how to teach students to write a 5 paragraph essay

Join my VIP teacher email club!

When I look back to my first experience teaching five paragraph essays to fifth graders, I can remember how terribly unprepared I felt.

I knew that the five paragraph essay format was what my students needed to help them pass our state’s writing assessment but I had no idea where to start.

I researched the few grade-appropriate essays I could find online (these were the days before Pinterest and Teachers Pay Teachers) and determined that there was a structure to follow.

Every essay followed the same basic structure. I taught the structure to my students and they did well.

I have been teaching five paragraph essay structure and everything that goes with it for several years now. I hope that after you read this blog post, you will have a good understanding of how to teach and grade five paragraph essays.

Once you’ve learned all about teaching basic essay structure, you’ll be ready to grow your writers from “blah” to brilliant! 

Teaching five paragraph essays is just one part of teaching 5th grade writing. Click here to find out exactly how I teach writing to my 5th graders! 

Start with Simple Paragraphs

We always start with simple paragraphs.

Yes, this is basic, but if your students cannot write excellent paragraphs, their five paragraph essays will be train wrecks. Trust me!

We spend a while cementing paragraph structure:

Topic Sentence

Closing Sentence

I give students topics, they come up with their own topics, we write together, they write with a partner or independently, the more variety, the better.

We have fun with simple paragraphs. Then, it’s time to move on to body paragraphs.

Organize and Write Body Paragraphs

Please refer to my five paragraph essay organizer below.

The three body paragraphs are absolutely crucial to the success of the five paragraph essay.

Some teachers have trouble teaching the structure of five paragraph essays because they start with the introduction paragraph.

Always teach the body paragraphs first!

I had a teacher say to me once, “What’s the point of just writing parts of the essay? They need to write the entire five paragraphs to get all of the practice they need.”

I understand that point. However, think of it as building a house. Should you test out the foundation and make sure it’s sound and sturdy before building on top of it? Absolutely! That’s what we’re doing here.

The three body paragraphs are the foundation of the essay.

Ask students to write out their three body paragraphs just like they have practiced…Topic sentence…Detail 1…Detail 2…Detail 3…Closing Sentence.

I “ooooh and aaaah” over their three paragraphs. Students are on their way to five paragraph essays, so be sure to build their confidence.

Teach the Introduction Paragraph

I have to say, this is my favorite paragraph to teach. The introduction paragraph is what draws readers into the essay and makes them want to read more.

We start with what I call a “hook.” The hook captures the readers’ attention and can come in many forms: asking a question, making a bold statement, sharing a memory, etc.

After the hook, I ask students to add a sentence or two of applicable commentary about the hook or about the prompt in general.

Finally, we add the thesis sentence. The thesis sentence always follows the same formula: Restate the prompt, topic 1, topic 2, and topic 3.

That’s all you need to write an excellent introduction paragraph!

I do suggest having students write the introduction paragraph plus body paragraphs a couple of times before teaching the closing paragraph.

Teach the Closing Paragraph

In the conclusion paragraph, we mainly focus on restating the thesis and including an engaging closing thought.

With my students, I use the analogy of a gift.

The introduction paragraph and body paragraphs are the gift and the conclusion paragraph is the ribbon that ties everything together and finishes the package.

When you talk about restating the thesis sentence, tell students that they need to make it sound different enough from their original thesis sentence to save their readers from boredom.

Who wants to read the same thing twice? No one!

Students can change up the format and wording a bit to make it fresh.

I enjoy teaching the closing thought because it’s so open to however students want to create it.

Ways to write the closing thought: ask a question, personal statement, call to action, or even a quote. 

I especially like reading the essays in which a quote is used as a closing thought or a powerful statement is used.

Example of a full five paragraph essay

Let’s Talk About Color-Coding!

Who doesn’t like to color? This is coloring with a purpose!

Training your students to color-code their paragraphs and essays will make grading so much easier and will provide reminders and reinforcements for students.

When students color-code their writing, they must think about the parts of their paragraphs, like topic sentences, details, and the closing sentence.

They will be able to see if they are missing something or if they’ve written something out of order.

Color-coding is a wonderful help for the teacher because you can skim to ensure that all parts of your students’ paragraphs and essays are present.

Also, when you are grading, you can quickly scan the paragraphs and essays. Trust me, you will develop a quick essay-grading ability.

I start color-coding with my students at the very beginning when they are working on simple paragraphs. I add the additional elements of the color-code as we progress through our five paragraph essays.

This is the code that I use:

Let’s Talk About Grading Five Paragraph Essays!

Imagine a lonely, stressed teacher grading five paragraph essays on the couch while her husband is working the night shift.

That was me!

Seriously, guys, I would spend about ten minutes per essay. I marked every little error, I made notes for improvement and notes of encouragement. I reworked their incorrect structure.

Those papers were full of marks.

On Monday, I proudly brought back the essays and asked students to look over them and learn what they needed to fix for next time.

You can guess what happened… there were lots of graded essays in the trashcan at the end of the day.

I decided that my grading practices had to change. I needed my weekends back and my students needed to find their own errors!

This is my best advice:

STOP correcting every error!

Your students are not benefiting from marks all over their writing. They need to find those errors themselves so that they will remember their mistakes and change their writing habits.

Do a quick scan of each student’s writing as soon as it’s turned in to you.

If there are major problems with a student’s writing, call him/her over individually and show him/her what needs to be fixed or put the student with a competent peer editor who will help them fix mistakes.

If you have several students who are struggling with a skill, like closing sentences, do a mini-lesson on this topic.

You can do a mini-lesson with a small group. However, I prefer doing mini-lessons with the entire class. The kids who need help will get it and the rest of your class will receive a refresher.

It’s OK if there are some small spelling/grammar mistakes!

If the errors are few and they don’t take away from the meaning/flow of the essay, I don’t worry about them.

Our students are still learning.

Even your brightest star writer will have a few spelling/grammar mistakes from time to time.

Don’t discourage students from writing because of small errors.

Students who receive papers back with markings all over them don’t think, “Oh boy, my teacher has made it so easy for me to make all of these corrections.” They are thinking, “What’s the point in writing? I must be a terrible writer. Look at all of these mistakes.”

If your students are taking a standardized writing assessment, the structure and flow of their essays will be worth much more than perfect spelling.

Need more help?

I created this five paragraph essay instructional unit for teachers who are new to teaching five paragraph essays OR just need all of the materials in one place.

“Teacher Talk” pages will guide you through the unit and this unit contains all materials needed to help students plan, organize, and write amazing five paragraph essays! Click here to check it out:

I have a freebie for you! Enter your first name and email address below. You’ll receive three original prompts with five paragraph essay organizers AND two lined final draft pages!

Once your students are good essay writers…

These task cards will help your students stay sharp on their five paragraph essay knowledge. Students will review hooks (attention-getters), thesis sentences, body paragraphs, topic sentences, closings, and more. Each card contains a unique writing example!

I suggest using these task cards as a quiz/test, scoot game, individual review, or cooperative group activity.

Click on the image to view these task cards:

To save this post for later, simply pin this image to your teacher Pinterest board!

21 comments.

Wow! I really enjoyed reading this. I’ve always stressed over the thought of teaching writing, but your blog makes me think I can do it successfully. Putting your writing packet on my TPT wish list!

Thank you, Shannon! I appreciate you taking the time to leave a comment. I am so glad that my blog post was helpful to you!

Thanks for the tips! When I taught 6th grade I taught this same subject matter, but struggled to get started. I wish I had this then!

I appreciate your comment! Teaching was much different before Pinterest, wasn’t it?!?

This helped me so much!🙂 thanks a lot, I imagined being one student of yours. I’d be so smart and good at essays! Would’ve been so much easier in person❤️❤️❤️

Thank you so much, Aizlyn!

Thank you so much for this! May I ask where I can see the rubric for scoring the compositions?

You are so welcome! Click on the resource link. Then, you will see the rubric in the preview!

Thank you so much,I am a parent and this really helped me be clear how to guide my son. God bless you always.,

Thanks for taking the time to leave a comment!

you are welcome!!!

This looks great! Looking forward to using your tips and freebies with my 6th graders. 🙂 THANK YOU.

You are so welcome! Thank you for taking the time to leave a comment!

Can’t wait to use this with my class tomorrow! Thanks a bunch for sharing!!

You are so welcome, Amy!

Thank you for making it easy to teach an essay with clarity.

You are very welcome, Yamuna! Thanks for taking the time to leave feedback 🙂

I am so happy I discovered your blog. I just started teaching grade 5 in September I have been searching for a simple method to hel me in guiding them in writing. I will be putting your method into practice in the coming week.

That’s wonderful, Cherry! Thank you for sharing your thoughts! Welcome to fifth grade 🙂

Beautiful lesson well explained! Thank you so very much .

Thank you so much, Cheryl!

Leave a Reply Cancel reply

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

Notify me of follow-up comments by email.

Notify me of new posts by email.

This site uses Akismet to reduce spam. Learn how your comment data is processed .

You may also enjoy...

A message to the teacher-mom who doesn’t want Winter Break to end…

The Step-By-Step Guide to Teaching Research Reports

History Hashtag Fan Club – A Fun, Easy Review Idea

5 Helpful Tips for Struggling Social Studies Teachers

Big List of Social Studies Journal Prompts – A Growing List

How to Make Your Social Studies Lessons Come to Life for Students

What can i help you teach, find it here, let's connect, i'd love to connect with you.

Enter your first name and email address to join my exclusive VIP email club.

Copyright © 2020  | Thrive in Grade Five | All Rights Reserved

Quick Links

Teaching with a Five-Paragraph Essay Example

Looking for a five-paragraph essay example? Look and listen in as a fourth grade teacher models this strong writing structure for her students.

Ms. Sneed Grades Her Kids’ Paragraphs

As our favorite fourth grade teacher graded her class’s latest paragraphs, she let out a satisfied sigh. First they tackled paragraph structure. Then they learned to elaborate. Additionally, they improved their writing by varying sentences and using transitions. Now that they had the writing strategies down, her kids were ready to scaffold from one paragraph to the five-paragraph essay .

Purposefully tackling each genre of writing – then scaffolding from shorter to longer – was sure to work for her.

A Five-Paragraph Essay Example

Ms. Sneed turned and opened her laptop. With just a few clicks, she found it. Her favorite prompt, You Should Try It , asked kids to persuade others to try an activity – in five paragraphs.

Teaching Paragraph by Paragraph

The following Monday, Ms. Sneed stood in front of her class. “Today,” she said, “you will learn how to write a longer essay.”

Several kids looked a little unsure, but their teacher continued. “For now, I’ll take you through a five-paragraph essay example. That should ease your concerns.”

First Paragraph

Ms. Sneed projected a sample. “The first paragraph, or introduction, includes a thesis statement and supportive factual reasons.”

With the mention of a new term, thesis statement , more kids looked uncomfortable. Some squirmed in their seats.

“Now I know the term  thesis statement is new, but no worries! You know it as a topic sentence. However, the thesis is the main idea of a multi-paragraph composition.”

The teacher read the paragraph aloud. “Can anyone pick out the thesis for this persuasive essay?” she asked.

One student slowly raised his hand. “Wouldn’t you like to try water skiing?”

“Yes! Although it’s written as a question, this sentence offers an opinion. Furthermore, the entire essay supports this thesis. Can you find the author’s three supporting reasons?”

Using the five-paragraph essay example, the class soon established the supporting details too: improving health, impressing friends, and teaching them to ski.

Second Paragraph

“Now let’s look at the second paragraph,” Ms. Sneed said.

“You identified one of the main details as health. As you can see, this paragraph expands on that reason.”

“That’s just what we were doing with one paragraph,” piped up a girl in the back row.

“Um-hm. True. But writing in five paragraphs gives you more room to elaborate.”

The kids seemed to relax in their seats. This wasn’t so bad after all.

Third Paragraph

With no further ado, she pulled up the third paragraph. “See, paragraph #3 discusses the second main supportive detail.”

After they read the paragraph aloud, Ms. Sneed asked, “Who can find the topic sentence of this paragraph?”

“Isn’t it the first sentence?” said a boy with purple glasses.

Ms. Sneed nodded. “Easy peasy. The main idea of this paragraph, as we said before, is the second reason.”

Fourth Paragraph

For the fourth paragraph, Ms. Sneed tried a new tactic. “Okay, think-pair-share! Find the the topic sentences and smaller details that support it.” Her students knew what this meant. Immediately, they turned to their seat partners and began to discuss.

After a few minutes, groups began to share:

“The first sentence is the topic sentence again,” said the first spokesperson.

“And the details are the steps in teaching,” said the second.

“Ahh, a sequence paragraph inside a five-paragraph persuasive essay,” Ms. Sneed remarked. That famous teacher smile spread across her face.

Fifth Paragraph

“Here we have the final paragraph, or conclusion,” the teacher continued.

After she read the paragraph aloud, Ms. Sneed pointed out the restated thesis statement and details. “It’s a repeat of the first paragraph in different words.”

A Five-Paragraph Essay Example – and a Hamburger!

Quickly, strode toward the board. She picked up a marker and sketched a hamburger with three patties. “Does this look familiar?”

Everyone smiled and nodded. Ms. Sneed’s favorite analogy for an writing a paragraph !

“We just used this again,” their teacher said. “The top bun is the first paragraph. It introduces the main idea with a thesis statement and supporting details. The first hamburger patty explores the first detail; the second, the second; and the third, the third! Finally, the bottom bun wraps it all up with a restatement of the thesis and details. This helps you write, as well as find the main idea and supporting details .”

“It’s just a giant version of the paragraph,” said a small girl in the front corner.

“Yep,” replied Ms. Sneed. “Not hard at all – if you know what you’re doing. Over the next few months, we’ll write more of these essays in our ELA block . Then you’ll feel even more confident.”

The Ultimate Guide to the 5-Paragraph Essay

PeopleImages / Getty Images

• M.Ed., Education Administration, University of Georgia
• B.A., History, Armstrong State University

A five-paragraph essay is a prose composition that follows a prescribed format of an introductory paragraph, three body paragraphs, and a concluding paragraph, and is typically taught during primary English education and applied on standardized testing throughout schooling.

Learning to write a high-quality five-paragraph essay is an essential skill for students in early English classes as it allows them to express certain ideas, claims, or concepts in an organized manner, complete with evidence that supports each of these notions. Later, though, students may decide to stray from the standard five-paragraph format and venture into writing an  exploratory essay  instead.

Still, teaching students to organize essays into the five-paragraph format is an easy way to introduce them to writing literary criticism, which will be tested time and again throughout their primary, secondary, and further education.

Writing a Good Introduction

The introduction is the first paragraph in your essay, and it should accomplish a few specific goals: capture the reader's interest, introduce the topic, and make a claim or express an opinion in a thesis statement.

It's a good idea to start your essay with a hook (fascinating statement) to pique the reader's interest, though this can also be accomplished by using descriptive words, an anecdote, an intriguing question, or an interesting fact. Students can practice with creative writing prompts to get some ideas for interesting ways to start an essay.

The next few sentences should explain your first statement, and prepare the reader for your thesis statement, which is typically the last sentence in the introduction. Your  thesis sentence  should provide your specific assertion and convey a clear point of view, which is typically divided into three distinct arguments that support this assertation, which will each serve as central themes for the body paragraphs.

Writing Body Paragraphs

The body of the essay will include three body paragraphs in a five-paragraph essay format, each limited to one main idea that supports your thesis.

To correctly write each of these three body paragraphs, you should state your supporting idea, your topic sentence, then back it up with two or three sentences of evidence. Use examples that validate the claim before concluding the paragraph and using transition words to lead to the paragraph that follows — meaning that all of your body paragraphs should follow the pattern of "statement, supporting ideas, transition statement."

Words to use as you transition from one paragraph to another include: moreover, in fact, on the whole, furthermore, as a result, simply put, for this reason, similarly, likewise, it follows that, naturally, by comparison, surely, and yet.

Writing a Conclusion

The final paragraph will summarize your main points and re-assert your main claim (from your thesis sentence). It should point out your main points, but should not repeat specific examples, and should, as always, leave a lasting impression on the reader.

The first sentence of the conclusion, therefore, should be used to restate the supporting claims argued in the body paragraphs as they relate to the thesis statement, then the next few sentences should be used to explain how the essay's main points can lead outward, perhaps to further thought on the topic. Ending the conclusion with a question, anecdote, or final pondering is a great way to leave a lasting impact.

Once you complete the first draft of your essay, it's a good idea to re-visit the thesis statement in your first paragraph. Read your essay to see if it flows well, and you might find that the supporting paragraphs are strong, but they don't address the exact focus of your thesis. Simply re-write your thesis sentence to fit your body and summary more exactly, and adjust the conclusion to wrap it all up nicely.

Practice Writing a Five-Paragraph Essay

Students can use the following steps to write a standard essay on any given topic. First, choose a topic, or ask your students to choose their topic, then allow them to form a basic five-paragraph by following these steps:

• Decide on your  basic thesis , your idea of a topic to discuss.
• Decide on three pieces of supporting evidence you will use to prove your thesis.
• Write an introductory paragraph, including your thesis and evidence (in order of strength).
• Write your first body paragraph, starting with restating your thesis and focusing on your first piece of supporting evidence.
• End your first paragraph with a transitional sentence that leads to the next body paragraph.
• Write paragraph two of the body focussing on your second piece of evidence. Once again make the connection between your thesis and this piece of evidence.
• End your second paragraph with a transitional sentence that leads to paragraph number three.
• Repeat step 6 using your third piece of evidence.
• Begin your concluding paragraph by restating your thesis. Include the three points you've used to prove your thesis.
• End with a punch, a question, an anecdote, or an entertaining thought that will stay with the reader.

Once a student can master these 10 simple steps, writing a basic five-paragraph essay will be a piece of cake, so long as the student does so correctly and includes enough supporting information in each paragraph that all relate to the same centralized main idea, the thesis of the essay.

Limitations of the Five-Paragraph Essay

The five-paragraph essay is merely a starting point for students hoping to express their ideas in academic writing; there are some other forms and styles of writing that students should use to express their vocabulary in the written form.

According to Tory Young's "Studying English Literature: A Practical Guide":

"Although school students in the U.S. are examined on their ability to write a  five-paragraph essay , its  raison d'être  is purportedly to give practice in basic writing skills that will lead to future success in more varied forms. Detractors feel, however, that writing to rule in this way is more likely to discourage imaginative writing and thinking than enable it. . . . The five-paragraph essay is less aware of its  audience  and sets out only to present information, an account or a kind of story rather than explicitly to persuade the reader."

Students should instead be asked to write other forms, such as journal entries, blog posts, reviews of goods or services, multi-paragraph research papers, and freeform expository writing around a central theme. Although five-paragraph essays are the golden rule when writing for standardized tests, experimentation with expression should be encouraged throughout primary schooling to bolster students' abilities to utilize the English language fully.

• How To Write an Essay
• How to Write a Great Essay for the TOEFL or TOEIC
• Write an Attention-Grabbing Opening Sentence for an Essay
• How to Write and Format an MBA Essay
• How to Structure an Essay
• How to Help Your 4th Grader Write a Biography
• Definition and Examples of Body Paragraphs in Composition
• What Is Expository Writing?
• What an Essay Is and How to Write One
• Paragraph Writing
• 3 Changes That Will Take Your Essay From Good To Great
• An Introduction to Academic Writing
• Tips on How to Write an Argumentative Essay
• The Five Steps of Writing an Essay
• How to Write a Solid Thesis Statement
• The Introductory Paragraph: Start Your Paper Off Right

Lessons from the Peace Corps

How to write (and teach) the five-paragraph essay.

For a student to participate in the western world of academics, it is essential they know the basics of the 5-paragraph essay. Organizing thoughts into an outline and then putting them into this formula is a specific skill that must be taught and practiced for students to master.

It is even more important to have a strong command of this form for students who want to apply for study abroad programs or work in Europe or the United States. I wrote this lesson plan while helping students prepare for the Future Leaders Exchange (FLEX) exam so they could have a better shot at becoming one of the amazing 60 or so students from Kyrgyzstan who spend an academic year at a US high school.

The following is a lesson plan for introducing and practicing the basics of the 5-paragraph essay. As always, it should be modified to meet the specific needs of your students.

Lesson Plan – The 5-paragraph Essay

Objectives: Students will be able to write a 200-250 word essay using 5-paragraph form to include 1) An attention grabbing introduction 2) A thesis listing 3 reasons 3) 3 paragraphs with 3 reasons being the topic sentences 4) A conclusion that restates the introduction using different words.

• Give students a straight-forward topic, like, “My favorite singer” or “Why I want to go to America.”
• Brainstorm and list many reasons why they like this particular singer, or why they want to go to America. Emphasize specific reasons.
• Have students complete the following chart to help them with the form and reasons. “My favorite singer is __Avril Lavigne__ because 1) __she is edgy__ 2) __she doesn’t take crap from anyone__ 3) __when I play her music all the cute girls gather around__”
• Explain the word “detail” (story, statistic, example, anecdote, supporting information) and brainstorm together a couple details for one of the reasons.
• Write the outline above on the board and have students copy into their notebooks.
• Provide a sample essay. Students must: a) Identify and underline the thesis; b) Number the reasons within the thesis; c) Number and underline the reasons in the topic sentences; and d)Number the reasons in the conclusion. Go over these one at a time and elicit answers from students. If students need help, have them work in pairs or small groups before providing answers.
• Students complete an outline for the sample essay.
• Students check their partners’ outline and match it against the elements in the example.
• Students write a practice essay. (For homework.)

Lesson notes:  Learning to write essays using the 5-paragraph technique takes lots of practice. Students should have many opportunities to sit down with the teacher one-on-one to discuss outlines and critique writing tasks. I have found this lesson to be more successful if you first spend lots of time only writing outlines. Slowly build on thesis, reasons, details, introduction, conclusion and transitions. It helps to assign a topic every lesson (or day) and then the next day working in pairs, students can critique each others’ essays underlining and labeling the elements of the 5-paragraph essay. Lastly, please, for the love of learning, and all that is good and bright in the world, add your own personality and above all, humor to your teaching. Just like how our essays should be interesting in order to be memorable, the more enjoyable your lesson, the more the students will get out of it.

Topic ideas to assign as homework:

• Describe a time you were a leader and give examples.
• If I were a banana, I would…
• If I don’t like my host mother’s food, I will…
• You are home alone and you accidentally break the coffee table. What do you do?
• The three most important people are…

For the FLEX test particularly, it’s necessary to stress to students the importance of being original, unique, and outgoing while showing a flavor of critical-thinking in their writing. FLEX recruiters are going to read a billion of these essays and students need to stand out to have a shot at a year in America.

5-paragraph essay outline

Introduction:

• Be interesting!
• Be unique! The reader should remember this.
• 2-3 sentences
• Write the topic and give your opinion using 3 reasons .
• “I think XYZ is good because 1)… 2)… 3)… ”
• 3 paragraphs (3-5 sentences each)
• Detail (example, story, anecdote, statistic)

Conclusion:

• Write the introduction and thesis again using different words
• “In conclusion, you can see that XYZ is very good because…”

Sample 5-paragraph essay

Topic: What will you do when you get back from the United States?

Studying in America will be an amazing experience, but I will also be very excited to come home. Of course I will miss my family. But I also am excited to meet my friends and tell them all about America! When I come back from the United states I will help lead an American Culture club, show videos of high school life and help Access students.

Leading an American Culture club will teach students about new things. I want to share new music and lead a hip-hop dance club. I went to many dances at my school in America and it was so fun! My dance group in America wants to keep in touch with us and we will record videos and send them to each other.

I took many videos of my high school in America. I want to show my school their cafeteria, their classrooms and the gymnasium. I know we can make some changes to our school to make it even better.

Access students learn American culture, but they don’t have a chance to visit, so I will help teach Access students English through American culture lessons. We will listen to songs and write letters to students in America. It is a good chance to learn English from native speakers!

After I come back from America I will be so happy to see my family and friends again! But I know I will miss my place in the United States too. I will be able to keep in touch with my friends in America and teach my friends new things by leading clubs, showing videos and helping with Access.

What ideas do you have for teaching the 5-paragraph essay? Write your suggestions below in the comments!

Share this:, one comment.

What a great, concise lesson plan. I loved it and am using it.

Leave a comment Cancel reply

• Already have a WordPress.com account? Log in now.
• Subscribe Subscribed
• Copy shortlink
• Report this content
• View post in Reader
• Manage subscriptions
• Collapse this bar

• Try for free

Teaching the Five-Paragraph Essay Resource Packet

Featured 5th Grade Resources

Related Resources

About the author

Contributor

How to Teach the 5-Paragraph Essay in Your Homeschool

by Misti Lacy | Sep 16, 2019 | College Prep , Essays & Research Papers , High school

Like many moms, you face new challenges as the high school years approach. Biology, chemistry, art, and geometry practically feel like a cakewalk compared with how to teach the 5-paragraph essay in your homeschool!

One thing is certain. Regardless of how we get through the high school years, our homeschool teens need to master the basics of 5-paragraph essay writing.

Of course they’ll write essays for college applications, entrance exams, and English classes. But they’ll also face essay assignments and papers in nearly every college class—even if they’re science, marketing, or criminal justice majors .

But wait … my teen can’t even write a solid paragraph!

I get it. Sometimes we need to pause and rewind . If your middle school or high school student struggles with basic paragraph writing , make that your top priority.

Taking a year to teach WriteShop I will cement the fundamentals of concise and concrete writing. Then move up to WriteShop II once their critical-thinking skills have matured a bit and they’re ready to write—and correctly format—those 5-paragraph essays.

Teach the 5-Paragraph Essay Format in Your Homeschool

Teaching your teens how to write a 5-paragraph essay is a homeschool necessity. Unlike narrative writing, this traditional essay has a stringent structure that includes an introductory paragraph, three body paragraphs, and a closing paragraph. Let’s look at each of these.

1. An Interesting Introduction Sets the Stage

The introductory paragraph sets the stage for the entire essay. It should include an attention-grabbing “ hook  ,” a bit of background info, and a thesis statement.

The “Hook”

The hook pulls the reader into the essay. As the first sentence of the essay, it gives a hint about the topic, captures the readers’ attention, and entices them to keep reading. A question, quotation, opinionated statement, or interesting fact can make an effective, engaging hook.

Background Information

Next in the lineup is the background information, which gives the reader a short history of the topic. In addition, the introductory paragraph must include at least a couple of sentences that express the main points of the paper. Think of the intro as an outline of the rest of the essay.

The Thesis Statement

The thesis statement closes the introduction. Because the thesis statement serves as a road map for the essay, it should give the reader a short summary of the paper’s intent. By stating the problem and solution, the thesis lays out the essay’s basic argument.

Let’s look at an example: Dogs make good pets.

“Dogs make good pets” isn’t a thesis statement. Why? Because it doesn’t state a problem or a solution. Instead, try starting the thesis statement with although or because. These words allow the writer to jump right into the problem.

• Although dog ownership can be inconvenient or expensive, dogs make good pets because they provide companionship and teach children responsibility.
• Because dogs provide companionship and teach responsibility, they make good pets—even though they require a huge commitment.

TIP: Use action verbs and limit personal pronouns such as I, me, my, we, and our .

2. The Body of the Essay Supports the Thesis Statement

After the introduction, your teen needs to develop the essay’s three main points, each in its own paragraph. These paragraphs must support the thesis statement and flesh out the argument. So make sure students know how to defend or explain their claims using facts and evidence .

All three body paragraphs have the same structure: topic sentence, supporting details, and closing sentence.

For older high school kids, the body paragraphs make a great place to practice in-text citations. It’s worth mentioning tha t end notes have gone to their grave , so homeschoolers must learn parenthetical documentation instead.

I required my students to use Diane Hacker’s Pocket Style Manual on how to format essays. It’s easy to use and not overwhelming .

3. A Strong Conclusion Wraps Up the Essay

After you’ve said everything you want to say, how do you wrap up the five-paragraph essay?

In speech class, my professor drummed into us: “Tell them what you’re going to tell them. Tell them. And then tell them what you told them.” The conclusion forms the “tell them what you told them” paragraph.

This final paragraph is more than just a summary of the paper ; it provides a solid conclusion  that affirms the reader’s new knowledge or understanding of the contents. To keep it interesting, it should move right along. Students shouldn’t rehash the details they covered in the intro and body paragraphs.

We want to leave the reader with a BANG! The conclusion wraps up the essay in tidy package.

Transition from Body to Conclusion

Start the conclusion with a transitional topic sentence—a general statement that flows nicely from the last sentence of the previous paragraph.

Restate the Thesis in a New Way

After the topic sentence, restate the thesis. Students should not simply copy and paste the same thesis statement. Instead, teach them to reword it to leave the reader with a fresh and memorable understanding of the essay’s theme.

Tie It All Together

Essays end with a closing sentence. The closing sentence should tie back to the hook from the intro, perhaps by referencing the same example, reiterating a word or a phrase, or ending with a new quote. When possible, the closing sentence should also tie into the title.

The 5-paragraph essay remains a time-tested and essential tool in your students’ learning toolbox. Once they have the structure down pat, they can write a wide variety of essays with the same tools.

You can teach the 5-paragraph essay in your homeschool, and you don’t have to conquer it alone. As you teach writing and essay skills, WriteShop is here to help!

As  WriteShop’s curriculum consultant , Misti Lacy draws from her years of experience as a veteran writing teacher and homeschool mom to help you build a solid writing foundation. Whether you’re  deciding on products for your family , exploring our program for your  school or co-op , or needing someone to walk you through your WriteShop curriculum, Misti takes the fear out of teaching writing . 

Let’s Stay Connected!

Subscribe to our newsletter.

• Gift Guides
• Reluctant or Struggling Writers
• Special Needs Writers
• Brainstorming Help
• Editing & Grading Help
• Encouragement for Moms
• Writing Games & Activities
• Writing for All Subjects
• Essays & Research Papers
• College Prep Writing
• Grammar & Spelling
• Writing Prompts

Recent Posts

• An exciting announcement!
• 10 Stumbling Blocks to Writing in Your Homeschool
• Help kids with learning challenges succeed at homeschool writing
• How to correct writing lessons without criticizing your child

Ideas for Teaching How to Write a Paragraph

• Differentiation , Planning , Strategies , Writing

Many students struggle to put together one paragraph, let alone the multi-paragraph essays that common core requires them to do. Since they often lack the ability to put together a paragraph, writing often becomes a chore and they lack the motivation to do any form of writing. So just how do we get out of this writing rut so that students can become engaged and learn to write a paragraph (and eventually the required multi-paragraphs)?

Ideas to Teach Writing a Paragraph

Start with the basics. When teaching students about paragraphs, we talk about the hard and fast rules, such as indenting, having approximately 3-5 sentences, and the structure of it. While I know paragraphs are not set in stone at 3-5 sentences, nor do they always have a main idea as the topic sentence, I like to give my students structure for the foundations and then as they progress expand a bit more with the “hard and fast” rules.

The Parts of a Paragraph. After we discuss the general “rules” of paragraphing, I then provide my students with sample paragraphs to analyze for the basic structure. We go through paragraphs and highlight the topic sentence, the supporting details, and the concluding sentence. I want students to start noticing that paragraphs always have a main idea and supporting details. Not only is this important for writing, but it helps them when it comes to reading. When you pull out highlighters, students are instantly engaged !

Sorting Strips Once students have gotten down to the basic structure of paragraphs, then I provide students with a paragraph that has been cut up into sentence strips. Each sentence of the paragraph is on its own strip and students have to determine which strip is likely the topic sentence, the concluding sentence, and supporting details. They also place the strips in order. This helps students take note of the characteristics of each type of sentence. For instance, a student is more likely to notice that a main idea sentence will sound very different from a supporting detail or a concluding sentence. This also helps them practice the flow of a paragraph.

Turning Lists into Paragraphs Once students really have the foundations of a basic paragraph down, I then start focusing on each individual piece. For instance, I might provide students with many supporting details and have them try to come up with a topic sentence. I may also provide students with a list of topic sentences and they have to brainstorm a list of supporting details. Another idea is to provide students with an object and have them make a list of ways it can be used. Then I work with my students to turn these lists into a paragraph.

Check out these related products

Writing Frames Another option I remember learning while attending an Anita Archer conference (and is very successful for emergent writers) is using writing frames. In this case, the basic premise of a paragraph is set up for a student and they fill in the examples. See below.

Guided Writing After we have experimented a bit with creating topic sentences and supporting details, then I guide my students into writing their own paragraphs off the top of their heads. I walk them through each part step-by-step. We usually create a booklet together to make it motivating.

Final Writing with Graphic Organizers Once we have worked together through these steps of scaffolding , I then provide students with a graphic organizer and let them loose to create their own paragraph independently . I try to make it engaging by having them create their own Paragraph Sandwich. My students really enjoy this activity and they turn out really great!

Hopefully, you can find some of these ideas useful in teaching your students about writing paragraphs. After students have the basic structure of writing paragraphs down, then you can begin moving into stretching those paragraphs with elaboration and much more!

Looking for a quick and easy way to implement these activities? You can  find them (plus more!) in my store  for an inexpensive price!

FIND IT NOW!

Check me out on tpt.

CHECK THESE OUT

Three Types of Rocks and Minerals with Rock Cycle Circle Book

Partitioning Shapes Equal Share Fractions Halves, Thirds, Fourths Math Puzzles

Want to save time?

COPYRIGHT © 2016-2024. The Owl Teacher | Privacy page | Disclosure Page | Shipping | Returns/Refunds

BOGO on EVERYTHING!

How to Write a Five-Paragraph Essay (with Examples)

By: Author Marcel Iseli

Posted on Last updated: April 13, 2023

Sharing is caring!

Writing can be either exciting or exacting depending on one’s patience and passion, hence not everyone’s cup of joe.

That said, writing even a short, snappy five-paragraph essay can require a bit of time and attention – at least for those who are not used to it.

Luckily enough, that’s what we’re dealing with today. If you’re paying enough attention, this post’s intro should already be giving you some idea of how to start one.

Writing a five-paragraph essay

• Write the hook and thesis statement in the first paragraph.
• Write the conflict of the essay in the second paragraph.
• Write the supporting details of the conflict in the third paragraph.
• Write the weakest arguments in the fourth paragraph.
• Write the summary and call-to-action prompt in the fifth paragraph.

Determining what to include in a five-paragraph essay

While there are hundreds, even thousands, of ways to write a five-paragraph essay, there are some universal processes that we can meanwhile follow.

The overall organization of the writer’s thought matters in any kind of writing piece. So, it is necessary that you fully understand what you’re being asked to do before writing a piece.

Topic, purpose, audience, rhetorical appeal, and length

Understanding what needs to be done means knowing your essay’s topic, purpose, audience, rhetorical appeal, as well as desired length.

Topic means the subject matter entailed by your essay, such as when you are asked to write an essay about yourself or people you admire.

“Purpose” means the core intent of writing your essay, which can be done in an argumentative, expository, narrative, or descriptive way.

“Audience” refers to your target reader or readers. You would know this by answering the question “Who will read and assess my essay?”

A “rhetorical appeal” is the “persuasive act” of your essay. It demonstrates the qualities of your essay that make it worth reading and even sharing.

Meanwhile, “length” means the measurable elements in your essay, such as the number of characters, words, sentences, or paragraphs.

Knowing these five important parts should give a head start when you write an essay, no matter what kind of setting it is.

If you are writing to apply for a particular job role, you may also be required to write a cover letter for your essay by the organization.

The possibility of this particular scenario should be enough to let us realize how important writing skills are, which is why we need to deliberately learn them at school.

In some cases, students may just mindlessly think that it is okay to cut and paste texts from online sources because their teacher won’t find out anyway.

Contrary to common belief, teachers, especially the most seasoned and passionate ones actually do read their students’ work.

So, by no stretch, one might actually end up writing an apology letter for plagiarism if and when worse comes to worst.

The key to preventing this tragedy is to always bear in mind that sincerity evokes originality; when you love what you do, you can always generate fresh ideas.

Meanwhile, the key to creating a good essay is to pre-plan what you need to include as well as what you need to exclude in the writing piece.

Now, how can we manifest all the things explained above in a five-paragraph essay? Let us find out below.

Paragraph 1 of the five-paragraph essay — The “plot”

The first or introductory paragraph can be considered the “plot” of the essay. This is where you would need to write your hook and thesis statement.

The hook is what grabs your readers’ attention from the start. It should be written in such a way that it anchors or “hooks” them to what they are reading.

You can use a general or all-inclusive idea for this part to make your readers relate to what you are trying to say.

Example: 

Meanwhile, the thesis statement briefly tells your readers what your topic is all about. In other words, it explains what they need to expect from the piece.

The thesis statement is perhaps the most important element that you should never miss out on because it is what links your thoughts as a writer to your audience.

Within the intro paragraph, you could add other ideas that would link your hook to your thesis statement, depending on the impression you would like to evoke.

Paragraph 2 of the five-paragraph essay — The “plot’s conflict”

The second paragraph is where you slowly build the tension and explain your plot in more detail. We might as well call it the conflict of the story you are trying to tell.

Here, you should be able to clearly explain your strongest point of argument. For narrative essays, this is where you write the most crucial part of the experience you’ve had.

You should also introduce the setting as well as other relevant characters in this part, such as this one:

Then, you have to carefully elaborate on the most critical part of the story. If you could be more “visual” with your words, that would also help more in letting your audience connect to your essay.

In the next example, you would see a person vs. nature conflict where the character struggles with the environmental forces.

Paragraph 3 of the five-paragraph essay — The “conflict’s sidekick”

As you may figure, paragraph three is a further elaboration of your second paragraph, which is why we could simply call it the “conflict’s support.”

Here, you need to clearly establish how the current paragraph connects to the previous one and end it in such a way that it also links to the succeeding paragraph.

This is also where you give more meticulous details about the conflict to let your readers understand the “whys.”

The airbag from the driver’s side malfunctioned and deployed on its own, causing Uncle Vince to lose control. I later found out too that Uncle Vince wanted to learn how to drive so he asked my dad to teach him.

Paragraph 4 of the five-paragraph essay — The “freebie”

The fourth paragraph is where you would put the least important part of your story, at least relatively speaking.

You should put here your weakest or most irrelevant argument and example details. Or, you could also provide a different point of view to your audience.

Feel free to shift from the past to the present times in this part to pull your audience back to reality.

If relevant, you could also add some more emotional details like guilt or regret, such as the following:

Then lastly, you should be able to establish a link to your last paragraph or conclusion. The example below has a lot to do with the ending of the story, which talks about realizations.

Paragraph 5 of the five-paragraph essay —  The “farewell”

The “farewell” or conclusion part basically needs to summarize your entire essay’s key ideas. It should also be able to draw a link to the plot or intro paragraph.

In other words, the fifth or last paragraph should bear ideas that reconcile the previous paragraphs, especially the first.

If you are sick and tired of using almost the same words and phrases in your essay’s conclusion part, you had better check out other alternatives for “in conclusion” to sound less repetitive.

There are actually a lot of effective transition words for your conclusion to choose from in the English lexicon, so feel free to experiment some time.

Then, you can talk about the positive things that happened after the storm to leave a positive message to your readers.

Last but not least, you can completely end your essay with a call-to-action prompt that urges your readers to “do” something about what they have just read.

You can easily do this by answering the question “What do I want my audience to do after reading my story?” such as in the example below:

Five-Paragraph Essay — Sample Essay

To really see how all the parts above fit together, here’s a complete example essay containing all the elements elaborated on earlier.

In this essay, the topic is “the greatest challenge in my life,” and it has a narrative purpose. The target audience is the general public, while the rhetorical appeal is “pathos” or emotional.

This is a five-paragraph essay with approximately six hundred words including the title that talks about the loss of a loved one.

❡ 2 One sunny afternoon in the early nineties, I was playing catch with my neighbors Dylan, Abby, and my adorable labrador Rio. We did love playing by the road because it annoys old Miss Vacuum Lady from across the street – she nags at us all the time. As I was throwing the beanbag for Rio to catch, I noticed an unfamiliar blue Ford Explorer coming. It was running funny, so I thought the driver was just trying to do some tricks. I managed to throw the beanbag nicely, and Rio ran with all his might to catch it before it falls. A few seconds later, I heard a deafening screech and saw the blue Explorer crashing onto the maple tree outside Miss Vaccum Lady’s house. I only got scared when I realized that the car was actually trying to avoid me and that it chose to crash onto the tree instead.

❡ 3 A few moments later, I saw my mom and my other neighbors rushing outside to see what had just happened. I and my friends ran towards the car too until I heard a loud scream coming from my mom. Then all of a sudden, it came to me. My dad was in the passenger seat of that car, while his fifteen-year-old younger brother Uncle Vince was in the driver’s seat. Miraculously, Uncle Vince only had a scratch on his arm, yet my dad was neither moving nor breathing anymore – he died at that exact moment. The airbag from the driver’s side malfunctioned and deployed on its own, causing Uncle Vince to lose control. I later found out too that Uncle Vince wanted to learn how to drive so he asked my dad to teach him. 

❡ 4 Everything changed after that day. No one was there to fix our busted lights anymore. No one was there to repair the roof when it leaked. I never even got to learn to play the guitar – dad had promised to buy me one on my birthday that same week he passed. For years and years, I kept blaming myself for what had happened that I never played catch again. They say “mothers know best,” and that’s a fact. Mom helped me get through all the pain and trauma even if she was also hurting a lot deep inside. For that reason, I never hesitate to trade my life for hers.

❡ 5 True enough, losing my dad has been the greatest challenge in my life. But, as time passed by, I also realized that seeing my mom suck it all up and pretend that she was fine even if she was hurting so much more. So, I made a decision never to waste a single moment with her. I have also managed to become an advocate for an organization that helps single mothers raise their kids. If there’s one thing I’ve learned from what happened, that is parental love is definitely the most selfless act in this world. So, never miss a beat with yours while you can.

Frequently Asked Questions on “How to Write a Five-paragraph Essay”

What are some good topics for a five-paragraph essay.

Social justice issues like healthcare, education, prejudice, and violence; environmental issues like climate change, resource depletion, wildlife protection, and natural disasters; life topics like near-death experiences, hobbies, and traveling are great topics for a five-paragraph essay.

How do you start a five-paragraph essay?

To start a five-paragraph essay, a hook and thesis statement are necessary. A hook can be a reflective assumption, a quote from a famous person, or a rhetorical question, while a thesis statement is a brief explanation of the essay’s topic.

How many sentences is a five-paragraph essay?

A five-paragraph essay is made of twenty-five to forty-five sentences. This structure is made up of five hundred to around one thousand words.

Writing requires time, patience, and dedication. That said, a read-worthy piece cannot come into form mindlessly but rather meticulously.

Join us again next time for some more interesting writing and other language-related hacks that can help you walk more easily through life.

Hey fellow Linguaholics! It’s me, Marcel. I am the proud owner of linguaholic.com. Languages have always been my passion and I have studied Linguistics, Computational Linguistics and Sinology at the University of Zurich. It is my utmost pleasure to share with all of you guys what I know about languages and linguistics in general.

Related posts:

• How to Write an Essay about Yourself — The Ultimate Guide
• How to Write a Cover Letter for an Essay in 13 Steps
• How to Write an Open Letter — Three Easy Steps
• Thank You Note for Engagement Gift Etiquette & Examples
• How to Write a Thank You Note to the Mailman (with Examples)

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

How to Teach Essay Writing

Last Updated: June 26, 2023 Fact Checked

This article was co-authored by Christopher Taylor, PhD . Christopher Taylor is an Adjunct Assistant Professor of English at Austin Community College in Texas. He received his PhD in English Literature and Medieval Studies from the University of Texas at Austin in 2014. There are 12 references cited in this article, which can be found at the bottom of the page. This article has been fact-checked, ensuring the accuracy of any cited facts and confirming the authority of its sources. This article has been viewed 88,767 times.

Teaching students how to write an essay is a big undertaking, but this is a crucial process for any high school or college student to learn. Start by assigning essays to read and then encourage students to choose an essay topic of their own. Spend class time helping students understand what makes a good essay. Then, use your assignments to guide students through writing their essays.

Choosing Genres and Topics

• Narrative , which is a non-fiction account of a personal experience. This is a good option if you want your students to share a story about something they did, such as a challenge they overcame or a favorite vacation they took. [2] X Trustworthy Source Purdue Online Writing Lab Trusted resource for writing and citation guidelines Go to source
• Expository , which is when you investigate an idea, discuss it at length, and make an argument about it. This might be a good option if you want students to explore a specific concept or a controversial subject. [3] X Trustworthy Source Purdue Online Writing Lab Trusted resource for writing and citation guidelines Go to source
• Descriptive , which is when you describe a person, place, object, emotion, experience, or situation. This can be a good way to allow your students to express themselves creatively through writing. [4] X Trustworthy Source Purdue Online Writing Lab Trusted resource for writing and citation guidelines Go to source
• Argumentative or persuasive essays require students to take a stance on a topic and make an argument to support that stance. This is different from an expository essay in that students won't be discussing a concept at length and then taking a position. The goal of an argumentative essay is to take a position right away and defend it with evidence. [5] X Trustworthy Source Purdue Online Writing Lab Trusted resource for writing and citation guidelines Go to source

• Make sure to select essays that are well-structured and interesting so that your students can model their own essays after these examples. Include essays written by former students, if you can, as well as professionally written essays.

Tip : Readers come in many forms. You can find readers that focus on a specific topic, such as food or pop culture. You can also find reader/handbook combos that will provide general information on writing along with the model essays.

• For example, for each of the essays you assign your students, you could ask them to identify the author's main point or focus, the structure of the essay, the author's use of sources, and the effect of the introduction and conclusion.
• Ask the students to create a reverse outline of the essay to help them understand how to construct a well-written essay. They'll identify the thesis, the main points of the body paragraphs, the supporting evidence, and the concluding statement. Then, they'll present this information in an outline. [8] X Research source

• For example, if you have assigned your students a narrative essay, then encourage them to choose a story that they love to tell or a story they have always wanted to tell but never have.
• If your students are writing argumentative essays, encourage them to select a topic that they feel strongly about or that they'd like to learn more about so that they can voice their opinion.

Explaining the Parts of an Essay

• For example, if you read an essay that begins with an interesting anecdote, highlight that in your class discussion of the essay. Ask students how they could integrate something like that into their own essays and have them write an anecdotal intro in class.
• Or, if you read an essay that starts with a shocking fact or statistic that grabs readers' attention, point this out to your students. Ask them to identify the most shocking fact or statistic related to their essay topic.

• For example, you could provide a few model thesis statements that students can use as templates and then ask them to write a thesis for their topic as an in-class activity or have them post it on an online discussion board.

Tip : Even though the thesis statement is only 1 sentence, this can be the most challenging part of writing an essay for some students. Plan to spend a full class session on writing thesis statements and review the information multiple times as well.

• For example, you could spend a class session going over topic sentences, and then look at how the authors of model essays have used topic sentences to introduce their claims. Then, identify where the author provides support for a claim and how they expand on the source.

• For example, you might direct students to a conclusion in a narrative essay that reflects on the significance of an author's experience. Ask students to write a paragraph where they reflect on the experience they are writing about and turn it in as homework or share it on class discussion board.
• For an expository or argumentative essay, you might show students conclusions that restate the most important aspect of a topic or that offer solutions for the future. Have students write their own conclusions that restate the most important parts of their subject or that outline some possible solutions to the problem.

Guiding Students Through the Writing Process

• Try giving students a sample timeline for how to work on their essays. For example, they might start brainstorming a topic, gathering sources (if required), and taking notes 4 weeks before the paper is due.
• Then, students might begin drafting 2 weeks before the paper is due with a goal of having a full draft 1 week before the essay's due date.
• Students could then plan to start revising their drafts 5 days before the essay is due. This will provide students with ample time to read through their papers a few times and make changes as needed.

• Freewriting, which is when you write freely about anything that comes to mind for a set amount of time, such as 10, 15, or 20 minutes.
• Clustering, which is when you write your topic or topic idea on a piece of paper and then use lines to connect that idea to others.
• Listing, which is when you make a list of any and all ideas related to a topic and ten read through it to find helpful information for your paper.
• Questioning, such as by answering the who, what, when, where, why, and how of their topic.
• Defining terms, such as identifying all of the key terms related to their topic and writing out definitions for each one.

• For example, if your students are writing narrative essays, then it might make the most sense for them to describe the events of a story chronologically.
• If students are writing expository or argumentative essays, then they might need to start by answering the most important questions about their topic and providing background information.
• For a descriptive essay, students might use spatial reasoning to describe something from top to bottom, or organize the descriptive paragraphs into categories for each of the 5 senses, such as sight, sound, smell, taste, and feel.

• For example, if you have just gone over different types of brainstorming strategies, you might ask students to choose 1 that they like and spend 10 minutes developing ideas for their essay.

• Try having students post a weekly response to a writing prompt or question that you assign.
• You may also want to create a separate discussion board where students can post ideas about their essay and get feedback from you and their classmates.

• You could also assign specific parts of the writing process as homework, such as requiring students to hand in a first draft as a homework assignment.

• For example, you might suggest reading the paper backward 1 sentence at a time or reading the paper out loud as a way to identify issues with organization and to weed out minor errors. [21] X Trustworthy Source University of North Carolina Writing Center UNC's on-campus and online instructional service that provides assistance to students, faculty, and others during the writing process Go to source
• Try peer-review workshops that ask students to review each others' work. Students can work in pairs or groups during the workshop. Provide them with a worksheet, graphic organizer, or copy of the assignment rubric to guide their peer-review.

Tip : Emphasize the importance of giving yourself at least a few hours away from the essay before you revise it. If possible, it is even better to wait a few days. After this time passes, it is often easier to spot errors and work out better ways of describing things.

Community Q&A

• Students often need to write essays as part of college applications, for assignments in other courses, and when applying for scholarships. Remind your students of all the ways that improving their essay writing skills can benefit them. Thanks Helpful 0 Not Helpful 0

You Might Also Like

• ↑ https://owl.purdue.edu/owl/general_writing/academic_writing/essay_writing/index.html
• ↑ https://owl.purdue.edu/owl/general_writing/academic_writing/essay_writing/narrative_essays.html
• ↑ https://owl.purdue.edu/owl/general_writing/academic_writing/essay_writing/expository_essays.html
• ↑ https://owl.purdue.edu/owl/general_writing/academic_writing/essay_writing/descriptive_essays.html
• ↑ https://owl.purdue.edu/owl/general_writing/academic_writing/essay_writing/argumentative_essays.html
• ↑ https://wac.colostate.edu/jbw/v1n2/petrie.pdf
• ↑ https://www.uww.edu/learn/restiptool/improve-student-writing
• ↑ https://twp.duke.edu/sites/twp.duke.edu/files/file-attachments/reverse-outline.original.pdf
• ↑ https://www.niu.edu/citl/resources/guides/instructional-guide/brainstorming.shtml
• ↑ https://writingcenter.unc.edu/faculty-resources/tips-on-teaching-writing/situating-student-writers/
• ↑ https://writingcenter.unc.edu/faculty-resources/tips-on-teaching-writing/in-class-writing-exercises/
• ↑ https://writingcenter.unc.edu/tips-and-tools/revising-drafts/

About This Article

• Send fan mail to authors

Reader Success Stories

Oct 13, 2017

Did this article help you?

Jul 11, 2017

Jan 26, 2017

Featured Articles

Trending Articles

Watch Articles

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

Get all the best how-tos!

Sign up for wikiHow's weekly email newsletter

Should We Teach the Five-Paragraph Essay?

• Share article

Headline: As Children’s Freedom Has Declined, So Has Their Creativity. Biggest decline? Creative elaboration--expanding on ideas in novel and creative ways. Have we done this to children, with “eminently gradable” assignments? Josh Boldt, who teaches writing at the University of Georgia in Athens, shares his thoughts:

College writing teachers hate the five-paragraph essay. According to Writing Analytically, the writing guide used by my first year composition department, a faculty survey conducted prior to publication indicated a consensus among college writing professors that “students are coming [to college] prepared to do five-paragraph themes and arguments but [are] radically unprepared in thinking analytically.”

The writing guide takes a sharp stance against the five-paragraph essay, claiming that its “rigid, arbitrary, and mechanical organizational scheme values structure over just about everything else, especially in-depth thinking” (7). The text completely dismisses the form, arguing that any value it holds as a helpful learning strategy is negated by its damaging long-term effects on creative thought. The writers, David Rosenwasser and Jill Stephens, argue that the format “handicaps” young writers by teaching them a method that “runs counter to virtually all of the values and attitudes that they need in order to grow as writers and thinkers--such as respect for complexity, tolerance of

uncertainty, and the willingness to test and complicate rather than just assert ideas” (8). Of all the writing handbooks I’ve read and taught, Writing Analytically is unquestionably the most excoriative of the five-paragraph form. Is its critique too harsh?

My practical observations of freshman comp pedagogy confirm the assertions of Rosenwasser and Stephens. I often hear college writing teachers bemoaning the five-paragraph essay for its tendency to restrict creativity and to encourage a tunnel vision approach to essay writing. Many of my colleagues make it a personal mission to “unteach” the habits students bring to the classroom during their first year of college.

Personally, I don’t consider my role to be quite so extreme. But, I have seen the negative effects of the form firsthand. I’ve had students ask which points should be cut in order to trim the body paragraphs down to the requisite three. I’ve also seen many page-long paragraphs jammed full of topics, a clear sign that the student is trying to force the information into the proper formulaic structure. When students think the five-paragraph form is the only acceptable way to write an essay, it can be paralyzing and creatively-stifling, which leads me to my primary concern with the form.

The worst offense of the five-paragraph essay is its ignorance of the fact that good writing must also be interesting. Professional writers shirk the format in favor of a looser and more creative style that engages readers rather than lecturing to them, as the five-paragraph form often does. On this point, I agree with the Writing Analytically denouncement. Creativity and voice take a backseat to structure. I want to see a voice in my students’ writing, and the structural limitations of the five-paragraph form inhibit the development of a unique writing process.

The antipathy ultimately comes down to our encounters with students who have become imprisoned by the method and have lost the ability to write and think creatively (or maybe never developed it). Nobody wants that. What began as a good thing becomes a crutch that students are reluctant to give up for fear of falling. I believe this is a big part of why the format is so widely criticized in freshman writing courses.

The five-paragraph essay isn’t all bad. The value lies in its usefulness as a teaching tool and as an entry-level organizational strategy for young writers. It works great as a foundation upon which students can later build. Incorporating outside research, crafting topic sentences, and using transitions are all strengths of the format. Thomas E. Nunnally has also explored the merits of the form even as he critiques them in his essay “Breaking the Five-Paragraph Theme Barrier.” As Nunnally notes “students learn to do one thing at a time, such as form a thesis statement, before putting all the parts together, and their progress can be monitored and evaluated piecemeal,” which makes the form “practical to teach and eminently gradable” (68). When composition pedagogy isolates these independent steps and teaches them as a function of the writing process, the structure of the five-paragraph essay can be immensely valuable.

Bottom line: the five-paragraph essay’s inherent prioritization of structure over style can have long-term damaging effects on students who never learn to move beyond it, but teaching the form provides a foundation upon which students can scaffold their writing as they grow intellectually. It allows teachers to emphasize the role of research and support, and it also provides a convenient framework for teaching basic writing skills like the use of transitions and topic sentences. College writing teachers and handbooks pick on the form and, to a certain extent, the criticism is deserved. Despite the controversy though, the five-paragraph essay isn’t all bad--as long as teachers remember that it works best as a method of teaching other skills rather than as a system of writing in and of itself.

What are your thoughts on the five-paragraph essay?

The opinions expressed in Teacher in a Strange Land are strictly those of the author(s) and do not reflect the opinions or endorsement of Editorial Projects in Education, or any of its publications.

Sign Up for EdWeek Update

You are using an outdated browser. Please upgrade your browser or activate Google Chrome Frame to improve your experience.

ESL Essay Writing: 7 Important Tips to Teach Students Plus Resources for Writing Lessons

“Every good story has a beginning, a middle and an end.”

This is true for a good essay, too.

An essay needs a coherent structure to successfully articulate its arguments. Strong preparation and planning is crucial to providing that structure.

Of course, essay writing can be challenging for ESL students. They must order their thoughts and construct their arguments—all in their second language.

So, here are seven ESL essay writing tips that will allow your students to weave together a coherent and persuasive essay, plus teacher resources for writing activities, prompts and lessons!

1. Build the Essay Around a Central Question

2. use the traditional 5-paragraph essay structure, 3. plan the essay carefully before writing, 4. encourage research and rewriting, 5. practice utilizing repetition, 6. aim to write a “full circle” essay, 7. edit the essay to the end, esl essay writing resources.

Download: This blog post is available as a convenient and portable PDF that you can take anywhere. Click here to get a copy. (Download)

Encourage your students to build all their writing around one central question.

That central question is the engine of the writing—it should drive everything!

If a word or sentence is not assisting that forward motion toward the explication of that question and its possible answers, then it needs to be reworded, rephrased or just plain cut out and discarded.

Lean writing is merciless. Focusing on a central question throughout the prewriting, writing and rewriting stages helps develop the critical faculties required to discern what to keep and what to throw away.

Providing a clear structure for the student to approach essay writing can do a lot to build their confidence. The 5-paragraph essay, or “hamburger” essay, provides that clear structure for ESL writers.

Generally, this structure employs five separate paragraphs for the entire essay. Each paragraph serves a specific purpose, melding together to form a coherent whole:

• Paragraph 1: The introductory paragraph. This includes the thesis statement, orientating the reader to the purpose of the essay.
• Paragraphs 2 to 4: The body paragraphs. These make individual points that are further backed up by various forms of evidence.
• Paragraph 5:  The conclusion paragraph. This provides a summation of the arguments and a final statement of the thesis.

While students do not need to rigidly follow this format forever, the simple structure outlined above can serve as excellent training wheels for your writers.

Using the 5-paragraph structure as outlined above makes planning clear cut.

Once they have their theses and are planning their paragraphs, share with the students the ridiculously useful acronym P.E.E. This stands for Point, Explanation and Evidence.

Each body paragraph should make a point or argument in favor of the central thesis, followed by an explanation of this point and relevant evidence to back it up.

Students can make note of all their points, explanations and evidence before they start writing them in essay form. This helps take away some of the pressure ESL writers feel when faced with a blank page.

Extol the necessity for students to constantly refer to their planning. The mind-mapping techniques popularized by Tony Buzan can be useful at the planning stage and make for easy reference points to ensure focus is maintained throughout the essay.

Having a visual reference such as this can help ensure that your student-writers see each piece of the whole as well as that elusive “bigger picture,” so it becomes a case of seeing the forest and the trees!

Just as planning is crucial, so too is research.

Often ideas or connections do not occur until the writing process has begun. This is a good thing! Essay writing is a creative act, so students can have more ideas along the way and work them in as they go.

The key is to always be able to back up these ideas. Students who have done their research on their subject will be much more confident and articulate in expressing their arguments in their writing.

One way you can help students with context and research is to show relevant video content via FluentU . This language learning program uses authentic videos made by and for native speakers to help students learn English.

You can watch videos as a class or assign them directly to students for individual viewing. Videos come equipped with interactive bilingual subtitles and other learning tools such as multimedia flashcards and personalized quizzes so you can see how each student is doing.

No matter how your students do their research, the important thing is that they explore and understand their topic area before beginning the big task of writing their essay.

Even with thorough planning and research, writing oneself into a linguistic cul-de-sac is a common error. Especially with higher-level students, unforeseen currents can pull the student-writer off course.

Sometimes abandoning such a sentence helps. Going back to the drawing board and rewriting it is often best.

Students can be creative with their sentence structures   when expressing simpler ideas and arguments. However, when it comes to more complex concepts, help them learn to use shorter sentences to break their arguments into smaller, more digestible chunks.

Essay writing falls firmly in the camp of non-fiction. However, that doesn’t mean that essay writers can’t use some of the techniques more traditionally associated with fiction, poetry and drama .

One technique that’s particularly useful in essay writing is repetition. Just as poetry relies heavily on rhythm, so too does argument. Repetition can provide that sense of rhythm.

This is because written language has its origins in oral language. Think of the great orators and demagogues and their use of repetition. Speechwriters, too, are well aware of the power of repetition.

The writing principle of the “rule of 3” states that ideas expressed in these terms are more convincing and memorable. This is true of both spoken and written words and the ideas they express. Teach your students to use this method in their essay writing.

The very structure of the 5-paragraph essay lends itself to planning for this repetition, in fact. Each idea that is explored in a body paragraph should be outlined first in the introductory paragraph.

Then, the single body paragraph devoted to the idea will explore it at greater length, supported by evidence. And the third rap of the hammer occurs in the summation of the concluding paragraph, driving the point securely and convincingly home.

As mentioned at the start of this post, every good essay has a beginning, a middle and an end.

Each point made, explained and supported by evidence is a step toward what the writing teacher Roy Peter Clark calls “closing the circle of meaning.”

In planning for the conclusion of the essay, the students should take the opportunity to reaffirm their position. By referring to the points outlined in the introduction and driving them home one last time, the student-writer is bringing the essay to a satisfying full circle.

This may be accomplished by employing various strategies: an apt quotation, referring to future consequences or attempting to inspire and mobilize the reader.

Ending with a succinct quotation has the double benefit of lending some authoritative weight to the argument while also allowing the student to select a well-written, distilled expression of their central thesis. This can make for a strong ending, particularly for ESL students.

Often the essay thesis will suggest its own ending. If the essay is structured around a problem, it’s frequently appropriate to end the essay by offering solutions to the problem and outlining potential consequences if those solutions are not followed.

In the more polemical type of essay, the student may end with a call to arms, a plea for action on the part of the reader.

The strategy chosen by the student will depend largely on what fits the central thesis of their essay best.

For the ESL student, the final edit is especially important.

It offers a final chance to check form and meaning. For all writers, this process can be daunting, but more so for language students.

Often, ESL students will use the same words over and over again due to a limited vocabulary. Encourage your students to employ a thesaurus in the final draft before submission. This will freshen up their work, making it more readable, and will also increase their active vocabulary in the long run!

Another useful strategy at this stage is to encourage students to read their work aloud before handing it in.

This can be good pronunciation practice , but it also provides an opportunity to listen for grammatical errors. Further, it helps students hear where punctuation is required in the text, helping the overall rhythm and readability of the writing.

To really help your students become master essay writers, you’ll want to provide them with plenty of opportunities to test and flex their skills.

Writing prompts and exercises are a good place to start:

Descriptive writing activities encourage students to get creative and use their five senses, literary devices and diverse vocabulary. Read on for eight descriptive writing…

https://www.fluentu.com/blog/educator-english/esl-writing-projects/ https://www.fluentu.com/blog/educator-english/esl-picture-description/

Giving good ESL writing prompts is important because inspiring prompts inspire students to write more and writing more is how they improve. Read this post to learn 50…

You’ll likely also want to teach them more about the mechanics of writing :

Are you looking for ESL writing skills to share with your ESL students? In this guide, you’ll find different ESL writing techniques, such as helping students understand…

Would you like to introduce journal writing into your ESL classes? Fantastic idea! Here are 9 essential tips to make it creative, engaging and fun.

https://www.fluentu.com/blog/educator-english/esl-writing-lessons/

Essays are a great way not only for students to learn how the language works, but also to learn about themselves.

Formulating thoughts and arguments about various subjects is good exercise for not only the students’ linguistic faculties, but also for understanding who they are and how they see the world.

Enter your e-mail address to get your free PDF!

We hate SPAM and promise to keep your email address safe

Perfect Paragraph Writing: The Ultimate Guide

Perfect paragraph writing is easy

A glance around any shopping mall crowded with teenagers on school break would suggest that our young people spend a reasonable amount of time writing. Sure, most of this writing is done with their thumb on a screen, but it’s still writing.

Yes, but tapping out a 280-character Tweet isn’t the ideal route to constructing well-organized writing pieces. To prepare our students to write coherently, they need to understand how to organize their ideas on paper. The ability to write strong paragraphs is an essential part of this.

Unfortunately, recent studies show that surprisingly few college graduates can achieve this, despite writing and communications skills being the most requested job requirements across all industries – including engineering and IT. Clearly, there is a pressing need for a strong focus on writing skills in the classroom.

For the most part, we live in a post-illiterate world. We can all read and write. This is undoubtedly a great thing, but it can lead to complacency for some of our students. At times there is an unwillingness to learn the craft of writing. A reluctance to learn how to organize writing in favor of just plunging in. The cost of this devil-may-care approach is, most often, clarity and coherence.

Fortunately, teaching what appears to be an apparently amorphous skill, such as writing, can be broken down into transparent step-by-step processes, and this includes how to write well-structured, coherent paragraphs.

A COMPLETE UNIT ON TEACHING PARAGRAPH WRITING

This complete PARAGRAPH WRITING UNIT takes students from zero to hero over FIVE STRATEGIC LESSONS to improve PARAGRAPH WRITING SKILLS through PROVEN TEACHING STRATEGIES.

BE SURE TO READ OUR COMPLETE GUIDE TO SENTENCE STRUCTURE

Before you can master paragraph writing, you will need a good understanding of constructing meaningful sentences.

We have a complete guide to sentence structure for teachers and students. Click here to view.

WHAT IS A PARAGRAPH? A DEFINITION

To teach our students how to effectively write paragraphs we need to clearly define what a paragraph is. Assuming your students understand how to construct a solid sentence, paragraphs are the next step to creating a lucid piece of writing. They are the main building blocks in the construction of a comprehensible text. 

Paragraphs are a group of single sentences united by a single topic or idea that help keep writing organized. They help the writer organize their thoughts during the writing process and further help the reader follow the thread of those thoughts in the reading. How paragraphs are used will depend, to some extent, on the genre of writing the students are engaged in, but any piece of writing longer than a few sentences will generally benefit from being organized into paragraphs. 

A simple way to help students to recognize paragraphs is to have them count the number of paragraphs on a page, either in a book or projected onto the whiteboard. Have them note too, that there are two ways to delineate a paragraph: indentation or skipping a line. Both methods are fine, just ensure the student chooses one method and sticks to it. If you indent there is no need to skip a line – and vice versa.

Writing starts with planning. It’s a bit like gazing at a beautiful cathedral or temple we visit on vacation. Once it was obscured by scaffolding and busy workers that were eventually peeled away to reveal the beauty beneath. The planning stage of writing serves the same purpose as architectural blueprints, that is: to foresee the problems of construction and solve them before building begins. It is often helpful to consider paragraphs as distinct units in the planning process. Now, let’s take a look at the structure of paragraphs and how they work.

HOW TO STRUCTURE A PARAGRAPH

The three-part structure of an essay – introduction, body, and conclusion is echoed in the underlying structure of most paragraphs. There are two concepts essential to understanding in the writing of the perfect paragraph:

i. Thesis Statement: The thesis statement represents the main idea of the text as a whole and usually occurs in the opening paragraph.

ii. Topic Sentence: The first sentence of each paragraph thereafter usually introduces a single central idea in support of the previously mentioned thesis statement. 

The topic sentence also serves the purpose of unifying the other sentences in the paragraph, while further setting up the order of those sentences. While the majority of paragraphs will contain a topic sentence and that topic sentence will come first, there are, as always, some exceptions. A narration of the sequence of events may not require the use of a topic sentence or changing paragraphs because of a change of speaker in dialogue, for example.

Subsequent sentences following the topic sentence should all relate back to the topic sentence and either discuss the point raised or support that point through the provision of evidence and examples. A good acronym that conveys this is P.E.E.L.

Point: Make the central argument or express the main idea in the topic sentence.

Evidence: Back up the point made by providing evidence or reasons. Evidence may take the form of quotations from a text or authority, reference to historical events, use of statistics etc.

Explanation: Explain the point and how the evidence provided supports it.

Link: Provide a bridge into the next paragraph at the end of the current paragraph by using a transition that links to the next paragraph and the main idea or thesis statement.

WHEN TO BEGIN A NEW PARAGRAPH

One of the more common difficulties for students is to recognize when it is time to begin a new paragraph. This often occurs because the student fails to distinguish between the thesis statement and the topic sentence. While the thesis (or more broadly, the theme) will remain consistent throughout the piece of writing, each paragraph should focus on a different point in support of that thesis.

Another useful way to determine when to start a new paragraph is to note that a new paragraph is necessary when there is a change of focus on a:

Person: This could be a character in a story or an important figure in history, for example. This could also refer to a change in speaker when writing dialogue. When there is a significant shift in focus from one person to another in a piece of writing, it’s time to indent or skip a line!

Place: As with a changing focus on a person, a shift from one location to another is most often best noted with a corresponding change in paragraphing. Instruct students that a move to a new paragraph in their writing is symbolic of the physical change of place – this will help them remember to start a new paragraph.

Time: Important shifts in time most often require a new paragraph too. These changes in time may be a mere matter of minutes or a significant movement through different historical periods. If the change in time opens up new material to the reader, students must mark this in their paragraphing.

Topic: Though usually united by the thesis statement or similar, a piece of writing will often explore clearly differentiated topics in its course. Usually, these topics will become apparent during the planning process. Each clearly identified topic will require at least one dedicated paragraph.

HOW LONG IS A PARAGRAPH? / HOW MANY SENTENCES IN A PARAGRAPH?

The question of how many sentences are in a paragraph, or how long is a paragraph is a common one. Unfortunately, there is no definitive answer to this question as quality paragraphs are measured in the ideas and concepts addressed rather than sentences and word counts.

Analytics of millions of paragraphs tell us that most paragraphs are approximately 100 – 200 words in length and are made up of 3 – 5 sentences but it must be stressed that this is purely a statistical coincidence and nothing more.

Excellent paragraphs can range from 12 words to 12 sentences when written correctly as you will discover from this guide.

HOW TO WRITE AN INTRODUCTION PARAGRAPH

Your  introductory paragraph  should contain the thesis statement. The Thesis statement usually appears at the middle or end of the introductory paragraph of a paper, providing a concise summary of the main point or claim of the piece of writing.

Your thesis statement should not exceed one sentence and is a guiding light for your essay or piece of writing.

The last sentence of an introduction paragraph should also contain a “hook” driving the reader to the next paragraph and onwards throughout your piece of writing as a whole.

Daily Quick Writes For All Text Types

Our FUN DAILY QUICK WRITE TASKS will teach your students the fundamentals of CREATIVE WRITING across all text types. Packed with 52 ENGAGING ACTIVITIES

HOW TO WRITE A CONCLUSION PARAGRAPH

The purpose of your conclusion is to wrap up your piece of writing as a whole. In your conclusion, you should summarize what you initially stated in your thesis statement without just repeating it word for word.

Your conclusion is not the place to bring up new ideas or evidence which should have been addressed before this point. In some instances, though you may raise questions or direct your reader to reconsider a specific aspect of your writing in an effort to challenge their thinking beyond this point. This is common practice in persuasive writing and some narrative styles such as mystery writing.

The final sentence of your conclusion will leave a lasting impression on your audience so never rush or disregard it. It is one of the most important sentences you will write.

Be sure to read our complete guide to writing a conclusion paragraph here.

TOP 5 TIPS FOR PARAGRAPH WRITING

●     Consistency is Key – Encourage students to be consistent in their verb tenses and point of view. For example, shifts from the past tense to present tense without good reason can be as disorientating as time travel itself. 

●     Use Transition Words and Phrases – These words and phrases are a great way to link concepts and ideas within a paragraph, as well as helping to form a bridge to the next paragraph. Some useful transitional words and phrases include: although, in spite of, therefore, for this reason, as a result.

●     Employ Parallel Structures: Using parallel structures brings flow to a piece of writing, making it easier to read and understand for the reader. Parallel structures involve using two or more phrases or sentences that use the same parts of speech and grammatical structures. Not only does this make the writing easier to read, but it also helps the reader make connections between ideas.

●     Breathe Life into the Writing: We often forget that the origins of the written word lie in speech. We lose a lot of the color and expression of the spoken word when we lay it out cold on the page. Fortunately, students can breathe life back into their words with a few simple techniques. Encourage your students to imbue their writing with color and vitality by weaving anecdotes, verbal illustrations, rich details, and facts and figures throughout their writing. Judiciously chosen, these techniques will have their writing rosy-cheeked in no time!

●     Edit and Proofreading: Unlike speaking, with writing you get more than one bite at the verbal cherry. Writing is a craft and like any craft, some refining is required. Ensure your students take the time to polish their final draft.

WRITING CHECKLISTS FOR ALL TEXT TYPES

TO PERFECT THE PARAGRAPH – PRACTICE!

Clarity comes from organization and without the ability to organize their own thoughts prior to writing, students will not be able to coherently express their thoughts and ideas to their readers. It is essential that students develop a clear and consistent approach to paragraph writing that is repeatable. This can only be attained through lots of practice – which means lots of writing. 

However, the principles underlying strong paragraph writing can also be reinforced through reading. Take the opportunity to reinforce good writing practices when engaged in classroom reading activities too. Repeatedly identify, and have students identify, the concepts and techniques discussed above until they become second nature. The more familiar students become with these concepts, the more they will naturally permeate the student’s writing. Getting a firm grasp on the mechanics of paragraph writing will make their communication much more effective. A skill that is hard-won, but easily carried.

PARAGRAPH WRITING TUTORIAL VIDEO

It's Lit Teaching

High School English and TPT Seller Resources

• Creative Writing
• Teachers Pay Teachers Tips
• Shop My Teaching Resources!
• Sell on TPT

5 Tips for Teaching How to Write A Thesis Statement

The first time I had students write a thesis, I assumed they knew how to do it. After all, I learned all about the five-paragraph essay myself in middle school in the same school district. To my disappointment, not a single student knew how to write an adequate thesis statement. I realized it was a skill I was going to have to teach myself. After several papers and many years, here are my tips for teaching how to write a thesis statement. 

Tips for Teaching How to Write a Thesis Statement #1: Teach Directly

You need a whole lesson around the thesis statement. 

It can be ten minutes or a whole class period with note-taking and an activity. 

But you have to spend some time directly teaching the thesis statement. You can’t expect students–even seniors in high school–to know what a thesis statement is, its purpose, or where it’s supposed to go. 

If you’re teaching an essay writing unit, go ahead and explain the whole essay structure. But make sure you plan some time to specifically touch on the thesis statement and its role. 

Don’t have a thesis-specific lesson? Check out my five-paragraph essay mini-lessons here , which include some thesis-specific slides. 

Tips for Teaching How to Write a Thesis Statement #2: Explain The Role of a Thesis

I think it’s easy for students to grasp the concept of a thesis. It states what the essay is going to be about. They can get that.

But I think it’s much harder for students to understand how the thesis also guides and outlines the rest of the essay.  

By the time they’re writing the conclusion statements for their body paragraphs, they’ve forgotten their own thesis and rarely reference it. Instead of letting their thesis dictate the topic of their body paragraphs, they get stuck trying to come up with something new.

Don’t just tell students what a thesis is. Spend some time showing them how the thesis continues to be referenced in every following paragraph. Show them how the ideas presented in their thesis statement will guide the following paragraphs. 

Not sure how? This Unscramble the 5-Paragraph Essay Activity is a great start . Students will have to put the sentences in an essay in order, which can lead to some great discussions about how a strong thesis statement adds clarity to the rest of the essay’s structure.

Tips for Teaching How to Write a Thesis Statement #3: Give Students A Framework 

If your students are struggling with writing strong thesis statements, give them a framework. 

I know as teachers, it can get really boring to read “W is true because X, Y, Z.” But the structure does work, and it’s a great place for struggling writers to start. 

If you’ve used other writing frameworks in class (such as claim, evidence, and reasoning or C-E-R ), your students will be familiar with having a structure for their writing. They’ll be familiar with the concept already and a lot more confident producing their own thesis statements. 

Engage your students in more creative writing!

Sign up and get five FREE Creative Writing journal prompts to use with your students! 

Opt in to receive news and updates.

Keep an eye on your inbox for your FREE journal prompts!

Tips for Teaching How to Write a Thesis Statement #4: Provide Lots of Examples

As with teaching all new skills, you can never have enough examples. 

If your students are writing essays, provide them with examples for the topic they’re covering. But also provide lots of examples for other essay topics.

Give them examples that are both strong and weak, and let them discuss why each is which. 

Let them peer-edit one another’s thesis statements. 

You can do this in a note-taking style lesson, sit and get discussions, or, my personal favorite, a gallery walk. 

If this last idea is interesting to you, check out my Writing Strong Thesis Statements Activity . You’ll place examples of both strong and weak thesis statements around the room. Then, students will have to walk around the room, identifying which statements are strong and which are weak. It’s a great jumping off point for deeper discussions around effective theses. 

Tips for Teaching How to Write a Thesis Statement #5: Give Sentence Starters for More Scaffolding

If your students are still struggling, give them sentence starters. 

Provide students with the thesis statement itself. Leave a blank for their overall argument and their three supporting reasons (if that’s the structure you expect from them). 

Even if your students do alright with writing thesis statements, it might be nice to offer a variety of sentence starters to encourage them to try a new structure for their thesis. 

Bonus Tip: Teach the Plural Form

This is a little silly, but I thought I would add it. Teach students that the plural of “thesis” is “theses.”

Every time I use the word “theses” in my classroom, students are tickled by it. I’m not sure why they find the plural version so odd, but it’s an interesting tidbit you can casually share with your students during one of your essay-writing lessons.

Like all good teaching, taking it slow and offering multiple forms of scaffolding is the key to teaching how to write a thesis statement. 

If you’re looking for thesis or general essay-writing resources, check out my 5-Paragraph Essay Writing Resources Bundle!

Ultimate Guide to Writing Your College Essay

Tips for writing an effective college essay.

College admissions essays are an important part of your college application and gives you the chance to show colleges and universities your character and experiences. This guide will give you tips to write an effective college essay.

Want free help with your college essay?

UPchieve connects you with knowledgeable and friendly college advisors—online, 24/7, and completely free. Get 1:1 help brainstorming topics, outlining your essay, revising a draft, or editing grammar.

Writing a strong college admissions essay

Learn about the elements of a solid admissions essay.

Avoiding common admissions essay mistakes

Learn some of the most common mistakes made on college essays

Brainstorming tips for your college essay

Stuck on what to write your college essay about? Here are some exercises to help you get started.

How formal should the tone of your college essay be?

Learn how formal your college essay should be and get tips on how to bring out your natural voice.

Taking your college essay to the next level

Hear an admissions expert discuss the appropriate level of depth necessary in your college essay.

Student Stories

Student Story: Admissions essay about a formative experience

Get the perspective of a current college student on how he approached the admissions essay.

Student Story: Admissions essay about personal identity

Get the perspective of a current college student on how she approached the admissions essay.

Student Story: Admissions essay about community impact

Student story: admissions essay about a past mistake, how to write a college application essay, tips for writing an effective application essay, sample college essay 1 with feedback, sample college essay 2 with feedback.

This content is licensed by Khan Academy and is available for free at www.khanacademy.org.

• 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