the structure of a persuasive essay

How to Write a Persuasive Essay (This Convinced My Professor!)

Table of contents

Meredith Sell

You can make your essay more persuasive by getting straight to the point.

In fact, that's exactly what we did here, and that's just the first tip of this guide. Throughout this guide, we share the steps needed to prove an argument and create a persuasive essay.

This AI tool helps you improve your essay > This AI tool helps you improve your essay >

Key takeaways: - Proven process to make any argument persuasive - 5-step process to structure arguments - How to use AI to formulate and optimize your essay

Why is being persuasive so difficult?

"Write an essay that persuades the reader of your opinion on a topic of your choice."

You might be staring at an assignment description just like this 👆from your professor. Your computer is open to a blank document, the cursor blinking impatiently. Do I even have opinions?

The persuasive essay can be one of the most intimidating academic papers to write: not only do you need to identify a narrow topic and research it, but you also have to come up with a position on that topic that you can back up with research while simultaneously addressing different viewpoints.

That’s a big ask. And let’s be real: most opinion pieces in major news publications don’t fulfill these requirements.

The upside? By researching and writing your own opinion, you can learn how to better formulate not only an argument but the actual positions you decide to hold. 

Here, we break down exactly how to write a persuasive essay. We’ll start by taking a step that’s key for every piece of writing—defining the terms.

What Is a Persuasive Essay?

A persuasive essay is exactly what it sounds like: an essay that persuades . Over the course of several paragraphs or pages, you’ll use researched facts and logic to convince the reader of your opinion on a particular topic and discredit opposing opinions.

While you’ll spend some time explaining the topic or issue in question, most of your essay will flesh out your viewpoint and the evidence that supports it.

The 5 Must-Have Steps of a Persuasive Essay

If you’re intimidated by the idea of writing an argument, use this list to break your process into manageable chunks. Tackle researching and writing one element at a time, and then revise your essay so that it flows smoothly and coherently with every component in the optimal place.

1. A topic or issue to argue

This is probably the hardest step. You need to identify a topic or issue that is narrow enough to cover in the length of your piece—and is also arguable from more than one position. Your topic must call for an opinion , and not be a simple fact .

It might be helpful to walk through this process:

• Identify a random topic
• Ask a question about the topic that involves a value claim or analysis to answer
• Answer the question

That answer is your opinion.

Let’s consider some examples, from silly to serious:

Topic: Dolphins and mermaids

Question: In a mythical match, who would win: a dolphin or a mermaid?

Answer/Opinion: The mermaid would win in a match against a dolphin.

Topic: Autumn

Question: Which has a better fall: New England or Colorado?

Answer/Opinion: Fall is better in New England than Colorado.

Topic: Electric transportation options

Question: Would it be better for an urban dweller to buy an electric bike or an electric car?

Answer/Opinion: An electric bike is a better investment than an electric car.

Your turn: Walk through the three-step process described above to identify your topic and your tentative opinion. You may want to start by brainstorming a list of topics you find interesting and then going use the three-step process to find the opinion that would make the best essay topic.

2. An unequivocal thesis statement

If you walked through our three-step process above, you already have some semblance of a thesis—but don’t get attached too soon! 

A solid essay thesis is best developed through the research process. You shouldn’t land on an opinion before you know the facts. So press pause. Take a step back. And dive into your research.

You’ll want to learn:

• The basic facts of your topic. How long does fall last in New England vs. Colorado? What trees do they have? What colors do those trees turn?
• The facts specifically relevant to your question. Is there any science on how the varying colors of fall influence human brains and moods?
• What experts or other noteworthy and valid sources say about the question you’re considering. Has a well-known arborist waxed eloquent on the beauty of New England falls?

As you learn the different viewpoints people have on your topic, pay attention to the strengths and weaknesses of existing arguments. Is anyone arguing the perspective you’re leaning toward? Do you find their arguments convincing? What do you find unsatisfying about the various arguments? 

Allow the research process to change your mind and/or refine your thinking on the topic. Your opinion may change entirely or become more specific based on what you learn.

Once you’ve done enough research to feel confident in your understanding of the topic and your opinion on it, craft your thesis. 

Your thesis statement should be clear and concise. It should directly state your viewpoint on the topic, as well as the basic case for your thesis.

Thesis 1: In a mythical match, the mermaid would overcome the dolphin due to one distinct advantage: her ability to breathe underwater.

Thesis 2: The full spectrum of color displayed on New England hillsides is just one reason why fall in the northeast is better than in Colorado.

Thesis 3: In addition to not adding to vehicle traffic, electric bikes are a better investment than electric cars because they’re cheaper and require less energy to accomplish the same function of getting the rider from point A to point B.

Your turn: Dive into the research process with a radar up for the arguments your sources are making about your topic. What are the most convincing cases? Should you stick with your initial opinion or change it up? Write your fleshed-out thesis statement.

3. Evidence to back up your thesis

This is a typical place for everyone from undergrads to politicians to get stuck, but the good news is, if you developed your thesis from research, you already have a good bit of evidence to make your case.

Go back through your research notes and compile a list of every …

… or other piece of information that supports your thesis. 

This info can come from research studies you found in scholarly journals, government publications, news sources, encyclopedias, or other credible sources (as long as they fit your professor’s standards).

As you put this list together, watch for any gaps or weak points. Are you missing information on how electric cars versus electric bicycles charge or how long their batteries last? Did you verify that dolphins are, in fact, mammals and can’t breathe underwater like totally-real-and-not-at-all-fake 😉mermaids can? Track down that information.

Next, organize your list. Group the entries so that similar or closely related information is together, and as you do that, start thinking through how to articulate the individual arguments to support your case. 

Depending on the length of your essay, each argument may get only a paragraph or two of space. As you think through those specific arguments, consider what order to put them in. You’ll probably want to start with the simplest argument and work up to more complicated ones so that the arguments can build on each other. 

Your turn: Organize your evidence and write a rough draft of your arguments. Play around with the order to find the most compelling way to argue your case.

4. Rebuttals to disprove opposing theses

You can’t just present the evidence to support your case and totally ignore other viewpoints. To persuade your readers, you’ll need to address any opposing ideas they may hold about your topic. 

You probably found some holes in the opposing views during your research process. Now’s your chance to expose those holes. 

Take some time (and space) to: describe the opposing views and show why those views don’t hold up. You can accomplish this using both logic and facts.

Is a perspective based on a faulty assumption or misconception of the truth? Shoot it down by providing the facts that disprove the opinion.

Is another opinion drawn from bad or unsound reasoning? Show how that argument falls apart.

Some cases may truly be only a matter of opinion, but you still need to articulate why you don’t find the opposing perspective convincing.

Yes, a dolphin might be stronger than a mermaid, but as a mammal, the dolphin must continually return to the surface for air. A mermaid can breathe both underwater and above water, which gives her a distinct advantage in this mythical battle.

While the Rocky Mountain views are stunning, their limited colors—yellow from aspen trees and green from various evergreens—leaves the autumn-lover less than thrilled. The rich reds and oranges and yellows of the New England fall are more satisfying and awe-inspiring.

But what about longer trips that go beyond the city center into the suburbs and beyond? An electric bike wouldn’t be great for those excursions. Wouldn’t an electric car be the better choice then? 

Certainly, an electric car would be better in these cases than a gas-powered car, but if most of a person’s trips are in their hyper-local area, the electric bicycle is a more environmentally friendly option for those day-to-day outings. That person could then participate in a carshare or use public transit, a ride-sharing app, or even a gas-powered car for longer trips—and still use less energy overall than if they drove an electric car for hyper-local and longer area trips.

Your turn: Organize your rebuttal research and write a draft of each one.

5. A convincing conclusion

You have your arguments and rebuttals. You’ve proven your thesis is rock-solid. Now all you have to do is sum up your overall case and give your final word on the subject. 

Don’t repeat everything you’ve already said. Instead, your conclusion should logically draw from the arguments you’ve made to show how they coherently prove your thesis. You’re pulling everything together and zooming back out with a better understanding of the what and why of your thesis. 

A dolphin may never encounter a mermaid in the wild, but if it were to happen, we know how we’d place our bets. Long hair and fish tail, for the win.

For those of us who relish 50-degree days, sharp air, and the vibrant colors of fall, New England offers a season that’s cozier, longer-lasting, and more aesthetically pleasing than “colorful” Colorado. A leaf-peeper’s paradise.

When most of your trips from day to day are within five miles, the more energy-efficient—and yes, cost-efficient—choice is undoubtedly the electric bike. So strap on your helmet, fire up your pedals, and two-wheel away to your next destination with full confidence that you made the right decision for your wallet and the environment.

3 Quick Tips for Writing a Strong Argument

Once you have a draft to work with, use these tips to refine your argument and make sure you’re not losing readers for avoidable reasons.

1. Choose your words thoughtfully.

If you want to win people over to your side, don’t write in a way that shuts your opponents down. Avoid making abrasive or offensive statements. Instead, use a measured, reasonable tone. Appeal to shared values, and let your facts and logic do the hard work of changing people’s minds.

Choose words with AI

You can use AI to turn your general point into a readable argument. Then, you can paraphrase each sentence and choose between competing arguments generated by the AI, until your argument is well-articulated and concise.

2. Prioritize accuracy (and avoid fallacies).

Make sure the facts you use are actually factual. You don’t want to build your argument on false or disproven information. Use the most recent, respected research. Make sure you don’t misconstrue study findings. And when you’re building your case, avoid logical fallacies that undercut your argument.

A few common fallacies to watch out for:

• Strawman: Misrepresenting or oversimplifying an opposing argument to make it easier to refute.
• Appeal to ignorance: Arguing that a certain claim must be true because it hasn’t been proven false.
• Bandwagon: Assumes that if a group of people, experts, etc., agree with a claim, it must be true.
• Hasty generalization: Using a few examples, rather than substantial evidence, to make a sweeping claim.
• Appeal to authority: Overly relying on opinions of people who have authority of some kind.

The strongest arguments rely on trustworthy information and sound logic.

Research and add citations with AI

We recently wrote a three part piece on researching using AI, so be sure to check it out . Going through an organized process of researching and noting your sources correctly will make sure your written text is more accurate.

3. Persuasive essay structure

If you’re building a house, you start with the foundation and go from there. It’s the same with an argument. You want to build from the ground up: provide necessary background information, then your thesis. Then, start with the simplest part of your argument and build up in terms of complexity and the aspect of your thesis that the argument is tackling.

A consistent, internal logic will make it easier for the reader to follow your argument. Plus, you’ll avoid confusing your reader and you won’t be unnecessarily redundant.

The essay structure usually includes the following parts:

• Intro - Hook, Background information, Thesis statement
• Topic sentence #1 , with supporting facts or stats
• Concluding sentence
• Topic sentence #2 , with supporting facts or stats
• Concluding sentence Topic sentence #3 , with supporting facts or stats
• Conclusion - Thesis and main points restated, call to action, thought provoking ending

Are You Ready to Write?

Persuasive essays are a great way to hone your research, writing, and critical thinking skills. Approach this assignment well, and you’ll learn how to form opinions based on information (not just ideas) and make arguments that—if they don’t change minds—at least win readers’ respect. ‍

Share This Article:

The Official Wordtune Guide

An Expert Guide to Writing Effective Compound Sentences (+ Examples)

A Step-by-Step Guide to Writing a Stellar Literature Review (with Help from AI)

Looking for fresh content, thank you your submission has been received.

• Writing services
• Proofreading
• Math/Science
• Copywriting
• Dissertation services
• Admission services
• Our Writers

How to Write a Perfect Persuasive Essay

Table of contents:

• Structure and format

Persuasive vs. argumentative essay

• Persuasive essay introduction
• Persuasive essay body part
• Persuasive essay conclusion

Writing tips

A persuasive essay is an important tool in an Australian student’s repertoire. It will be useful not only for your assignments, but sets a good foundation for your life outside of high school, VET, or university as well, when you may have to negotiate with bosses, persuade customers to purchase your amazing goods, or even calm down an upset child.

But how do you write a 5 paragraph persuasive essay which will get you that coveted high grade? Your teacher or professor will be using a specific rubric to set your grades for these kinds of assignments. Let’s take a look.

Persuasive essay structure and format

The basic structural persuasive essay outline is, indeed, 5 paragraphs. It can be more, of course, and often will be, as you should try to keep each point supporting your main argument, or thesis , to one paragraph.

Typical structure for a persuasive essay:

• Introduction
• Body paragraphs (3 or more)

This is the fundamental layout: you will start with one paragraph as an introduction, then go on to write three or more paragraphs containing the body of your essay, then finally your conclusion, wrapping everything up with a neat little bow on top.

You may have also heard of argumentative essays and wonder what the difference is from a persuasive essay. Simply put, an argumentative essay must be based on cold hard facts which have been researched and are verifiable. It must be an essay devoted to the arguments in favour of a particular topic.

However, a persuasive essay has a wider range of resources available, as its only goal is to persuade the reader of the thesis. You can use appeals to emotion, social validation, stories and anecdotes, as well as of course facts and logic to persuade your audience. Think of the difference between a politician trying to persuade people to vote for him or her versus a scientist laying out the evidence they have gathered.

Part 1: Persuasive essay introduction

You begin with a hook , grabbing your audience’s attention from the start with your very first sentence. This can take the form of a relevant quote, or perhaps a personal anecdote, an interesting statistic or fact, an outrageous statement, or a question.

Having seized your reader’s attention, you will need to define who that reader should be. Make the definition of your intended audience clear, whether that’s your teacher, your fellow students, cat owners, fans of Star Wars, or Pokémon collectors.

The third and final part of the intro should consist of your thesis . This is a clear, strong, focused sentence that tells the reader the specific topic or purpose you’re writing about. It is your essay’s foundation, and everything else you will say in the essay rests on it. This is not the time to be wishy-washy or half-hearted; you must take an active, bold stance on the issue of your choice.

If you are not sure how to start persuasive essay, or feel you need prompts or samples of ideas, try looking at the news, whether local to your college or high school, or Aussie news in general. Use the techniques of making a checklist of questions or opinions you have about the world or about Australia, then proceed step by step through your worksheet. Do some research about your topics and find out which one inspires you the most. 

Once you’ve made your thesis statement you can continue onward and write the body of your essay.

Part 2: Persuasive essay body paragraphs

Your essay’s body is the meat of the essay. It’s where you do the actual persuading to convince people to believe in your thesis. You should have at least three paragraphs’ worth of evidence for your argument, and if you do not, it’s likely that your thesis isn’t strong enough. If that’s the case, take a step back, and come up with ideas for a statement you feel strongly about, and take your topic from there.

Each separate point you make in defence of your thesis should be contained in a body paragraph of its own, and any facts, examples, stats, or quotes backing up that point included in the same paragraph. Take the time to fully examine each of your points and their meaning. You will also need to consider what someone who disagreed with your thesis might say in response and try to counteract their argument before they can make it.

If appropriate, it may well be worth conceding to, or finding common ground with, any opponents. Anticipating their arguments and agreeing where necessary is a show of strength and confidence on your part. On the other hand, a failure to address an obvious opposing argument looks weak and unprepared, so make sure you’ve got all your ducks in a row.

Part 3: Persuasive essay conclusion

Once you reach the conclusion of your essay, your audience should be at the point of agreeing with you. The conclusion is just to reinforce what they have already been told and leave them with a call to action so that they will carry on with their day in a somewhat different frame of mind than they were when they started reading your essay.

Begin your conclusion by restating your thesis, then your main points. This is important to keep the information fresh in their minds. Once you’ve done this, then close with the idea of the action you want them to take, whether that’s a question for them to think about, a prediction of what might happen in the future, or a literal call for them to do something, like donate to a particular charity or sign a petition.

Now you know how to write a persuasive essay, and are hopefully on your way to great grades. If you still need help, see the writing tips below.

• As you move between points on towards the inevitable conclusion, use transition words and phrases as sentence starters, as they serve as cues for the audience that the argument is moving onward. Some examples of these words are: however , therefore , consequently , in fact , on the other hand , instead , thus , and still .
• If you are truly stuck, why not consider if you can buy persuasive essay online? Another writer’s pages or papers can provide you with a template for the structure or serve as a generator for your own thoughts.
• Persuasive essay writing is like planning a house somewhere in Australia. Think of your thesis as the roof of a building, and each of your supporting points as pillars underneath it. Like a real roof, it has to have at least three pillars to stay up, and the more, the sturdier the whole argument is.
• The titles of your persuasive essays should be a pared-down version of your thesis statements.
• Essay samples
• Infographics
• Essay writing
• Crafting a Powerful Essay on Political Polarization
• Oral Health Overview Essay: Preventing Tooth Decay in Australia
• How to Write a Good Expository Essay About Macbeth
• How to Write An Expository Essay About Love
• How to Write a Great Expository Essay About Life

Price per page

Total price:

Limitless Amendments

Bibliography

Plagiarism Report

Get all these features for A$93.12 FREE

If you don't know exactly what type of paper you need or can't find the necessary one on the website - don't worry! Contact us and we'll help you out!

• Terms of Use
• Money Back Guarantee
• Cookie Policy
• Privacy Policy
• Write My Essay
• Custom Essay
• Essay Writer
• Do My Essay
• Type My Essay
• Pay For Essay
• Cheap Essay
• Write My Paper
• Write My Assignment
• Assignment Writer
• Buy Assignment
• Assignment Help
• Do My Assignment
• Nursing Essay Writing Service
• Management Essay
• Business Essay
• Law Essay Writing Service
• Education Essay Service
• Marketing Essay
• Accounting Essay
• Sociology Essay

Before continuing to use our service please make sure you got acquainted with our Cookie Policy and accepted it by clicking OK

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, generate accurate citations for free.

• Knowledge Base
• How to write an argumentative essay | Examples & tips

How to Write an Argumentative Essay | Examples & Tips

Published on July 24, 2020 by Jack Caulfield . Revised on July 23, 2023.

An argumentative essay expresses an extended argument for a particular thesis statement . The author takes a clearly defined stance on their subject and builds up an evidence-based case for it.

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Table of contents

When do you write an argumentative essay, approaches to argumentative essays, introducing your argument, the body: developing your argument, concluding your argument, other interesting articles, frequently asked questions about argumentative essays.

You might be assigned an argumentative essay as a writing exercise in high school or in a composition class. The prompt will often ask you to argue for one of two positions, and may include terms like “argue” or “argument.” It will frequently take the form of a question.

The prompt may also be more open-ended in terms of the possible arguments you could make.

Argumentative writing at college level

At university, the vast majority of essays or papers you write will involve some form of argumentation. For example, both rhetorical analysis and literary analysis essays involve making arguments about texts.

In this context, you won’t necessarily be told to write an argumentative essay—but making an evidence-based argument is an essential goal of most academic writing, and this should be your default approach unless you’re told otherwise.

Examples of argumentative essay prompts

At a university level, all the prompts below imply an argumentative essay as the appropriate response.

Your research should lead you to develop a specific position on the topic. The essay then argues for that position and aims to convince the reader by presenting your evidence, evaluation and analysis.

• Don’t just list all the effects you can think of.
• Do develop a focused argument about the overall effect and why it matters, backed up by evidence from sources.
• Don’t just provide a selection of data on the measures’ effectiveness.
• Do build up your own argument about which kinds of measures have been most or least effective, and why.
• Don’t just analyze a random selection of doppelgänger characters.
• Do form an argument about specific texts, comparing and contrasting how they express their thematic concerns through doppelgänger characters.

Prevent plagiarism. Run a free check.

An argumentative essay should be objective in its approach; your arguments should rely on logic and evidence, not on exaggeration or appeals to emotion.

There are many possible approaches to argumentative essays, but there are two common models that can help you start outlining your arguments: The Toulmin model and the Rogerian model.

Toulmin arguments

The Toulmin model consists of four steps, which may be repeated as many times as necessary for the argument:

• Make a claim
• Provide the grounds (evidence) for the claim
• Explain the warrant (how the grounds support the claim)
• Discuss possible rebuttals to the claim, identifying the limits of the argument and showing that you have considered alternative perspectives

The Toulmin model is a common approach in academic essays. You don’t have to use these specific terms (grounds, warrants, rebuttals), but establishing a clear connection between your claims and the evidence supporting them is crucial in an argumentative essay.

Say you’re making an argument about the effectiveness of workplace anti-discrimination measures. You might:

• Claim that unconscious bias training does not have the desired results, and resources would be better spent on other approaches
• Cite data to support your claim
• Explain how the data indicates that the method is ineffective
• Anticipate objections to your claim based on other data, indicating whether these objections are valid, and if not, why not.

Rogerian arguments

The Rogerian model also consists of four steps you might repeat throughout your essay:

• Discuss what the opposing position gets right and why people might hold this position
• Highlight the problems with this position
• Present your own position , showing how it addresses these problems
• Suggest a possible compromise —what elements of your position would proponents of the opposing position benefit from adopting?

This model builds up a clear picture of both sides of an argument and seeks a compromise. It is particularly useful when people tend to disagree strongly on the issue discussed, allowing you to approach opposing arguments in good faith.

Say you want to argue that the internet has had a positive impact on education. You might:

• Acknowledge that students rely too much on websites like Wikipedia
• Argue that teachers view Wikipedia as more unreliable than it really is
• Suggest that Wikipedia’s system of citations can actually teach students about referencing
• Suggest critical engagement with Wikipedia as a possible assignment for teachers who are skeptical of its usefulness.

You don’t necessarily have to pick one of these models—you may even use elements of both in different parts of your essay—but it’s worth considering them if you struggle to structure your arguments.

Regardless of which approach you take, your essay should always be structured using an introduction , a body , and a conclusion .

Like other academic essays, an argumentative essay begins with an introduction . The introduction serves to capture the reader’s interest, provide background information, present your thesis statement , and (in longer essays) to summarize the structure of the body.

Hover over different parts of the example below to see how a typical introduction works.

The spread of the internet has had a world-changing effect, not least on the world of education. The use of the internet in academic contexts is on the rise, and its role in learning is hotly debated. For many teachers who did not grow up with this technology, its effects seem alarming and potentially harmful. This concern, while understandable, is misguided. The negatives of internet use are outweighed by its critical benefits for students and educators—as a uniquely comprehensive and accessible information source; a means of exposure to and engagement with different perspectives; and a highly flexible learning environment.

The body of an argumentative essay is where you develop your arguments in detail. Here you’ll present evidence, analysis, and reasoning to convince the reader that your thesis statement is true.

In the standard five-paragraph format for short essays, the body takes up three of your five paragraphs. In longer essays, it will be more paragraphs, and might be divided into sections with headings.

Each paragraph covers its own topic, introduced with a topic sentence . Each of these topics must contribute to your overall argument; don’t include irrelevant information.

This example paragraph takes a Rogerian approach: It first acknowledges the merits of the opposing position and then highlights problems with that position.

Hover over different parts of the example to see how a body paragraph is constructed.

A common frustration for teachers is students’ use of Wikipedia as a source in their writing. Its prevalence among students is not exaggerated; a survey found that the vast majority of the students surveyed used Wikipedia (Head & Eisenberg, 2010). An article in The Guardian stresses a common objection to its use: “a reliance on Wikipedia can discourage students from engaging with genuine academic writing” (Coomer, 2013). Teachers are clearly not mistaken in viewing Wikipedia usage as ubiquitous among their students; but the claim that it discourages engagement with academic sources requires further investigation. This point is treated as self-evident by many teachers, but Wikipedia itself explicitly encourages students to look into other sources. Its articles often provide references to academic publications and include warning notes where citations are missing; the site’s own guidelines for research make clear that it should be used as a starting point, emphasizing that users should always “read the references and check whether they really do support what the article says” (“Wikipedia:Researching with Wikipedia,” 2020). Indeed, for many students, Wikipedia is their first encounter with the concepts of citation and referencing. The use of Wikipedia therefore has a positive side that merits deeper consideration than it often receives.

Receive feedback on language, structure, and formatting

Professional editors proofread and edit your paper by focusing on:

• Academic style
• Vague sentences
• Style consistency

See an example

An argumentative essay ends with a conclusion that summarizes and reflects on the arguments made in the body.

No new arguments or evidence appear here, but in longer essays you may discuss the strengths and weaknesses of your argument and suggest topics for future research. In all conclusions, you should stress the relevance and importance of your argument.

Hover over the following example to see the typical elements of a conclusion.

The internet has had a major positive impact on the world of education; occasional pitfalls aside, its value is evident in numerous applications. The future of teaching lies in the possibilities the internet opens up for communication, research, and interactivity. As the popularity of distance learning shows, students value the flexibility and accessibility offered by digital education, and educators should fully embrace these advantages. The internet’s dangers, real and imaginary, have been documented exhaustively by skeptics, but the internet is here to stay; it is time to focus seriously on its potential for good.

If you want to know more about AI tools , college essays , or fallacies make sure to check out some of our other articles with explanations and examples or go directly to our tools!

• Ad hominem fallacy
• Post hoc fallacy
• Appeal to authority fallacy
• False cause fallacy
• Sunk cost fallacy

College essays

• Choosing Essay Topic
• Write a College Essay
• Write a Diversity Essay
• College Essay Format & Structure
• Comparing and Contrasting in an Essay

 (AI) Tools

• Grammar Checker
• Paraphrasing Tool
• Text Summarizer
• AI Detector
• Plagiarism Checker
• Citation Generator

An argumentative essay tends to be a longer essay involving independent research, and aims to make an original argument about a topic. Its thesis statement makes a contentious claim that must be supported in an objective, evidence-based way.

An expository essay also aims to be objective, but it doesn’t have to make an original argument. Rather, it aims to explain something (e.g., a process or idea) in a clear, concise way. Expository essays are often shorter assignments and rely less on research.

At college level, you must properly cite your sources in all essays , research papers , and other academic texts (except exams and in-class exercises).

Add a citation whenever you quote , paraphrase , or summarize information or ideas from a source. You should also give full source details in a bibliography or reference list at the end of your text.

The exact format of your citations depends on which citation style you are instructed to use. The most common styles are APA , MLA , and Chicago .

The majority of the essays written at university are some sort of argumentative essay . Unless otherwise specified, you can assume that the goal of any essay you’re asked to write is argumentative: To convince the reader of your position using evidence and reasoning.

In composition classes you might be given assignments that specifically test your ability to write an argumentative essay. Look out for prompts including instructions like “argue,” “assess,” or “discuss” to see if this is the goal.

Cite this Scribbr article

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

Caulfield, J. (2023, July 23). How to Write an Argumentative Essay | Examples & Tips. Scribbr. Retrieved April 2, 2024, from https://www.scribbr.com/academic-essay/argumentative-essay/

Is this article helpful?

Jack Caulfield

Other students also liked, how to write a thesis statement | 4 steps & examples, how to write topic sentences | 4 steps, examples & purpose, how to write an expository essay, what is your plagiarism score.

PRDV002: Professional Writing

Approaching Persuasion

Read this article for a comprehensive look at how to approach persuasion as a writer. It identifies common aspects of persuasive writing and how to construct or develop a project.

The Structure of a Persuasive Essay

Writing a persuasive essay.

You first need to choose a topic that you feel passionate about. If your instructor requires you to write about a specific topic, approach the subject from an angle that interests you. Begin your essay with an engaging introduction. Your thesis should typically appear somewhere in your introduction.

Next, need to acknowledge and explain points of view that may conflict with your own to build credibility and trust with your audience. You also should state the limits of your argument. This helps you sound more reasonable and honest to those who may naturally be inclined to disagree with your view. By respectfully acknowledging opposing arguments and conceding limitations to your own view, you set a measured and responsible tone for the essay.

Be sure to make your appeals in support of your thesis by using sound, credible evidence. Use a balance of facts and opinions from a wide range of sources, such as scientific studies, expert testimony, statistics, and personal anecdotes. Each piece of evidence should be fully explained and clearly stated. Also, write in a style and tone that is appropriate for your subject and audience. Tailor your language and word choice to these two factors while still being true to your own voice. Finally, write a conclusion that effectively summarizes the main argument and reinforces your thesis.

Structuring a Persuasive Essay

The formula below for organizing a persuasive essay may be one with which you are familiar. It will present a convincing argument to your reader because your discussion is well-rounded and thorough, and yo u leave your audience with your point of view at the end. Remember to consider each of these components in this formula as  sections instead of paragraphs because you will probably want to discuss multiple ideas backing up your point of view to make it more convincing.

When writing a persuasive essay, it is best to begin with the most important point because it immediately captivates your readers and compels them to continue reading. For example, if you were supporting your thesis that homework is detrimental to the education of high school students, you would want to present your most convincing argument first and then move on to the less important points for your case.

Some key transitional words you should use with this method of organization are: most importantly, almost as importantly, just as importantly, and finally.

The Formula: You need to come up with objection points, but you also need to think of direct rebuttals to each of those ideas. Remember to consult your outline as you are writing because you may need to double-check that you have countered each of the possible opposing ideas you presented.

Section 1: Introduction

• Attention getter.
• Thesis (showing main and controlling ideas).
• Background.
• Signposts (make sure you outline the structure your argument will follow: Pros Cons/Pros).

Section 2: (Multiple) Ideas in Support of Claim

• Give a topic sentence introducing the point (showing main and controlling ideas).
• Give explanations + evidence on the first point.
• Make a concluding statement summarizing the point discussion (possibly transitioning to the next supporting idea).
• Repeat with multiple ideas in separate paragraphs.

Section 3: Summary of ( Some) Opposing Views

• Give a topic sentence explaining how the paragraph will include opposing points of view to provide a thorough, convincing argument.
• Present a general summary of some opposing ideas.
• Present some generalized evidence.
• Provide a brief concluding sentence for the paragraph – transitioning into the next rebuttal paragraph.

Section 4: Response to Opposing Views

• Give a topic sentence explaining how this paragraph or section connects to or expands on the previous paragraph .
• You [may recognize the validity of some of the points] then resent how your ideas are stronger.
• Present evidence directly countering or refuting ideas  mentioned in the previous section.
• Give a concluding statement summarizing the countering arguments.

Section 5: Conclusion

• Restate your thesis.
• Summarize your discussion points.
• Leave the reader with a strong impression; do not waiver here.
• May provide a "call for action."

In a persuasive essay, the writer's point of view should be clearly expressed at the beginning of each paragraph in the topic sentence, which should contain the main idea of the paragraph and the writer's controlling idea.

persuasive essay

What is persuasive essay definition, usage, and literary examples, persuasive essay definition.

A persuasive essay (purr-SWEY-siv ESS-ey) is a composition in which the essayist’s goal is to persuade the reader to agree with their personal views on a debatable topic. A persuasive essay generally follows a five-paragraph model with a thesis, body paragraphs, and conclusion, and it offers evidential support using research and other persuasive techniques.

Persuasive Essay Topic Criteria

To write an effective persuasive essay, the essayist needs to ensure that the topic they choose is polemical, or debatable. If it isn’t, there’s no point in trying to persuade the reader.

For example, a persuasive essayist wouldn’t write about how honeybees make honey; this is a well-known fact, and there’s no opposition to sway. The essayist might, however, write an essay on why the reader shouldn’t put pesticides on their lawn, as it threatens the bee population and environmental health.

A topic should also be concrete enough that the essayist can research and find evidence to support their argument. Using the honeybee example, the essayist could cite statistics showing a decline in the honeybee population since the use of pesticides became prevalent in lawncare. This concrete evidence supports the essayist’s opinion.

Persuasive Essay Structure

The persuasive essay generally follows this five-paragraph model.

Introduction

The introduction includes the thesis, which is the main argument of the persuasive essay. A thesis for the essay on bees and pesticides might be: “Bees are essential to environmental health, and we should protect them by abstaining from the use of harmful lawn pesticides that dwindle the bee population.”

The introductory paragraph should also include some context and background info, like bees’ impact on crop pollination. This paragraph may also include common counterarguments, such as acknowledging how some people don’t believe pesticides harm bees.

Body Paragraphs

The body consists of two or more paragraphs and provides the main arguments. This is also where the essayist’s research and evidential support will appear. For example, the essayist might elaborate on the statistics they alluded to in the introductory paragraph to support their points. Many persuasive essays include a counterargument paragraph to refute conflicting opinions.

The final paragraph readdresses the thesis statement and reexamines the essayist’s main arguments.

Types of Persuasive Essays

Persuasive essays can take several forms. They can encourage the reader to change a habit or support a cause, ask the reader to oppose a certain practice, or compare two things and suggest that one is superior to the other. Here are thesis examples for each type, based on the bee example:

• Call for Support, Action, or Change : “Stop using pesticides on your lawns to save the environmentally essential bees.”
• Call for Opposition : “Oppose the big businesses that haven’t conducted environmental studies concerning bees and pesticides.”
• Superior Subject : “Natural lawn care is far superior to using harmful pesticides.”

The Three Elements of Persuasion

Aristotle first suggested that there were three main elements to persuading an audience: ethos, pathos, and logos. Essayists implement these same tactics to persuade their readers.

Ethos refers to the essayist’s character or authority; this could mean the writer’s name or credibility. For example, a writer might seem more trustworthy if they’ve frequently written on a subject, have a degree related to the subject, or have extensive experience concerning a subject. A writer can also refer to the opinions of other experts, such as a beekeeper who believes pesticides are harming the bee population.

Pathos is an argument that uses the reader’s emotions and morality to persuade them. An argument that uses pathos might point to the number of bees that have died and what that suggests for food production: “If crop production decreases, it will be impoverished families that suffer, with perhaps more poor children having to go hungry.” This argument might make the reader empathetic to the plight of starving children and encourage them to take action against pesticide pollution.

The logos part of the essay uses logic and reason to persuade the reader. This includes the essayist’s research and whatever evidence they’ve collected to support their arguments, such as statistics.

Terms Related to Persuasive Essays

Argumentative Essays

While persuasive essays may use logic and research to support the essayist’s opinions, argumentative essays are more solely based on research and refrain from using emotional arguments. Argumentative essays are also more likely to include in-depth information on counterarguments.

Persuasive Speeches

Persuasive essays and persuasive speeches are similar in intent, but they differ in terms of format, delivery, emphasis, and tone .

In a speech, the speaker can use gestures and inflections to emphasize their points, so the delivery is almost as important as the information a speech provides. A speech requires less structure than an essay, though the repetition of ideas is often necessary to ensure that the audience is absorbing the material. Additionally, a speech relies more heavily on emotion, as the speaker must hold the reader’s attention and interest. In Queen Elizabeth I’s “Tilbury Speech,” for example, she addresses her audience in a personable and highly emotional way: “My loving people, We have been persuaded by some that are careful of our safety, to take heed how we commit our selves to armed multitudes for fear of treachery; but I assure you I do not desire to live to distrust my faithful and loving people. Let tyrants fear.”

Examples of Persuasive Essay

1. Martin Luther King, Jr., “Letter From Birmingham Jail”

Dr. King directs his essay at the Alabama clergymen who opposed his call for protests. The clergymen suggested that King had no business being in Alabama, that he shouldn’t oppose some of the more respectful segregationists, and that he has poor timing. However, here, King attempts to persuade the men that his actions are just:

I am in Birmingham because injustice is here. Just as the prophets of the eight century B.C. left their villages and carried their ‘thus saith the Lord’ far beyond the boundaries of their hometowns, and just as the Apostle Paul left his village of Tarsus and carried the gospel of Jesus Christ to the far corners of the Greco-Roman world, so am I compelled to carry the gospel of freedom beyond my hometown.

Here, King is invoking the ethos of Biblical figures who the clergymen would’ve respected. By comparing himself to Paul, he’s claiming to be a disciple spreading the “gospel of freedom” rather than an outsider butting into Alabama’s affairs.

2. Garrett Hardin, “The Tragedy of Commons”

Hardin argues that a society that shares resources is apt to overuse those resources as the population increases. He attempts to persuade readers that the human population’s growth should be regulated for the sake of preserving resources:

The National Parks present another instance of the working out of the tragedy of commons. At present, they are open to all, without limit. The parks themselves are limited in extent—there is only one Yosemite Valley—whereas population seems to grow without limit. The values that visitors seek in the parks are steadily eroded. Plainly, we must soon cease to treat the parks as commons, or they will be of no value to anyone.

In this excerpt, Harden uses an example that appeals to the reader’s logic. If the human population continues to rise, causing park visitors to increase, parks will continue to erode until there’s nothing left.

Further Resources on Persuasive Essays

We at SuperSummary offer excellent resources for penning your own essays .

Find a list of famous persuasive speeches at Highspark.co .

Read up on the elements of persuasion at the American Management Association website.

Related Terms

• Argumentative Essay

Want to create or adapt books like this? Learn more about how Pressbooks supports open publishing practices.

10.9 Persuasion

Learning objectives.

• Determine the purpose and structure of persuasion in writing.
• Identify bias in writing.
• Assess various rhetorical devices.
• Distinguish between fact and opinion.
• Understand the importance of visuals to strengthen arguments.
• Write a persuasive essay.

The Purpose of Persuasive Writing

The purpose of persuasion in writing is to convince, motivate, or move readers toward a certain point of view, or opinion. The act of trying to persuade automatically implies more than one opinion on the subject can be argued.

The idea of an argument often conjures up images of two people yelling and screaming in anger. In writing, however, an argument is very different. An argument is a reasoned opinion supported and explained by evidence. To argue in writing is to advance knowledge and ideas in a positive way. Written arguments often fail when they employ ranting rather than reasoning.

Most of us feel inclined to try to win the arguments we engage in. On some level, we all want to be right, and we want others to see the error of their ways. More times than not, however, arguments in which both sides try to win end up producing losers all around. The more productive approach is to persuade your audience to consider your opinion as a valid one, not simply the right one.

The Structure of a Persuasive Essay

The following five features make up the structure of a persuasive essay:

• Introduction and thesis
• Opposing and qualifying ideas
• Strong evidence in support of claim
• Style and tone of language
• A compelling conclusion

Creating an Introduction and Thesis

The persuasive essay begins with an engaging introduction that presents the general topic. The thesis typically appears somewhere in the introduction and states the writer’s point of view.

Avoid forming a thesis based on a negative claim. For example, “The hourly minimum wage is not high enough for the average worker to live on.” This is probably a true statement, but persuasive arguments should make a positive case. That is, the thesis statement should focus on how the hourly minimum wage is low or insufficient.

Acknowledging Opposing Ideas and Limits to Your Argument

Because an argument implies differing points of view on the subject, you must be sure to acknowledge those opposing ideas. Avoiding ideas that conflict with your own gives the reader the impression that you may be uncertain, fearful, or unaware of opposing ideas. Thus it is essential that you not only address counterarguments but also do so respectfully.

Try to address opposing arguments earlier rather than later in your essay. Rhetorically speaking, ordering your positive arguments last allows you to better address ideas that conflict with your own, so you can spend the rest of the essay countering those arguments. This way, you leave your reader thinking about your argument rather than someone else’s. You have the last word.

Acknowledging points of view different from your own also has the effect of fostering more credibility between you and the audience. They know from the outset that you are aware of opposing ideas and that you are not afraid to give them space.

It is also helpful to establish the limits of your argument and what you are trying to accomplish. In effect, you are conceding early on that your argument is not the ultimate authority on a given topic. Such humility can go a long way toward earning credibility and trust with an audience. Audience members will know from the beginning that you are a reasonable writer, and audience members will trust your argument as a result. For example, in the following concessionary statement, the writer advocates for stricter gun control laws, but she admits it will not solve all of our problems with crime:

Although tougher gun control laws are a powerful first step in decreasing violence in our streets, such legislation alone cannot end these problems since guns are not the only problem we face.

Such a concession will be welcome by those who might disagree with this writer’s argument in the first place. To effectively persuade their readers, writers need to be modest in their goals and humble in their approach to get readers to listen to the ideas. See Table 10.5 “Phrases of Concession” for some useful phrases of concession.

Table 10.5 Phrases of Concession

Try to form a thesis for each of the following topics. Remember the more specific your thesis, the better.

• Foreign policy
• Television and advertising
• Stereotypes and prejudice
• Gender roles and the workplace
• Driving and cell phones

Collaboration

Please share with a classmate and compare your answers. Choose the thesis statement that most interests you and discuss why.

Bias in Writing

Everyone has various biases on any number of topics. For example, you might have a bias toward wearing black instead of brightly colored clothes or wearing jeans rather than formal wear. You might have a bias toward working at night rather than in the morning, or working by deadlines rather than getting tasks done in advance. These examples identify minor biases, of course, but they still indicate preferences and opinions.

Handling bias in writing and in daily life can be a useful skill. It will allow you to articulate your own points of view while also defending yourself against unreasonable points of view. The ideal in persuasive writing is to let your reader know your bias, but do not let that bias blind you to the primary components of good argumentation: sound, thoughtful evidence and a respectful and reasonable address of opposing sides.

The strength of a personal bias is that it can motivate you to construct a strong argument. If you are invested in the topic, you are more likely to care about the piece of writing. Similarly, the more you care, the more time and effort you are apt to put forth and the better the final product will be.

The weakness of bias is when the bias begins to take over the essay—when, for example, you neglect opposing ideas, exaggerate your points, or repeatedly insert yourself ahead of the subject by using I too often. Being aware of all three of these pitfalls will help you avoid them.

The Use of I in Writing

The use of I in writing is often a topic of debate, and the acceptance of its usage varies from instructor to instructor. It is difficult to predict the preferences for all your present and future instructors, but consider the effects it can potentially have on your writing.

Be mindful of the use of I in your writing because it can make your argument sound overly biased. There are two primary reasons:

• Excessive repetition of any word will eventually catch the reader’s attention—and usually not in a good way. The use of I is no different.
• The insertion of I into a sentence alters not only the way a sentence might sound but also the composition of the sentence itself. I is often the subject of a sentence. If the subject of the essay is supposed to be, say, smoking, then by inserting yourself into the sentence, you are effectively displacing the subject of the essay into a secondary position. In the following example, the subject of the sentence is underlined:

Smoking is bad.

I think smoking is bad.

In the first sentence, the rightful subject, smoking , is in the subject position in the sentence. In the second sentence, the insertion of I and think replaces smoking as the subject, which draws attention to I and away from the topic that is supposed to be discussed. Remember to keep the message (the subject) and the messenger (the writer) separate.

Developing Sound Arguments

Does my essay contain the following elements?

• An engaging introduction
• A reasonable, specific thesis that is able to be supported by evidence
• A varied range of evidence from credible sources
• Respectful acknowledgement and explanation of opposing ideas
• A style and tone of language that is appropriate for the subject and audience
• Acknowledgement of the argument’s limits
• A conclusion that will adequately summarize the essay and reinforce the thesis

Fact and Opinion

Facts are statements that can be definitely proven using objective data. The statement that is a fact is absolutely valid. In other words, the statement can be pronounced as true or false. For example, 2 + 2 = 4. This expression identifies a true statement, or a fact, because it can be proved with objective data.

Opinions are personal views, or judgments. An opinion is what an individual believes about a particular subject. However, an opinion in argumentation must have legitimate backing; adequate evidence and credibility should support the opinion. Consider the credibility of expert opinions. Experts in a given field have the knowledge and credentials to make their opinion meaningful to a larger audience.

For example, you seek the opinion of your dentist when it comes to the health of your gums, and you seek the opinion of your mechanic when it comes to the maintenance of your car. Both have knowledge and credentials in those respective fields, which is why their opinions matter to you. But the authority of your dentist may be greatly diminished should he or she offer an opinion about your car, and vice versa.

In writing, you want to strike a balance between credible facts and authoritative opinions. Relying on one or the other will likely lose more of your audience than it gains.

The word prove is frequently used in the discussion of persuasive writing. Writers may claim that one piece of evidence or another proves the argument, but proving an argument is often not possible. No evidence proves a debatable topic one way or the other; that is why the topic is debatable. Facts can be proved, but opinions can only be supported, explained, and persuaded.

On a separate sheet of paper, take three of the theses you formed in Note 10.94 “Exercise 1” , and list the types of evidence you might use in support of that thesis.

Using the evidence you provided in support of the three theses in Note 10.100 “Exercise 2” , come up with at least one counterargument to each. Then write a concession statement, expressing the limits to each of your three arguments.

Using Visual Elements to Strengthen Arguments

Adding visual elements to a persuasive argument can often strengthen its persuasive effect. There are two main types of visual elements: quantitative visuals and qualitative visuals.

Quantitative visuals present data graphically. They allow the audience to see statistics spatially. The purpose of using quantitative visuals is to make logical appeals to the audience. For example, sometimes it is easier to understand the disparity in certain statistics if you can see how the disparity looks graphically. Bar graphs, pie charts, Venn diagrams, histograms, and line graphs are all ways of presenting quantitative data in spatial dimensions.

Qualitative visuals present images that appeal to the audience’s emotions. Photographs and pictorial images are examples of qualitative visuals. Such images often try to convey a story, and seeing an actual example can carry more power than hearing or reading about the example. For example, one image of a child suffering from malnutrition will likely have more of an emotional impact than pages dedicated to describing that same condition in writing.

Writing at Work

When making a business presentation, you typically have limited time to get across your idea. Providing visual elements for your audience can be an effective timesaving tool. Quantitative visuals in business presentations serve the same purpose as they do in persuasive writing. They should make logical appeals by showing numerical data in a spatial design. Quantitative visuals should be pictures that might appeal to your audience’s emotions. You will find that many of the rhetorical devices used in writing are the same ones used in the workplace. For more information about visuals in presentations, see Chapter 14 “Creating Presentations: Sharing Your Ideas” .

Writing a Persuasive Essay

Choose a topic that you feel passionate about. If your instructor requires you to write about a specific topic, approach the subject from an angle that interests you. Begin your essay with an engaging introduction. Your thesis should typically appear somewhere in your introduction.

Start by acknowledging and explaining points of view that may conflict with your own to build credibility and trust with your audience. Also state the limits of your argument. This too helps you sound more reasonable and honest to those who may naturally be inclined to disagree with your view. By respectfully acknowledging opposing arguments and conceding limitations to your own view, you set a measured and responsible tone for the essay.

Make your appeals in support of your thesis by using sound, credible evidence. Use a balance of facts and opinions from a wide range of sources, such as scientific studies, expert testimony, statistics, and personal anecdotes. Each piece of evidence should be fully explained and clearly stated.

Make sure that your style and tone are appropriate for your subject and audience. Tailor your language and word choice to these two factors, while still being true to your own voice.

Finally, write a conclusion that effectively summarizes the main argument and reinforces your thesis. See Chapter 15 “Readings: Examples of Essays” to read a sample persuasive essay.

Choose one of the topics you have been working on throughout this section. Use the thesis, evidence, opposing argument, and concessionary statement as the basis for writing a full persuasive essay. Be sure to include an engaging introduction, clear explanations of all the evidence you present, and a strong conclusion.

Key Takeaways

• The purpose of persuasion in writing is to convince or move readers toward a certain point of view, or opinion.
• An argument is a reasoned opinion supported and explained by evidence. To argue, in writing, is to advance knowledge and ideas in a positive way.
• A thesis that expresses the opinion of the writer in more specific terms is better than one that is vague.
• It is essential that you not only address counterarguments but also do so respectfully.
• It is also helpful to establish the limits of your argument and what you are trying to accomplish through a concession statement.
• To persuade a skeptical audience, you will need to use a wide range of evidence. Scientific studies, opinions from experts, historical precedent, statistics, personal anecdotes, and current events are all types of evidence that you might use in explaining your point.
• Make sure that your word choice and writing style is appropriate for both your subject and your audience.
• You should let your reader know your bias, but do not let that bias blind you to the primary components of good argumentation: sound, thoughtful evidence and respectfully and reasonably addressing opposing ideas.
• You should be mindful of the use of I in your writing because it can make your argument sound more biased than it needs to.
• Facts are statements that can be proven using objective data.
• Opinions are personal views, or judgments, that cannot be proven.
• In writing, you want to strike a balance between credible facts and authoritative opinions.
• Quantitative visuals present data graphically. The purpose of using quantitative visuals is to make logical appeals to the audience.
• Qualitative visuals present images that appeal to the audience’s emotions.

Writing for Success Copyright © 2015 by University of Minnesota is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License , except where otherwise noted.

How to Write Perfect Persuasive Essays in 5 Simple Steps

WHAT IS A PERSUASIVE ESSAY?

A persuasive text presents a point of view around a topic or theme that is backed by evidence to support it.

The purpose of a persuasive text can be varied.  Maybe you intend to influence someone’s opinion on a specific topic, or you might aim to sell a product or service through an advertisement.

The challenge in writing a good persuasive text is to use a mix of emotive language and, in some cases, images that are supported by hard evidence or other people’s opinions.

In a persuasive essay or argument essay, the student strives to convince the reader of the merits of their opinion or stance on a particular issue. The student must utilise several persuasive techniques to form a coherent and logical argument to convince the reader of a point of view or to take a specific action.

PERSUADING PEOPLE REQUIRES A CONSISTENT APPROACH…

Persuasive texts are simple in structure.  You must clearly state your opinion around a specific topic and then repeatedly reinforce your opinions with external facts or evidence.  A robust concluding summary should leave little doubt in the reader’s mind.  ( Please view our planning tool below for a detailed explanation. )

TYPES OF PERSUASIVE TEXT

We cover the broad topic of writing a general persuasive essay in this guide, there are several sub-genres of persuasive texts students will encounter as they progress through school. We have complete guides on these text types, so be sure to click the links and read these in detail if required.

• Argumentative Essays – These are your structured “Dogs are better pets than Cats” opinion-type essays where your role is to upsell the positive elements of your opinions to your audience whilst also highlighting the negative aspects of any opposing views using a range of persuasive language and techniques.
• Advertising – Uses persuasive techniques to sell a good or service to potential customers with a call to action.
• Debating Speeches – A debate is a structured discussion between two teams on a specific topic that a moderator judges and scores. Your role is to state your case, sell your opinions to the audience, and counteract your opposition’s opinions.
• Opinion Articles, Newspaper Editorials. – Editorials often use more subtle persuasive techniques that blur the lines of factual news reporting and opinions that tell a story with bias. Sometimes they may even have a call to action at the end.
• Reviews – Reviews exist to inform others about almost any service or product, such as a film, restaurant, or product. Depending on your experiences, you may have firm opinions or not even care that much about recommending it to others. Either way, you will employ various persuasive techniques to communicate your recommendations to your audience.
• Please note a DISCUSSION essay is not a traditional persuasive text, as even though you are comparing and contrasting elements, the role of the author is to present an unbiased account of both sides so that the reader can make a decision that works best for them. Discussions are often confused as a form of persuasive writing.

A COMPLETE TEACHING UNIT ON PERSUASIVE WRITING SKILLS

Teach your students to produce writing that  PERSUADES  and  INFLUENCES  thinking with this  HUGE  writing guide bundle covering: ⭐ Persuasive Texts / Essays ⭐ Expository Essays⭐ Argumentative Essays⭐ Discussions.

A complete 140 PAGE unit of work on persuasive texts for teachers and students. No preparation is required.

THE STRUCTURE OF A PERSUASIVE ESSAY

1. Introduction

In the introduction, the student will naturally introduce the topic. Controversial issues make for great topics in this writing genre. It’s a cliche in polite society to discourage discussions involving politics, sex, or religion because they can often be very divisive. While these subjects may not be the best topics of conversation for the dinner table at Thanksgiving, they can be perfect when deciding on a topic for persuasive writing. Obviously, the student’s age and abilities should be considered, as well as cultural taboos, when selecting a topic for the essay. But the point holds, the more controversial, the better.

Let’s take a look at some of the critical elements of the introduction when writing a persuasive essay:

Title: Tell your audience what they are reading.

This will often be posed as a question; for example, if the essay is on the merits of a vegetarian lifestyle, it may be called something like: To Eat Meat or Not?

Hook : Provide your audience with a reason to continue reading.

As with any genre of writing, capturing the reader’s interest from the outset is crucial. There are several methods of doing this, known as hooks. Students may open their essays with anecdotes, jokes, quotations, or relevant statistics related to the topic under discussion.

Background: Provide some context to your audience.

In this introductory section, students will provide the reader with some background on the topic. This will place the issue in context and briefly weigh some opinions on the subject.

Thesis statement: Let the audience know your stance.

After surveying the topic in the first part of the introduction, it is now time for the student writer to express their opinion and briefly preview the points they will make later in the essay.

2. Body Paragraphs

The number of paragraphs forming this essay section will depend on the number of points the writer chooses to make to support their opinion. Usually three main points will be sufficient for beginning writers to coordinate. More advanced students can increase the number of paragraphs based on the complexity of their arguments, but the overall structure will largely remain intact.

Be sure to check out our complete guide to writing perfect paragraphs here .

The TEEL acronym is valuable for students to remember how to structure their paragraphs.  Read below for a deeper understanding.

Topic Sentence:

The topic sentence states the central point of the paragraph. This will be one of the reasons supporting the thesis statement made in the introduction.

These sentences will build on the topic sentence by illustrating the point further, often by making it more specific.

These sentences’ purpose is to support the paragraph’s central point by providing supporting evidence and examples. This evidence may be statistics, quotations, or anecdotal evidence.

The final part of the paragraph links back to the initial statement of the topic sentence while also forming a bridge to the next point to be made. This part of the paragraph provides some personal analysis and interpretation of how the student arrived at their conclusions and connects the essay as a cohesive whole.

3. Conclusion

The conclusion weaves together the main points of the persuasive essay. It does not usually introduce new arguments or evidence but instead reviews the arguments made already and restates them by summing them up uniquely. It is important at this stage to tie everything back to the initial thesis statement. This is the writer’s last opportunity to drive home their point, to achieve the essay’s goal, to begin with – persuade the reader of their point of view.

Ending an essay well can be challenging, but it is essential to end strongly, especially for persuasive essays. As with the hooks of the essay’s opening, there are many tried and tested methods of leaving the reader with a strong impression. Encourage students to experiment with different endings, for example, concluding the essay with a quotation that amplifies the thesis statement.

Another method is to have the student rework their ending in simple monosyllabic words, as simple language often has the effect of being more decisive in impact. The effect they are striving for in the final sentence is the closing of the circle.

Several persuasive writing techniques can be used in the conclusion and throughout the essay to amp up the persuasive power of the writing. Let’s take a look at a few.

ETHOS, PATHOS & LOGOS TUTORIAL VIDEO (2:20)

TIPS FOR WRITING A GREAT PERSUASIVE ESSAY

PERSUASIVE TECHNIQUES

In this article, we have outlined a basic structure that will be helpful to students in approaching the organization of their persuasive writing. It will also be helpful for the students to be introduced to a few literary techniques that will help your students to present their ideas convincingly. Here are a few of the more common ones:

Repetition: There is a reason why advertisements and commercials are so repetitive – repetition works! Students can use this knowledge to their advantage in their persuasive writing. It is challenging to get the reader to fully agree with the writer’s opinion if they don’t fully understand it. Saying the same thing in various ways ensures the reader gets many bites at the ‘understanding’ cherry.

Repetition Example: “The use of plastic bags is not only bad for the environment, but it is also bad for our economy. Plastic bags are not biodegradable, meaning they will not decompose and will continue to take up space in landfills. Plastic bags are also not recyclable, meaning they will not be reused and will instead end up in landfills. Plastic bags are not only bad for the environment, but they are also bad for our economy as they are costly to dispose of and take up valuable space in landfills.”

In this example, the phrase “not only bad for the environment but also bad for our economy” is repeated multiple times to reinforce the idea that plastic bags are not just a problem for the environment but also the economy. The repetition of the phrase emphasizes the point and makes it more persuasive.

It is also important to note that repetition could be used differently, such as repeating a word or phrase to create rhythm or emphasis.

Storytelling: Humans tend to understand things better through stories. Think of how we teach kids important values through time-tested fables like Peter and the Wolf . Whether through personal anecdotes or references to third-person experiences, stories help climb down the ladder of abstraction and reach the reader on a human level.

Storytelling Example: “Imagine you are walking down the street, and you come across a stray dog clearly in need of food and water. The dog looks up at you with big, sad eyes, and you cannot help but feel a twinge of compassion. Now, imagine that same scenario, but instead of a stray dog, it’s a homeless person sitting on the sidewalk. The person is clearly in need of food and shelter, and their eyes also look up at her with a sense of hopelessness.

The point of this story is to show that just as we feel compelled to help a stray animal in need, we should also feel compelled to help a homeless person. We should not turn a blind eye to the suffering of our fellow human beings, and we should take action to address homelessness in our community. It is important to remember that everyone deserves a roof over their head and a warm meal to eat. The story is designed to elicit an emotional response in the reader and make the argument more relatable and impactful.

By using storytelling, this passage creates an image in the reader’s mind and creates an emotional connection that can be more persuasive than just stating facts and figures.

Dissent: We live in a cynical age, so leaving out the opposing opinion will smack of avoidance to the reader. Encourage your students to turn to that opposing viewpoint and deal with those arguments in their essays .

Dissent Example: “Many people argue that students should not have to wear uniforms in school. They argue that uniforms stifle creativity and individuality and that students should be able to express themselves through their clothing choices. While these are valid concerns, I strongly disagree.

In fact, uniforms can actually promote individuality by levelling the playing field and removing the pressure to dress in a certain way. Furthermore, uniforms can promote a sense of community and belonging within a school. They can also provide a sense of discipline and structure, which can help to create a more focused and productive learning environment. Additionally, uniforms can save families money and eliminate the stress of deciding what to wear daily .

While some may argue that uniforms stifle creativity and individuality, the benefits of uniforms far outweigh the potential drawbacks. It is important to consider the impact of uniforms on the school as a whole, rather than focusing solely on individual expression.”

In this example, the writer presents the opposing viewpoint (uniforms stifle creativity and individuality) and then provides counterarguments to refute it. By doing so, the writer can strengthen their own argument and present a more convincing case for why uniforms should be worn in school.

A Call to Action: A staple of advertising, a call to action can also be used in persuasive writing. When employed, it usually forms part of the conclusion section of the essay and asks the reader to do something, such as recycle, donate to charity, sign a petition etc.

A quick look around reveals to us the power of persuasion, whether in product advertisements, newspaper editorials, or political electioneering; persuasion is an ever-present element in our daily lives. Logic and reason are essential in persuasion, but they are not the only techniques. The dark arts of persuasion can prey on emotion, greed, and bias. Learning to write persuasively can help our students recognize well-made arguments and help to inoculate them against the more sinister manifestations of persuasion.

Call to Action Example: “Climate change is a pressing issue that affects us all, and it’s important that we take action now to reduce our carbon footprint and protect the planet for future generations. As a society, we have the power to make a difference and it starts with small changes that we can make in our own lives.

I urge you to take the following steps to reduce your carbon footprint:

• Reduce your use of single-use plastics
• Use public transportation, carpool, bike or walk instead of driving alone.
• Support clean energy sources such as solar and wind power
• Plant trees and support conservation efforts

It’s easy to feel like one person can’t make a difference, but the truth is that every little bit helps. Together, we can create a more sustainable future for ourselves and for the planet.

So, let’s take action today and make a difference for a better future, it starts with minor changes, but it all adds up and can make a significant impact. We need to take responsibility for our actions and do our part to protect the planet.”

In this example, the writer gives a clear and specific call to action and encourages the reader to take action to reduce their carbon footprint and protect the planet. By doing this, the writer empowers the reader to take action and enables them to change.

Now, go persuade your students of the importance of perfecting the art of persuasive writing!

A COMPLETE UNIT ON TEACHING FACT AND OPINION

This  HUGE 120 PAGE  resource combines four different fact and opinion activities you can undertake as a  WHOLE GROUP  or as  INDEPENDENT READING GROUP TASKS  in either  DIGITAL  or  PRINTABLE TASKS.

20 POPULAR PERSUASIVE ESSAY TOPICS FOR STUDENTS

Writing an effective persuasive essay demonstrates a range of skills that will be of great use in nearly all aspects of life after school.

In essence, if you can influence a person to change their ideas or thoughts on a given topic through how you structure your words and thoughts, you possess a very powerful skill.

Be careful not to rant wildly.  Use facts and other people’s ideas who think similarly to you in your essay to strengthen your concepts.

Your biggest challenge in getting started may be choosing a suitable persuasive essay topic.  These 20 topics for a persuasive essay should make this process a little easier.

• WHY ARE WE FASCINATED WITH CELEBRITIES AND WEALTHY PEOPLE ON TELEVISION AND SOCIAL MEDIA?
• IS IT RIGHT FOR SCHOOLS TO RAISE MONEY BY SELLING CANDY AND UNHEALTHY FOODS TO STUDENTS?
• SHOULD GIRLS BE ALLOWED TO PLAY ON BOYS SPORTING TEAMS?
• IS TEACHING HANDWRITING A WASTE OF TIME IN THIS DAY AND AGE?
• SHOULD THERE BE FAR GREATER RESTRICTIONS AROUND WHAT CAN BE POSTED ON THE INTERNET?
• SHOULD PROFESSIONAL ATHLETES HAVE TO TAKE DRUG TESTS?
• ARE TEENAGE PREGNANCY SHOWS A NEGATIVE OR POSITIVE INFLUENCE ON VIEWERS?
• SHOULD GAMBLING BE PROMOTED IN ANY WAY IN SPORTS EVEN THOUGH IT BRINGS IN LARGE AMOUNTS OF REVENUE?
• SHOULD SPORTING TEAMS THAT LOSE BE REWARDED BY RECEIVING INCENTIVES SUCH AS HIGH DRAFT PICKS AND / OR FINANCIAL BENEFITS?
• SHOULD SHARKS THAT ATTACK PEOPLE BE DESTROYED? SHOULD WE GET INVOLVED IN FOREIGN CONFLICTS AND ISSUES THAT DON’T DIRECTLY AFFECT OUR COUNTRY?
• SHOULD WE GET INVOLVED IN FOREIGN CONFLICTS AND ISSUES THAT DON’T DIRECTLY AFFECT OUR COUNTRY?
• COULD VIDEO GAMES BE CONSIDERED AS A PROFESSIONAL SPORT?
• IF YOU WERE THE LEADER OF YOUR COUNTRY AND HAD A LARGE SURPLUS TO SPEND, WHAT WOULD YOU DO WITH IT?
• WHEN SHOULD A PERSON BE CONSIDERED AND TREATED AS AN ADULT?
• SHOULD SMOKING BECOME AN ILLEGAL ACTIVITY?
• SHOULD THE VOTING AGE BE LOWERED?
• DOES PROTECTIVE PADDING IN SPORTS MAKE IT MORE DANGEROUS?
• SHOULD CELL PHONES BE ALLOWED IN THE CLASSROOM?
• IS TEACHING A FOREIGN LANGUAGE A WASTE OF TIME?
• SHOULD WE TEACH ETIQUETTE IN SCHOOLS?

PERSUASIVE PROMPTS FOR RELUCTANT WRITERS

If your students need a little more direction and guidance, here are some journal prompts that include aspects to consider.

• Convince us that students would be better off having a three-day weekend .  There are many angles you could take with this, such as letting children maximize their childhood or trying to convince your audience that a four-day school week might actually be more productive.
• Which is the best season?  And why?   You will really need to draw on the benefits of your preferred season and sell them to your audience.  Where possible, highlight the negatives of the competing seasons.  Use lots of figurative language and sensory and emotional connections for this topic.
• Aliens do / or don’t exist?  We can see millions of stars surrounding us just by gazing into the night sky, suggesting alien life should exist, right? Many would argue that if there were aliens we would have seen tangible evidence of them by now.  The only fact is that we just don’t know the answer to this question.  It is your task to try and convince your audience through some research and logic what your point of view is and why.
• Should school uniforms be mandatory? Do your research on this popular and divisive topic and make your position clear on where you stand and why.  Use plenty of real-world examples to support your thoughts and points of view.  
• Should Smartphones be banned in schools?   Whilst this would be a complete nightmare for most students’ social lives, maybe it might make schools more productive places for students to focus and learn.  Pick a position, have at least three solid arguments to support your point of view, and sell them to your audience.

VISUAL JOURNAL PROMPTS FOR PERSUASIVE WRITING

Try these engaging, persuasive prompts with your students to ignite the writing process . Scroll through them.

Persuasive Essay Examples (Student Writing Samples)

Below are a collection of persuasive essay samples.  Click on the image to enlarge and explore them in greater detail.  Please take a moment to read the persuasive texts in detail and the teacher and student guides highlight some of the critical elements of writing a persuasion.

Please understand these student writing samples are not intended to be perfect examples for each age or grade level but a piece of writing for students and teachers to explore together to critically analyze to improve student writing skills and deepen their understanding of persuasive text writing.

We recommend reading the example either a year above or below, as well as the grade you are currently working with, to gain a broader appreciation of this text type.

VIDEO TUTORIALS FOR PERSUASIVE WRITING

OTHER GREAT ARTICLES RELATED TO PERSUASIVE ESSAY WRITING

Teaching Resources

Use our resources and tools to improve your student’s writing skills through proven teaching strategies.

WHERE CAN I FIND A COMPLETE UNIT OF WORK ON HOW TO WRITE PERSUASIVE ESSAYS?

We pride ourselves on being the web’s best resource for teaching students and teachers how to write a persuasive text. We value the fact you have taken the time to read our comprehensive guides to understand the fundamentals of writing skills.

We also understand some of you just don’t have the luxury of time or the resources to create engaging resources exactly when you need them.

If you are time-poor and looking for an in-depth solution that encompasses all of the concepts outlined in this article, I strongly recommend looking at the “ Writing to Persuade and Influence Unit. ”

Working in partnership with Innovative Teaching Ideas , we confidently recommend this resource as an all-in-one solution to teach how to write persuasively.

This unit will find over 140 pages of engaging and innovative teaching ideas.

PERSUASIVE ESSAY WRITING CHECKLIST AND RUBRIC BUNDLE

The Ultimate Guide to Opinion Writing for Students and Teachers

Top 5 Persuasive Writing Techniques for Students

5 Top Persuasive Writing Lesson Plans for Students and Teachers

23 Persuasive writing Topics for High School students

How to Write an Advertisement: A Complete Guide for Students and Teachers

How to Start an Essay with Strong Hooks and Leads

My Speech Class

Public Speaking Tips & Speech Topics

Persuasive Essay Outline – Examples, Templates & Structure

Amanda Green was born in a small town in the west of Scotland, where everyone knows everyone. I joined the Toastmasters 15 years ago, and I served in nearly every office in the club since then. I love helping others gain confidence and skills they can apply in every day life.

Writing a good persuasive essay can help convince others of a point that means a lot to you. It can be anything from an environmental crisis to something as simple as the importance of ebooks to the modern reader. But how do you write a persuasive essay? Where do you even start? Right here! I’ll explain everything you need to know and even show you an example of a persuasive essay.

What Is a Persuasive Essay?

Persuasive essays are meant to convince someone or a group of people to agree with you on a certain topic or point of view. As the writer, you’ll use definitive evidence, simple reasoning, and even examples to support your argument and persuade them to understand the point of the essay.

Why Write a Persuasive Essay?

Believe it or not, you’ll have to form convincing arguments throughout real life. This could be in the form of college essays or academic essays, speeches for debate club that requires a valid argument, or even presenting an idea for change to your town council.

Argumentative vs. Persuasive Essay

An argumentative essay presents an argument on a specific topic and tries to persuade people to accept that argument as valid. It uses evidence, logic, and sometimes counterarguments to support the main point.

A persuasive essay is similar but presents an argument and focuses more on appealing to the reader’s emotions and values to convince them of your point of view. Think of it as convincing vs. persuading. And, yes, persuasive essays can also use evidence, but they often rely more on personal anecdotes and moral appeals to plead their case.

Let me give you an example. I’m a content writer, but I’m also a published author. If I were going to write an argumentative essay, I’d probably choose a topic like “Do you think authors should self-edit their work?”

But if I were doing a persuasive essay with a similar angle, the topic would look more like “The benefits of self-editing for authors.” Make sense?

Can We Write Your Speech?

Get your audience blown away with help from a professional speechwriter. Free proofreading and copy-editing included.

Basically, the main difference between argumentative and persuasive essays is all in the emphasis placed on logic and emotion.

How Many Paragraphs in a Persuasive Essay?

A decent persuasive essay should be around five or six paragraphs with double line spacing, depending on the topic, and can range from 500-2000 words in length. This includes your introduction and conclusion.

Introduction of a Persuasive Essay Example

Our world is facing a crisis, and that crisis is plastic pollution! Every day, a disgusting amount of plastic waste is just dumped into our oceans, killing and harming innocent marine life and ultimately affecting the entire food chain, including us.

Even though there is a clear and present danger that plastic presents, there are still a lot of people and corporations that continue to use single-use plastics with zero regards for their impact on our environment. It’s time for people to really look around and take some responsibility.

We can make a change by learning and using environmentally friendly alternatives in our everyday lives. So, in this essay, I’ll argue that using reusable bags, water bottles, and containers is not only necessary for the health of our precious planet but also a simple and effective way to make a real difference.

A Persuasive Essay Structure

As persuasive essay writers, you can write it however you like, but to follow a traditional persuasive essay structure, use this basic layout to get an effective paper:

• An Introduction: You need a good hook to grab the reader’s attention, a thesis statement presenting the main argument, and a roadmap of the essay, so they know what to expect.
• The Body Paragraphs: 2-3 paragraphs should suffice to provide strong evidence, examples, and any reasoning to support the thesis statement. Each paragraph should focus on a single main idea. 
• The Counterargument: This section acknowledges and refutes the opposing viewpoint, strengthening your argument but still without being as forward as an argumentative essay.
• A Conclusion or Closing Statement: Here is where you would summarize the main points of the essay and a restatement of the thesis, including a call to action for the reader and/or a final thought.

In the end, a persuasive essay usually consists of 5-6 paragraphs and needs to be clear, concise, and logically structured to really persuade the reader on the point.

Tips for Persuasive Writing

• Choose a strong, clear thesis statement that presents your argument well.
• Know your audience and tailor your language and arguments to them. You’ll need a different approach if you’re speaking to a group of teenagers versus a team of adults.
• Use credible and reliable sources to support your argument so no one can second guess your point.
• Expect that people will have counterarguments and prepare a few talking points to address them.
• Use strong pieces of evidence and back them up with facts, statistics, examples, and personal anecdotes. Putting a personal touch on it helps ground the essay and lets people know you’re serious about the topic.
• Use an emotional appeal to engage the reader and make a personal connection to your argument. Basically, tug at their heartstrings and play into their guilt.
• Use clear and concise wordage. Try and avoid confusing technical jargon that might confuse people, and maintain a consistent tone throughout the essay.
• Make sure you’re confident and use an assertive tone but avoid being overly aggressive or confrontational. That will just spark a fight.
• Finish up with a powerful call to action or a final thought that leaves a lasting impact on the reader or listener.
• Use the same font throughout your essay, even for headings and titles. Go with easy-to-read fonts like Calibri, Times New Roman, or Garamond.
• Proofread and edit your essay for clarity, grammar, and style. I cannot stress this one enough. If you’re not confident, use programs like Grammarly to help spot typos and inconsistencies.

Persuasive Essay Topic Ideas

If you’re stuck on some ideas of what to form your essay around, here’s a list of some popular topics to inspire you.

• Importance of recycling and reducing waste in today’s climate.
• The need for stricter gun control laws all over the world.
• A paper on abortion rights in today’s age.
• Benefits of alternative energy sources over fossil fuels and how we can be using them.
• How social media has negative impacts on mental health in kids.
• Key benefits of a vegetarian or vegan diet and how it can help the planet.
• The value of a college education.
• Rise of plastic pollution on the environment and sea life and how it is affecting us.
• Why physical exercise and leading an active lifestyle are important.
• The dangers of texting while driving.
• How our public schools need better funding.
• Benefits of a diverse and inclusive workplace both online and in-person.

Any of these could be used as logical arguments. Still, to make a persuasive argument from either of them, just follow the basic persuasive essay outline examples I’ve given you.

Example of a Persuasive Essay

Introduction.

In today’s age of ever-changing technology, the way we consume and experience books have changed dramatically in just a short time. While physical books were once the only option, ebooks have grown increasingly popular in recent years. In my essay, I’ll argue that, while we all still love paperbacks and hardcovers, ebooks offer so many benefits over physical books, making them the number one choice for most readers today.

Body Paragraph 1: Convenience

Ebooks are convenient; there’s just no denying it. They’re easily accessible through devices like smartphones, tablets, and e-readers, and they allow readers to carry hundreds of books with them at all times. This makes them perfect for traveling or heading to work, or even going to the gym. Readers can now have an entire library with them without the added weight of physical books. Plus, ebooks are easily bought online with just the click of a button, further adding to their convenience.

Body Paragraph 2: Customization

Ebooks offer a level of customization that physical books just can’t match. For one, the font size can be adjusted for easier reading, which is great for those who have eyesight problems. The background color can also be changed from light to dark to reduce eye strain. Personally, as someone who suffers from Meniere’s disease, this is a great feature. All of these options make ebooks a great choice for people with visual impairments, neurological disorders, or reading difficulties.

Body Paragraph 3: Affordability

Ebooks are often far cheaper than physical books, especially when purchased in bulk. You can get an entire series for a fraction of the cost of one paperback. This makes them a more accessible option for budget-conscious readers and people who simply don’t have the disposable funds for books. Also, tons of ebooks are available for free, which is a great option for readers that are looking for ways to save money but keep up with their reading habits.

Body Paragraph 4: Environmentally Friendly

626,000 tons of paper is used to produce all the books we see published every year. That’s a scary number when you consider the rate of deforestation and the state of our world in terms of global warming. We simply can’t afford to move ahead at a rate like that. Ebooks help tackle the issue because they require zero trees to produce.

In conclusion, ebooks offer endless benefits over physical books, including convenience, customization, and affordability. While physical books will always hold a special place in our hearts, you have to admit that the benefits of ebooks just can’t be ignored. For modern, busy, on-the-go readers, ebooks are the preferred choice. It’s time to embrace the digital age and make the switch to ebooks.

Now Write Your Persuasive Essay!

I hope this guide has helped you figure out persuasive essay writing and how to put together powerful arguments. Just stick to the facts and ease the reader into your point with gentle arguments that continue to prove your point. Don’t be afraid to get personal if it can help the essay and convince the reader.

Writing a Thesis Statement – Template & Examples

Leave a Comment

I accept the Privacy Policy

Reach out to us for sponsorship opportunities

Vivamus integer non suscipit taciti mus etiam at primis tempor sagittis euismod libero facilisi.

© 2024 My Speech Class

Want to create or adapt books like this? Learn more about how Pressbooks supports open publishing practices.

The Structure of a Persuasive Essay

Writing a persuasive essay.

You first need to choose a topic that you feel passionate about. If your instructor requires you to write about a specific topic, approach the subject from an angle that interests you. Begin your essay with an engaging introduction. Your thesis should typically appear somewhere in your introduction.

Next, you must acknowledge and explain points of view that may conflict with your own to build credibility and trust with your audience. You should also state the limits of your argument. This helps you sound more reasonable and honest to those who may naturally be inclined to disagree with your view. By respectfully acknowledging opposing arguments and conceding limitations to your own view, you set a measured and responsible tone for the essay.

Be sure to make your appeals in support of your thesis by using sound, credible evidence. Use a balance of facts and opinions from a wide range of sources, such as scientific studies, expert testimony, statistics, and personal anecdotes. Each piece of evidence should be fully explained and clearly stated. Also, write in a style and tone that is appropriate for your subject and audience. Tailor your language and word choice to these two factors, while still being true to your own voice. Finally, write a conclusion that effectively summarizes the main argument and reinforces your thesis.

Structuring a Persuasive Essay

You may already be familiar with the formula below for organizing a persuasive essay. It will present a convincing argument to your reader because your discussion is well rounded and thorough, and you leave your audience with your point of view at the end. Remember to consider each of these components in this formula sections instead of paragraphs because you will probably want to discuss multiple ideas backing up your point of view to make it more convincing.

When writing a persuasive essay, it is best to begin with the most important point because it immediately captivates your readers and compels them to continue reading. For example, if you were supporting your thesis that homework is detrimental to the education of high school students, you would want to present your most convincing argument first, and then move on to the less important points for your case.

Some key transitional words you should use with this method of organization are: most importantly ,  almost as importantly ,  just as importantly , and  finally .

The Formula

You will need to come up with objection points, but you will also need to think of direct rebuttals to each of those ideas. Remember to consult your outline as you are writing because you may need to double-check that you have countered each of the possible opposing ideas you presented.

Section 1: Introduction

• Attention-getter
• Thesis (showing main and controlling ideas)
• Signposts (make sure you outline the structure your argument will follow)

Section 2: (Multiple) Ideas in Support of Claim

• Give a topic sentence introducing the point (showing main and controlling ideas)
• Give explanations and evidence on the first point
• Make a concluding statement summarizing the point discussion (possibly transitioning to the next supporting idea)
• Repeat with multiple ideas in separate paragraphs

Section 3: Summary of (Some) Opposing Views

• Give a topic sentence explaining that this paragraph will present opposing points of view as part of providing a thorough, convincing argument
• Present a general summary of some opposing ideas
• Present some generalized evidence
• Provide a brief concluding sentence for the paragraph—transitioning into the next rebuttal paragraph

Section 4: Response to Opposing Views

• Give a topic sentence explaining/indicating how this paragraph/section connects to or expands on the previous paragraph
• [Here, you may recognize the validity of some of the points; then you need to] Present how your ideas are stronger
• Present evidence directly countering/refuting ideas mentioned in the previous section
• Give a concluding statement summarizing the countering arguments

Section 5: Conclusion

• Restate your thesis
• Summarize your discussion points
• Leave the reader with a strong impression; do not waiver here
• May provide a “call for action”

In a persuasive essay, the writer’s point of view should be clearly expressed at the beginning of each paragraph in the topic sentence, which should contain the main idea of the paragraph and the writer’s controlling idea.

Watch It: How to Write an Argumentative Essay with Example

Watch How to write an argumentative essay with example (3 minutes) on YouTube

Video source : Literacy In Focus. (2023, February 1). How to write an argumentative essay with example [Video]. YouTube. https://youtu.be/VZKUeEBryOk

Attribution & References

Except where otherwise noted, this chapter is adapted from “ 10.2 The Structure of a Persuasive Essay ” In  Writing for Success – 1st Canadian H5P Edition by Tara Horkoff, licensed under CC BY-NC-SA 4.0 . / Adaptations include the addition of the How to Write an Argumentative Argument Essay with example video.

English for Degree Entrance Preparation Copyright © by Carrie Molinski and Sue Slessor is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License , except where otherwise noted.

Share This Book

Task2gather

• Persuasive Essay Structure

So, you’ve got an assignment to write such an essay. Don’t rush into creating a text document – you’ll probably end up staring at the blank page. Instead, invest your time and effort into the preparation stage. Do your research, brainstorm, and outline your text.

Knowing how to do the latter is impossible without understanding what the typical structure for persuasive essay looks like. Luckily, this structure works for all essays of this type, regardless of the topic. 

So, what is it, exactly? And how do you use it to map out the text?

What Is Persuasive Essay?

If it’s your first time having this kind of task at hand, you might be confused about what a persuasive essay means in practice. Don’t worry: if you had to take a guess, you’d probably guess right. 

Such essays are written with one goal in mind – to convince the reader to agree with your standpoint. To do that, you’ll need to use arguments and counterarguments organized in a specific persuasive structure.

All persuasive text structures can include arguments and counterarguments of three types, as coined by Aristotle.

• Ethos . It’s about the credibility of the sources you use in the text. For example, you can use a quote by an expert in the field as evidence for your argument.
• Logos . These are the arguments that appeal to the logic. They include facts, figures, and studies.
• Pathos . It appeals to the person’s emotions. Depending on the topic, you may be discouraged from using pathos at all or make it the cornerstone of your argumentation.

How to Structure a Persuasive Essay

As you already probably know, any text consists of three parts:

• introduction;
• conclusion.

But what is the most common structure of a persuasive essay in particular? While it does follow the model above, there’s also a more detailed persuasive writing structure you can (and should) use.  

The introduction consists of four key parts (in most cases).  

• Hook . It’s an attention-grabbing first sentence, often in the form of a rhetorical question or a surprising fact or figure. Its point is to make the person want to read further.
• Background information . This is a summary of the context for the reader. In a nutshell, it’s meant to describe the existing problem or state of affairs. It’s also the right place to explain why the reader should care about the question at hand.
• Definitions . They’re not always required, but this is how you ensure you and the reader are on the same page. Definitions are especially useful when talking about abstract or complex concepts, like freedom or state.
• Thesis . It’s a statement that reveals your standpoint that you’re going to support in the text. The previous two parts might be omitted, but any structure of persuasive essay writing requires a thesis.

When it comes to the body, the general rule is “one argument per paragraph.” 

Remember to include both arguments and counterarguments. The latter ones require you to imagine what your opponent in an imaginary debate would say and how you would respond to their claim.

How many arguments should you include? It depends on the assignment itself – specifically, on the minimum (and maximum) text length. Typically, though, three to five paragraphs are considered enough.

Every single one of persuasive essay body paragraphs should follow this structure.

• Topic sentence . This is your argument that you’re going to use in this paragraph.
• Evidence . This is how you prove your argument is right – with facts, figures, quotes. Some assignments may allow using personal experience as evidence.
• Analysis . Don’t just drop the evidence and move on. Explain how it backs up your point at the beginning of the paragraph.

The conclusion is where you neatly sum up all of your arguments and counterarguments and paraphrase your thesis. You can also describe why this conclusion is significant. Some persuasive text structures advise you to answer the “So what?” question for that purpose.

Persuasive Essay Structure Examples

Before you jump right to the examples, keep in mind: topics and requirements vary. So, read the task carefully and focus on what’s in there when approaching the structure of a persuasive essay.

Here are five topics you can use to practice how you structure persuasive essay.

• Should you become a vegetarian?
• Do aliens exist?
• Is it important to learn cursive writing at school?
• Should humankind colonize Mars?
• Does money equal happiness?

And in case you’re looking for something more advanced, here are five more topics for applying persuasive text structures in practice.

• Should capital punishment be abolished in the US?
• Can personal freedom and personal responsibility coexist?
• Should we put a minimum age limit for using social media?
• Should access to broadband Internet become a human right?
• Can personal behavior changes have a substantial impact on society?

Let’s take the “Should capital punishment be abolished in the US?” topic. Here’s how the structure of persuasive essay writing can be used to argue in support of it.  

• Hook . How could we revert the death sentence if the person is found innocent after the execution?
• Background information . Capital punishment is legal in 27 US states, as well as in 54 other countries around the world. In 2020, 483 people were executed around the world (Amnesty International).
• Thesis . Considering the issues with the justice system, its inefficiency, and high financial costs, capital abolishment should be abolished in the United States.
• Argument #1 . The price of an error is too high. An estimated 4.1% of those sentenced to death in the US are, in fact, innocent. The problem is, if the executed person gets exonerated later, it’s impossible to bring them back to life.
• Argument #2 . It’s not a deterrent for crime. States with higher murder rates are also the states where 80% of executions take place. The US National Research Council advised policymakers to disregard studies that “prove” the deterrent effect. So, it’s not an efficient means of reducing the crime rate.
• Argument #3 . It’s more expensive than a life sentence. Cases themselves are costlier (three times more expensive in Maryland, four times – in Kansas, 3.2 times – in Oklahoma). This is the taxpayer money that could finance schools, hospitals, etc.
• Conclusion . The United States should abolish the death penalty, whether on the state-by-state or federal level. Until it’s abolished, there’ll be innocent lives lost, funds used inefficiently, and the crime rate unaffected by the death penalty’s existence.

Leave a Reply Cancel reply

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

Save my name, email, and website in this browser for the next time I comment.

• Easy Organization of an Essay Is Possible with Task2Gather
• Argumentative Essay Structure
• College Essay Format
• Scholarship Essay Format

College Writing: Argument

The persuasive essay, learning objectives.

• Determine the purpose and structure of persuasion in writing.
• Identify bias in writing.
• Assess various rhetorical devices.
• Distinguish between fact and opinion.
• Understand the importance of visuals to strengthen arguments.
• Write a persuasive essay.

The Purpose of Persuasive Writing

The purpose of persuasion in writing is to convince, motivate, or move readers toward a certain point of view, or opinion. The act of trying to persuade automatically implies more than one opinion on the subject can be argued.

The idea of an argument often conjures up images of two people yelling and screaming in anger. In writing, however, an argument is very different. An argument is a reasoned opinion supported and explained by evidence. To argue in writing is to advance knowledge and ideas in a positive way. Written arguments often fail when they employ ranting rather than reasoning.

Most of us feel inclined to try to win the arguments we engage in. On some level, we all want to be right, and we want others to see the error of their ways. More times than not, however, arguments in which both sides try to win end up producing losers all around. The more productive approach is to persuade your audience to consider your opinion as a valid one, not simply the right one.

The Structure of a Persuasive Essay

The following five features make up the structure of a persuasive essay:

• Introduction and thesis
• Opposing and qualifying ideas
• Strong evidence in support of claim
• Style and tone of language
• A compelling conclusion

Creating an Introduction and Thesis

The persuasive essay begins with an engaging introduction that presents the general topic. The thesis typically appears somewhere in the introduction and states the writer’s point of view.

Avoid forming a thesis based on a negative claim. For example, “The hourly minimum wage is not high enough for the average worker to live on.” This is probably a true statement, but persuasive arguments should make a positive case. That is, the thesis statement should focus on how the hourly minimum wage is low or insufficient.

Acknowledging Opposing Ideas and Limits to Your Argument

Because an argument implies differing points of view on the subject, you must be sure to acknowledge those opposing ideas. Avoiding ideas that conflict with your own gives the reader the impression that you may be uncertain, fearful, or unaware of opposing ideas. Thus it is essential that you not only address counterarguments but also do so respectfully.

Try to address opposing arguments earlier rather than later in your essay. Rhetorically speaking, ordering your positive arguments last allows you to better address ideas that conflict with your own, so you can spend the rest of the essay countering those arguments. This way, you leave your reader thinking about your argument rather than someone else’s. You have the last word.

Acknowledging points of view different from your own also has the effect of fostering more credibility between you and the audience. They know from the outset that you are aware of opposing ideas and that you are not afraid to give them space.

It is also helpful to establish the limits of your argument and what you are trying to accomplish. In effect, you are conceding early on that your argument is not the ultimate authority on a given topic. Such humility can go a long way toward earning credibility and trust with an audience. Audience members will know from the beginning that you are a reasonable writer, and audience members will trust your argument as a result. For example, in the following concessionary statement, the writer advocates for stricter gun control laws, but she admits it will not solve all of our problems with crime:

Although tougher gun control laws are a powerful first step in decreasing violence in our streets, such legislation alone cannot end these problems since guns are not the only problem we face.

Such a concession will be welcome by those who might disagree with this writer’s argument in the first place. To effectively persuade their readers, writers need to be modest in their goals and humble in their approach to get readers to listen to the ideas. These phrases of concession include:

• granted that

Bias in Writing

Everyone has various biases on any number of topics. For example, you might have a bias toward wearing black instead of brightly colored clothes or wearing jeans rather than formal wear. You might have a bias toward working at night rather than in the morning, or working by deadlines rather than getting tasks done in advance. These examples identify minor biases, of course, but they still indicate preferences and opinions.

Handling bias in writing and in daily life can be a useful skill. It will allow you to articulate your own points of view while also defending yourself against unreasonable points of view. The ideal in persuasive writing is to let your reader know your bias, but do not let that bias blind you to the primary components of good argumentation: sound, thoughtful evidence and a respectful and reasonable address of opposing sides.

The strength of a personal bias is that it can motivate you to construct a strong argument. If you are invested in the topic, you are more likely to care about the piece of writing. Similarly, the more you care, the more time and effort you are apt to put forth and the better the final product will be.

The weakness of bias is when the bias begins to take over the essay—when, for example, you neglect opposing ideas, exaggerate your points, or repeatedly insert yourself ahead of the subject by using I too often. Being aware of all three of these pitfalls will help you avoid them.

The Use of I in Writing

The use of I in writing is often a topic of debate, and the acceptance of its usage varies from instructor to instructor. It is difficult to predict the preferences for all your present and future instructors, but consider the effects it can potentially have on your writing.

Be mindful of the use of I in your writing because it can make your argument sound overly biased. There are two primary reasons:

• Excessive repetition of any word will eventually catch the reader’s attention—and usually not in a good way. The use of I is no different.
• The insertion of I into a sentence alters not only the way a sentence might sound but also the composition of the sentence itself. I is often the subject of a sentence. If the subject of the essay is supposed to be, say, smoking, then by inserting yourself into the sentence, you are effectively displacing the subject of the essay into a secondary position. In the following example, the subject of the sentence is underlined:

Smoking is bad.

I think smoking is bad.

In the first sentence, the rightful subject, smoking , is in the subject position in the sentence. In the second sentence, the insertion of I and think replaces smoking as the subject, which draws attention to I and away from the topic that is supposed to be discussed. Remember to keep the message (the subject) and the messenger (the writer) separate.

Developing Sound Arguments

Does my essay contain the following elements?

• An engaging introduction
• A reasonable, specific thesis that is able to be supported by evidence
• A varied range of evidence from credible sources
• Respectful acknowledgement and explanation of opposing ideas
• A style and tone of language that is appropriate for the subject and audience
• Acknowledgement of the argument’s limits
• A conclusion that will adequately summarize the essay and reinforce the thesis

Fact and Opinion

Facts are statements that can be definitely proven using objective data. The statement that is a fact is absolutely valid. In other words, the statement can be pronounced as true or false. For example, 2 + 2 = 4. This expression identifies a true statement, or a fact, because it can be proved with objective data.

Opinions are personal views, or judgments. An opinion is what an individual believes about a particular subject. However, an opinion in argumentation must have legitimate backing; adequate evidence and credibility should support the opinion. Consider the credibility of expert opinions. Experts in a given field have the knowledge and credentials to make their opinion meaningful to a larger audience.

For example, you seek the opinion of your dentist when it comes to the health of your gums, and you seek the opinion of your mechanic when it comes to the maintenance of your car. Both have knowledge and credentials in those respective fields, which is why their opinions matter to you. But the authority of your dentist may be greatly diminished should he or she offer an opinion about your car, and vice versa.

In writing, you want to strike a balance between credible facts and authoritative opinions. Relying on one or the other will likely lose more of your audience than it gains.

The word prove is frequently used in the discussion of persuasive writing. Writers may claim that one piece of evidence or another proves the argument, but proving an argument is often not possible. No evidence proves a debatable topic one way or the other; that is why the topic is debatable. Facts can be proved, but opinions can only be supported, explained, and persuaded.

Using Visual Elements to Strengthen Arguments

Adding visual elements to a persuasive argument can often strengthen its persuasive effect. There are two main types of visual elements: quantitative visuals and qualitative visuals.

Quantitative visuals present data graphically. They allow the audience to see statistics spatially. The purpose of using quantitative visuals is to make logical appeals to the audience. For example, sometimes it is easier to understand the disparity in certain statistics if you can see how the disparity looks graphically. Bar graphs, pie charts, Venn diagrams, histograms, and line graphs are all ways of presenting quantitative data in spatial dimensions.

Qualitative visuals present images that appeal to the audience’s emotions. Photographs and pictorial images are examples of qualitative visuals. Such images often try to convey a story, and seeing an actual example can carry more power than hearing or reading about the example. For example, one image of a child suffering from malnutrition will likely have more of an emotional impact than pages dedicated to describing that same condition in writing.

Writing at Work

When making a business presentation, you typically have limited time to get across your idea. Providing visual elements for your audience can be an effective timesaving tool. Quantitative visuals in business presentations serve the same purpose as they do in persuasive writing. They should make logical appeals by showing numerical data in a spatial design. Quantitative visuals should be pictures that might appeal to your audience’s emotions. You will find that many of the rhetorical devices used in writing are the same ones used in the workplace. For more information about visuals in presentations, see Chapter 14 “Creating Presentations: Sharing Your Ideas”.

Writing a Persuasive Essay

Choose a topic that you feel passionate about. If your instructor requires you to write about a specific topic, approach the subject from an angle that interests you. Begin your essay with an engaging introduction. Your thesis should typically appear somewhere in your introduction.

Start by acknowledging and explaining points of view that may conflict with your own to build credibility and trust with your audience. Also state the limits of your argument. This too helps you sound more reasonable and honest to those who may naturally be inclined to disagree with your view. By respectfully acknowledging opposing arguments and conceding limitations to your own view, you set a measured and responsible tone for the essay.

Make your appeals in support of your thesis by using sound, credible evidence. Use a balance of facts and opinions from a wide range of sources, such as scientific studies, expert testimony, statistics, and personal anecdotes. Each piece of evidence should be fully explained and clearly stated.

Make sure that your style and tone are appropriate for your subject and audience. Tailor your language and word choice to these two factors, while still being true to your own voice.

Finally, write a conclusion that effectively summarizes the main argument and reinforces your thesis. See Chapter 15 “Readings: Examples of Essays” to read a sample persuasive essay.

Key Takeaways

• The purpose of persuasion in writing is to convince or move readers toward a certain point of view, or opinion.
• An argument is a reasoned opinion supported and explained by evidence. To argue, in writing, is to advance knowledge and ideas in a positive way.
• A thesis that expresses the opinion of the writer in more specific terms is better than one that is vague.
• It is essential that you not only address counterarguments but also do so respectfully.
• It is also helpful to establish the limits of your argument and what you are trying to accomplish through a concession statement.
• To persuade a skeptical audience, you will need to use a wide range of evidence. Scientific studies, opinions from experts, historical precedent, statistics, personal anecdotes, and current events are all types of evidence that you might use in explaining your point.
• Make sure that your word choice and writing style is appropriate for both your subject and your audience.
• You should let your reader know your bias, but do not let that bias blind you to the primary components of good argumentation: sound, thoughtful evidence and respectfully and reasonably addressing opposing ideas.
• You should be mindful of the use of I in your writing because it can make your argument sound more biased than it needs to.
• Facts are statements that can be proven using objective data.
• Opinions are personal views, or judgments, that cannot be proven.
• In writing, you want to strike a balance between credible facts and authoritative opinions.
• Quantitative visuals present data graphically. The purpose of using quantitative visuals is to make logical appeals to the audience.
• Qualitative visuals present images that appeal to the audience’s emotions.
• Successful Writing Section 10.9: Persuasion. Authored by : Anonymous. Located at : http://2012books.lardbucket.org/books/successful-writing/s14-09-persuasion.html . License : Public Domain: No Known Copyright

Privacy Policy

How to Write a Persuasive Essay

Everyone has disagreements – whether it’s “who is the best performer of all time” or “what is the tastiest flavor of ice cream”, someone is going to have an opinion that might differ from yours. That doesn’t stop us from trying to convince each other of our perspective. This is where persuasive essays come into play. Persuasive writing is used to sway our readers to a certain viewpoint or opinion of the writer. How is that done? Today, well go over the purpose of persuasive writing and how to create an effective persuasive piece. Let’s get started!

Persuasive essays, also known as argumentative essays, are texts that are meant to convince the reader of something. There are other things besides essays that can be persuasive, such as speeches and social media posts. From politics to music to arguing why purple is the best color ever – anything can be made into a persuasive text.

But, the focus of this video is persuasive essays. When writing a persuasive essay, there is a structure you can follow to help make your argument clear and effective.

The essay is typically made up of 3 main sections: the introduction , the body , and the conclusion. To write an effective persuasive essay, each section should contain specific points you want to discuss.

Crafting Effective Introductions

The introduction paragraph of your essay should always introduce the topic you will be discussing. A good introduction paragraph will also have a hook, which is a sentence that grabs your readers attention. Once you have your hook, you will state your thesis. A thesis is the main point or argument you want to prove in your essay. Every persuasive essay must have a thesis. Lastly, you should always end each section of your essay with a concluding sentence. This is a sentence that wraps up the end of a paragraph and helps transition into the next paragraph.

Let’s look at an example of an introduction paragraph of a persuasive essay.

Long ago, ancient Egyptians worshiped cats. They believed they were godly creatures. Today, cats are still very beloved, but as household pets. Some cats aren’t so lucky; there are many cats who have yet to find their forever home. Cats are amazing animals that you should consider adopting because they are very intelligent, have an urgent need to be placed in a home, and make great companions. These are just a few reasons I’ll discuss as to why cats should be protected.

This introduction paragraph had a hook, it grabbed our attention by talking about ancient cats, and related it to cats today.

We see there is a thesis, the writer believes we need to adopt homeless cats, ideally from shelters, and gives three reasons why.

Lastly, they concluded the introduction paragraph by saying they would give more details about their reasons.

Building a Persuasive Body

Next comes the body paragraphs. The body of a persuasive essay holds all the main points you as the writer want to argue. It’s best to separate your points by paragraphs; so, if you have three main arguments, you should have at least three body paragraphs explaining them in detail. When you argue your points in the paragraph, you must make sure to explain why these reasons support your thesis. Let’s look at an example.

Cats are very smart animals. Despite what many people think, cats do in fact know their names and will react when you call out to them. They are also great at solving problems. Cats can easily get bored, when that happens, they may act mischievous. That’s why cats have puzzle toys to stimulate their curious minds. Such a smart animal should be able to have a safe home to live and play in peace.

Secondly, cats that end up in shelters don’t always find good homes. Pet shops are popular places to get cats as pets. When you get a cat from a pet shop, it will live there until it finds a good home. In shelters however, they can become packed with cats who haven’t found a home. Unfortunately, some shelters resort to euthanizing the animals when they run out space for new ones. For people who are interested in helping a cat find a home, why not consider getting one from a shelter instead?

Lastly, despite their bad reputation, cats are very friendly. Cats of all ages are able to cuddle with their owner and other pets. Some cats, just like people, need time to get used to you, but once they do, you’ll find you have a great couch-surfing buddy that keeps you company. Cats are also low maintenance pets, and are cleaner than most roommates. Just another reason to consider bringing a cat to your home.

We can see here that the author addressed the 3 main reasons that support the thesis with 3 body paragraphs. Each paragraph began with a transition word or hook, then it went into detail to support the reason, and lastly, it ended the paragraph with a concluding sentence.

Concluding with Impact

The conclusion of a persuasive essay is a summary of all the points mentioned earlier that wraps up the essay and often includes a catchy ending to drive the point home.

Whether you have been thinking of adopting for a long time or just considered it, cats everywhere are in need of a home. What better way to help an intelligent animal in need and make a new friend than to adopt a shelter cat!

As we can see, conclusion paragraphs don’t need to be super long. As long as they summarize the overall thesis and arguments of the essay, it is an effective closing to a persuasive essay.

As you’re writing the essay, there are a few tips and tricks to keep in mind to make sure your persuasion is more effective:

Repetition – Don’t say the same thing so many times that you start to sound redundant, but find ways to bring back your main argument throughout the essay. Your readers and listeners will remember your argument better if you repeat and emphasize it throughout the piece.

Real-world examples – Whether you are using data, emotions, or credibility to drive your point home, you should try to always use real-world examples to further persuade your readers.

Call to action – A good thesis in a persuasive essay is a statement that asks the reader to do something. Think hard about what you want to convince people of and narrow that action into one clear sentence. The rest of your essay should revolve around that.

Okay, let’s quickly review everything we talked about to wrap up.

The main purpose of a persuasive essay is to persuade the reader to a certain viewpoint or opinion of the writer. The essay will have an introduction paragraph that introduces the main argument, multiple body paragraphs that discuss sub-arguments that support the main argument, and a conclusion that wraps things up. And finally, if you want to make your persuasion more effective, remember to repeat your main argument throughout the paper, try to use real-world examples to support your points, and make your thesis a call to action.

That’s all for this review! Thanks for watching, and happy studying!

• “Persuasive Essay Definition and Writing Tips.” n.d.

Return to Writing Videos

by Mometrix Test Preparation | This Page Last Updated: February 8, 2024

• school Campus Bookshelves
• menu_book Bookshelves
• perm_media Learning Objects
• login Login
• how_to_reg Request Instructor Account
• hub Instructor Commons
• Download Page (PDF)
• Download Full Book (PDF)
• Periodic Table
• Physics Constants
• Scientific Calculator
• Reference & Cite
• Tools expand_more
• Readability

selected template will load here

This action is not available.

4.5: Persuasion

• Last updated
• Save as PDF
• Page ID 20304

• Ann Inoshita, Karyl Garland, Kate Sims, Jeanne K. Tsutsui Keuma, and Tasha Williams
• University of Hawaii via University of Hawaiʻi OER

Writers of persuasive essays take a stand on a controversial issue and give well-researched arguments to support this position. This section will help students define the persuasive essay as well as understand its purpose and structure.

What is an Argument?

In today’s society, arguments are all around us, in our every waking moment throughout the day, whether in online ads or in the messages one reads on one’s favorite box of cereal. The ability to think critically in terms of deciding what to believe is highly important due to the fact that individuals are bombarded by arguments, on the internet and elsewhere, on a daily basis. Deciding what arguments to accept or reject not only makes for a good essay, but has implications for success in life and for one’s future career.

Understanding the nature of argument is essential to writing a good persuasive essay. So, what is argument? It is not the act of proving who is right or wrong. Television and social media convey argument as a means of proving one’s point for the sake of arguing. This is not argument. Ancient rhetoricians such as Aristotle, Plato, and Socrates understood argument in terms of truth-seeking, and conceptualized it as a means of preventing war. In this vein, good writers engage in truth-seeking to find out what is valid so that they may communicate truths to others. Sometimes in this process of truth-seeking, the writers themselves may change their minds on a given topic. Leaders such as Queen Lili‘uokalani and Dr Martin Luther King, Jr. demonstrate argument as a means of engaging in truth-seeking. See A Letter of Protest (Queen Lili‘uokalani of Hawai‘i, 1898) and Letter from a Birmingham Jail (Dr. Martin Luther King, Jr., AU, University of Alabama, April 16, 1963).

Structure of a Persuasive Essay

Before students begin creating persuasive essays, they should engage in preliminary research. Persuasive essays often include quotes or paraphrases from experts or statistics from academic studies. These essays must also demonstrate the writer’s ability to think critically and to avoid logical errors.

Note: Persuasive essays often require research, so students should see the Research and Plagiarism chapter of this text before drafting the essay.

After writers have conducted some preliminary research to enter the conversation, they will be ready to begin writing. Drafting should include at least four aspects:

• Introduction and thesis
• Strong arguments and evidence in support of thesis
• Opposing and qualifying ideas
• A compelling and satisfying conclusion

Creating an Introduction and Thesis

The persuasive essay begins with an engaging introduction that presents the general issue. The role of this paragraph is to do the following:

• Create interest.
• Introduce a controversial topic.
• Include a thesis statement that clearly presents the writer’s position on the chosen issue, and the major points to be discussed. Instructors will give students further guidelines on where the thesis should appear, but it is usually located at the very end of the introduction.

Strong Arguments and Evidence in Support of the Thesis

The body of the persuasive essay presents the reasons for the writer’s position on the issue. Writers should provide at least three solid reasons for their position.

When developing arguments and evidence, a writer would be wise to do the following:

• Provide at least one paragraph for each reason that is presented (though some reasons may require more than one paragraph). Clearly state each reason in a topic sentence.
• Provide sufficient evidence for each reason. Much of the evidence will come from research, though writers can effectively integrate their own knowledge as evidence.
• Explain ideas thoroughly and carefully, connecting one’s sources together smoothly and logically.
• Provide follow-up discussion or explanation for the researched information one has provided.
• Remember that arguments are usually “won” or “lost” on the quantity and quality of the evidence.

Ways to Persuade

There are three primary ways to appeal to the emotion and response of readers: ethos, logos, and pathos.

Ethos is the appeal to what is right, fair and trustworthy. For example, if Aaron is arguing for more access to parks in Hawai‘i for individuals who are disabled, he could do so by pointing out that many citizens who happen to have some sort of disability pay taxes that support these parks and yet are denied access simply due to design. The unfairness of this situation would appeal to the readers’ sense of what is right or fair.

Logos appeals to the reader’s logic and reason. If Aaron is arguing for the need to make college tuition more affordable or even free, such as is the case in Norway, Sweden, and Germany, among other countries, and he uses statistics about the number of students who would not be able to obtain a college degree without some country-wide assistance, he is appealing to his reader’s logic.

An argument with pathos appeals to the reader’s emotions. In his essay in favor of students joining a sports team in high school, he could highlight his own experience of overcoming fears and physical challenges while running in high school. Such an approach would pull the heartstrings of his readers who are touched by his success due to the self-discipline, social connections, and physical strength he developed through running on a team.

Addressing Opposing Ideas and the Author’s Position

Any good argument anticipates the opposing arguments and attempts to answer or refute its main points. In refuting the opposing point, writers do the following:

• Address at least one major opposing point. Writers briefly summarize viewpoints on the other side of the argument.
• Provide reasons and evidence showing the weaknesses in this opposing idea. They may address more than one opposing viewpoint.

Conclusion: Call to Action

The conclusion should provide insight into the significance of the issue. Most important is the fact that such a conclusion would do well not to use the word “should” as in the following. “In order for the United States to increase college attendance, encourage young people to seek out higher education and advanced knowledge to be used within the professional world, and truly support the process of learning, making college tuition more affordable or even free is key.”

If writers have proven their stance within the body paragraphs using examples and quoted, paraphrased, or summarized information from professionals within the given community, a “should” isn’t needed because the reader has already been convinced.

• What facts (logos) does the advertiser provide?
• What emotions do you feel after viewing the advertisement?
• What occurred in the advertisement to cause these emotions (pathos)?
• What occurred in the advertisement that appealed to your sense of morals and ethics (ethos)?
• Overall, was the advertisement effective to persuade you to purchase their product? Why or why not?

Further Resources

• Read more about writing a thesis statement in the handout by University of North Carolina at Chapel Hill: Thesis Statements , The Writing Center.
• Watch the following video to learn more about persuasive appeals: Ethos, Pathos, Logos
• Read more about counterarguments and the language used to signal the counterargument and refutation in this handout by Harvard College Writing Center: Counterargument , Writing Resources.
• See sample persuasive essays in “Chapter 15: Introduction to Sample Essays,” Writing for Success.
• Other sample persuasive essays are “Online Monitoring: A Threat to Employee Privacy in the Wired Workplace“; (Hacker), and “ Performance Enhancement through Biotechnology Has No Place in Sports “; (Hacker). These essays are excellent references because they contain notes in the margins that explain the components of the essays and MLA format.
• Purdue Online Writing Lab (OWL). “ Transitional Devices ,” The Purdue OWL.

Works Cited

Hacker, Diana. Writer’s Reference . Bedford/St. Martins, 2007.

King, Jr., Martin Luther. “ Letter from a Birmingham Jail ,” AU, University of Alabama , April 16, 1963.

Lili`uokalani (Queen of Hawai`i). Letter to the U.S. House of Representatives (protesting U.S. assertion of ownership of Hawai`i), U.S. National Archives, Records of the U.S. House of Representatives, Record Group 233, Record HR 55A-H28.3, 19 December 1898.

• 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