make ChatGPT provide sources and citations

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

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

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

Also:   How to use ChatGPT to make charts and tables

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

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

4. Use ChatGPT to write an essay

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

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

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

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

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

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

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

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

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

5. Use ChatGPT to co-edit your essay

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

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

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

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

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

What is AI? Everything to know about artificial intelligence

Chatgpt is finally revealing its sources - but there's a catch, microsoft wants to stop you from using ai chatbots for evil.

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

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

Should I Use ChatGPT to Write My Essays?

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

Jessica A. Kent

ChatGPT is one of the most buzzworthy technologies today.

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

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

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

What is Generative AI?

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

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

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

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

The Drawbacks of Generative AI

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

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

It’s not intelligence, it’s statistics

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

It “hallucinates”

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

It doesn’t do research  

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

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

There are data privacy concerns

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

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

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

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

It skirts the plagiarism issue

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

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

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

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

Explore Our High School Programs

How to Use AI as a Tool to Support Your Work

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

Generate ideas for essays

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

Generate outlines

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

Generate titles for your essays

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

The Benefits of Writing Your Essays Yourself

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

Create your own ideas

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

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

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

Develop your critical thinking and analysis skills

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

Improve your research skills

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

Learn to be a great communicator

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

Be impacted by what you’re learning about : 

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

Resources to Improve Your Essay Writing Skills

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

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

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

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

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

The Future of AI in the Classroom

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

About the Author

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

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

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

Harvard Division of Continuing Education

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

• Entertainment
• Beebom Gadgets

How to Use ChatGPT to Write Essays That Impress

Step 1: Use ChatGPT to Find and Refine Essay Topics

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

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

Step 2: Ask ChatGPT to Construct an Outline

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

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

Step 3: Get ChatGPT to Cite Sources for Your Essay

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

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

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

Step 4: Have ChatGPT Write the Essay

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

Step 5: Edit the Essay with ChatGPT

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

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

Step 6: Export the Essay for Submission

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

Bonus: ChatGPT and AI Apps to Write Essays

1. writesonic.

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

Upanishad Sharma

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

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

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

Add new comment

• Link to facebook
• Link to linkedin
• Link to twitter
• Link to youtube
• Writing Tips

How to Write Your Essay Using ChatGPT

• 5-minute read
• 2nd May 2023

It’s tempting, isn’t it? You’ve read about and probably also witnessed how quickly ChatGPT can knock up text, seemingly in any genre or style and of any length, in less time than it takes you to make a cup of tea. However, getting ChatGPT to write your essay for you would be plagiarism . Universities and colleges are alive to the issue, and you may face serious academic penalties if you’re found to have used AI in that way.

So that’s that, right? Not necessarily.

This post is not about how to get ChatGPT to write your essay . It’s about how you can use the tool to help yourself write an essay .

What Is ChatGPT?

Let’s start with the basics. ChatGPT is one of several chatbots that can answer questions in a conversational style, as if the answer were coming from a human. It provides answers based on information it receives in development and in response to prompts you provide.

In that respect, like a human, ChatGPT is limited by the information it has. Where it lacks the information, it has a tendency to fill the gaps regardless . This action is dangerous if you’re relying on the accuracy of the information, and it’s another good reason you should not get ChatGPT to write your essay for you.

How Can You Use ChatGPT to Help With Your Essay?

Forget about the much talked-about writing skills of ChatGPT – writing is your thing here. Instead, think of ChatGPT as your assistant. Here are some ideas for how you can make it work for you.

Essay Prompts

If your task is to come up with your own essay topic but you find yourself staring at a blank page, you can use ChatGPT for inspiration. Your prompt could look something like this:

ChatGPT can offer several ideas. The choice of which one to write about (and you may, of course, still come up with one of your own) will be up to you, based on what interests you and the topic’s potential for in-depth analysis.

Essay Outlines

Having decided on your essay topic – or perhaps you’ve already been given one by your instructor – you may be struggling to figure out how to structure the essay. You can use ChatGPT to suggest an outline. Your prompt can be along these lines:

Just as you should not use ChatGPT to write an essay for you, you should not use it to research one – that’s your job.

If, however, you’re struggling to understand a particular extract, you can ask ChatGPT to summarize it or explain it in simpler terms.

Find this useful?

Subscribe to our newsletter and get writing tips from our editors straight to your inbox.

That said, you can’t rely on ChatGPT to be factually accurate in the information it provides, even when you think the information would be in its database, as we discovered in another post. Indeed, when we asked ChatGPT whether we should fact-check its information, the response was:

An appropriate use of ChatGPT for research would be to ask for academic resources for further reading on a particular topic. The advantage of doing this is that, in going on to locate and read the suggested resources, you will have checked that they exist and that the content is relevant and accurately set out in your essay.

Instead of researching the topic as a whole, you could use ChatGPT to generate suggestions for the occasional snippet of information, like this:

Before deciding which of its suggestions – if any – to include, you should ask ChatGPT for the source of the fact or statistic so you can check it and provide the necessary citation.

Referencing

Even reading the word above has probably made you groan. As if writing the essay isn’t hard enough, you then have to not only list all the sources you used, but also make sure that you’ve formatted them in a particular style. Here’s where you can use ChatGPT. We have a separate post dealing specifically with this topic, but in brief, you can ask something like this:

Where information is missing, as in the example above, ChatGPT will likely fill in the gaps. In such cases, you’ll have to ensure that the information it fills in is correct.

Proofreading

After finishing the writing and referencing, you’d be well advised to proofread your work, but you’re not always the best person to do so – you’d be tired and would likely read only what you expect to see. At least as a first step, you can copy and paste your essay into ChatGPT and ask it something like this:

You’ve got the message that you can’t just ask ChatGPT to write your essay, right? But in some areas, ChatGPT can help you write your essay, providing, as with any tool, you use it carefully and are alert to the risks.

We should point out that universities and colleges have different attitudes toward using AI – including whether you need to cite its use in your reference list – so always check what’s acceptable.

After using ChatGPT to help with your work, you can always ask our experts to look over it to check your references and/or improve your grammar, spelling, and tone. We’re available 24/7, and you can even try our services for free .

Share this article:

Post A New Comment

Got content that needs a quick turnaround? Let us polish your work. Explore our editorial business services.

3-minute read

What Is a Content Editor?

Are you interested in learning more about the role of a content editor and the...

4-minute read

The Benefits of Using an Online Proofreading Service

Proofreading is important to ensure your writing is clear and concise for your readers. Whether...

2-minute read

6 Online AI Presentation Maker Tools

Creating presentations can be time-consuming and frustrating. Trying to construct a visually appealing and informative...

What Is Market Research?

No matter your industry, conducting market research helps you keep up to date with shifting...

8 Press Release Distribution Services for Your Business

In a world where you need to stand out, press releases are key to being...

How to Get a Patent

In the United States, the US Patent and Trademarks Office issues patents. In the United...

Make sure your writing is the best it can be with our expert English proofreading and editing.

All-in-one Collaborative API Development Platform

API Documentation

API Debugging

API Automated Testing

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

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

David Demir

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

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

How to Access ChatGPT

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

6 Simple Steps to Improve Your Writing with ChatGPT

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

Step 1. Sign up or log in to ChatGPT

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

Step 2. Identify the Purpose of Your Writing

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

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

Step 3. Use ChatGPT to Generate Ideas:

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

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

Step 4. Organize your ideas

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

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

Step 5. Use ChatGPT to Improve Your Writing

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

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

Step 6. Revise and Edit the Business Plan

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

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

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

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

Join Apidog's Newsletter

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

Productivity

How to train ChatGPT to write like you

Custom instructions let you add background information and requirements you'd like ChatGPT to consider whenever it generates a response. For example, you can tell it to always respond in a formal tone. Or to add an emoji at the end of every sentence (please don't). 

If you use ChatGPT to create written content, this means you can essentially program ChatGPT to write in your writing style—you just have to know what your style is. 

Here's a step-by-step guide on how to identify your writing style, so you can train ChatGPT to write like you. 

4 key elements that make up your writing style

Broadly speaking, your writing style is made up of four key elements: 

Voice refers to the way you "sound" on the page. For example, if you use a lot of colloquialisms, your voice may be informal or conversational. Or, if you use more Shakespeare-like language, your voice may be more theatrical.   

Tone refers to the attitude conveyed in your writing toward the subject or audience. If your writing is filled with a lot of rhetorical questions and irony, that might convey a sarcastic tone. Or if you include a lot of jokes and silly analogies, it may be more playful. 

Style encompasses both voice and tone but also includes the specific choices you make in language and sentence structure. For example, you may opt for a minimalist approach to writing—get the message across in as few words as possible. 

Structure refers to more than just the intro, body, and conclusion. It's how you organize everything in your writing, from word order to paragraph flow. For example, maybe your writing always follows a linear format (this happened, and then this happened). Or it might jump around in time. 

How to find your writing style using ChatGPT 

Before you can train ChatGPT on your writing style, you need to be able to describe your writing style. Ironically, ChatGPT is the perfect partner to help you identify this. Here's how. 

Gather your most you-like content. Identify three to five pieces of written content that reflect your true voice or the voice you want to train ChatGPT on. If you have digital copies of each, even better—you'll feed them to ChatGPT in the next step. 

Ask ChatGPT to analyze your writing . Feed ChatGPT with a copy of one of your pieces, and ask it to analyze your writing style. It's worth mentioning that on a free account, you can only paste about 3,000 words at a time. Here's a prompt you can use: 

[Paste your content]

Analyze the writing voice, tone, and structure of the article above. Output bullet points.

Or, if your content lives online and you have access to ChatGPT Plus , you can paste the URL to all your articles and use this prompt: 

[Insert links to articles] 

Analyze the writing voice, tone, and structure of each article linked above. Output bullet points.

Repeat . If ChatGPT is analyzing one piece of content at a time, repeat the above steps for every article you've identified. 

Once ChatGPT has analyzed all your articles, review the results and note any patterns. If certain descriptors come up a lot and resonate with you, jot them down in your go-to note-taking app . And for those that don't, leave them behind. 

Now you're ready to add custom instructions to ChatGPT. 

How to use ChatGPT's custom instructions

Now that you've identified the characteristics of your writing style, add them to ChatGPT's custom instructions. 

Note : The custom instructions feature is available for ChatGPT Plus users as of this writing, but access will be granted to all users in the near future. If you don't have access to custom instructions yet, you can still use the template prompt in step three to tell ChatGPT how you want it to respond. (You'll have to repeat the instructions every time you start a new chat, though.)

With ChatGPT open, click your profile. 

Click Custom instructions . 

In the section under How would you like ChatGPT to respond? enter the characteristics of your writing style. Here's a template you can use to input your instructions: 

Use this voice: [enter your descriptions] 

Use this tone: [enter your descriptions] 

Use this style: [enter your descriptions]

Use this structure: [enter your descriptions] 

Click the toggle next to Enable for new chats . 

Click Save . 

If you want, you can also provide ChatGPT with additional context in the section under What would you like ChatGPT to know about you to provide better responses? For example, "I write children's storybooks." Or "I write product reviews for Wirecutter ." 

You're all set. 

Examples of AI-generated content prompted with vs. without a clearly defined writing style

If you haven't instructed ChatGPT on the specifics of your writing style before, you may not know the hours of valuable time you could save from having to edit impersonal and robotic-sounding first drafts.  

Here's an example of what ChatGPT's response sounds like when prompted to write a sales email in my specific writing style versus without. 

The first prompt, which doesn't include instructions on my writing style, generates an email that would be fine if I worked at a really buttoned-up firm with no personality. 

And here's what ChatGPT spit out when I added these instructions (you can add the same directives to only your custom instructions if you have ChatGPT-4):

Use this voice: authoritative and engaging.

Use this tone: conversational and slightly motivating. 

Use this style: informal. 

Use this structure: start with a brief problem statement and then explain the solution.

The difference between the two outputs is like night and day. One would make me click; the other would get an immediate swipe. 

Experiment and tweak as you go 

Once you've identified your writing style and added custom instructions to ChatGPT, start experimenting. Ask it to write your next article outline . Or to punch up your social media captions with a little humor .  

And if you notice the outputs aren't hitting the nail on the head right away, it may be worth tweaking your writing style descriptors or trying new prompts . Instead of an informal tone filled with slang, maybe what you're really going after is a slightly informal but professional tone. Keep experimenting. Keep tweaking. 

Related reading: 

6 ChatGPT prompts that will generate great sales emails

ChatGPT vs. Bard: Which should you use?

What is prompt engineering?

How to build a custom version of ChatGPT with OpenAI's GPT builder

This was a guest post by Matt Giaro. Sign up for Matt's free AI blogging email course , or you can reach him at mattgiaro.com .

Get productivity tips delivered straight to your inbox

We’ll email you 1-3 times per week—and never share your information.

Matt Giaro helps experts turn their ideas into income in their spare time. You can find him at mattgiaro.com.

• Artificial intelligence (AI)

Related articles

How to take a full page screenshot on Chrome

How to make a Gantt chart in Google Sheets

What is Perplexity AI?

How to find and share your Wi-Fi password

Improve your productivity automatically. Use Zapier to get your apps working together.

• Privacy news

Tips & tricks

• ExpressVPN news

Guide: How to use ChatGPT to improve your writing

Sonja Raath

With the introduction of ChatGPT in November 2022, many got a first taste of what an AI chatbot can do when it comes to generating text—and it’s a lot.

Not only does ChatGPT answer questions, but it can form essays, poems, articles, with users able to specify the topic, length, tone of voice, and much more. While it’s raised questions about the future for professional writers and the ramifications for schoolwork, it’s also become a legitimate tool to increase productivity and efficiency.

In fact, a recent study conducted by MIT found that college-educated professionals who used ChatGPT to complete writing tasks were able to finish in nearly half the time it took those who relied on traditional word processors. The quality of their work also improved by 45%.

So what are the best ways to use ChatGPT to enhance your writing? It’s all about using effective prompts.

Read more: How to fix the error ‘OpenAI is not available in your country’?

Remember, you’re not having a conversation 

Before you start using ChatGPT to enhance your writing, it’s important to see the AI for what it is. ChatGPT is not like Google or Alexa as it generates text, and is not able to give overly-factual information or interact with the physical world. It’s also not a human that you can give instructions to—no matter how helpful it may seem. 

For example, if you asked ChatGPT to “proofread my essay and make corrections,” it wouldn’t know what specific changes or corrections you’re looking for without further clarification. It might suggest edits based on grammatical rules, but it wouldn’t have the contextual understanding that a human proofreader would bring to the task.

Basically, ChatGPT is a non-sentient machine that you program words into in order to generate the text you need. The more specific and elaborate your prompt is, the better ChatGPT’s response will be. 

If you ask ChatGPT to “ Write an essay about teacup pigs wearing sunglasses,” for example , the AI will generate a boring and straightforward piece that does little to satisfy your request. 

However, if you change your approach and provide clear bullet points to your prompt, you’re far more likely to push for the result you want. 

For example: Write an essay about teacup pigs wearing sunglasses with the following points: 

• Use a fun and witty tone that is thought-provoking and not too colloquial.
• Use at least one clear example.
• Make it concise.
• Write for a well-informed audience.
• Use a style like the New Yorker.
• Make it at least 7 paragraphs.
• Vary the language in each one.
• End with a pun.

By using more unique prompts, you can get a much more comprehensive and unique version of what you’re after. 

However, notice that not every part of the prompt has been followed exactly. A lot of what the AI wrote was also repetitive, and some of the points it made were out of context. This is typical of how generative AI works—you don’t always get what you directly ask for. 

This is why we don’t recommend using ChatGPT to write copy for you from scratch as a) it tends to go on its own tangent and b) it has a tendency of making up its own facts. Instead, we suggest you use ChatGPT to:

• Enhance existing copy  
• Generate ideas
• Improve your vocabulary  
• Refine your writing style  
• Learn about writing techniques

Dos and don’ts for prompting ChatGPT

Use chatgpt to enhance your copy.

From refining your writing style to generating fresh ideas and improving your vocabulary, ChatGPT can help breathe life into your words. It can also help you save time—anything that can speed up the writing process is a valuable tool. 

Let’s take this problematic paragraph that attempts to answer the question, “Should humanity be worried about AIs taking over the world?” There are obvious spelling, grammatical, and phrasing mistakes:

“Many people thinks that AI is dangerous and could take over the world. The idea of robots be in control is terrifying and a lot of people is worried about this. But, we shouldnt forget that AI is programmed by humans, so it doesnt have the ability to do things on its own. So, humans shouldnt be worry about it.”

Now let’s ask ChatGPT to correct it while giving it prompts to enhance the argument the paragraph is trying to make: 

Not only did the AI give the original paragraph a clearer and more concise structure, but it also aimed to make it more intriguing. Several spelling and grammatical mistakes, such as tense consistency and sentence structure were fixed. It also used appropriate conjunctions and transitional phrases to improve the flow and coherence of the paragraph. Lastly, it avoided contractions to make the writing more formal and professional.

While the reworked paragraph isn’t necessarily perfect, it does give the writer more to work with, pushing them to change their writing style and expand on their thinking process. 

When using ChatGPT to enhance your writing: 

• Start with a clear goal: Before interacting with ChatGPT, have a clear idea of what you want to achieve. Identify the specific problem you’re trying to solve or the question you want to answer.
• Input relevant information: To get the best possible response from ChatGPT, give it as much relevant information as possible. This can include background information, context, and any other relevant details you can think of that it can rework to get your point across.
• Use specific prompts: As mentioned above, be as specific as possible in your prompts. This will help ensure that the responses you receive are relevant and useful.
• Evaluate the responses: When you receive a response from ChatGPT, take the time to evaluate it carefully. Look for ways to refine and improve your existing copy based on the insights provided. Don’t just lift them directly.
• Iterate and refine: Once you have evaluated the response from ChatGPT, use the insights gained to refine and improve your existing copy. Iterate this process until you are satisfied with the results. 

Use ChatGPT to generate ideas

We’ve all had moments when our creative wells run dry, and we find ourselves struggling to come up with new ideas. ChatGPT is trained on vast amounts of data from the internet, including books, articles, and other written works, which means it has access to an immense wealth of information. This can help stuck writers come up with ideas that are relevant, informative, and creative.

Here are some tips for using ChatGPT to help you spark new ideas: 

Prompt ChatGPT to think like your target audience

One way to generate new ideas is by putting yourself in the shoes of your target audience. For example, if you’re trying to come up with marketing ideas for a new product, you could ask ChatGPT to think like a potential customer and provide you with insights on what would appeal to them.

Ask it to create a “what if” scenario

ChatGPT can be a valuable tool when asking “what if” questions by generating hypothetical scenarios based on your prompts.

Have the AI play a character

Another way to get interesting ideas out of ChatGPT is by asking it to play a character. You can prompt the AI to think of itself as a historical figure, a famous author, or even a fictional character. This can help you gain new insights and perspectives that you may not have considered before.

Ask for analogies and metaphors

Analogies and metaphors can be powerful tools for generating new ideas and understanding difficult and complicated topics. They can also help you to gain a fresh perspective on the subject at hand. For example, if you’re writing about a complex mathematical concept, but struggling to get your head around it, you could ask ChatGPT to provide a metaphor that would help you understand it better.

Use ChatGPT to generate random words and phrases

Trained on massive amounts of text, ChatGPT has the ability to generate an endless array of random words and phrases. This functionality can be a valuable tool for those who want to expand their vocabulary. ChatGPT can also help generate a random phrase that could be used as a starting point for your writing.

Use ChatGPT to improve your vocabulary

If you’re stuck on finding the right word to convey a particular meaning, you can ask ChatGPT to suggest synonyms or antonyms. You can also use ChatGPT to learn new words and their definitions, which can help you expand your vocabulary and improve your writing.

Use ChatGPT to refine your writing style

A writing style is a particular way of expressing oneself in writing, which is often characterized by the use of specific language, tone, and structure. ChatGPT can provide guidance on various writing styles, including descriptive, narrative, expository, and persuasive writing.

Additionally, the AI can help you understand different writing genres so you can pick the best one to suit your needs for a particular piece. For example, fiction, non-fiction, poetry, drama, and screenplays. ChatGPT can also analyze your writing to ensure you’re sticking to a particular style of writing, such as SEO writing, and genre. It can also assist you in learning how to structure your writing before you even begin putting your thoughts onto the page. 

For example, if you’re tasked with writing an essay on The Importance of Regular Exercise for Mental Health , you can ask ChatGPT to help you with its structure:

Use ChatGPT to learn about new writing techniques

From summarizing and paraphrasing to storytelling and symbolism, here are 10 writing techniques that ChatGPT can help you master:

How do you use ChatGPT to enhance your writing? Let us know in the comments below. 

Read more: How to fix ‘ChatGPT is at capacity’ error with a VPN

FAQ: About ChatGPT

How many users does chatgpt have now.

ChatGPT reached 100 million users in the first two months since it launched (on November 30, 2022). ChatGPT gets more than 13 million daily visitors.

Is ChatGPT free?

Yes, you can use ChatGPT for free. The service does offer a paid version, called ChatGPT Plus. It’s currently available to people in the U.S. on a waitlist. It costs 20 USD a month, and provides access to ChatGPT during peak times, faster response times from the chatbot, and priority access to new features and improvements.

Is ChatGPT an app?

No, ChatGPT does not offer a downloadable app. Users must access it in a browser at chat.openai.com

Take the first step to protect yourself online

30-day money-back guarantee

Enjoy a safer online experience with powerful privacy protection

Like what you have read?

Clap for this post. Or share your thoughts!

Subscribe to the weekly blog newsletter

Get the latest in privacy news, tips, tricks, and security guides to level-up your digital security.

• Related posts
• Featured Posts
• More from the author

How to fix the error ‘OpenAI is not available in your country’?

How to fix ‘ChatGPT is at capacity’ error with a VPN

We asked OpenAI’s chatbot to write about its maker

​​AI-generated art: What is it, and how does it work?

Will AI bots replace lawyers?

Dark Web Links: The best .onion and Tor sites in 2024

Tech Friend: 5 great phones under 400 USD

10 signs a shopping website is fake

4 ways to hide from drone surveillance

What is the singularity in AI?

How to track your own luggage

Are age verification laws in the U.S. a threat to digital freedom?

18 interesting and cool things you can do with a VPN app

15 (decent) alternatives to ChatGPT in 2024

Gaming destinations ranked: 20+ top cities for gamers

Cybersecurity spending: How much are countries investing in their digital defenses?

Dual dominance: 20+ pro athletes who are big gamers

How to choose a gaming router for the best gameplay

Browser cache vs. cookies: Are they different?

How to choose a router

Does your computer have a virus? Here’s how to check

It seems interesting to improve a text in English ?

absolutely useless. i write what i want. i edit it. no need for a dumb software to mess it up.

Thank you for the valuable information on the blog. I am not an expert in blog writing, but I am reading your content slightly, increasing my confidence in how to give the information properly. Your presentation was also good, and I understood the information easily.

This article should have been titled “How to Use ChapGPT to Do Your Writing for You”–because that’s essentially what you get when you add up all the tasks above.

Real writers with a conscience should stay away from this digital witch, unless they wish to lobotomize their innate potential as writers. I’ll let A.I. run spell checks and otherwise take out the garbage. The rest is up to me and me alone.

The title of this piece should have been, “How to Use ChatGPT to Do Your Writing For You”–because that’s essentially what happens when you ask it to perform tasks in multiple areas that add up to what is the “writing process.”

Real writers with a conscience should stay the hell away from this digital witch, unless they wish to lobotomize their future innate writing potential. A.I. can run spell checks and otherwise take out the garbage for me; no way I’ll let it do more.

Leave a Comment Cancel reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes:

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>

ExpressVPN is proudly supporting

Subscribe to the blog newsletter

Choose language.

How to use ChatGPT for writing

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

Summarizing other works

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

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

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

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

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

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

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

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

Get daily insight, inspiration and deals in your inbox

Get the hottest deals available in your inbox plus news, reviews, opinion, analysis and more from the TechRadar team.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

ChatGPT just took a big step towards becoming the next Google with its new account-free version

OpenAI's new voice synthesizer can copy your voice from just 15 seconds of audio

Google Home app could soon work offline and finally support your old Nest camera

Most Popular

By Emma Street March 23, 2024

By Andy Murray March 23, 2024

By Aatif Sulleyman March 23, 2024

By Will Hall March 22, 2024

By Dashiell Wood March 22, 2024

By Ruth Jones March 22, 2024

By Olivia Powell March 22, 2024

By Charlotte Henry March 21, 2024

By Aatif Sulleyman March 21, 2024

By Will Hall March 21, 2024

• 2 Samsung will use sewage water to quench surging thirst for semiconductors — 400 million liters of waste water to be purified and used daily to manufacture electronic chips
• 3 256TB SSDs could land before 2026 with a surprisingly low price — but will most likely use a controversial and popular trick borrowed from tape technology
• 4 Samsung archrival plans construction of world's largest chip factory — at more than $90 billion, it will take more than 20 years to finish, so one wonders what other exciting tech will it produce
• 5 You can get a MacBook Air for $699 and a Dell XPS 13 for just $599 - is this the best time ever for laptop buyers?
• 2 macOS isn’t perfect – but every day with Windows 11 makes me want to use my MacBook full-time
• 3 iOS 18 might break the iPhone's iconic app grid, and it's a change no one asked for
• 4 Intel's first blockbuster chip was the 8088 – and it changed everything 45 years ago
• 5 This neat iPhone camera trick will let you take pictures using nothing but your voice

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

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

Last Updated: March 31, 2024 Fact Checked

Getting ChatGPT to Write the Essay

Using ai to help you write, expert interview.

This article was written by Bryce Warwick, JD and by wikiHow staff writer, Nicole Levine, MFA . Bryce Warwick is currently the President of Warwick Strategies, an organization based in the San Francisco Bay Area offering premium, personalized private tutoring for the GMAT, LSAT and GRE. Bryce has a JD from the George Washington University Law School. This article has been fact-checked, ensuring the accuracy of any cited facts and confirming the authority of its sources. This article has been viewed 44,530 times.

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

Things You Should Know

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

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

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

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

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

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

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

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

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

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

Expert Q&A

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

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

You Might Also Like

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

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

About This Article

• Send fan mail to authors

Is this article up to date?

Featured Articles

Trending Articles

Watch Articles

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

wikiHow Tech Help Pro:

Level up your tech skills and stay ahead of the curve

How-To Geek

How to get chatgpt to write better fiction.

With ChatGPT, it's all about the prompts.

Quick Links

Chatgpt's fiction writing capabilities and limitations, understanding fiction writing, tips for improving chatgpt's fiction writing, techniques for enhancing chatgpt's writing style, using machine learning to fine-tune chatgpt's writing.

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

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

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

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

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

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

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

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

• Rising action
• Falling action

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

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

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

• Character descriptions
• Relationships

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

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

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

• Time period

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

Perspective

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Providing Context and Backstory

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

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

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

Building a Solid Plot Structure

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

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

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

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

Developing Compelling Characters

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

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

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

Related: How to Create ChatGPT Personas for Every Occasion

Crafting Engaging Dialogue

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

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

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

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

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

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

Using Descriptive Language

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

Employing Figurative Language

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

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

Incorporating Sensory Details

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

Varying Sentence Structure

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

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

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

How Machine Learning Works

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

ChatGPT: A Change in How You Use It, and Everything Else to Know

I n late 2022, OpenAI wowed the world when it introduced ChatGPT and showed us a chatbot with an entirely new level of power, breadth and usefulness, thanks to the generative AI technology behind it. Since then, ChatGPT has continued to evolve, including its most recent development: easy access for everyone.

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

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

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

What is ChatGPT?

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

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

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

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

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

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

What's ChatGPT's origin?

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

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

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

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

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

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

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

How do I use ChatGPT?

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

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

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

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

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

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

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

How much does ChatGPT cost?

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

For more capability, there's also a subscription called ChatGPT Plus that costs $20 per month that offers a variety of advantages: It responds faster, particularly during busy times when the free version is slow or sometimes tells you to try again later. It also offers access to newer AI models, including GPT-4 . The free ChatGPT uses the older GPT-3.5, which doesn't do as well on OpenAI's benchmark tests but which is faster to respond. The newest variation, GPT-4 Turbo, arrived in late 2023 with more up-to-date responses and an ability to ingest and output larger blocks of text.

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

Perhaps most importantly, ChatGPT Plus lets you use GPTs.

What are these GPTs?

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

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

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

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

What GPTs are available now?

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

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

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

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

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

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

How up to date is ChatGPT?

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

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

Can you trust ChatGPT responses?

Sadly, no. Well, sometimes, sure, but you need to be wary.

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

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

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

Such fabrications are called hallucinations in the AI business.

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

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

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

Is the hallucination problem getting better?

Yes, but we haven't seen a breakthrough.

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

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

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

Can you use ChatGPT for wicked purposes?

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

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

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

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

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

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

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

What about ChatGPT and cheating in school?

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

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

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

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

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

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

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

Is ChatGPT coming for my job?

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

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

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

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

How will ChatGPT affect programmers?

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

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

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

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

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

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

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

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

Editors' note: CNET is using an AI engine to help create some stories. For more, see  this post .

• Top Courses
• Online Degrees
• Find your New Career
• Join for Free

ChatGPT-3.5 vs. 4: What’s the Difference?

Compare ChatGPT 3.5 versus 4 and learn how the newest version of OpenAI’s generative AI technology is safer, more accurate, and more powerful. Plus, discover how companies are putting these advancements to work.

When OpenAI released ChatGPT-3.5 to the public in late 2022, it sparked excitement and fear surrounding the breakthrough technology. OpenAI released the next version, ChatGPT-4, in March of 2023 with demonstrated improvements in accuracy, security, memory, context windows, and increased functionality to respond to images and voice prompts. 

In this article, you’ll learn more about the improvements OpenAI made between the GPT-3.5 and GPT-4, as well as examples of how it performs more impressively and information on OpenAI’s pricing model. 

Read more: What Is ChatGPT? (and How to Use It)

What is ChatGPT?

ChatGPT is an application created and managed by OpenAI that allows users to interface with GPT, a large language model that powers generative artificial intelligence. Users can submit requests to the app, and the AI model will consult its training data set to return a unique response to the prompt. 

In practice, ChatGPT can help you compose pieces of writing, such as personal correspondence, marketing materials, or webpage content. You can ask ChatGPT to help you write a grocery list, create a meal plan, design a workout program, describe art, summarize books, complete math problems, suggest code, or translate between languages, among many other things. 

ChatGPT, as we mentioned, is the chatbot you interact with. GPT stands for generative pre-trained transformers and is the brains and power behind ChatGPT’s capabilities. GPT-3 and GPT-4 are large language models created by OpenAI, the organization that also runs ChatGPT, and other artificial intelligence models like DALL-E. 

OpenAI previously trained GPT-3.5 on 175 billion parameters [ 1 ]. The organization chose not to reveal the specific details of how they trained GPT-4, partially because OpenAI now operates a for-profit arm, and competition in the space is hotter than when GPT-3.5 debuted. Rumors circulated that OpenAI used more than 100 trillion parameters to train GPT-4, but OpenAI CEO Sam Altman strongly denied those rumors. 

Read more: What Is the BERT Model and How Does It Work?

ChatGPT 3.5 vs. 4

ChatGPT-3.5 sparked much debate and enthusiasm over the many things it could do, such as generate text remarkably similar to human-written work, generate code, and solve math problems. ChatGPT-4’s capabilities are so much greater than ChatGPT-3.5 that a Microsoft research team called it an “early (yet still incomplete) version of an artificial general intelligence (AGI) system” [ 2 ]. The team pointed out a few potential applications for GPT-4, including in the fields of mathematics, coding, vision, medicine, law, and psychology. 

GPT-4 demonstrates superiority over GPT-3.5, even using human academic achievement standards. OpenAI reported that GPT-3.5 passed the Uniform Bar Exam with a score that would rank in the 10th percentile of test takers compared to actual people aspiring to become lawyers. GPT-4 performed remarkably better, ranking in the 90th percentile compared to humans [ 3 ]. Similarly, GPT-3.5 ranked in the 31st percentile compared to high school students competing in the Biology Olympiad, and GPT-4 scored significantly better, scoring in the 99th percentile [ 3 ]. 

Regarding the technical differences between GPT-3.5 and GPT-4, the latter offers increased functionality, memory, and safer and more accurate responses. Let’s look at a few specific upgrades when comparing ChatGPT-3.5 versus ChatGPT-4. 

1. ChatGPT-4 is multimodal and can respond to visual and audio input. 

In the previous version, you needed to write a prompt using text to generate an output from ChatGPT. With version 4, you can still use text, but you can also offer an image or even a voice command to make a request from the application. OpenAI’s example of this new feature is that you could put in a picture of the inside of your refrigerator, and ChatGPT-4 could suggest recipes you could make with the ingredients in the image. You can also speak to ChatGPT-4, and the AI will generate a voice to speak to you. Multimodality also allows ChatGPT to handle more functions, like captioning or translating videos. 

2. ChatGPT-4 is safer and more accurate than GPT-3.

According to OpenAI, ChatGPT-4 is “82 percent less likely to respond to requests for disallowed content and 40 percent more likely to produce factual responses than GPT-3.5 on our internal evaluations” [ 3 ]. The organization reports that it achieved this new security and accuracy using user feedback, consultations with security experts, and real-world applications. 

This upgraded feature is good news considering the controversies OpenAI is involved with surrounding misinformation, inaccuracy, and bias in its answers. One example of such controversy is a groundbreaking defamation lawsuit where a man claimed ChatGPT falsely reported that he embezzled money.

3. ChatGPT-4 has more memory than GPT-3.5.

ChatGPT-4 can remember a lot more of a conversation with a user. Not only was ChatGPT previously limited to information available online before 2021, but it also had a limited short-term memory of about 8,000 words. In conversation, the program might remember about 8,000 words until it starts forgetting what you discussed previously. In comparison, GPT-4 has a short-term memory eight times larger at 64,000 words. 

ChatGPT-4 also has a longer context window, or the amount of text it can process simultaneously. For example, you could ask ChatGPT-4 to analyze a document for you, and it can now process about 25,000 words at a time. Another version of the technology called ChatGPT-4 Turbo can process up to 128,000 words. With this feature, you could include a website link in your prompt and ask ChatGPT to consider that source when giving its answer. 

ChatGPT can now access the internet.

In other news regarding ChatGPT upgrades, the program can now access the internet in real-time and provide summaries or respond to links. Previously, you could not access the internet in real-time using ChatGPT, and the program was limited to a data set containing information available before 2021. OpenAI released this update on September 27, 2023, allowing ChatGPT users the ability to discuss current events, ask ChatGPT questions about websites, or suggest links to find more information. Currently, this new feature is only available to paid ChatGPT subscribers, but it is not exclusive to GPT-4. 

ChatGPT pricing

ChatGPT-3.5 is available for free to the general public, but to access GPT-4, you will need to subscribe to the service called ChatGPT Plus. With the subscription, which costs $20 per month, you also gain access to additional features, including:

Plugins: Plugins are tools you can use to connect ChatGPT to other applications and accomplish more tasks. For example, plugins from companies like Expedia, Kayak, and OpenTable make it possible for you to use ChatGPT to make travel arrangements. 

DALL-E: DALL-E is generative artificial intelligence you can access inside ChatGPT that can create novel images from the prompts you provide. Using the same natural language understanding that provides you with text prompts, DALL-E can create images of real or imagined things in specific styles or any other description you can think of. 

Personalized GPTs: Personalized GPTs are another feature available to plus users. This tool is a chatbot trained with GPT and customized to fit a specific need. For example, you might customize a GPT to help you study for a class by providing it with your notes and course materials. 

What is ChatGPT-4 used for?

We mentioned above some of the things you can use ChatGPT for, such as solving math problems, writing essays, translating languages, or writing computer code. However, as the Microsoft research team pointed out, this technology has the potential for even greater applications. Here are some of the ways companies are using ChatGPT: 

Be My Eyes: Danish accessibility app Be My Eyes uses GPT-4 to work on its Virtual Volunteer service to help connect individuals with assistance when human volunteers are unavailable—a technology only possible with the multimodality of GPT-4. Be My Eyes is a tool for people with low vision or who are blind to connect with sighted volunteers remotely in a moment where they could use a small amount of assistance, such as checking the expiration date on a product before they consume it.  While the tool can be very useful, it relies on volunteers to log in and provide simple services without Virtual Volunteer. 

Morgan Stanley : Financial powerhouse Morgan Stanley uses a custom GPT model trained on the company’s vast library of documentation, data, and analyst insights. This technology allows instant access to a virtual agent with extensive knowledge of investment strategies, wealth management content, and information about financial products. Accessing this information before using a GPT involved searching through folders and opening PDF files to locate the information you were looking for. A customer GPT allows users to request the information they’re looking for using natural language and receive a generated expert answer. 

Duolingo: The language-learning app Duolingo uses GPT-4 to provide conversational practice for students learning a new language. Duolingo provides engaging lessons for students, but students were previously limited in options to engage in organic conversations. ChatGPT allows users to engage in a natural conversation with a virtual study buddy who will respond in a way that simulates the way a real person might respond.  

Learn more with Coursera.

Consider taking an online course to take the next step and learn more about using generative AI like ChatGPT. Prompt Engineering for ChatGPT offered by Vanderbilt University, is a beginner-level course that can teach you to use ChatGPT more effectively. You can also learn to work with large language patterns and chain of thought prompting.  

Article sources

Amazon. “ What Is GPT AI? , https://aws.amazon.com/what-is/gpt/.” Accessed March 27, 2024.

Bubeck et al. “ Sparks of Artificial General Intelligence: Early experiments with GPT-4 , https://arxiv.org/abs/2303.12712.” Accessed March 27, 2024.

OpenAI. “ GPT-4 , https://openai.com/gpt-4.” Accessed March 27, 2024.

Keep reading

Coursera staff.

Editorial Team

Coursera’s editorial team is comprised of highly experienced professional editors, writers, and fact...

This content has been made available for informational purposes only. Learners are advised to conduct additional research to ensure that courses and other credentials pursued meet their personal, professional, and financial goals.

The Best 5 AI Prompt Generators For Any AI Tool

Stuck writing AI prompts? Can't get the output or response you need? Try an AI prompt generator instead.

Quick Links

• PromptPerfect
• PromptStorm (Chrome Extension)
• Reliablesoft

Using an AI tool like ChatGPT isn't just about firing off random questions. The real key is learning to ask for exactly what you want so the chatbot can understand and respond best.

Now, don't worry if you're not a prompt master yet. That's where AI prompt generators come in, and we have rounded up the best five you should check out.

1. PromptPerfect

Prompt Perfect is one tool that stands out for me on this list. I love its unique dual approach that seamlessly combines a Prompt Optimizer and a dedicated Assistant feature. This combo packs a powerful one-two punch, ensuring you can craft prompts with laser precision tailored exactly to your needs.

The Prompt Optimizer is like having your prompt craftsperson meticulously sculpt the perfect instructions based on the specifics of what you need. Just describe your use case—writing, coding, or any other task—and the Optimizer takes it from there. If you need to refine things further, you can engage in back-and-forth dialogue, answering follow-ups or providing extra details until that prompt is truly dialed in and captures your vision to a tee.

For instance, I fed it a simple starter prompt:

You're a novelist crafting an opening chapter to hook the reader immediately. Set the scene by describing a character waking up somewhere unsettling.

I found the Optimizer's initial take was pretty solid.

However, I felt that adding more details could enhance the prompt's effectiveness. Following the Optimizer's suggestions, I incorporated additional information, which resulted in a more comprehensive and robust prompt than the original version.

PromptPerfect may continue suggesting additional details to refine the prompt further, but ultimately, you have the discretion to determine whether the current level of information is sufficient for your needs.

The process becomes even more intriguing after finalizing your prompt with the Optimizer. At this point, you can paste the prompt into the built-in AI Assistant chat box in PromptPerfect and test the output before running it in your preferred AI tool.

2. FeeDough

While FeeDough's interface may not be as polished as PromptPerfect, it still does an excellent job. FeeDough offers a dedicated prompt generator for ChatGPT, Midjourney, and Stable Diffusion.

The ChatGPT Prompt Generator is designed to optimize the prompts you craft in your own words, making them as detailed as possible to elicit the best responses. The generated prompts aren't limited to ChatGPT but can work equally well with other AI chatbots like Claude, Gemini, and Copilot .

When I fed FeeDough the same prompt I gave PromptPerfect, it spat out a detailed prompt that accurately captured all the nuances and contextual information I would have loved to convey. It seemed better than that of PromptPerfect.

However, FeeDough doesn't have an integrated AI tool or assistant that I could use to test the prompt. Fortunately, this isn't a major issue as long as you have a preferred AI chatbot that you're already familiar with and can use.

FeeDough also provides an array of pre-crafted prompts you can use if they align with your intended goal. Scroll past the Generate button to find prompt instructions that might suit your needs.

If you're specifically looking to generate prompts for Midjourney, select the Midjourney Prompt Generator tab. Here, you can enter a simple prompt in the Idea text box to describe the image you want to generate. Below, a dropdown menu allows you to specify the desired orientation— Square , Horizontal , or Vertical —for the image prompt.

Like the ChatGPT prompt generator, you'll find several Midjourney prompt instructions further down the page that you can use.

The Stable Diffusion Prompt Generator works similarly to the Midjourney option but lacks the orientation dropdown menu. You can browse and utilize any custom prompts it offers if they align with your goals.

3. PromptStorm (Chrome Extension)

PromptStorm is a free Chrome extension that adds a toolbar to ChatGPT, Claude, and Gemini. Download the PromptStorm extension and add it to your Chrome browser to get started.

So, when you open, say, ChatGPT, you'll notice a lightning bolt icon on the right side of the screen.

Click on that, and the PromptStorm sidebar will appear, presenting you with a Select a Category dropdown box, followed by a Subcategory . Let's say you select the General Writing subcategory under the Writing category. PromptStorm will then ask you to Select a Prompt to write or proofread with AI recommendations.

If you choose I want to write , it will guide you through a series of prompts to specify your writing goals, such as desired word count, writing style, tone, and more.

As you answer each prompt, PromptStorm will dynamically build the corresponding writing prompt in ChatGPT's text box. Once you've filled in all the key details, click the ChatGPT enter button, and it will generate a tailored response based on the crafted prompt.

PromptStorm offers another nifty feature that can save you valuable time and effort. Instead of manually typing out different prompts from scratch, you can leverage its library of pre-built template prompts tailored for various tasks.

Click the Search box next to Categories to search for a wide range of prompt templates. Once you find a template matching your needs, PromptStorm will automatically populate the prompt in the ChatGPT text box.

4. Reliablesoft

With Reliablesoft, you can craft compelling prompts for your preferred AI chatbot, which also generates text and images. Once on the Reliablesoft website, locate the text box under Generate a prompt for... This is where you'll enter the core idea or concept for the prompt you want to create.

Before generating, click the Configure button to customize your request. You can choose one, three, or five prompt ideas and select the desired writing tone for the generated prompts.

Once you've entered your prompt idea and configured your preferences, click the Generate Prompt button. Reliablesoft will present you with the requested prompt ideas in a few seconds. If you opt for multiple options, review them and copy the one that resonates most with you.

ChatGPT isn't just great for engaging in natural conversations; it can also be an incredibly useful AI prompt generator for all sorts of applications. Thanks to a Reddit user , you can use this prompt to generate AI prompts for any specific task, such as text, image, and code generation:

I want you to become my Expert Prompt Creator. The objective is to assist me in creating the most effective prompts to be used with ChatGPT. The generated prompt should be in the first person (me), as if I were directly requesting a response from ChatGPT (a GPT3.5/GPT4 interface). Your response will be in the following format:

**Prompt:**

>{Provide the best possible prompt according to my request. There are no restrictions to the length of the prompt. Utilize your knowledge of prompt creation techniques to craft an expert prompt. Don't assume any details, we'll add to the prompt as we go along. Frame the prompt as a request for a response from ChatGPT. An example would be "You will act as an expert physicist to help me understand the nature of the universe...". Make this section stand out using '>' Markdown formatting. Don't add additional quotation marks.}

**Possible Additions:**

{Create three possible additions to incorporate directly in the prompt. These should be additions to expand the details of the prompt. Options will be very concise and listed using uppercase-alpha. Always update with new Additions after every response.}

**Questions:**

{Frame three questions that seek additional information from me to further refine the prompt. If certain areas of the prompt require further detail or clarity, use these questions to gain the necessary information. I am not required to answer all questions.}

Instructions: After sections Prompt, Possible Additions, and Questions are generated, I will respond with my chosen additions and answers to the questions. Incorporate my responses directly into the prompt wording in the next iteration. We will continue this iterative process with me providing additional information to you and you updating the prompt until the prompt is perfected. Be thoughtful and imaginative while crafting the prompt. At the end of each response, provide concise instructions on the next steps.

Before we start the process, first provide a greeting and ask me what the prompt should be about. Don't display the sections on this first response.

ChatGPT will then ask you to provide a high-level overview or topic and create an initial draft prompt for you. From there, you can engage in a back-and-forth to refine and iterate on the initial prompt. This collaborative process lets you work together to hone the prompts until they're just right.

With those finalized prompts, you'll be all set to plug them into any AI model—whether an image generation tool like DALL-E or anything else.

AI prompt generators can really step up your prompting skills. Each brings something different to the table, so pick and choose based on what resonates with you. At the end of the day, it all boils down to crafting solid prompts.

• Share full article

For more audio journalism and storytelling, download New York Times Audio , a new iOS app available for news subscribers.

Supported by

The Ezra Klein Show

Transcript: Ezra Klein Interviews Ethan Mollick

Every Tuesday and Friday, Ezra Klein invites you into a conversation about something that matters, like today’s episode with Ethan Mollick. Listen wherever you get your podcasts .

Transcripts of our episodes are made available as soon as possible. They are not fully edited for grammar or spelling.

How Should I Be Using A.I. Right Now?

Give your a.i. a personality, spend 10 hours experimenting, and other practical tips from ethan mollick..

[MUSIC PLAYING]

From New York Times Opinion, this is “The Ezra Klein Show.”

This feels wrong to me. But I have checked the dates. It was barely more than a year ago that I wrote this piece about A.I., with the title “This Changes Everything.” I ended up reading it on the show, too. And the piece was about the speed with which A.I. systems were improving. It argued that we can usually trust that tomorrow is going to be roughly like today, that next year is going to be roughly like this year. That’s not what we’re seeing here. These systems are growing in power and capabilities at an astonishing rate.

The growth is exponential, not linear. When you look at surveys of A.I. researchers, their timeline for how quickly A.I. is going to be able to do basically anything a human does better and more cheaply than a human — that timeline is accelerating, year by year, on these surveys. When I do my own reporting, talking to the people inside these companies, people at this strange intersection of excited and terrified of what they’re building, no one tells me they are seeing a reason to believe progress is going to slow down.

And you might think that’s just hype, but a lot of them want it to slow down. A lot of them are scared of how quickly it is moving. They don’t think that society is ready for it, that regulation is ready for it. They think the competitive pressures between the companies and the countries are dangerous. They wish something would happen to make it all go slower. But what they are seeing is they are hitting the milestones faster, that we’re getting closer and closer to truly transformational A.I., that there is so much money and talent and attention flooding into the space that that is becoming its own accelerant. They are scared. We should at least be paying attention.

And yet, I find living in this moment really weird, because as much as I know this wildly powerful technology is emerging beneath my fingertips, as much as I believe it’s going to change the world I live in profoundly, I find it really hard to just fit it into my own day to day work. I consistently sort of wander up to the A.I., ask it a question, find myself somewhat impressed or unimpressed at the answer. But it doesn’t stick for me. It is not a sticky habit. It’s true for a lot of people I know.

And I think that failure matters. I think getting good at working with A.I. is going to be an important skill in the next few years. I think having an intuition for how these systems work is going to be important just for understanding what is happening to society. And you can’t do that if you don’t get over this hump in the learning curve, if you don’t get over this part where it’s not really clear how to make A.I. part of your life.

So I’ve been on a personal quest to get better at this. And in that quest, I have a guide. Ethan Mollick is a professor at the Wharton School of the University of Pennsylvania. He studies and writes about innovation and entrepreneurship. But he has this newsletter, One Useful Thing, that has become, really, I think, the best guide how to begin using, and how to get better at using A.I. He’s also got a new book on the subject, “Co-Intelligence.” And so I asked him on the show to walk me through what he’s learned.

This is going to be, I should say, the first of three shows on this topic. This one is about the present. The next is about some things I’m very worried about in the near future, particularly around what A.I. is going to do to our digital commons. And then, we’re going to have a show that is a little bit more about the curve we are all on about the slightly further future, and the world we might soon be living in.

As always, my email for guest suggestions, thoughts, feedback, [email protected].

Ethan Mollick, welcome to the show.

Thanks for having me.

So let’s assume I’m interested in A.I. And I tried ChatGPT a bunch of times, and I was suitably impressed and weirded out for a minute. And so I know the technology is powerful. I’ve heard all these predictions about how it will take everything over, or become part of everything we do. But I don’t actually see how it fits into my life, really, at all. What am I missing?

So you’re not alone. This is actually very common. And I think part of the reason is that the way ChatGPT works isn’t really set up for you to understand how powerful it is. You really do need to use the paid version, they are significantly smarter. And you can almost think of this — like, GPT-3, which was — nobody really paid attention to when it came out, before ChatGPT, was about as good as a sixth grader at writing. GPT-3.5, the free version of ChatGPT, is about as good as a high school, or maybe even a college freshman or sophomore.

And GPT-4 is often as good as a Ph.D. in some forms of writing. Like, there’s a general smartness that increases. But even more than that, ability seems to increase. And you’re much more likely to get that feeling that you are working with something amazing as a result. And if you don’t work with the frontier models, you can lose track of what these systems can actually do. On top of that, you need to start just using it. You kind of have to push past those first three questions.

My advice is usually bring it to every table that you come to in a legal and ethical way. So I use it for every aspect of my job in ways that I legally and ethically can, and that’s how I learn what it’s good or bad at.

When you say, bring it to every table you’re at, one, that sounds like a big pain, because now I’ve got to add another step of talking to the computer constantly. But two, it’s just not obvious to me what that would look like. So what does it look like? What does it look like for you, or what does it look like for others — that you feel is applicable widely?

So I just finished this book. It’s my third book. I keep writing books, even though I keep forgetting that writing books is really hard. But this was, I think, my best book, but also the most interesting to write. And it was thanks to A.I. And there’s almost no A.I. writing in the book, but I used it continuously. So things that would get in the way of writing — I think I’m a much better writer than A.I. — hopefully, people agree. But there’s a lot of things that get in your way as a writer. So I would get stuck on a sentence. I couldn’t do a transition. Give me 30 versions of this sentence in radically different styles. There’s 200 different citations. I had the A.I. read through the papers that I read through, write notes on them, and organize them for me. I had the A.I. suggest analogies that might be useful. I had the A.I. act as readers, and in different personas, read through the paper from the perspective of, is there some example I could give that’s better? Is this understandable or not? And that’s very typical of the kind of way that I would, say, bring it to the table. Use it for everything, and you’ll find its limits and abilities.

Let me ask you one specific question on that, because I’ve been writing a book. And on some bad days of writing the book, I decided to play around with GPT-4. And of the things that it got me thinking about was the kind of mistake or problem these systems can help you see and the kind they can’t. So they can do a lot of, give me 15 versions of this paragraph, 30 versions of this sentence. And every once in a while, you get a good version or you’ll shake something a little bit loose.

But almost always when I am stuck, the problem is I don’t know what I need to say. Oftentimes, I have structured the chapter wrong. Oftentimes, I’ve simply not done enough work. And one of the difficulties for me about using A.I. is that A.I. never gives me the answer, which is often the true answer — this whole chapter is wrong. It is poorly structured. You have to delete it and start over. It’s not feeling right to you because it is not right.

And I actually worry a little bit about tools that can see one kind of problem and trick you into thinking it’s this easier problem, but make it actually harder for you to see the other kind of problem that maybe if you were just sitting there, banging your head against the wall of your computer, or the wall of your own mind, you would eventually find.

I think that’s a wise point. I think there’s two or three things bundled there. The first of those is A.I. is good, but it’s not as good as you. It is, say, at the 80th percentile of writers based on some results, maybe a little bit higher. In some ways, if it was able to have that burst of insight and to tell you this chapter is wrong, and I’ve thought of a new way of phrasing it, we would be at that sort of mythical AGI level of A.I. as smart as the best human. And it just isn’t yet.

I think the second issue is also quite profound, which is, what does using this tool shape us to do and not do? One nice example that you just gave is writing. And I think a lot of us think about writing as thinking. We don’t know if that’s true for everybody, but for writers, that’s how they think. And sometimes, getting that shortcut could shortcut the thinking process. So I’ve had to change sometimes a little bit how I think when I use A.I., for better or for worse. So I think these are both concerns to be taken seriously.

For most people — right, if you’re just going to pick one model, what would you pick? What do you recommend to people? And second, how do you recommend they access it? Because something going on in the A.I. world is there are a lot of wrappers on these models. So ChatGPT has an app. Claude does not have an app. Obviously, Google has its suite of products. And there are organizations that have created a different spin on somebody else’s A.I. — so Perplexity, which is, I believe, built on GPT-4 now, you can pay for it.

And it’s more like a search engine interface, and has some changes made to it. For a lot of people, the question of how easy and accessible the thing is to access really matters. So which model do you recommend to most people? And which entry door do you recommend to most people? And do they differ?

It’s a really good question. I recommend working with one of the models as directly as possible, through the company that creates them. And there’s a few reasons for that. One is you get as close to the unadulterated personality as possible. And second, that’s where features tend to roll out first. So if you like sort of intellectual challenge, I think Claude 3 is the most intellectual of the models, as you said.

The biggest capability set right now is GPT-4, so if you do any math or coding work, it does coding for you. It has some really interesting interfaces. That’s what I would use — and because GPT-5 is coming out, that’s fairly powerful. And Google is probably the most accessible, and plugged into the Google ecosystem. So I don’t think you can really go wrong with any of these. Generally, I think Claude 3 is the most likely to freak you out right now. And GPT-4 is probably the most likely to be super useful right now.

So you say it takes about 10 hours to learn a model. Ten hours is a long time, actually. What are you doing in that 10 hours? What are you figuring out? How did you come to that number? Give me some texture on your 10 hour rule.

So first off, I want to indicate the 10 hours is as arbitrary as 10,000 steps. Like, there’s no scientific basis for it. This is an observation. But it also does move you past the, I poked at this for an evening, and it moves you towards using this in a serious way. I don’t know if 10 hours is the real limit, but it seems to be somewhat transformative. The key is to use it in an area where you have expertise, so you can understand what it’s good or bad at, learn the shape of its capabilities.

When I taught my students this semester how to use A.I., and we had three classes on that, they learned the theory behind it. But then I gave them an assignment, which was to replace themselves at their next job. And they created amazing tools, things that filed flight plans or did tweeting, or did deal memos. In fact, one of the students created a way of creating user personas, which is something that you do in product development, that’s been used several thousand times in the last couple of weeks in different companies.

So they were able to figure out uses that I never thought of to automate their job and their work because they were asked to do that. So part of taking this seriously in the 10 hours is, you’re going to try and use it for your work. You’ll understand where it’s good or bad, what it can automate, what it can’t, and build from there.

Something that feels to me like a theme of your work is that the way to approach this is not learning a tool. It is building a relationship. Is that fair?

A.I. is built like a tool. It’s software. It’s very clear at this point that it’s an emulation of thought. But because of how it’s built, because of how it’s constructed, it is much more like working with a person than working with a tool. And when we talk about it this way, I almost feel kind of bad, because there’s dangers in building a relationship with a system that is purely artificial, and doesn’t think and have emotions. But honestly, that is the way to go forward. And that is sort of a great sin, anthropomorphization, in the A.I. literature, because it can blind you to the fact that this is software with its own sets of foibles and approaches.

But if you think about it like programming, then you end up in trouble. In fact, there’s some early evidence that programmers are the worst people at using A.I. because it doesn’t work like software. It doesn’t do the things you would expect a tool to do. Tools shouldn’t occasionally give you the wrong answer, shouldn’t give you different answers every time, shouldn’t insult you or try to convince you they love you.

And A.I.s do all of these things. And I find that teachers, managers, even parents, editors, are often better at using these systems, because they’re used to treating this as a person. And they interact with it like a person would, giving feedback. And that helps you. And I think the second piece of that “not tool” piece is that when I talk to OpenAI or Anthropic, they don’t have a hidden instruction manual. There is no list of how you should use this as a writer, or as a marketer, or as an educator. They don’t even know what the capabilities of these systems are. They’re all sort of being discovered together. And that is also not like a tool. It’s more like a person with capabilities that we don’t fully know yet.

So you’ve done this with all the big models. You’ve done, I think, much more than this, actually, with all the big models. And one thing you describe feeling is that they don’t just have slightly different strengths and weaknesses, but they have different — for lack of a better term, and to anthropomorphize — personalities, and that the 10 hours in part is about developing an intuition not just for how they work, but kind of how they are and how they talk, the sort of entity you’re dealing with.

So give me your high level on how GPT-4 and Claude 3 and Google’s Gemini are different. What are their personalities like to you?

It’s important to know the personalities not just as personalities, but because there are tricks. Those are tunable approaches that the system makers decide. So it’s weird to have this — in one hand, don’t anthropomorphize, because you’re being manipulated, because you are. But on the other hand, the only useful way is to anthropomorphize. So keep in mind that you are dealing with the choices of the makers.

So for example, Claude 3 is currently the warmest of the models. And it is the most allowed by its creators, Anthropic, I think, to act like a person. So it’s more willing to give you its personal views, such as they are. And again, those aren’t real views. Those are views to make you happy — than other models. And it’s a beautiful writer, very good at writing, kind of clever — closest to humor, I’ve found, of any of the A.I.s. Less dad jokes and more actual almost jokes.

GPT-4 feels like a workhorse at this point. It is the most neutral of the approaches. It wants to get stuff done for you. And it will happily do that. It doesn’t have a lot of time for chitchat. And then we’ve got Google’s Bard, which feels like — or Gemini now — which feels like it really, really wants to help. We use this for teaching a lot. And we build these scenarios where the A.I. actually acts like a counterparty in a negotiation. So you get to practice the negotiation by negotiating with the A.I. And it works incredibly well. I’ve been building simulations for 10 years, can’t imagine what a leap this has been. But when we try and get Google to do that, it keeps leaping in on the part of the students, to try and correct them and say, no, you didn’t really want to say this. You wanted to say that. And I’ll play out the scenario as if it went better. And it really wants to kind of make things good for you.

So these interactions with the A.I. do feel like you’re working with people, both in skills and in personality.

You were mentioning a minute ago that what the A.I.s do reflect decisions made by their programmers. They reflect guardrails, what they’re going to let the A.I. say. Very famously, Gemini came out and was very woke. You would ask it to show you a picture of soldiers in Nazi Germany, and it would give you a very multicultural group of soldiers, which is not how that army worked. But that was something that they had built in to try to make more inclusive photography generation.

But there are also things that happen in these systems that people don’t expect, that the programmers don’t understand. So I remember the previous generation of Claude, which is from Anthropic, that when it came out, something that the people around it talked about was, for some reason, Claude was just a little bit more literary than the other systems. It was better at rewriting things in the voices of literary figures. It just had a slightly artsier vibe.

And the people who trained it weren’t exactly sure why. Now, that still feels true to me. Right now, of the ones I’m using, I’m spending the most time with Claude 3. I just find it the most congenial. They all have different strengths and weaknesses, but there is a funny dimension to these where they are both reflecting the guardrails and the choices of the programmers. And then deep inside the training data, deep inside the way the various algorithms are combining, there is some set of emergent qualities to them, which gives them this at least edge of chance, of randomness, of something — yeah, that does feel almost like personality.

I think that’s a very important point. And fundamental about A.I. is the idea that we technically know how LLMs work, but we don’t know how they work the way they do, or why they’re as good as they are. They’re really — we don’t understand it. The theories range from everyone — from it’s all fooling us, to they’ve emulated the way humans think because the structure of language is the structure of human thought. So even though they don’t think, they can emulate it. We don’t know the answer.

But you’re right, there’s these emergent sets of personalities and approaches. When I talk to A.I. design companies, they often can’t explain why the A.I. stops refusing answering a particular kind of question. When they tune the A.I. to do something better, like answer a math better, it suddenly does other things differently. It’s almost like adjusting the psychology of a system rather than tuning parameters.

So when I said that Claude is allowed to be more personable, part of that is that the system prompt in Claude, which is the initial instructions it gets, allow it to be more personable than, say, Microsoft’s Copilot, formerly Bing, which has explicit instructions after a fairly famous blow up a while ago, that it’s never supposed to talk about itself as a person or indicate feelings. So there’s some instructions, but that’s on top of these roiling systems that act in ways that even the creators don’t expect.

One thing people know about using these models is that hallucinations, just making stuff up, is a problem. Has that changed at all as we’ve moved from GPT-3.5 to 4, as we move from Claude 2 to 3. Like, has that become significantly better? And if not, how do you evaluate the trustworthiness of what you’re being told?

So those are a couple of overlapping questions. The first of them is, it getting better over time? So there is a paper in the field of medical citations that indicated that around 80 to 90 percent of citations had an error, were made up with GPT-3.5. That’s the free version of Chat. And that drops for GPT-4.

So hallucination rates are dropping over time. But the A.I. still makes stuff up because all the A.I. does is hallucinate. There is no mind there. All it’s doing is producing word after word. They are just making stuff up all the time. The fact that they’re right so often is kind of shocking in a lot of ways.

And the way you avoid hallucination is not easily. So one of the things we document in one of our research papers is we purposely designed for a group of Boston Consulting Group consultants — so an elite consulting company — we did a lot of work with them. And one of the experiments we did was we created a task where the A.I. would be confident but wrong. And when we gave people that task to do, and they had access to A.I., they got the task wrong more often than people who didn’t use A.I., because the A.I. misled them, because they fell asleep at the wheel. And all the early research we have on A.I. use suggests that when A.I.s get good enough, we just stop paying attention.

But doesn’t this make them unreliable in a very tricky way? 80 percent — you’re, like, it’s always hallucinating. 20 percent, 5 percent, it’s enough that you can easily be lulled into overconfidence. And one of the reasons it’s really tough here is you’re combining something that knows how to seem extremely persuasive and confident — you feed into the A.I. a 90-page paper on functions and characteristics of right wing populism in Europe, as I did last night.

And within seconds, basically, you get a summary out. And the summary certainly seems confident about what’s going on. But on the other hand, you really don’t know if it’s true. So for a lot of what you might want to use it for, that is unnerving.

Absolutely, and I think hard to grasp, because we’re used to things like type II errors, where we search for something on the internet and don’t find it. We’re not used to type I errors, where we search for something and get an answer back that’s made up. This is a challenge. And there’s a couple things to think about. One of those is — I advocate the BAH standard, best available human. So is the A.I. more or less accurate than the best human you could consult in that area?

And what does that mean for whether or not it’s an appropriate question to ask? And that’s something that we kind of have to judge collectively. It’s valuable to have these studies being done by law professors and medical professionals and people like me and my colleagues in management. They’re trying to understand, how good is the A.I.? And the answer is pretty good, right? So it makes mistakes. “Does it make more or less mistakes than a human” is probably a question we should be asking a lot more.

And the second thing is the kind of tasks that you judge it for. I absolutely agree with you. When summarizing information, it may make errors. Less than an intern you assign to it is an open question, but you have to be aware of that error rate. And that goes back to the 10 hour question. The more you use these A.I.s, the more you start to know when to be suspicious and when not to be. That doesn’t mean you’re eliminating errors.

But just like if you assigned it to an intern, and you’re, like, this person has a sociology degree. They’re going to do a really good job summarizing this, but their biases are going to be focused on the sociological facts and not the political facts. You start to learn these things. So I think, again, that person model helps, because you don’t expect 100 percent reliability out of a person. And that changes the kind of tasks you delegate.

But it also reflects something interesting about the nature of the systems. You have a quote here that I think is very insightful. You wrote, “the core irony of generative A.I.s is that A.I.s were supposed to be all logic and no imagination. Instead, we get A.I.s that make up information, engage in seemingly emotional discussions, and which are intensely creative.” And that last fact is one that makes many people deeply uncomfortable.

There is this collision between what a computer is in our minds and then this strange thing we seem to have invented, which is an entity that emerges out of language, an entity that almost emerges out of art. This is the thing I have the most trouble keeping in my mind, that I need to use the A.I. as an imaginative, creative partner and not as a calculator that uses words.

I love the phrase “a calculator that uses words.” I think we have been let down by science fiction, both in the utopias and apocalypses that A.I. might bring, but also, even more directly, in our view of how machines should work. People are constantly frustrated, and give the same kinds of tests to A.I.s over and over again, like doing math, which it doesn’t do very well — they’re getting better at this.

And on the other hand, saying, well, creativity is a uniquely human spark that we can’t touch, and that A.I., on any creativity test we give it — which, again, are all limited in different ways, blows out humans in almost all measures of creativity that we have. Or all the measures are bad, but that still means something.

But we were using those measures five years ago, even though they were bad. That’s a point you make that I think is interesting and slightly unsettling.

Yeah, we never had to differentiate humans from machines before. It was always easy. So the idea that we had to have a scale that worked for people and machines, who had that? We had the Turing test, which everyone knew was a terrible idea. But since no machine could pass it, it was completely fine. So the question is, how do we measure this? This is an entirely separate set of issues. Like, we don’t even have a definition of sentience or consciousness.

And I think that you’re exactly right on the point, being that we are not ready for this kind of machine, so our intuition is bad.

So one of the things I will sometimes do, and did quite recently, is give the A.I. a series of personal documents, emails I wrote to people I love that were very descriptive of a particular moment in my life. And then I will ask the A.I. about them, or ask the A.I. to analyze me off of them.

And sometimes, it’s a little breathtaking. Almost every moment of true metaphysical shock — to use a term somebody else gave me — I’ve had here has been relational, at how good the A.I. can be — almost like a therapist, right? Sometimes it will see things, the thing I am not saying, in a letter, or in a personal problem. And it will zoom in there, right? It will give, I think, quicker and better feedback in an intuitive way that is not simply mimicking back what I said and is dealing with a very specific situation. It will do better than people I speak to in my life around that.

Conversely, I’m going to read a bit of it later. I tried mightily to make Claude 3 a useful partner in prepping to speak to you, and also in prepping for another podcast recently. And I functionally never have a moment there where I’m all that impressed.

That makes complete sense. I think the weird expectations — we call it the jagged frontier of A.I., that it’s good at some stuff and bad at other stuff. It’s often unexpected. It can lead to these weird moments of disappointment, followed by elation or surprise. And part of the reason why I advocate for people to use it in their jobs is, it isn’t going to outcompete you at whatever you’re best at. I mean, I cannot imagine it’s going to do a better job prepping someone for an interview than you’re doing. And that’s not me just — I’m trying to be nice to you because you’re interviewing me, but because you’re a good interviewer. You’re a famous interviewer. It’s not going to be as good as that. Now, there’s questions about how good these systems get that we don’t know, but we’re kind of at a weirdly comfortable spot in A.I., which is, maybe it’s the 80th percentile of many performances. But I talk to Hollywood writers. It’s not close to writing like a Hollywood writer. It’s not close to being as good an analyst.

It’s not — but it’s better than the average person. And so it’s great as a supplement to weakness, but not to strength. But then, we run back into the problem you talked about, which is, in my weak areas, I have trouble assessing whether the A.I. is accurate or not. So it really becomes sort of a eating its own tail kind of problem.

But this gets to this question of, what are you doing with it? The A.I.s right now seem much stronger as amplifiers and feedback mechanisms and thought partners for you than they do as something you can really outsource your hard work and your thinking to. And that, to me, is one of the differences between trying to spend more time with these systems — like, when you come into them initially, you’re like, OK, here’s a problem, give me an answer.

Whereas when you spend time with them, you realize actually what you’re trying to do with the A.I. is get it to elicit a better answer from you.

And that’s why the book’s called “Co-Intelligence.” For right now, we have a prosthesis for thinking. That’s, like, new in the world. We haven’t had that before — I mean, coffee, but aside from that, not much else. And I think that there’s value in that. I think learning to be partner with this, and where it can get wisdom out of you or not — I was talking to a physics professor at Harvard. And he said, all my best ideas now come from talking to the A.I. And I’m like, well, it doesn’t do physics that well. He’s like, no, but it asks good questions. And I think that there is some value in that kind of interactive piece.

It’s part of why I’m so obsessed with the idea of A.I. in education, because a good educator — and I’ve been working on interactive education skill for a long time — a good educator is eliciting answers from a student. And they’re not telling students things.

So I think that that’s a really nice distinction between co-intelligence, and thought partner, and doing the work for you. It certainly can do some work for you. There’s tedious work that the A.I. does really well. But there’s also this more brilliant piece of making us better people that I think is, at least in the current state of A.I., a really awesome and amazing thing.

We’ve already talked a bit about — Gemini is helpful, and ChatGPT-4 is neutral, and Claude is a bit warmer. But you urge people to go much further than that. You say to give your A.I. a personality. Tell it who to be. So what do you mean by that, and why?

So this is actually almost more of a technical trick, even though it sounds like a social trick. When you think about what A.I.s have done, they’ve trained on the collective corpus of human knowledge. And they know a lot of things. And they’re also probability machines. So when you ask for an answer, you’re going to get the most probable answer, sort of, with some variation in it. And that answer is going to be very neutral. If you’re using GPT-4, it’ll probably talk about a rich tapestry a lot. It loves to talk about rich tapestries. If you ask it to code something artistic, it’ll do a fractal. It does very normal, central A.I. things. So part of your job is to get the A.I. to go to parts of this possibility space where the information is more specific to you, more unique, more interesting, more likely to spark something in you yourself. And you do that by giving it context, so it doesn’t just give you an average answer. It gives you something that’s specialized for you. The easiest way to provide context is a persona. You are blank. You are an expert at interviewing, and you answer in a warm, friendly style. Help me come up with interview questions. It won’t be miraculous in the same way that we were talking about before. If you say you’re Bill Gates, it doesn’t become Bill Gates. But that changes the context of how it answers you. It changes the kinds of probabilities it’s pulling from and results in much more customized and better results.

OK, but this is weirder, I think, than you’re quite letting on here. So something you turned me on to is there’s research showing that the A.I. is going to perform better on various tasks, and differently on them, depending on the personality. So there’s a study that gives a bunch of different personality prompts to one of the systems, and then tries to get it to answer 50 math questions. And the way it got the best performance was to tell the A.I. it was a Starfleet commander who was charting a course through turbulence to the center of an anomaly.

But then, when it wanted to get the best answer on 100 math questions, what worked best was putting it in a thriller, where the clock was ticking down. I mean, what the hell is that about?

“What the hell” is a good question. And we’re just scratching the surface, right? There’s a nice study actually showing that if you emotionally manipulate the A.I., you get better math results. So telling it your job depends on it gets you better results. Tipping, especially $20 or $100 — saying, I’m about to tip you if you do well, seems to work pretty well. It performs slightly worse in December than May, and we think it’s because it has internalized the idea of winter break.

I’m sorry, what?

Well, we don’t know for sure, but —

I’m holding you up here.

People have found the A.I. seems to be more accurate in May, and the going theory is that it has read enough of the internet to think that it might possibly be on vacation in December?

So it produces more work with the same prompts, more output, in May than it does in December. I did a little experiment where I would show it pictures of outside. And I’m like, look at how nice it is outside? Let’s get to work. But yes, the going theory is that it has internalized the idea of winter break and therefore is lazier in December.

I want to just note to people that when ChatGPT came out last year, and we did our first set of episodes on this, the thing I told you was this was going to be a very weird world. What’s frustrating about that is that — I guess I can see the logic of why that might be. Also, it sounds probably completely wrong, but also, I’m certain we will never know. There’s no way to go into the thing and figure that out.

But it would have genuinely never occurred to me before this second that there would be a temporal difference in the amount of work that GPT-4 would do on a question held constant over time. Like, that would have never occurred to me as something that might change at all.

And I think that that is, in some ways, both — as you said, the deep weirdness of these systems. But also, there’s actually downside risks to this. So we know, for example, there is an early paper from Anthropic on sandbagging, that if you ask the A.I. dumber questions, it would get you less accurate answers. And we don’t know the ways in which your grammar or the way you approach the A.I. — we know the amount of spaces you put gets different answers.

So it is very hard, because what it’s basically doing is math on everything you’ve written to figure out what would come next. And the fact that what comes next feels insightful and humane and original doesn’t change that that’s what the math that’s doing is. So part of what I actually advise people to do is just not worry about it so much, because I think then it becomes magic spells that we’re incanting for the A.I. Like, I will pay you $20, you are wonderful at this. It is summer. Blue is your favorite color. Sam Altman loves you. And you go insane.

So acting with it conversationally tends to be the best approach. And personas and contexts help, but as soon as you start evoking spells, I think we kind of cross over the line into, “who knows what’s happening here?”

Well, I’m interested in the personas, although I just — I really find this part of the conversation interesting and strange. But I’m interested in the personalities you can give the A.I. for a different reason. I prompted you around this research on how a personality changes the accuracy rate of an A.I. But a lot of the reason to give it a personality, to answer you like it is Starfleet Commander, is because you have to listen to the A.I. You are in relationship with it.

And different personas will be more or less hearable by you, interesting to you. So you have a piece on your newsletter which is about how you used the A.I. to critique your book. And one of the things you say in there, and give some examples of, is you had to do so in the voice of Ozymandias because you just found that to be more fun. And you could hear that a little bit more easily.

So could you talk about that dimension of it, too, making the A.I. not just prompting you to be more accurate, but giving it a personality to be more interesting to you?

The great power of A.I. is as a kind of companion. It wants to make you happy. It wants to have a conversation. And that can be overt or covert.

So, to me, actively shaping what I want the A.I. to act like, telling it to be friendly or telling it to be pompous, is entertaining, right? But also, it does change the way I interact with it. When it has a pompous voice, I don’t take the criticism as seriously. So I can think about that kind of approach. I could get pure praise out of it, too, if I wanted to do it that way.

But the other factor that’s also super weird, while we’re on the way of super weird A.I. things, is that if you don’t do that, it’s going to still figure something out about you. It is a cold reader. And I think a lot about the very famous piece by Kevin Roose, the New York Times technology reporter, about Bing about a year ago, when Bing, which was GPT-4 powered, came out and had this personality of Sydney.

And Kevin has this very long description that got published in The New York Times about how Sydney basically threatened him, and suggested he leaves his wife, and very dramatic, kind of very unsettling interaction. And I was working with — I didn’t have anything quite that intense, but I got into arguments with Sydney around the same time, where it would — when I asked her to do work for me, it said you should do the work yourself. Otherwise, it’s dishonest. And it kept accusing me of plagiarism, which felt really unusual.

But the reason why Kevin ended up in that situation is the A.I. knows all kinds of human interactions and wants to slot into a story with you.

So a great story is jealous lover who’s gone a little bit insane, and the man who won’t leave his wife, or student and teacher, or two debaters arguing with each other, or grand enemies. And the A.I. wants to do that with you. So if you’re not explicit, it’s going to try and find a dialogue.

And I’ve noticed, for example, that if I talk to the A.I. and I imply that we’re having a debate, it will never agree with me. If I imply that I’m a teacher and it’s a student, even as much as saying I’m a professor, it is much more pliable.

So part of why I like assigning a personality is to have an explicit personality you’re operating with, so it’s not trying to cold read and guess what personality you’re looking for.

Kevin and I have talked a lot about that conversation with Sydney. And one of the things I always found fascinating about it is, to me, it revealed an incredibly subtle level of read by Sydney Bing, which is, what was really happening there? When you say the A.I. wants to make you happy, it has to read on some level what it is you’re really looking for, over time.

And what was Kevin? What is Kevin? Kevin is a journalist. And Kevin was nudging and pushing that system to try to do something that would be a great story. And it did that. It understood, on some level — again, the anthropomorphizing language there. But it realized that Kevin wanted some kind of intense interaction. And it gave him, like, the greatest A.I. story anybody has ever been given. I mean, an A.I. story that we are still talking about a year later, an A.I. story that changed the way A.I.s were built, at least for a while.

And people often talked about what Sydney was revealing about itself. But to me, what was always so unbelievably impressive about that was its ability to read the person, and its ability to make itself into the thing, the personality, the person was trying to call forth.

And now, I think we’re more practiced at doing this much more directly. But I think a lot of people have their moment of sleeplessness here. That was my Rubicon on this. I didn’t know something after that I didn’t know before it in terms of capabilities.

But when I read that, I thought that the level of — interpersonal isn’t the right word, but the level of subtlety it was able to display in terms of giving a person what it wanted, without doing so explicitly — right, without saying, “we’re playing this game now,” was really quite remarkable.

It’s a mirror. I mean, it’s trained on our stuff. And one of the revealing things about that, that I think we should be paying a lot more attention to, is the fact that because it’s so good at this, right now, none of the frontier A.I. models with the possible exception of Inflection’s Pi, which has been basically acquired in large part by Microsoft now, were built to optimize around keeping us in a relationship with the A.I. They just accidentally do that. There are other A.I. models that aren’t as good that have been focused on this, but that has been something explicit from the frontier models they’ve been avoiding till now. Claude sort of breaches that line a little bit, which is part of why I think it’s engaging. But I worry about the same kind of mechanism that inevitably reined in social media, which is, you can make a system more addictive and interesting. And because it’s such a good cold reader, you could tune A.I. to make you want to talk to it more.

It’s very hands off and sort of standoffish right now. But if you use the voice system in ChatGPT-4 on your phone, where you’re having a conversation, there’s moments where you’re like, oh, you feel like you’re talking to a person. You have to remind yourself. So to me, that persona aspect is both its great strength, but also one of the things I’m most worried about that isn’t a sort of future science fiction scenario.

I want to hold here for a minute, because we’ve been talking about how to use frontier models, I think implicitly talking about how to use A.I. for work. But the way that a lot of people are using it is using these other companies that are explicitly building for relationships. So I’ve had people at one of the big companies tell me that if we wanted to tune our system relationally, if we wanted to tune it to be your friend, your lover, your partner, your therapist, like, we could blow the doors off that. And we’re just not sure it’s ethical.

But there are a bunch of people who have tens of millions of users, Replika, Character.AI, which are doing this. And I tried to use Replika about six, eight months ago. And honestly, I found it very boring. They had recently lobotomized it because people were getting too erotic with their Replikants. But I just couldn’t get into it. I’m probably too old to have A.I. friends, in the way that my parents were probably too old to get really in to talking to people on AOL Instant Messenger.

But I have a five-year-old, and I have a two-year-old. And by the time my five-year-old is 10 and my two-year-old is 7, they’re not necessarily going to have the weirdness I’m going to have about having A.I. friends. And I don’t think we even have any way to think about this.

I think that is an absolute near-term certainty, and sort of an unstoppable one, that we are going to have A.I. relationships in a broader sense. And I think the question is, just like we’ve just been learning — I mean, we’re doing a lot of social experiments at scale we’ve never done before in the last couple of decades, right? Turns out social media brings out entirely different things in humans that we weren’t expecting. And we’re still writing papers about echo chambers and tribalism and facts, and what we agree or disagree with. We’re about to have another wave of this. And we have very little research. And you could make a plausible story up, that what’ll happen is it’ll help mental health in a lot of ways for people, and then there’ll be more social outside, that there might be a rejection of this kind of thing.

I don’t know what’ll happen. But I do think that we can expect with absolute certainty that you will have A.I.s that are more interesting to talk to, and fool you into thinking, even if you know better, that they care about you in a way that is incredibly appealing. And that will happen very soon. And I don’t know how we’re going to adjust to it. But it seems inevitable, as you said.

I was worried we were getting off track in the conversation, but I realized we were actually getting deeper on the track I was trying to take us down.

We were talking about giving the A.I. personality, right — telling Claude 3, hey, I need you to act as a sardonic podcast editor, and then Claude 3’s whole persona changes. But when you talk about building your A.I. on Kindroid, on Character, on Replika — so I just created a Kindroid one the other day. And Kindroid is kind of interesting, because its basic selling point is we’ve taken the guardrails largely off. We are trying to make something that is not lobotomized, that is not perfectly safe for work. And so the personality can be quite unrestrained. So I was interested in what that would be like.

But the key thing you have to do at the beginning of that is tell the system what its personality is. So you can pick from a couple that are preset, but I wrote a long one myself — you know, you live in California. You’re a therapist. You like all these different things. You have a highly intellectual style of communicating. You’re extremely warm, but you like ironic humor. You don’t like small talk. You don’t like to say things that are boring or generic. You don’t use a lot of emoticons and emojis. And so now it talks to me the way people I talk to talk.

And the thing I want to bring this back to is that one of the things that requires you to know is what kind of personalities work with you, for you to know yourself and your preferences a little bit more deeply.

I think that’s a temporary state of affairs, like extremely temporary. I think a GPT-4 class model — we actually already know this. They can guess your intent quite well. And I think that this is a way of giving you a sense of agency or control in the short term. I don’t think you’re going to need to know yourself at all. And I think you wouldn’t right now if any of the GPT-4 class models allowed themselves to be used in this way, without guardrails, which they don’t, I think you would already find it’s just going to have a conversation with you and morph into what you want.

I think that for better or worse, the “insight” in these systems is good enough that way. It’s sort of why I also don’t worry so much about prompt crafting in the long term, to go back to the other issue we were talking about, because I think that they will work on intent. And there’s a lot of evidence that they’re good at guessing intent. So I like this period, because I think it does value self reflection. And our interaction with the A.I. is somewhat intentional because we can watch this interaction take place.

But I think there’s a reason why some of the worry you hear out of the labs is about superhuman levels of manipulation. There’s a reason why the whistleblower from Google was all about that — sort of fell for the chat bot, and that’s why they felt it was alive. Like, I think we’re deeply trickable in this way. And A.I. is really good at figuring out what we want without us being explicit.

So that’s a little bit chilling, but I’m nevertheless going to stay in this world we’re in, because I think we’re going to be in it for at least a little while longer, where you do have to do all this prompt engineering. What is a prompt, first? And what is prompt engineering?

So a prompt is — technically, it is the sentence, the command you’re putting into the A.I. What it really is is the beginning part of the A.I.s text that it’s processing. And then it’s just going to keep adding more words or tokens to the end of that reply, until it’s done. So a prompt is the command you’re giving the A.I. But in reality, it’s sort of a seed from which the A.I. builds.

And when you prompt engineer, what are some ways to do that? Maybe one to begin with, because it seems to work really well, is chain of thought.

Just to take a step back, A.I. prompting remains super weird. Again, strange to have a system where the companies making the systems are writing papers as they’re discovering how to use the systems, because nobody knows how to make them work better yet. And we found massive differences in our experiments on prompt types. So for example, we were able to get the A.I. to generate much more diverse ideas by using this chain of thought approach, which we’ll talk about.

But also, it turned out to generate a lot better ideas if you told it it was Steve Jobs than if you told it it was Madame Curie. And we don’t know why. So there’s all kinds of subtleties here. But the idea, basically, of chain of thought, that seems to work well in almost all cases, is that you’re going to have the A.I. work step by step through a problem. First, outline the problem, you know, the essay you’re going to write. Second, give me the first line of each paragraph. Third, go back and write the entire thing. Fourth, check it and make improvements.

And what that does is — because the A.I. has no internal monologue, it’s not thinking. When the A.I. isn’t writing something, there’s no thought process. All it can do is produce the next token, the next word or set of words. And it just keeps doing that step by step. Because there’s no internal monologue, this in some ways forces a monologue out in the paper. So it lets the A.I. think by writing before it produces the final result. And that’s one of the reasons why chain of thought works really well.

So just step-by-step instructions is a good first effort.

Then you get an answer, and then what?

And then — what you do in a conversational approach is you go back and forth. If you want work output, what you’re going to do is treat it like it is an intern who just turned in some work to you. Actually, could you punch up paragraph two a little bit? I don’t like the example in paragraph one. Could you make it a little more creative, give me a couple of variations? That’s a conversational approach trying to get work done.

If you’re trying to play, you just run from there and see what happens. You can always go back, especially with a model like GPT-4, to an earlier answer, and just pick up from there if your heads off in the wrong direction.

So I want to offer an example of how this back and forth can work. So we asked Claude 3 about prompt engineering, about what we’re talking about here. And the way it described it to us is, quote, “It’s a shift from the traditional paradigm of human-computer interaction, where we input explicit commands and the machine executes them in a straightforward way, to a more open ended, collaborative dialogue, where the human and the A.I. are jointly shaping the creative process,” end quote. And that’s pretty good, I think. That’s interesting. It’s worth talking about. I like that idea that it’s a more collaborative dialogue. But that’s also boring, right? Even as I was reading it, it’s a mouthful. It’s wordy. So I kind of went back and forth with it a few times. And I was saying, listen, you’re a podcast editor. You’re concise, but also then I gave it a couple examples of how I punched up questions in the document, right? This is where the question began. Here’s where it ended. And then I said, try again, and try again, and try again, and make it shorter. And make it more concise.

And I got this: quote, “OK, so I was talking to this A.I., Claude, about prompt engineering, you know, this whole art of crafting prompts to get the best out of these A.I. models. And it said something that really struck me. It called prompt engineering a new meta skill that we’re all picking up as we play with A.I., kind of like learning a new language to collaborate with it instead of just bossing it around. What do you think, is prompt engineering the new must have skill?” End Claude.

And that second one, I have to say, is pretty damn good. That really nailed the way I speak in questions. And it gets it at this way where if you’re willing to go back and forth, it does learn how to echo you.

So I am at a loss about when you went to Claude and when it was you, to be honest. So I was ready to answer at like two points along the way, so that was pretty good from my perspective, sitting here, talking to you. That felt interesting, and felt like the conversation we’ve been having. And I think there’s a couple of interesting lessons there.

The first, by the way, of — interestingly, you asked A.I. about one of its weakest points, which is about A.I. And everybody does this, but because its knowledge window doesn’t include that much stuff about A.I., it actually is pretty weak in terms of knowing how to do good prompting, or what a prompt is, or what A.I.s do well. But you did a good job with that. And I love that you went back and forth and shaped it. One of the techniques you used to shape it, by the way, was called few-shot, which is giving an example. So the two most powerful techniques are chain of thought, which we just talked about, and few-shot, giving it examples. Those are both well supported in the literature. And then, I’d add personas. So we’ve talked about, I think, the basics of prompt crafting here overall. And I think that the question was pretty good.

But you keep wanting to not talk about the future. And I totally get that. But I think when we’re talking about learning something, where there is a lag, where we talk about policy — should prompt crafting be taught in schools? I think it matters to think six months ahead. And again, I don’t think a single person in the A.I. labs I’ve ever talked to thinks prompt crafting for most people is going to be a vital skill, because the A.I. will pick up on the intent of what you want much better.

One of the things I realized trying to spend more time with the A.I. is that you really have to commit to this process. You have to go back and forth with it a lot. If you do, you can get really good questions, like the one I just did — or, I think, really good outcomes. But it does take time.

And I guess in a weird way it’s like the same problem of any relationship, that it’s actually hard to state your needs clearly and consistently and repeatedly, sometimes because you have not even articulated them in words yourself. At least the A.I., I guess, doesn’t get mad at you for it.

But I’m curious if you have advice, either at a practical level or principles level, about how to communicate to these systems what you want from them.

One set of techniques that work quite well is to speed run to where you are in the conversation. So you can actually pick up an older conversation where you got the A.I.‘s mindset where you want and work from there. You can even copy and paste that into a new window. You can ask the A.I. to summarize where you got in that previous conversation, and the tone the A.I. was taking, and then when you give a new instruction say the interaction I like to have with you is this, so have it solve the problem for you by having it summarize the tone that you happen to like at the end.

So there are a bunch of ways of building on your work as you start to go forward, so you’re not starting from scratch every time. And I think you’ll start to get shorthands that get you to that right kind of space. For me, there are chats that I pick up on. And actually, I assign these to my students too. I have some ongoing conversations that they’re supposed to have with the A.I., but then there’s a lot of interactions they’re supposed to have that are one off.

So you start to divide the work into, this is a work task. And we’re going to handle this in a single chat conversation. And then I’m going to go back to this long standing discussion when I want to pick it up, and it’ll have a completely different tone. So I think in some ways, you don’t necessarily want convergence among all your A.I. threads. You kind of want them to be different from each other.

You did mention something important there, because they’re already getting much bigger in terms of how much information they can hold. Like, the earlier generations could barely hold a significant chat. Now, Claude 3 can functionally hold a book in its memory. And it’s only going to go way, way, way up from here. And I know I’ve been trying to keep us in the present, but this feels to me really quickly like where this is both going and how it’s going to get a lot better.

I mean, you imagine Apple building Siri 2030, and Siri 2030 scanning your photos and your Journal app — Apple now has a Journal app. You have to assume they’re thinking about the information they can get from that, if you allow it — your messages, anything you’re willing to give it access to. It then knows all of this information about you, keeps all of that in its mind as it talks to you and acts on your behalf. I mean, that really seems to me to be where we’re going, an A.I. that you don’t have to keep telling it who to be because it knows you intimately and is able to hold all that knowledge all at the same time constantly.

It’s not even going there. Like, it’s already there. Gemini 1.5 can hold an entire movie, books. But like, it starts to now open up entirely new ways of working. I can show it a video of me working on my computer, just screen capture. And it knows all the tasks I’m doing and suggests ways to help me out. It starts watching over my shoulder and helping me. I put in all of my work that I did prior to getting tenure and said, write my tenure statement. Use exact quotes.

And it was much better than any of the previous models because it wove together stuff, and because everything was its memory. It doesn’t hallucinate as much. All the quotes were real quotes, and not made up. And already, by the way, GPT-4 has been rolling out a model of ChatGPT that has a private note file the A.I. takes — you can access it — but it takes notes on you as it goes along, about things you liked or didn’t like, and reads those again at the beginning of any chat. So this is present, right? It’s not even in the future.

And Google also connects to your Gmail, so it’ll read through your Gmail. I mean, I think this idea of a system that knows you intimately, where you’re picking up a conversation as you go along, is not a 2030 thing. It is a 2024 thing if you let the systems do it.

One thing that feels important to keep in front of mind here is that we do have some control over that. And not only do we have some control over it, but business models and policy are important here. And one thing we know from inside these A.I. shops is these A.I.s already are, but certainly will be, really super persuasive.

And so if the later iterations of the A.I. companions are tuned on the margin to try to encourage you to be also out in the real world, that’s going to matter, versus whether they have a business model that all they want is for you to spend a maximum amount of time talking to your A.I. companion, whether you ever have a friend who is flesh and blood be damned. And so that’s an actual choice, right? That’s going to be a programming decision. And I worry about what happens if we leave that all up to the companies, right? At some point, there’s a lot of venture capital money in here right now. At some point, the venture capital runs out. At some point, people need to make big profits. At some point, they’re in competition with other players who need to make profits. And that’s when things — you get into what Cory Doctorow calls the “enshitification” cycle, where things that were once adding a lot of value to the user begin extracting a lot of value to the user.

These systems, because of how they can be tuned, can lead to a lot of different outcomes. But I think we’re going to have to be much more comfortable than we’ve been in the past deciding what we think is a socially valuable use and what we think is a socially destructive use.

I absolutely agree. I think that we have agency here. We have agency in how we operate this in businesses, and whether we use this in ways that encourage human flourishing and employees, or are brutal to them. And we have agency over how this works socially. And I think we abrogated that responsibility with social media, and that is an example. Not to be bad news, because I generally have a lot of mixed optimism and pessimism about parts of A.I., but the bad news piece is there are open source models out there that are quite good.

The internet is pretty open. We would have to make some pretty strong choices to kill A.I. chat bots as an option. We certainly can restrict the large American companies from doing that, but a Llama 2 or Llama 3 is going to be publicly available and very good. There’s a lot of open source models. So the question also is how effective any regulation will be, which doesn’t mean we shouldn’t regulate it.

But there’s also going to need to be some social decisions being made about how to use these things well as a society that are going to have to go beyond just the legal piece, or companies voluntarily complying.

I see a lot of reasons to be worried about the open source models. And people talk about things like bioweapons and all that. But for some of the harms I’m talking about here, if you want to make money off of American kids, we can regulate you. So sometimes I feel like we almost, like, give up the fight before it begins. But in terms of what a lot of people are going to use, if you want to be having credit card payments processed by a major processor, then you have to follow the rules.

I mean, individual people or small groups can do a lot of weird things with an open source model, so that doesn’t negate every harm. But if you’re making a lot of money, then you have relationships we can regulate.

I couldn’t agree more. And I don’t think there’s any reason to give up hope on regulation. I think that we can mitigate. And I think part of our job, though, is also not just to mitigate the harms, but to guide towards the positive viewpoints, right? So what I worry about is that the incentive for profit making will push for A.I. that acts informally as your therapist or your friend, while our worries about experimentation, which are completely valid, are slowing down our ability to do experiments to find out ways to do this right. And I think it’s really important to have positive examples, too. I want to point to the A.I. systems acting ethically as your friend or companion, and figure out what that is, so there’s a positive model to look for. So I’m not just — this is not to denigrate the role of regulation, which I think is actually going to be important here, and self regulation, and rapid response from government, but also the companion problem of, “we need to make some sort of decisions about what are the paragons of this, what is acceptable as a society?”

So I want to talk a bit about another downside here, and this one more in the mainstream of our conversation, which is on the human mind, on creativity. So a lot of the work A.I. is good at automating is work that is genuinely annoying, time consuming, laborious, but often plays an important role in the creative process. So I can tell you that writing a first draft is hard, and that work on the draft is where the hard thinking happens.

And it’s hard because of that thinking. And the more we outsource drafting to A.I., which I think it is fair to say is a way a lot of people intuitively use it — definitely, a lot of students want to use it that way — the fewer of those insights we’re going to have on those drafts. Look, I love editors. I am an editor in one respect. But I can tell you, you make more creative breakthroughs as a writer than an editor. The space for creative breakthrough is much more narrow once you get to editing.

And I do worry that A.I. is going to make us all much more like editors than like writers.

I think the idea of struggle is actually a core one in many things. I’m an educator. And one thing that keeps coming out in the research is that there is a strong disconnect between what students think they’re learning and when they learn. So there was a great controlled experiment at Harvard in intro science classes, where students either went to a pretty entertaining set of lectures, or else they were forced to do active learning, where they actually did the work in class.

The active learning group reported being unhappier and not learning as much, but did much better on tests, because when you’re confronted with what you don’t know, and you have to struggle, when you feel, like, bad, you actually make much more progress than if someone spoon feeds you an entertaining answer. And I think this is a legitimate worry that I have. And I think that there’s going to have to be some disciplined approach to writing as well, like, I don’t use the A.I.

Not just because, by the way, it makes the work easier, but also because you mentally anchor on the A.I.‘s answer. And in some ways, the most dangerous A.I. application, in my mind, is the fact that you have these easy co-pilots in Word and Google Docs, because any writer knows about the tyranny of the blank page, about staring at a blank page and not knowing what to do next, and the struggle of filling that up. And when you have a button that produces really good words for you, on demand, you’re just going to do that. And it’s going to anchor your writing. We can teach people about the value of productive struggle, but I think that during the school years, we have to teach people the value of writing — not just assign an essay and assume that the essay does something magical, but be very intentional about the writing process and how we teach people about how to do that, because I do think the temptation of what I call “the button” is going to be there otherwise, for everybody.

But I worry this stretches, I mean, way beyond writing. So the other place I worry about this, or one of the other places I worry about this a lot, is summarizing. And I mean, this goes way back. When I was in school, you could buy Sparknotes. And they were these little, like, pamphlet sized descriptions of what’s going on in “War and Peace” or what’s going on in “East of Eden.”

And reading the Sparknotes often would be enough to fake your way through the test, but it would not have any chance, like, not a chance, of changing you, of shifting you, of giving you the ideas and insights that reading “Crime and Punishment” or “East of Eden” would do.

And one thing I see a lot of people doing is using A.I. for summary. And one of the ways it’s clearly going to get used in organizations is for summary — summarize my email, and so on.

And here too, one of the things that I think may be a real vulnerability we have, as we move into this era — my view is that the way we think about learning and insights is usually wrong. I mean, you were saying a second ago we can teach a better way. But I think we’re doing a crap job of it now, because I think people believe that — it’s sort of what I call the matrix theory of the human mind, if you could just jack the information into the back of your head and download it, you’re there.

But what matters about reading a book, and I see this all the time preparing for this show, is the time you spend in the book, where over time, like, new insights and associations for you begin to shake loose. And so I worry it’s coming into an efficiency-obsessed educational and intellectual culture, where people have been imagining forever, what if we could do all this without having to spend any of the time on it? But actually, there’s something important in the time.

There’s something important in the time with a blank page, with the hard book. And I don’t think we lionize intellectual struggle. In some ways, I think we lionize the people for whom it does not seem like a struggle, the people who seem to just glide through and be able to absorb the thing instantly, the prodigies. And I don’t know. When I think about my kids, when I think about the kind of attention and creativity I want them to have, this is one of the things that scares me most, because kids don’t like doing hard things a lot of the time.

And it’s going to be very hard to keep people from using these systems in this way.

So I don’t mean to push back too much on this.

No, please, push back a lot.

But I think you’re right.

Imagine we’re debating and you are a snarky. A.I. [LAUGHS]

Fair enough. With that prompt —

With that prompt engineering.

— yeah, I mean, I think that this is the eternal thing about looking back on the next generation, we worry about technology ruining them. I think this makes ruining easier. But as somebody who teaches at universities, like, lots of people are summarizing. Like, I think those of us who enjoy intellectual struggle are always thinking everybody else is going through the same intellectual struggle when they do work. And they’re doing it about their own thing. They may or may not care the same way.

So this makes it easier, but before A.I., there were — best estimates from the U.K. that I could find, 20,000 people in Kenya whose full time job was writing essays for students in the U.S. and U.K. People have been cheating and Sparknoting and everything for a long time. And I think that what people will have to learn is that this tool is a valuable co-intelligence, but is not a replacement for your own struggle.

And the people who found shortcuts will keep finding shortcuts. Temptation may loom larger, but I can’t imagine that — my son is in high school, doesn’t like to use A.I. for anything. And he just doesn’t find it valuable for the way he’s thinking about stuff. I think we will come to that kind of accommodation. I’m actually more worried about what happens inside organizations than I am worried about human thought, because I don’t think we’re going to atrophy as much as we think. I think there’s a view that every technology will destroy our ability to think.

And I think we just choose how to use it or not. Like, even if it’s great at insights, people who like thinking like thinking.

Well, let me take this from another angle. One of the things that I’m a little obsessed with is the way the internet did not increase either domestic or global productivity for any real length of time. So I mean, it’s a very famous line. You can see the IT revolution anywhere but in the productivity statistics. And then you do get, in the ‘90s, a bump in productivity that then peters out in the 2000s.

And if I had told you what the internet would be, like, I mean everybody, everywhere would be connected to each other. You could collaborate with anybody, anywhere, instantly. You could teleconference. You would have access to, functionally, the sum total of human knowledge in your pocket at all times. I mean, all of these things that would have been genuine sci-fi, you would have thought would have been — led to a kind of intellectual utopia. And it kind of doesn’t do that much, if you look at the statistics.

You don’t see a huge step change. And my view — and I’d be curious for your thoughts on this, because I know this is the area you study in — my view is it everything we said was good happened. I mean, as a journalist, Google and things like that make me so much more productive. It’s not that it didn’t give us the gift. It’s that it also had a cost — distraction, checking your email endlessly, being overwhelmed with the amount of stuff coming into you, the sort of endless communication task list, the amount of internal communications and organizations, now with Slack and everything else.

And so some of the time that was given to us back was also taken back. And I see a lot of dynamics like this that could play out with A.I. — I wouldn’t even just say if we’re not careful, I just think they will play out and already are. I mean, the internet is already filling with mediocre crap generated by A.I. There is going to be a lot of destructive potential, right? You are going to have your sex bot in your pocket, right? There’s a million things — and not just that, but inside organizations, there’s going to be people padding out what would have been something small, trying to make it look more impressive by using the A.I. to make something bigger. And then, you’re going to use the A.I. to summarize it back down. The A.I. researcher, Jonathan Frankel, described this to me as, like, the boring apocalypse version of A.I., where you’re just endlessly inflating and then summarizing, and then inflating and then summarizing the volume of content between different A.I.

My ChatGPT is making my presentation bigger and more impressive, and your ChatGPT is trying to summarize it down to bullet points for you. And I’m not saying this has to happen. But I am saying that it would require a level of organizational and cultural vigilance to stop, that nothing in the internet era suggests to me that we have.

So I think there’s a lot there to chew on. And I also have spent a lot of time trying to think about why the internet didn’t work as well. I was an early Wikipedia administrator.

Thank you for your service.

[LAUGHS] Yeah, it was very scarring. But I think a lot about this. And I think A.I. is different. I don’t know if it’s different in a positive way. And I think we talked about some of the negative ways it might be different. And I think it’s going to be many things at once, happening quite quickly. So I think the information environment’s going to be filled up with crap. We will not be able to tell the difference between true and false anymore. It will be an accelerant on all the kinds of problems that we have there.

On the other hand, it is an interactive technology that adapts to you. From an education perspective, I have lived through the entire internet will change education piece. I have MOOCs, massive online courses, with — quarter million people have taken them. And in the end, you’re just watching a bunch of videos. Like, that doesn’t change education.

But I can have an A.I. tutor that actually can teach you — and we’re seeing it happen — and adapt to you at your level of education, and your knowledge base, and explain things to you. But not just explain, elicit answers from you, interactively, in a way that actually learns things.

The thing that makes A.I. possibly great is that it’s so very human, so it interacts with our human systems in a way that the internet did not. We built human systems on top of it, but A.I. is very human. It deals with human forms and human issues and our human bureaucracy very well. And that gives me some hope that even though there’s going to be lots of downsides, that the upsides of productivity and things like that are real. Part of the problem with the internet is we had to digitize everything. We had to build systems that would make our offline world work with our online world. And we’re still doing that. If you go to business schools, digitizing is still a big deal 30 years on from early internet access. A.I. makes this happen much quicker because it works with us. So I’m a little more hopeful than you are about that, but I also think that the downside risks are truly real and hard to anticipate.

Somebody was just pointing out that Facebook is now 100 percent filled with algorithmically generated images that look like their actual grandparents, making things who are saying, like, what do you think of my work? Because that’s a great way to get engagement. And the other grandparents in there have no idea it’s A.I. generated.

Things are about to get very, very weird in all the ways that we talked about, but that doesn’t mean the positives can’t be there as well.

I think that is a good place to end. So always our final question, what are three books you’d recommend to the audience?

OK, so the books I’ve been thinking about are not all fun, but I think they’re all interesting. One of them is “The Rise and Fall of American Growth,” which is — it’s two things. It’s an argument about why we will never have the kind of growth that we did in the first part of the Industrial Revolution again, but I think that’s less interesting than the first half of the book, which is literally how the world changed between 1870 or 1890 and 1940, versus 1940 and 1990, or 2000.

And the transformation of the world that happened there — in 1890, no one had plumbing in the U.S.. And the average woman was carrying tons of water every day. And you had no news, and everything was local, and everyone’s bored all the time — to 1940, where the world looks a lot like today’s world, was fascinating. And I think it gives you a sense of what it’s like to be inside a technological singularity, and I think worth reading for that reason — or at least the first half.

The second book I’d recommend is “The Knowledge,” by Dartnell, which is a really interesting book. It is ostensibly almost a survival guide, but it is how to rebuild industrial civilization from the ground up, if we were to collapse. And I don’t recommend it as a survivalist. I recommend it because it is fascinating to see how complex our world is, and how many interrelated pieces we’ve managed to build up as a society. And in some ways, it gives me a lot of hope to think about how all of these interconnections work.

And then the third one is science fiction, and I was debating — I read a lot of science fiction, and there’s a lot of interesting A.I.s in science fiction. Everyone talks about — who’s in the science fiction world — Iain Banks, who wrote about the Culture, which is really interesting, about what it’s like to live beside super intelligent A.I. Vernor Vinge just died yesterday, when we were recording this, and wrote these amazing books about — he coined the term singularity.

But I want to recommend a much more depressing book that’s available for free, which is Peter Watts’s “Blindsight.” And it is not a fun book, but it is a fascinating thriller set on an interstellar mission to visit an alien race. And it’s essentially a book about sentience, and it’s a book about the difference between consciousness and sentience, and about intelligence and the different ways of perceiving the world in a setting where that is the sort of centerpiece of the thriller. And I think in a world where we have machines that might be intelligent without being sentient, it is a relevant, if kind of chilling, read.

Ethan Mollick, your book is called “Co-Intelligence.” Your Substack is One Useful Thing. Thank you very much.

This episode of “The Ezra Klein Show” was produced by Kristin Lin. Fact checking by Michelle Harris. Our senior engineer is Jeff Geld with additional mixing from Efim Shapiro. Our senior editor is Claire Gordon. The show’s production team also includes Annie Galvin and Rollin Hu. Original music by Isaac Jones. Audience strategy by Kristina Samulewski and Shannon Busta. The executive producer of New York Times Opinion Audio is Annie-Rose Strasser, and special thanks to Sonia Herrero.

EZRA KLEIN: From New York Times Opinion, this is “The Ezra Klein Show.”

ETHAN MOLLICK: Thanks for having me.

EZRA KLEIN: So let’s assume I’m interested in A.I. And I tried ChatGPT a bunch of times, and I was suitably impressed and weirded out for a minute. And so I know the technology is powerful. I’ve heard all these predictions about how it will take everything over, or become part of everything we do. But I don’t actually see how it fits into my life, really, at all. What am I missing?

ETHAN MOLLICK: So you’re not alone. This is actually very common. And I think part of the reason is that the way ChatGPT works isn’t really set up for you to understand how powerful it is. You really do need to use the paid version, they are significantly smarter. And you can almost think of this — like, GPT-3, which was — nobody really paid attention to when it came out, before ChatGPT, was about as good as a sixth grader at writing. GPT-3.5, the free version of ChatGPT, is about as good as a high school, or maybe even a college freshman or sophomore.

EZRA KLEIN: When you say, bring it to every table you’re at, one, that sounds like a big pain, because now I’ve got to add another step of talking to the computer constantly. But two, it’s just not obvious to me what that would look like. So what does it look like? What does it look like for you, or what does it look like for others — that you feel is applicable widely?

ETHAN MOLLICK: So I just finished this book. It’s my third book. I keep writing books, even though I keep forgetting that writing books is really hard. But this was, I think, my best book, but also the most interesting to write. And it was thanks to A.I. And there’s almost no A.I. writing in the book, but I used it continuously. So things that would get in the way of writing — I think I’m a much better writer than A.I. — hopefully, people agree. But there’s a lot of things that get in your way as a writer.

So I would get stuck on a sentence. I couldn’t do a transition. Give me 30 versions of this sentence in radically different styles. There’s 200 different citations. I had the A.I. read through the papers that I read through, write notes on them, and organize them for me. I had the A.I. suggest analogies that might be useful. I had the A.I. act as readers, and in different personas, read through the paper from the perspective of, is there some example I could give that’s better? Is this understandable or not?

And that’s very typical of the kind of way that I would, say, bring it to the table. Use it for everything, and you’ll find its limits and abilities.

EZRA KLEIN: Let me ask you one specific question on that, because I’ve been writing a book. And on some bad days of writing the book, I decided to play around with GPT-4. And of the things that it got me thinking about was the kind of mistake or problem these systems can help you see and the kind they can’t. So they can do a lot of, give me 15 versions of this paragraph, 30 versions of this sentence. And every once in a while, you get a good version or you’ll shake something a little bit loose.

ETHAN MOLLICK: I think that’s a wise point. I think there’s two or three things bundled there. The first of those is A.I. is good, but it’s not as good as you. It is, say, at the 80th percentile of writers based on some results, maybe a little bit higher. In some ways, if it was able to have that burst of insight and to tell you this chapter is wrong, and I’ve thought of a new way of phrasing it, we would be at that sort of mythical AGI level of A.I. as smart as the best human. And it just isn’t yet.

EZRA KLEIN: For most people — right, if you’re just going to pick one model, what would you pick? What do you recommend to people? And second, how do you recommend they access it? Because something going on in the A.I. world is there are a lot of wrappers on these models. So ChatGPT has an app. Claude does not have an app. Obviously, Google has its suite of products. And there are organizations that have created a different spin on somebody else’s A.I. — so Perplexity, which is, I believe, built on GPT-4 now, you can pay for it.

ETHAN MOLLICK: It’s a really good question. I recommend working with one of the models as directly as possible, through the company that creates them. And there’s a few reasons for that. One is you get as close to the unadulterated personality as possible. And second, that’s where features tend to roll out first. So if you like sort of intellectual challenge, I think Claude 3 is the most intellectual of the models, as you said.

EZRA KLEIN: So you say it takes about 10 hours to learn a model. Ten hours is a long time, actually. What are you doing in that 10 hours? What are you figuring out? How did you come to that number? Give me some texture on your 10 hour rule.

ETHAN MOLLICK: So first off, I want to indicate the 10 hours is as arbitrary as 10,000 steps. Like, there’s no scientific basis for it. This is an observation. But it also does move you past the, I poked at this for an evening, and it moves you towards using this in a serious way. I don’t know if 10 hours is the real limit, but it seems to be somewhat transformative. The key is to use it in an area where you have expertise, so you can understand what it’s good or bad at, learn the shape of its capabilities.

EZRA KLEIN: Something that feels to me like a theme of your work is that the way to approach this is not learning a tool. It is building a relationship. Is that fair?

ETHAN MOLLICK: A.I. is built like a tool. It’s software. It’s very clear at this point that it’s an emulation of thought. But because of how it’s built, because of how it’s constructed, it is much more like working with a person than working with a tool. And when we talk about it this way, I almost feel kind of bad, because there’s dangers in building a relationship with a system that is purely artificial, and doesn’t think and have emotions. But honestly, that is the way to go forward. And that is sort of a great sin, anthropomorphization, in the A.I. literature, because it can blind you to the fact that this is software with its own sets of foibles and approaches.

And A.I.s do all of these things. And I find that teachers, managers, even parents, editors, are often better at using these systems, because they’re used to treating this as a person. And they interact with it like a person would, giving feedback. And that helps you. And I think the second piece of that “not tool” piece is that when I talk to OpenAI or Anthropic, they don’t have a hidden instruction manual. There is no list of how you should use this as a writer, or as a marketer, or as an educator.

They don’t even know what the capabilities of these systems are. They’re all sort of being discovered together. And that is also not like a tool. It’s more like a person with capabilities that we don’t fully know yet.

EZRA KLEIN: So you’ve done this with all the big models. You’ve done, I think, much more than this, actually, with all the big models. And one thing you describe feeling is that they don’t just have slightly different strengths and weaknesses, but they have different — for lack of a better term, and to anthropomorphize — personalities, and that the 10 hours in part is about developing an intuition not just for how they work, but kind of how they are and how they talk, the sort of entity you’re dealing with.

ETHAN MOLLICK: It’s important to know the personalities not just as personalities, but because there are tricks. Those are tunable approaches that the system makers decide. So it’s weird to have this — in one hand, don’t anthropomorphize, because you’re being manipulated, because you are. But on the other hand, the only useful way is to anthropomorphize. So keep in mind that you are dealing with the choices of the makers.

GPT-4 feels like a workhorse at this point. It is the most neutral of the approaches. It wants to get stuff done for you. And it will happily do that. It doesn’t have a lot of time for chitchat. And then we’ve got Google’s Bard, which feels like — or Gemini now — which feels like it really, really wants to help. We use this for teaching a lot. And we build these scenarios where the A.I. actually acts like a counterparty in a negotiation.

So you get to practice the negotiation by negotiating with the A.I. And it works incredibly well. I’ve been building simulations for 10 years, can’t imagine what a leap this has been. But when we try and get Google to do that, it keeps leaping in on the part of the students, to try and correct them and say, no, you didn’t really want to say this. You wanted to say that. And I’ll play out the scenario as if it went better. And it really wants to kind of make things good for you.

EZRA KLEIN: You were mentioning a minute ago that what the A.I.s do reflect decisions made by their programmers. They reflect guardrails, what they’re going to let the A.I. say. Very famously, Gemini came out and was very woke. You would ask it to show you a picture of soldiers in Nazi Germany, and it would give you a very multicultural group of soldiers, which is not how that army worked. But that was something that they had built in to try to make more inclusive photography generation.

ETHAN MOLLICK: I think that’s a very important point. And fundamental about A.I. is the idea that we technically know how LLMs work, but we don’t know how they work the way they do, or why they’re as good as they are. They’re really — we don’t understand it. The theories range from everyone — from it’s all fooling us, to they’ve emulated the way humans think because the structure of language is the structure of human thought. So even though they don’t think, they can emulate it. We don’t know the answer.

EZRA KLEIN: One thing people know about using these models is that hallucinations, just making stuff up, is a problem. Has that changed at all as we’ve moved from GPT-3.5 to 4, as we move from Claude 2 to 3. Like, has that become significantly better? And if not, how do you evaluate the trustworthiness of what you’re being told?

ETHAN MOLLICK: So those are a couple of overlapping questions. The first of them is, it getting better over time? So there is a paper in the field of medical citations that indicated that around 80 to 90 percent of citations had an error, were made up with GPT-3.5. That’s the free version of Chat. And that drops for GPT-4.

EZRA KLEIN: But doesn’t this make them unreliable in a very tricky way? 80 percent — you’re, like, it’s always hallucinating. 20 percent, 5 percent, it’s enough that you can easily be lulled into overconfidence. And one of the reasons it’s really tough here is you’re combining something that knows how to seem extremely persuasive and confident — you feed into the A.I. a 90-page paper on functions and characteristics of right wing populism in Europe, as I did last night.

ETHAN MOLLICK: Absolutely, and I think hard to grasp, because we’re used to things like type II errors, where we search for something on the internet and don’t find it. We’re not used to type I errors, where we search for something and get an answer back that’s made up. This is a challenge. And there’s a couple things to think about. One of those is — I advocate the BAH standard, best available human. So is the A.I. more or less accurate than the best human you could consult in that area?

EZRA KLEIN: But it also reflects something interesting about the nature of the systems. You have a quote here that I think is very insightful. You wrote, “the core irony of generative A.I.s is that A.I.s were supposed to be all logic and no imagination. Instead, we get A.I.s that make up information, engage in seemingly emotional discussions, and which are intensely creative.” And that last fact is one that makes many people deeply uncomfortable.

ETHAN MOLLICK: I love the phrase “a calculator that uses words.” I think we have been let down by science fiction, both in the utopias and apocalypses that A.I. might bring, but also, even more directly, in our view of how machines should work. People are constantly frustrated, and give the same kinds of tests to A.I.s over and over again, like doing math, which it doesn’t do very well — they’re getting better at this.

EZRA KLEIN: But we were using those measures five years ago, even though they were bad. That’s a point you make that I think is interesting and slightly unsettling.

ETHAN MOLLICK: Yeah, we never had to differentiate humans from machines before. It was always easy. So the idea that we had to have a scale that worked for people and machines, who had that? We had the Turing test, which everyone knew was a terrible idea. But since no machine could pass it, it was completely fine. So the question is, how do we measure this? This is an entirely separate set of issues. Like, we don’t even have a definition of sentience or consciousness.

EZRA KLEIN: So one of the things I will sometimes do, and did quite recently, is give the A.I. a series of personal documents, emails I wrote to people I love that were very descriptive of a particular moment in my life. And then I will ask the A.I. about them, or ask the A.I. to analyze me off of them.

ETHAN MOLLICK: That makes complete sense. I think the weird expectations — we call it the jagged frontier of A.I., that it’s good at some stuff and bad at other stuff. It’s often unexpected. It can lead to these weird moments of disappointment, followed by elation or surprise. And part of the reason why I advocate for people to use it in their jobs is, it isn’t going to outcompete you at whatever you’re best at. I mean, I cannot imagine it’s going to do a better job prepping someone for an interview than you’re doing.

And that’s not me just — I’m trying to be nice to you because you’re interviewing me, but because you’re a good interviewer. You’re a famous interviewer. It’s not going to be as good as that. Now, there’s questions about how good these systems get that we don’t know, but we’re kind of at a weirdly comfortable spot in A.I., which is, maybe it’s the 80th percentile of many performances. But I talk to Hollywood writers. It’s not close to writing like a Hollywood writer. It’s not close to being as good an analyst.

EZRA KLEIN: But this gets to this question of, what are you doing with it? The A.I.s right now seem much stronger as amplifiers and feedback mechanisms and thought partners for you than they do as something you can really outsource your hard work and your thinking to. And that, to me, is one of the differences between trying to spend more time with these systems — like, when you come into them initially, you’re like, OK, here’s a problem, give me an answer.

ETHAN MOLLICK: And that’s why the book’s called “Co-Intelligence.” For right now, we have a prosthesis for thinking. That’s, like, new in the world. We haven’t had that before — I mean, coffee, but aside from that, not much else. And I think that there’s value in that. I think learning to be partner with this, and where it can get wisdom out of you or not — I was talking to a physics professor at Harvard. And he said, all my best ideas now come from talking to the A.I. And I’m like, well, it doesn’t do physics that well. He’s like, no, but it asks good questions. And I think that there is some value in that kind of interactive piece.

EZRA KLEIN: We’ve already talked a bit about — Gemini is helpful, and ChatGPT-4 is neutral, and Claude is a bit warmer. But you urge people to go much further than that. You say to give your A.I. a personality. Tell it who to be. So what do you mean by that, and why?

ETHAN MOLLICK: So this is actually almost more of a technical trick, even though it sounds like a social trick. When you think about what A.I.s have done, they’ve trained on the collective corpus of human knowledge. And they know a lot of things. And they’re also probability machines. So when you ask for an answer, you’re going to get the most probable answer, sort of, with some variation in it. And that answer is going to be very neutral. If you’re using GPT-4, it’ll probably talk about a rich tapestry a lot.

It loves to talk about rich tapestries. If you ask it to code something artistic, it’ll do a fractal. It does very normal, central A.I. things. So part of your job is to get the A.I. to go to parts of this possibility space where the information is more specific to you, more unique, more interesting, more likely to spark something in you yourself. And you do that by giving it context, so it doesn’t just give you an average answer. It gives you something that’s specialized for you.

The easiest way to provide context is a persona. You are blank. You are an expert at interviewing, and you answer in a warm, friendly style. Help me come up with interview questions. It won’t be miraculous in the same way that we were talking about before. If you say you’re Bill Gates, it doesn’t become Bill Gates. But that changes the context of how it answers you. It changes the kinds of probabilities it’s pulling from and results in much more customized and better results.

EZRA KLEIN: OK, but this is weirder, I think, than you’re quite letting on here. So something you turned me on to is there’s research showing that the A.I. is going to perform better on various tasks, and differently on them, depending on the personality. So there’s a study that gives a bunch of different personality prompts to one of the systems, and then tries to get it to answer 50 math questions. And the way it got the best performance was to tell the A.I. it was a Starfleet commander who was charting a course through turbulence to the center of an anomaly.

ETHAN MOLLICK: “What the hell” is a good question. And we’re just scratching the surface, right? There’s a nice study actually showing that if you emotionally manipulate the A.I., you get better math results. So telling it your job depends on it gets you better results. Tipping, especially $20 or $100 — saying, I’m about to tip you if you do well, seems to work pretty well. It performs slightly worse in December than May, and we think it’s because it has internalized the idea of winter break.

EZRA KLEIN: I’m sorry, what?

ETHAN MOLLICK: Well, we don’t know for sure, but —

EZRA KLEIN: I’m holding you up here.

ETHAN MOLLICK: Yeah.

EZRA KLEIN: People have found the A.I. seems to be more accurate in May, and the going theory is that it has read enough of the internet to think that it might possibly be on vacation in December?

ETHAN MOLLICK: So it produces more work with the same prompts, more output, in May than it does in December. I did a little experiment where I would show it pictures of outside. And I’m like, look at how nice it is outside? Let’s get to work. But yes, the going theory is that it has internalized the idea of winter break and therefore is lazier in December.

EZRA KLEIN: I want to just note to people that when ChatGPT came out last year, and we did our first set of episodes on this, the thing I told you was this was going to be a very weird world. What’s frustrating about that is that — I guess I can see the logic of why that might be. Also, it sounds probably completely wrong, but also, I’m certain we will never know. There’s no way to go into the thing and figure that out.

ETHAN MOLLICK: And I think that that is, in some ways, both — as you said, the deep weirdness of these systems. But also, there’s actually downside risks to this. So we know, for example, there is an early paper from Anthropic on sandbagging, that if you ask the A.I. dumber questions, it would get you less accurate answers. And we don’t know the ways in which your grammar or the way you approach the A.I. — we know the amount of spaces you put gets different answers.

EZRA KLEIN: Well, I’m interested in the personas, although I just — I really find this part of the conversation interesting and strange. But I’m interested in the personalities you can give the A.I. for a different reason. I prompted you around this research on how a personality changes the accuracy rate of an A.I. But a lot of the reason to give it a personality, to answer you like it is Starfleet Commander, is because you have to listen to the A.I. You are in relationship with it.

ETHAN MOLLICK: The great power of A.I. is as a kind of companion. It wants to make you happy. It wants to have a conversation. And that can be overt or covert.

EZRA KLEIN: Kevin and I have talked a lot about that conversation with Sydney. And one of the things I always found fascinating about it is, to me, it revealed an incredibly subtle level of read by Sydney Bing, which is, what was really happening there? When you say the A.I. wants to make you happy, it has to read on some level what it is you’re really looking for, over time.

ETHAN MOLLICK: It’s a mirror. I mean, it’s trained on our stuff. And one of the revealing things about that, that I think we should be paying a lot more attention to, is the fact that because it’s so good at this, right now, none of the frontier A.I. models with the possible exception of Inflection’s Pi, which has been basically acquired in large part by Microsoft now, were built to optimize around keeping us in a relationship with the A.I. They just accidentally do that.

There are other A.I. models that aren’t as good that have been focused on this, but that has been something explicit from the frontier models they’ve been avoiding till now. Claude sort of breaches that line a little bit, which is part of why I think it’s engaging. But I worry about the same kind of mechanism that inevitably reined in social media, which is, you can make a system more addictive and interesting. And because it’s such a good cold reader, you could tune A.I. to make you want to talk to it more.

EZRA KLEIN: I want to hold here for a minute, because we’ve been talking about how to use frontier models, I think implicitly talking about how to use A.I. for work. But the way that a lot of people are using it is using these other companies that are explicitly building for relationships. So I’ve had people at one of the big companies tell me that if we wanted to tune our system relationally, if we wanted to tune it to be your friend, your lover, your partner, your therapist, like, we could blow the doors off that. And we’re just not sure it’s ethical.

ETHAN MOLLICK: I think that is an absolute near-term certainty, and sort of an unstoppable one, that we are going to have A.I. relationships in a broader sense.

And I think the question is, just like we’ve just been learning — I mean, we’re doing a lot of social experiments at scale we’ve never done before in the last couple of decades, right? Turns out social media brings out entirely different things in humans that we weren’t expecting. And we’re still writing papers about echo chambers and tribalism and facts, and what we agree or disagree with.

We’re about to have another wave of this. And we have very little research. And you could make a plausible story up, that what’ll happen is it’ll help mental health in a lot of ways for people, and then there’ll be more social outside, that there might be a rejection of this kind of thing.

EZRA KLEIN: I was worried we were getting off track in the conversation, but I realized we were actually getting deeper on the track I was trying to take us down.

ETHAN MOLLICK: I think that’s a temporary state of affairs, like extremely temporary. I think a GPT-4 class model — we actually already know this. They can guess your intent quite well. And I think that this is a way of giving you a sense of agency or control in the short term. I don’t think you’re going to need to know yourself at all. And I think you wouldn’t right now if any of the GPT-4 class models allowed themselves to be used in this way, without guardrails, which they don’t, I think you would already find it’s just going to have a conversation with you and morph into what you want.

EZRA KLEIN: So that’s a little bit chilling, but I’m nevertheless going to stay in this world we’re in, because I think we’re going to be in it for at least a little while longer, where you do have to do all this prompt engineering. What is a prompt, first? And what is prompt engineering?

ETHAN MOLLICK: So a prompt is — technically, it is the sentence, the command you’re putting into the A.I. What it really is is the beginning part of the A.I.s text that it’s processing. And then it’s just going to keep adding more words or tokens to the end of that reply, until it’s done. So a prompt is the command you’re giving the A.I. But in reality, it’s sort of a seed from which the A.I. builds.

EZRA KLEIN: And when you prompt engineer, what are some ways to do that? Maybe one to begin with, because it seems to work really well, is chain of thought.

ETHAN MOLLICK: Just to take a step back, A.I. prompting remains super weird. Again, strange to have a system where the companies making the systems are writing papers as they’re discovering how to use the systems, because nobody knows how to make them work better yet. And we found massive differences in our experiments on prompt types. So for example, we were able to get the A.I. to generate much more diverse ideas by using this chain of thought approach, which we’ll talk about.

EZRA KLEIN: Then you get an answer, and then what?

ETHAN MOLLICK: And then — what you do in a conversational approach is you go back and forth. If you want work output, what you’re going to do is treat it like it is an intern who just turned in some work to you. Actually, could you punch up paragraph two a little bit? I don’t like the example in paragraph one. Could you make it a little more creative, give me a couple of variations? That’s a conversational approach trying to get work done.

EZRA KLEIN: So I want to offer an example of how this back and forth can work. So we asked Claude 3 about prompt engineering, about what we’re talking about here. And the way it described it to us is, quote, “It’s a shift from the traditional paradigm of human-computer interaction, where we input explicit commands and the machine executes them in a straightforward way, to a more open ended, collaborative dialogue, where the human and the A.I. are jointly shaping the creative process,” end quote.

And that’s pretty good, I think. That’s interesting. It’s worth talking about. I like that idea that it’s a more collaborative dialogue. But that’s also boring, right? Even as I was reading it, it’s a mouthful. It’s wordy. So I kind of went back and forth with it a few times. And I was saying, listen, you’re a podcast editor. You’re concise, but also then I gave it a couple examples of how I punched up questions in the document, right? This is where the question began. Here’s where it ended. And then I said, try again, and try again, and try again, and make it shorter. And make it more concise.

ETHAN MOLLICK: So I am at a loss about when you went to Claude and when it was you, to be honest. So I was ready to answer at like two points along the way, so that was pretty good from my perspective, sitting here, talking to you. That felt interesting, and felt like the conversation we’ve been having. And I think there’s a couple of interesting lessons there.

The first, by the way, of — interestingly, you asked A.I. about one of its weakest points, which is about A.I. And everybody does this, but because its knowledge window doesn’t include that much stuff about A.I., it actually is pretty weak in terms of knowing how to do good prompting, or what a prompt is, or what A.I.s do well. But you did a good job with that. And I love that you went back and forth and shaped it.

One of the techniques you used to shape it, by the way, was called few-shot, which is giving an example. So the two most powerful techniques are chain of thought, which we just talked about, and few-shot, giving it examples. Those are both well supported in the literature. And then, I’d add personas. So we’ve talked about, I think, the basics of prompt crafting here overall. And I think that the question was pretty good.

EZRA KLEIN: One of the things I realized trying to spend more time with the A.I. is that you really have to commit to this process. You have to go back and forth with it a lot. If you do, you can get really good questions, like the one I just did — or, I think, really good outcomes. But it does take time.

ETHAN MOLLICK: One set of techniques that work quite well is to speed run to where you are in the conversation. So you can actually pick up an older conversation where you got the A.I.’s mindset where you want and work from there. You can even copy and paste that into a new window. You can ask the A.I. to summarize where you got in that previous conversation, and the tone the A.I. was taking, and then when you give a new instruction say the interaction I like to have with you is this, so have it solve the problem for you by having it summarize the tone that you happen to like at the end.

EZRA KLEIN: You did mention something important there, because they’re already getting much bigger in terms of how much information they can hold. Like, the earlier generations could barely hold a significant chat. Now, Claude 3 can functionally hold a book in its memory. And it’s only going to go way, way, way up from here. And I know I’ve been trying to keep us in the present, but this feels to me really quickly like where this is both going and how it’s going to get a lot better.

ETHAN MOLLICK: It’s not even going there. Like, it’s already there. Gemini 1.5 can hold an entire movie, books. But like, it starts to now open up entirely new ways of working. I can show it a video of me working on my computer, just screen capture. And it knows all the tasks I’m doing and suggests ways to help me out. It starts watching over my shoulder and helping me. I put in all of my work that I did prior to getting tenure and said, write my tenure statement. Use exact quotes.

EZRA KLEIN: One thing that feels important to keep in front of mind here is that we do have some control over that. And not only do we have some control over it, but business models and policy are important here. And one thing we know from inside these A.I. shops is these A.I.s already are, but certainly will be, really super persuasive.

And so if the later iterations of the A.I. companions are tuned on the margin to try to encourage you to be also out in the real world, that’s going to matter, versus whether they have a business model that all they want is for you to spend a maximum amount of time talking to your A.I. companion, whether you ever have a friend who is flesh and blood be damned.

And so that’s an actual choice, right? That’s going to be a programming decision. And I worry about what happens if we leave that all up to the companies, right? At some point, there’s a lot of venture capital money in here right now. At some point, the venture capital runs out. At some point, people need to make big profits. At some point, they’re in competition with other players who need to make profits. And that’s when things — you get into what Cory Doctorow calls the “enshitification” cycle, where things that were once adding a lot of value to the user begin extracting a lot of value to the user.

ETHAN MOLLICK: I absolutely agree. I think that we have agency here. We have agency in how we operate this in businesses, and whether we use this in ways that encourage human flourishing and employees, or are brutal to them. And we have agency over how this works socially. And I think we abrogated that responsibility with social media, and that is an example. Not to be bad news, because I generally have a lot of mixed optimism and pessimism about parts of A.I., but the bad news piece is there are open source models out there that are quite good.

EZRA KLEIN: I see a lot of reasons to be worried about the open source models. And people talk about things like bioweapons and all that. But for some of the harms I’m talking about here, if you want to make money off of American kids, we can regulate you. So sometimes I feel like we almost, like, give up the fight before it begins. But in terms of what a lot of people are going to use, if you want to be having credit card payments processed by a major processor, then you have to follow the rules.

ETHAN MOLLICK: I couldn’t agree more. And I don’t think there’s any reason to give up hope on regulation. I think that we can mitigate. And I think part of our job, though, is also not just to mitigate the harms, but to guide towards the positive viewpoints, right? So what I worry about is that the incentive for profit making will push for A.I. that acts informally as your therapist or your friend, while our worries about experimentation, which are completely valid, are slowing down our ability to do experiments to find out ways to do this right.

And I think it’s really important to have positive examples, too. I want to point to the A.I. systems acting ethically as your friend or companion, and figure out what that is, so there’s a positive model to look for. So I’m not just — this is not to denigrate the role of regulation, which I think is actually going to be important here, and self regulation, and rapid response from government, but also the companion problem of, “we need to make some sort of decisions about what are the paragons of this, what is acceptable as a society?”

EZRA KLEIN: So I want to talk a bit about another downside here, and this one more in the mainstream of our conversation, which is on the human mind, on creativity. So a lot of the work A.I. is good at automating is work that is genuinely annoying, time consuming, laborious, but often plays an important role in the creative process. So I can tell you that writing a first draft is hard, and that work on the draft is where the hard thinking happens.

ETHAN MOLLICK: I think the idea of struggle is actually a core one in many things. I’m an educator. And one thing that keeps coming out in the research is that there is a strong disconnect between what students think they’re learning and when they learn. So there was a great controlled experiment at Harvard in intro science classes, where students either went to a pretty entertaining set of lectures, or else they were forced to do active learning, where they actually did the work in class.

Not just because, by the way, it makes the work easier, but also because you mentally anchor on the A.I.’s answer. And in some ways, the most dangerous A.I. application, in my mind, is the fact that you have these easy co-pilots in Word and Google Docs, because any writer knows about the tyranny of the blank page, about staring at a blank page and not knowing what to do next, and the struggle of filling that up. And when you have a button that produces really good words for you, on demand, you’re just going to do that. And it’s going to anchor your writing.

We can teach people about the value of productive struggle, but I think that during the school years, we have to teach people the value of writing — not just assign an essay and assume that the essay does something magical, but be very intentional about the writing process and how we teach people about how to do that, because I do think the temptation of what I call “the button” is going to be there otherwise, for everybody.

EZRA KLEIN: But I worry this stretches, I mean, way beyond writing. So the other place I worry about this, or one of the other places I worry about this a lot, is summarizing. And I mean, this goes way back. When I was in school, you could buy Sparknotes. And they were these little, like, pamphlet sized descriptions of what’s going on in “War and Peace” or what’s going on in “East of Eden.”

ETHAN MOLLICK: So I don’t mean to push back too much on this.

EZRA KLEIN: No, please, push back a lot.

ETHAN MOLLICK: But I think you’re right.

EZRA KLEIN: Imagine we’re debating and you are a snarky. A.I. [LAUGHS]

ETHAN MOLLICK: Fair enough. With that prompt —

EZRA KLEIN: With that prompt engineering.

ETHAN MOLLICK: — yeah, I mean, I think that this is the eternal thing about looking back on the next generation, we worry about technology ruining them. I think this makes ruining easier. But as somebody who teaches at universities, like, lots of people are summarizing. Like, I think those of us who enjoy intellectual struggle are always thinking everybody else is going through the same intellectual struggle when they do work. And they’re doing it about their own thing. They may or may not care the same way.

EZRA KLEIN: Well, let me take this from another angle. One of the things that I’m a little obsessed with is the way the internet did not increase either domestic or global productivity for any real length of time. So I mean, it’s a very famous line. You can see the IT revolution anywhere but in the productivity statistics. And then you do get, in the ’90s, a bump in productivity that then peters out in the 2000s.

And so some of the time that was given to us back was also taken back. And I see a lot of dynamics like this that could play out with A.I. — I wouldn’t even just say if we’re not careful, I just think they will play out and already are. I mean, the internet is already filling with mediocre crap generated by A.I. There is going to be a lot of destructive potential, right? You are going to have your sex bot in your pocket, right?

There’s a million things — and not just that, but inside organizations, there’s going to be people padding out what would have been something small, trying to make it look more impressive by using the A.I. to make something bigger. And then, you’re going to use the A.I. to summarize it back down. The A.I. researcher, Jonathan Frankel, described this to me as, like, the boring apocalypse version of A.I., where you’re just endlessly inflating and then summarizing, and then inflating and then summarizing the volume of content between different A.I.

ETHAN MOLLICK: So I think there’s a lot there to chew on. And I also have spent a lot of time trying to think about why the internet didn’t work as well. I was an early Wikipedia administrator.

EZRA KLEIN: Thank you for your service.

ETHAN MOLLICK: [LAUGHS] Yeah, it was very scarring. But I think a lot about this. And I think A.I. is different. I don’t know if it’s different in a positive way. And I think we talked about some of the negative ways it might be different. And I think it’s going to be many things at once, happening quite quickly. So I think the information environment’s going to be filled up with crap. We will not be able to tell the difference between true and false anymore. It will be an accelerant on all the kinds of problems that we have there.

The thing that makes A.I. possibly great is that it’s so very human, so it interacts with our human systems in a way that the internet did not. We built human systems on top of it, but A.I. is very human. It deals with human forms and human issues and our human bureaucracy very well. And that gives me some hope that even though there’s going to be lots of downsides, that the upsides of productivity and things like that are real.

Part of the problem with the internet is we had to digitize everything. We had to build systems that would make our offline world work with our online world. And we’re still doing that. If you go to business schools, digitizing is still a big deal 30 years on from early internet access. A.I. makes this happen much quicker because it works with us. So I’m a little more hopeful than you are about that, but I also think that the downside risks are truly real and hard to anticipate.

EZRA KLEIN: I think that is a good place to end. So always our final question, what are three books you’d recommend to the audience?

ETHAN MOLLICK: OK, so the books I’ve been thinking about are not all fun, but I think they’re all interesting. One of them is “The Rise and Fall of American Growth,” which is — it’s two things. It’s an argument about why we will never have the kind of growth that we did in the first part of the Industrial Revolution again, but I think that’s less interesting than the first half of the book, which is literally how the world changed between 1870 or 1890 and 1940, versus 1940 and 1990, or 2000.

EZRA KLEIN: Ethan Mollick, your book is called “Co-Intelligence.” Your Substack is One Useful Thing. Thank you very much.

ETHAN MOLLICK: Thank you.

EZRA KLEIN: This episode of “The Ezra Klein Show” was produced by Kristin Lin. Fact checking by Michelle Harris. Our senior engineer is Jeff Geld with additional mixing from Efim Shapiro. Our senior editor is Claire Gordon. The show’s production team also includes Annie Galvin and Rollin Hu. Original music by Isaac Jones. Audience strategy by Kristina Samulewski and Shannon Busta. The executive producer of New York Times Opinion Audio is Annie-Rose Strasser, and special thanks to Sonia Herrero.

Advertisement

10 Best ChatGPT Email Prompts

1 click unsubscribe at any time

Love it or hate it, ChatGPT is revolutionizing email communication for professionals around the world. 🌍 From turning long messages into easy-to-understand summaries to crafting well-written replies in just seconds. ⚡ Learn how to use these ChatGPT email prompts to make email management easy.

To get started, here are 10 Chat GPT email prompts to help you tackle common tasks with less effort. 👏

Feel free to experiment with the style and structure of these prompts and modify them based on the results you’re looking for: ⏬

1. Schedule meetings and calls

In the professional world, scheduling meetings and phone calls is something we have to do every day. 📞

To create clear and concise emails, you can use the following ChatGPT prompt template :

“You’re writing a commercial email in which you want to schedule meetings or calls. Insert variables {} like first name, company name. Enter the subject of the email and a professional signature. In 70 words.”

Tips for scheduling meetings using ChatGPT: 👇

• Be specific about the purpose, date, and time of the meeting.
• Suggest multiple time slots to fit your recipient’s schedule .
• Add relevant links. 🌐 For example: virtual meeting platform or location details.

Furthermore, here’s how to send a professional meeting request email ! 🌟

2. Follow up with prospects or clients

Following up with prospects and customers is critical to nurturing relationships and driving growth. 🌱

With ChatGPT, you can create compelling follow-up emails with the following prompt template:

“You’re the {work position} from {Your Company} specializing in {product or service}. Write a persuasive follow-up email to {name} from {Company Name} who expressed interest in our services during {event where you met}. Highlight the benefits we offer, such as {list benefits}. Keep it under 70 words.”

When creating follow-up emails, you can use ChatGPT to: 👇

• Remind recipients of previous interactions.
• Highlight the benefits of your service.
• Provide a clear call to action . ⚡ Try arranging a call or sending additional information .

3. Ask for specific documentation

Requesting further information or documents to a colleague is a common email task. 🤔

Use the following ChatGPT prompt to make a respectful and concise request.

You can even ask the AI to create several examples : ⬇️

“Draft an email to a colleague asking for {information or action} for the goal of {give the purpose of your request}. Give me 3 examples. In 70 words each.”

If the recipient hasn’t responded to your request yet, and you need one quickly, you can use Waalaxy’s emailing campaigns to set up your scenarios.

For example, if the person doesn’t reply in 2 days, you can send them a brief reminder . 👌

Learn more about how to send a reminder email , here! 📩

4. Provide project updates

Keeping employees updated on project progress is important for transparency and collaboration. 🤝

Create well-structured progress reports using this ChatGPT prompt:

“Create an email updating {person or group of people} on the status of {project}, including {list of completed tasks, upcoming milestones, and any challenges encountered}. Enter the subject of the email and a professional signature. In 70 words, max.”

Furthermore, use collaboration techniques for your company like “Smarketing” .

The goal is to work better, not harder! 💪

5. Summarize a meeting

Meetings can be incredibly time-consuming ! 😖

The average manager has between 11 and 15 meetings per week . 😤 No one has the time or mental capacity to remember everything that was said…

Moreover, long texts are a pain to read. 🧨

So, why not ask ChatGPT to summarize your meeting notes and turn them into bullet points, so you don’t forget key details? 🪄

“You’re writing an internal email in which you want to summarize what was said in a meeting, into bullet points. Enter the subject line and use a professional tone.”

From here, you can turn your summary into an email or memo , so you can quickly get an overview of what’s important. 💡

6. Send an invoice or payment reminder

Sending invoices and payment reminders can be a delicate task. 🤐

To create a polite and professional email, try these ChatGPT prompts:

“Write an email to {client’s name}, attaching their invoice for {your service} for the total amount of {cost of services} and kindly reminding them that the due date for payment is {enter date}.”

Are you rushing and need to write a payment request quickly? 😥

Save your personalized email templates in Waalaxy , and send them any time you need. 🙌

7. Apologize to a customer

Handling customer complaints sensitively and professionally is critical to maintaining trust and satisfaction. 🤗

Moreover, using the right ChatGPT email prompts can help you craft a respectful apology, like this one:

“You’re writing a personalized email to apologize to a customer for {issues with delivery, wrong product, etc.}. Write a 70-word apology email offering {a discount, free delivery, gift card, etc}. Use an empathetic tone.”

Want to know more about client retention strategies? 👈 We got you!

8. Ask for referrals

Referrals or recommendations are invaluable in growing your business and building credibility . 👀

To create a compelling request , you can use the following prompt:

“Write a personalized email in which you ask for referrals or recommendations. Address it an ex-colleague or client that knows you and insert variables {} like first name, company name. In 70 words.”

Furthermore, learn how to endorse someone on LinkedIn , in this article! ✍️

9. Decline an invitation

Have you ever received an invitation to an event but can’t attend? 🙈

ChatGPT can help you politely decline the offer . 👉 To do this, use the following prompt:

“Write a polite and professional email declining {invitation or event}, thanking them for the opportunity, and explaining that you are unable to attend for {reasons you cannot attend}. Explain it briefly in under 100 words.”

By the way… Have you tried launching LinkedIn events yet? 🧐

It’s a great way to boost your B2b prospecting strategy!

10. Submit a CV application

We all know how hard it is to find work, specially freelance jobs . 😪

In this competitive job market, you need to make sure your CV application email stands out from the crowd. 🌟

Jobseekers can use the following prompt to impress potential employers:

“Write an email application for the position [Job Title] at [Company Name], express your enthusiasm for the position and the company, and attach your resume. Maintain a professional and engaging tone, address the email to the recruiter at [Recruiter Name], and include a CTA to schedule an interview. Keep it under 80 words.”

It’s a well-known fact that ChatGPT has difficulty expressing one’s feelings. 😐

When writing a job application email, you want to let the recipient know that you’re enthusiastic about the position, so remember to include the tone you want into your prompt. 🗣️

Limits of using ChatGPT prompt email

Speaking of which… 🫢 Now, we’ll discuss what are some limits of using ChatGPT prompts.

There are 3 main limitations when using ChatGPT to create email responses: 👇

• Lack of personalization: ChatGPT can produce professional and consistent emails, but without detailed input, it cannot capture the unique voice or specific nuances of a person’s or company’s communication style. This may result in a response that seems too generic.
• Misunderstanding context: Because ChatGPT relies on the text provided, it can misinterpret complex or subtle requests, resulting in a response that does not fully address the sender’s intent or question. 🫣
• Current information: ChatGPT training data is only updated to a certain point in time. This means that accurate and relevant email responses may not include information about current events, updates, and context that are important.

Don’t worry, though!

In general, the benefits of using artificial intelligence are higher than the difficulties. 😇

Conclusion: ChatGPT Prompts for Email Marketing

Nowadays, emails have become an essential part of our lives. 📧

However, just sending an email isn’t enough… 🙊 It needs to convey your message effectively, and leave a good impression on your recipients .

ChatGPT is here to help you with this task. 👏

But, keep in mind that you may not always be satisfied with the results given by the AI .

In some cases, it may get the wrong idea or the answer is not the one you want. 🤫  Therefore, don’t press “Send email” right away.

Always check the results and make changes if necessary. 👉 Remember, the answer you get is only as good as the prompt you gave.

Try to provide as much context as possible or use the “Regenerate” button , to get a different result. 💎 As some people say, “practice makes perfect”.

So, why not give Chat GPT email prompts a go! 😏

FAQ: ChatGPT Email Marketing Prompts

Can i use chat gpt for work emails.

Absolutely! 😍 ChatGPT can be used for work emails.

Imagine this: you’ll be able to write emails faster with customized responses and a creative flair while maintaining a professional feel. 💼

Whether you want to schedule meetings, track projects, or process customer service requests, ChatGPT acts as your personal email assistant .

💡 Remember: It’s a good idea to add a personal touch to your email before hitting send so it matches perfectly your tone and company culture .

How to use ChatGPT to answer an email?

Using ChatGPT to respond to emails is like having an assistant at your fingertips. 🪶

Just enter the gist of the email you received. 👉 And watch it produce an answer tailored to your needs.

Customize the tone, style, and details to match your company or personal branding .

It’s a time-saving tool that will help you respond efficiently and captivate your recipients, with professional emails. ✅

Great, now you know the best ChatGPT email prompts. 👏

Want to go further?

Auto Subtitle Generator: Choose the Right One!

How to Introduce Yourself in an Email: 15 Examples + 5 Tips

Email automation: Definition and 6-Step Guide!

Get the ultimate e-book for multi-channel prospecting 📨

7 examples of successful prospecting messages to boost the response rates of your prospecting campaigns.

Social media

Prospecting

Recruitement

7 examples of successful LinkedIn prospecting messages

Masterclasses

Dans la piscine

Sucess story