transition words in a persuasive essay

Transition words for essays - wordscoach.com

70+ Transition words for essays with examples

Transition words for essays.

Ever stared at a blank page, your thoughts swirling like a disorganized storm? Crafting a compelling essay often hinges on smooth transitions between ideas. Fear not, fellow writer! Here’s your guide to essential transition words , those linguistic gems that bridge the gaps in your essay and create a clear, logical flow.

List of Transition words for essays

Additionally
Furthermore
In addition
In the same way
In other words
That is to say
For example
For instance
Specifically
To illustrate
In particular
Without a doubt
Essentially
In conclusion
To conclude
On the whole
Consequently
Accordingly
As a result
For this reason
Because of this
Due to this
In light of this
Considering that
Seeing that
As a matter of fact
Nonetheless
Nevertheless
Even though
In spite of
On the contrary

Transition words for essays with examples

Here are examples of sentences using each of the transition words for cause:

Additionally : “She enjoys playing the piano. Additionally, she is proficient in playing the guitar.”
Furthermore : “The research indicated a positive correlation between exercise and mental health. Furthermore, it suggested that regular physical activity reduces stress levels.”
Moreover : “The company reported an increase in sales for the third quarter. Moreover, profits also saw a significant rise.”
In addition : “He enjoys outdoor activities such as hiking and camping. In addition, he is passionate about photography.”
Also : “He enjoys playing tennis. Also, he participates in swimming competitions.”
Likewise : “She volunteered at the local shelter. Likewise, her brother also dedicated his time to community service.”
Similarly : “The team implemented new strategies to improve productivity. Similarly, other departments adopted similar approaches.”
In the same way : “She excels in academics. In the same way, her siblings also achieve high grades.”
Equally : “Both candidates possess strong leadership skills. Equally, they demonstrate excellent communication abilities.”
Besides : “She enjoys reading novels. Besides, she also enjoys writing short stories.”
In other words : “The product received mixed reviews due to its functionality issues. In other words, customers experienced difficulties with its performance.”
That is to say : “She loves traveling to exotic destinations. That is to say, she prefers exploring off-the-beaten-path locations.”
Namely : “The research focused on several key areas, namely, customer satisfaction, product quality, and market trends.”
For example : “Many countries have implemented strict environmental policies. For example, Denmark has achieved significant progress in renewable energy.”
For instance : “Some popular social media platforms, for instance, Facebook and Instagram, have millions of active users.”
Specifically : “The training program focuses specifically on enhancing leadership skills and fostering teamwork.”
To illustrate : “To illustrate the concept further, let’s consider a real-life example.”
In particular : “The company aims to expand its operations globally. In particular, it plans to target emerging markets in Asia.”
In fact : “Contrary to popular belief, exercise is not only beneficial for physical health but also for mental well-being. In fact, it has been shown to reduce symptoms of depression and anxiety.”
Indeed : “The company’s efforts to promote diversity have yielded positive results. Indeed, diversity has been linked to increased innovation and creativity.”
Actually : “Contrary to what many people believe, the situation is actually quite different.”
Truly : “She was truly dedicated to her work and always gave her best effort.”
Certainly : “The results of the study certainly support the hypothesis.”
Of course : “Of course, you are welcome to join us for dinner.”
Without a doubt : “Without a doubt, she is one of the most talented musicians I’ve ever met.”
In essence : “The policy change, in essence, aims to improve customer satisfaction.”
Essentially : “The project, essentially, involves redesigning the user interface.”
In summary : “In summary, the findings suggest a need for further research in this area.”
In conclusion : “In conclusion, it is evident that climate change poses significant challenges.”
To sum up : “To sum up, the main points of the argument are as follows.”
In brief : “In brief, the report highlights key areas for improvement.”
To conclude : “To conclude, let’s consider the implications of these findings.”
Overall : “Overall, the project was a success.”
All in all : “All in all, it was a memorable experience.”
On the whole : “On the whole, the feedback has been positive.”
Therefore : “The traffic was heavy; therefore, they arrived late to the meeting.”
Thus : “The factory implemented new safety measures; thus, the number of accidents decreased.”
Hence : “The flight was canceled; hence, they had to make alternative travel arrangements.”
Consequently : “He missed the deadline; consequently, he faced disciplinary action.”
Accordingly : “The instructions were unclear; accordingly, many participants made mistakes.”
As a result : “The market demand increased; as a result, prices rose.”
For this reason : “She forgot her umbrella; for this reason, she got wet in the rain.”
Because of this : “He missed the train because of this, he couldn’t attend the meeting.”
Due to this : “Due to this unforeseen circumstance, the event had to be postponed.”
In light of this : “In light of this new information, we need to reconsider our strategy.”
Since : “Since it was raining heavily, they decided to stay indoors.”
Because : “He didn’t study for the exam because he was feeling unwell.”
For : “He received a promotion for his outstanding performance.”
As : “As the temperature dropped, people bundled up in warm clothing.”
Owing to : “Owing to his persistent efforts, he achieved success.”
Given that : “Given that she had prior experience, she was appointed as the team leader.”
Considering that : “Considering that it was his first attempt, he performed exceptionally well.”
Seeing that : “Seeing that the store was closing soon, they hurried to finish their shopping.”
In view of : “In view of the current situation, we need to take immediate action.”
As a matter of fact : “As a matter of fact, he was the first to arrive at the party.”
Regardless : “He continued with the project regardless of the challenges he faced.”
Nonetheless : “The weather was unfavorable; nonetheless, they decided to go ahead with the outdoor event.”
Nevertheless : “The plan faced criticism; nevertheless, it was implemented successfully.”
However : “She forgot her passport; however, she managed to board the flight with a temporary permit.”
Although : “Although it was raining, they decided to go for a walk.”
Though : “Though she was tired, she continued working late into the night.”
Even though : “Even though he was warned about the risks, he proceeded with the plan.”
Despite : “Despite the challenges, they remained committed to their goal.”
In spite of : “In spite of the obstacles, they persevered and succeeded.”
On the contrary : “The results were contrary to expectations; on the contrary, they were favorable.”
Conversely : “He expected to feel relieved; conversely, he felt even more anxious.”
But : “The weather was sunny, but they decided to cancel the picnic due to other commitments.”
Yet : “He had a busy schedule, yet he managed to find time for his hobbies.”
Whereas : “She preferred coffee, whereas her sister preferred tea.”

By mastering the art of transition words, you’ll transform your essay from a disjointed collection of ideas into a powerful and persuasive piece of writing. So, the next time you sit down to write, remember these transition words and watch your essay flow majestically!

Download the Word of the day

200+ Sentences with Besides
Conjunctive Adverbs
Transition Phrases
Ways to Say “I Really Appreciate It”
Happy Promise Day 2024: Wishes, Quotes, and Messages
Transition words for sequencing with examples
The Power of Transition Words and Phrases
Transition words for contrast and compare with examples

Download the Word coach App on your Android phone

Word Coach - IELTS and GRE Vocabulary Builder & word coach Quiz (10 Words a Day) application helps, you and your friends to improve English Vocabulary and help you become the smartest among your group.

Tapping to Agree I hereby consent to the use of cookies, confirm that I have read Cookie Policy and allow this website to collect and process my personal data in a safe and secure way

Essay Writers for Hire
Pay For Essays
Plagiarism Free Essays
Business Essay Writing Service
Scholarship Essay Writing
Masters Essay Writing Service
Essay Editing
Persuasive Essay Writing Service
Personal Statement Writing Service
College Paper Writing
Coursework Writing
Dissertation Editing
Write My Dissertation
Essays for Sale
Buy Research Paper
Research Paper Help
Pay For Research Paper
Write My Research Paper
Research Paper Editing
Write My Philosophy Research Paper
Write My Assignment
Conclusion Generator
Paraphrasing Tool
Essay Maker
Testimonials
How It Works
Essay Writing

Transition Words for Persuasive Essays

Persuasive essays are those in which you must convince a reader that your position on an issue is the correct one. Thus, you may want to convince an audience that animal testing is immoral or that genetically modified foods are harmful. Perhaps you want to convince someone that the proposed Canadian pipeline or fracking poses dangers to our environment; maybe you believe that there is too much money spent on political campaigns. Whatever your topic and whatever your position, you must organize an essay that flows logically from one point to the next.

Good Transitions to Improve Logical Flow

You may have done great research and you may have great arguments in favor of our position. If they are not presented well, though, your essay will fall flat and your reader will not be convinced.

Part of a good presentation means than you understand how to use transition words for persuasive essays. So, let’s first look at what a transition is and then take a look at good transition words and phrases for essays .

Definition of Transitions: These are words or phrases that connect one thought or idea to the next. They can be used to connect thoughts in two sentences or to move the reader on to the next paragraph in a logical way. They can be single words, phrases, or complete sentences. Typical examples might include the following:

Words: Clearly, Definitely, Obviously, Furthermore, However, Notwithstanding, First (Second, etc.)
Phrases: Without question, What is more, In reality, In fact, Yet another, For example (instance), In other words, According to,
Sentences: These usually occur at the end of a paragraph as you are trying to move your reader into the point that will be covered in the next paragraph. For example, if you are writing a persuasive essay about money in politics, and you have just completed a paragraph on the Supreme Court “Citizens United” decision, you might end that paragraph with something like, “This decision has impacted campaign and elections in many ways.” Now, your reader is prepared for what is to come next – the ways in which that decision has affected campaigns/elections.

Useful info: Custom essays services will have your back when it comes to writing.

Now, your next paragraph in such an essay will speak to one impact that the decision has had – perhaps the establishment of PAC’s into which donors can throw a much money as they wish. At the end of that paragraph, you will want to transition into the next point you will be making, so your transition sentence might read something like, “And once a campaign has been successful because of all of the donated money, the elected official will have certain obligations to those who have provided that campaign funding.” This sentence contains great a lead in to the next paragraph which will discuss how an elected official is then obligate to vote and make decisions based upon the desires of those who provided the funding.

Whether you are using persuasive essay transition words between sentences or entire phrases or sentences between paragraphs, your transitions connect your arguments and allow the reader to see where you are going next. If you don’t use these transitions, the reader cannot follow your argument!

Remember! You can always buy an essay online at GrabMyEssay

Primary Uses for Transition Words and Phrases of Essays that Attempt to Persuade

You have to think about the flow of your essay and what you are trying to do with your use of transitional words, phrases and sentences. Basically, the purposes of your transitions are any one of the following:

Adding to a Point You Have Made: You will use such words/phrases as: Furthermore, What is more, In addition to, Likewise, Moreover
Providing Examples: Use such phrases as, for instance, for example, in other words
Providing Lists: Use any of the following: First, second, third (etc.), yet another, the following.
Same Point Stated in a Different Way: Good phrases include, in other words, with this in mind, another way to look at this, etc.

Read also: Personal statement service for successful college admission.

Transitions Can Be Tricky

You know that you need to use transitional words correctly, especially when you are trying to make points that will persuade someone to accept your point of view. Without them, your essay loses clarity and logic. If you are having trouble with transitions, you can get great help at GrabMyEssay, just ask us “ write an essay for me .” These pros can either write your persuasive essay in its entirety or provide a review and edit, adding the words, phrases, and/or sentences that should be included in order to achieve your persuasive purose.

Blog writer for GrabMyEssay

Andy Preisler

I’m Andy Preisler, and I’m super happy to be joining the blog team at GrabMyEssay.com!

While I hail from Fayetteville, Arkansas (I know, not the most progressive state!), I left the Southern life behind me many years ago when I went to college for my first degree. I’ve received it in University of Arkansas, Fayetteville and I’m really proud of this. Since then, I have studied in the U.S., and later on, continued my education in Loughborough University, UK, where I actually my second Bachelor’s Degree along the way.

With my perpetual studies (my parents wonder if it will ever stop), I have become a bit of an expert on college life – academic, social, and financial – and love sharing my experiences and my methods of “circumventing the system” with others. I will be sharing all of these great tips and strategies with my readers, so stay tuned!

When I am not blogging or enrolling in some new course that interests me, I am backpacking through Europe and staying in hostels, working on my second novel (a riveting murder mystery), and pursuing my interest in music. Yes, I travel with my guitar, and you would be amazed at the amount of cash I can accumulate, just performing on the streets of European cities (they are so much more tolerant of vagabond musicians).

My other passion is environmental. In my short 27 years of life on this planet, I have witnessed the extinction of species, the destruction of rain forests, and irreparable harm to our oceans. I contribute both time and money to several international environmental organizations, because we all must do our part to save Mother Earth.

But I digress! If you are interested in the “ins and outs” of college life, and want some great tales of navigating through the game of “degree attainment,” as well as tips for easing the pain of those pesky essay and paper assignments, follow my blog!

I would love to hear from you, to give you advice, and to lend a listening ear. You can contact me at [email protected] anytime! And follow my posts – you won’t be disappointed!

10 Things I Now Know About Narrative Essay Writing
Boring Essays? Change up Your Transition Words and Phrases for Essays!
What is the Purpose of a Persuasive Essay?
An Explanation of the Purpose of a Descriptive Essay
How To Write A Personal Narrative Essay For College
Narrative Essay Vs Descriptive Essay
The Autobiographical Narrative Essay
First Person Essay
How to Organize a Compare and Contrast Essay
The Compare and Contrast Essay Prompts
Good Words for Definition Essay Assignments
How To Write A Descriptive Essay About A Person
Studying Famous Narrative Essays
The Personal Narrative Essay Outline
Descriptive Essay Prompts and Writing Tips
Essay Topics
Research Paper Guides
Research Paper Topics
Dissertation Writing Guide
Academic Writing Tips

Try our service with 15% Discount for your first order! Try our service with 15% Discount for your first order! Try our service with 15% Discount for your first order!

Some experts argue that focusing on individual actions to combat climate change takes the focus away from the collective action required to keep carbon levels from rising. Change will not be effected, say some others, unless individual actions raise the necessary awareness.

While a reader can see the connection between the sentences above, it’s not immediately clear that the second sentence is providing a counterargument to the first. In the example below, key “old information” is repeated in the second sentence to help readers quickly see the connection. This makes the sequence of ideas easier to follow.

Sentence pair #2: Effective Transition

You can use this same technique to create clear transitions between paragraphs. Here’s an example:

Some experts argue that focusing on individual actions to combat climate change takes the focus away from the collective action required to keep carbon levels from rising. Other experts argue that individual actions are key to raising the awareness necessary to effect change. According to Annie Lowery, individual actions are important to making social change because when individuals take action, they can change values, which can lead to more people becoming invested in fighting climate change. She writes, “Researchers believe that these kinds of household-led trends can help avert climate catastrophe, even if government and corporate actions are far more important” (Lowery).

So, what’s an individual household supposed to do?

The repetition of the word “household” in the new paragraph helps readers see the connection between what has come before (a discussion of whether household actions matter) and what is about to come (a proposal for what types of actions households can take to combat climate change).

Sometimes, transitional words can help readers see how ideas are connected. But it’s not enough to just include a “therefore,” “moreover,” “also,” or “in addition.” You should choose these words carefully to show your readers what kind of connection you are making between your ideas.

To decide which transitional word to use, start by identifying the relationship between your ideas. For example, you might be

making a comparison or showing a contrast Transitional words that compare and contrast include also, in the same way, similarly, in contrast, yet, on the one hand, on the other hand. But before you signal comparison, ask these questions: Do your readers need another example of the same thing? Is there a new nuance in this next point that distinguishes it from the previous example? For those relationships between ideas, you might try this type of transition: While x may appear the same, it actually raises a new question in a slightly different way.
expressing agreement or disagreement When you are making an argument, you need to signal to readers where you stand in relation to other scholars and critics. You may agree with another person’s claim, you may want to concede some part of the argument even if you don’t agree with everything, or you may disagree. Transitional words that signal agreement, concession, and disagreement include however, nevertheless, actually, still, despite, admittedly, still, on the contrary, nonetheless .
showing cause and effect Transitional phrases that show cause and effect include therefore, hence, consequently, thus, so. Before you choose one of these words, make sure that what you are about to illustrate is really a causal link. Novice writers tend to add therefore and hence when they aren’t sure how to transition; you should reserve these words for when they accurately signal the progression of your ideas.
explaining or elaborating Transitions can signal to readers that you are going to expand on a point that you have just made or explain something further. Transitional words that signal explanation or elaboration include in other words, for example, for instance, in particular, that is, to illustrate, moreover .
drawing conclusions You can use transitions to signal to readers that you are moving from the body of your argument to your conclusions. Before you use transitional words to signal conclusions, consider whether you can write a stronger conclusion by creating a transition that shows the relationship between your ideas rather than by flagging the paragraph simply as a conclusion. Transitional words that signal a conclusion include in conclusion , as a result, ultimately, overall— but strong conclusions do not necessarily have to include those phrases.

If you’re not sure which transitional words to use—or whether to use one at all—see if you can explain the connection between your paragraphs or sentence either out loud or in the margins of your draft.

For example, if you write a paragraph in which you summarize physician Atul Gawande’s argument about the value of incremental care, and then you move on to a paragraph that challenges those ideas, you might write down something like this next to the first paragraph: “In this paragraph I summarize Gawande’s main claim.” Then, next to the second paragraph, you might write, “In this paragraph I present a challenge to Gawande’s main claim.” Now that you have identified the relationship between those two paragraphs, you can choose the most effective transition between them. Since the second paragraph in this example challenges the ideas in the first, you might begin with something like “but,” or “however,” to signal that shift for your readers.

picture_as_pdf Transitions

Essay Writing Guide

Transition Words For Essays

Transition Words For Essays - The Ultimate List

11 min read

What are Good Transition Words for Essays?

Transition words are essential tools in essay writing , providing a clear path for your readers to follow. They serve the crucial purpose of connecting words, phrases, sentences, or even entire paragraphs.

By using these transitions effectively, you can effortlessly convey your ideas and thoughts in a coherent and easily understandable manner.

However, it's crucial to exercise moderation when using transition words. Overusing them can clutter your essay, making it confusing and difficult to read.

On the other hand, omitting them entirely can result in a piece that lacks flow and direction. Striking the right balance ensures that your essay is both engaging and comprehensible.

Purpose of Transition Words

Let’s take a look at the purpose of using transitions in essays:

Enhance Readability: Transition words improve the overall flow and coherence of your writing.
Clarify Relationships: They signal connections between ideas, whether it's adding, contrasting, or summarizing.
Improve Comprehension: Readers can follow your argument or narrative more easily.
Smooth Transitions: They act as bridges, seamlessly guiding your audience from one point to the next.
Manage Change: They prepare the reader for shifts in topic or perspective.
Enhance Engagement: Well-placed transitions keep readers interested and invested in your content.
Encourage Flow: They maintain a logical progression, aiding in the overall structure of your work.

Examples of Different Types of Transition Words

Here are some common types of transitions for essays that can be used in almost any situation.

Addition Transitions

Furthermore
Additionally
In addition
Not only...but also

Comparison Transitions

In the same way
Comparable to
Correspondingly
In comparison
By the same token

Contrast Transitions

On the other hand
In contrast
Nevertheless
Nonetheless
Even though

Cause and Effect Transitions

Consequently
As a result
For this reason
Accordingly

Time Transitions

Simultaneously
In the meantime
Subsequently
At the same time

Illustration Transitions

For example
For instance
Specifically
To illustrate
In particular
In this case
As an illustration

Emphasis Transitions

Undoubtedly
Without a doubt

Summary Transitions

To summarize
To conclude

Sequence Transitions

Example transitions.

As an example
To demonstrate
For one thing
As evidence
As an instance

For Showing Exception

At The Same Time
Nevertheless
On The Other Hand
But At The Same Time
Conversely

For Proving

For This Reason
Certainly
To Demonstrate
In Fact
Clearly
As A Result

This transition words for essays list will make it easier for you to understand what words to use in which kind of essay or for which purpose.

Transition Words for Argumentative Essays

To begin with
By contrast
One alternative is
To put more simply
On the contrary
With this in mind
All things considered
Generally speaking
That is to say
Yet another

Transition Words for Persuasive Essays

furthermore
Moreover
Because
Besides that
Pursuing this further

Transition Words for Essays PDF

Transition Words for Compare and Contrast Essays

Althoughyhtjyjum,u
Notwithstanding

Transition Words for Informative Essays

After all
As can be expected
Obviously

Transition Words for Expository Essays

Equally important
Another reason
Not long after that
Looking back

Transition Words for Cause and Effect Essays

In order to
Provided that
Because of this

Transition Words for Synthesis Essays

As noted earlier
Consequently
Whereas
This leads to
Another factor
This lead to
The underlying concept
In this respect

Transition Words for Analysis Essays

(once) again
Primarily
Due to
Accordingly
That is to say
Subsequently
To demonstrate
However

Conclusion Transition Words for Essays

In any event
As mentioned
In other words
As you can see

Beginning Transition Words for Essays

These are some introduction transition words for essays to start writing:

In the first place
First of all
For the most part
On one hand
As a rule

Paragraph Transition Words for Essays

To put it differently
Once and for all

Transition Words for Essay’s First Body Paragraph

To start with
First and foremost
In the beginning

Transition Words for Essay’s Second Body Paragraph

In addition to this
Furthermore

Transition Words for Essay’s Last Body Paragraph

In conclusion
Finally
Last but not least
To sum up
Altogether

Transition Words for Quotes in Essays

Acknowledges

Transition Words for Essays Middle School

In conclusion
For instance

Transition Words for Essays High School

Today
In addition
To summarize
On the other hand
As well as
Although

Transition Words for Essays College

Here are some college level transition words for essay:

Pursuing this
Similarly
What’s more
As much as
In a like manner
In the same fashion

Do’s and Don’ts of Using Transition Words

So, now you have some strong transition words for essays at hand. But how do you use these transition words?

Here are the basic dos and don’ts of using transition words for essays.

Understand that these terms are an important part of any type of essay or paper, adding to its overall flow and readability.
Use these words when you are presenting a new idea. For example, start a new paragraph with these phrases, followed by a comma.
Do not overuse transition words. It is one of the most common essay writing problems that students end up with. It is important to only use those words required to convey your message clearly. It is good to sound smart by using these words but don’t overdo it.
Avoid using these words at the start and in the middle. Always try to use transition words only a few times where it is necessary to make it easy for the readers to follow the ideas.

So, now you have an extensive list of transition words. These are some of the best transition words for essays that you can add to your essays.

If your essay seems redundant because you used similar transition words, you can always have a look at this list to find some good replacements.

So, whenever you’re writing an essay, refer back to this list and let your words flow!

If you still feel that your essay is not properly conveying your ideas, turn to our expert essay writers at MyPerfectWords.com.

If you have some write-up, our essay writing service will make it flow without changing the entire content. Or, if you wish to have an essay from scratch, we will write a paper for you!

Simply contact us and place your order now. Our writers will take care of everything to help you ace your assignment.

Write Essay Within 60 Seconds!

Nova Allison is a Digital Content Strategist with over eight years of experience. Nova has also worked as a technical and scientific writer. She is majorly involved in developing and reviewing online content plans that engage and resonate with audiences. Nova has a passion for writing that engages and informs her readers.

Paper Due? Why Suffer? That’s our Job!

Keep reading

Have a language expert improve your writing

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

Knowledge Base
Transition sentences | Tips & examples for clear writing

Transition Sentences | Tips & Examples for Clear Writing

Published on June 9, 2020 by Jack Caulfield . Revised on July 23, 2023.

Clear transitions are crucial to clear writing: They show the reader how different parts of your essay, paper, or thesis are connected. Transition sentences can be used to structure your text and link together paragraphs or sections.

… In this case, the researchers concluded that the method was unreliable.

However , evidence from a more recent study points to a different conclusion . …

Instantly correct all language mistakes in your text

Upload your document to correct all your mistakes in minutes

Transitioning between paragraphs, transitioning to a new section, transitions within a paragraph, other interesting articles.

When you start a new paragraph , the first sentence should clearly express:

What this paragraph will discuss
How it relates to the previous paragraph

The examples below show some examples of transition sentences between paragraphs and what they express.

Placement of transition sentences

The beginning of a new paragraph is generally the right place for a transition sentence. Each paragraph should focus on one topic, so avoid spending time at the end of a paragraph explaining the theme of the next one.

The first dissenter to consider is …

However, several scholars dissent from this consensus. The first one to consider is …

Prevent plagiarism. Run a free check.

While transitions between paragraphs are generally a single sentence, when you start a new section in a longer text, you may need an entire transition paragraph. Transitioning to a new section involves summarizing the content of the previous section and expressing how the new one will build upon or depart from it.

For example, the following sentences might be an effective transition for a new section in a literary analysis essay.

Having established that the subjective experience of time is one of Mann’s key concerns in The Magic Mountain , it is now possible to explore how this theme facilitates the novel’s connection with World War I. The war itself is not narrated in the book, but rather hinted at as something awaiting Castorp beyond the final pages. In this way, Mann links his protagonist’s subjective experience of time to more than just his illness; it is also used to explore the period leading up to the outbreak of war.

As in academic writing generally, aim to be as concise as you can while maintaining clarity: If you can transition to a new section clearly with a single sentence, do so, but use more when necessary.

It’s also important to use effective transitions within each paragraph you write, leading the reader through your arguments efficiently and avoiding ambiguity.

The known-new contract

The order of information within each of your sentences is important to the cohesion of your text. The known-new contract , a useful writing concept, states that a new sentence should generally begin with some reference to information from the previous sentence, and then go on to connect it to new information.

In the following example, the second sentence doesn’t follow very clearly from the first. The connection only becomes clear when we reach the end.

By reordering the information in the second sentence so that it begins with a reference to the first, we can help the reader follow our argument more smoothly.

Note that the known-new contract is just a general guideline. Not every sentence needs to be structured this way, but it’s a useful technique if you’re struggling to make your sentences cohere.

Transition words and phrases

Using appropriate transition words helps show your reader connections within and between sentences. Transition words and phrases come in four main types:

Additive transitions, which introduce new information or examples
Adversative transitions, which signal a contrast or departure from the previous text
Causal transitions, which are used to describe cause and effect
Sequential transitions, which indicate a sequence

The table below gives a few examples for each type:

Grouping similar information

While transition words and phrases are essential, and every essay will contain at least some of them, it’s also important to avoid overusing them. One way to do this is by grouping similar information together so that fewer transitions are needed.

For example, the following text uses three transition words and jumps back and forth between ideas. This makes it repetitive and difficult to follow.

Rewriting it to group similar information allows us to use just one transition, making the text more concise and readable.

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

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

College essays

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

(AI) Tools

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

Cite this Scribbr article

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

Caulfield, J. (2023, July 23). Transition Sentences | Tips & Examples for Clear Writing. Scribbr. Retrieved April 2, 2024, from https://www.scribbr.com/academic-essay/transition-sentences/

Is this article helpful?

Jack Caulfield

Other students also liked, transition words & phrases | list & examples, how to write topic sentences | 4 steps, examples & purpose, academic paragraph structure | step-by-step guide & examples, "i thought ai proofreading was useless but..".

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

The Writing Center • University of North Carolina at Chapel Hill

Transitions

What this handout is about.

In this crazy, mixed-up world of ours, transitions glue our ideas and our essays together. This handout will introduce you to some useful transitional expressions and help you employ them effectively.

The function and importance of transitions

In both academic writing and professional writing, your goal is to convey information clearly and concisely, if not to convert the reader to your way of thinking. Transitions help you to achieve these goals by establishing logical connections between sentences, paragraphs, and sections of your papers. In other words, transitions tell readers what to do with the information you present to them. Whether single words, quick phrases, or full sentences, they function as signs that tell readers how to think about, organize, and react to old and new ideas as they read through what you have written.

Transitions signal relationships between ideas—relationships such as: “Another example coming up—stay alert!” or “Here’s an exception to my previous statement” or “Although this idea appears to be true, here’s the real story.” Basically, transitions provide the reader with directions for how to piece together your ideas into a logically coherent argument. Transitions are not just verbal decorations that embellish your paper by making it sound or read better. They are words with particular meanings that tell the reader to think and react in a particular way to your ideas. In providing the reader with these important cues, transitions help readers understand the logic of how your ideas fit together.

Signs that you might need to work on your transitions

How can you tell whether you need to work on your transitions? Here are some possible clues:

Your instructor has written comments like “choppy,” “jumpy,” “abrupt,” “flow,” “need signposts,” or “how is this related?” on your papers.
Your readers (instructors, friends, or classmates) tell you that they had trouble following your organization or train of thought.
You tend to write the way you think—and your brain often jumps from one idea to another pretty quickly.
You wrote your paper in several discrete “chunks” and then pasted them together.
You are working on a group paper; the draft you are working on was created by pasting pieces of several people’s writing together.

Organization

Since the clarity and effectiveness of your transitions will depend greatly on how well you have organized your paper, you may want to evaluate your paper’s organization before you work on transitions. In the margins of your draft, summarize in a word or short phrase what each paragraph is about or how it fits into your analysis as a whole. This exercise should help you to see the order of and connection between your ideas more clearly.

If after doing this exercise you find that you still have difficulty linking your ideas together in a coherent fashion, your problem may not be with transitions but with organization. For help in this area (and a more thorough explanation of the “reverse outlining” technique described in the previous paragraph), please see the Writing Center’s handout on organization .

How transitions work

The organization of your written work includes two elements: (1) the order in which you have chosen to present the different parts of your discussion or argument, and (2) the relationships you construct between these parts. Transitions cannot substitute for good organization, but they can make your organization clearer and easier to follow. Take a look at the following example:

El Pais , a Latin American country, has a new democratic government after having been a dictatorship for many years. Assume that you want to argue that El Pais is not as democratic as the conventional view would have us believe.

One way to effectively organize your argument would be to present the conventional view and then to provide the reader with your critical response to this view. So, in Paragraph A you would enumerate all the reasons that someone might consider El Pais highly democratic, while in Paragraph B you would refute these points. The transition that would establish the logical connection between these two key elements of your argument would indicate to the reader that the information in paragraph B contradicts the information in paragraph A. As a result, you might organize your argument, including the transition that links paragraph A with paragraph B, in the following manner:

Paragraph A: points that support the view that El Pais’s new government is very democratic.

Transition: Despite the previous arguments, there are many reasons to think that El Pais’s new government is not as democratic as typically believed.

Paragraph B: points that contradict the view that El Pais’s new government is very democratic.

In this case, the transition words “Despite the previous arguments,” suggest that the reader should not believe paragraph A and instead should consider the writer’s reasons for viewing El Pais’s democracy as suspect.

As the example suggests, transitions can help reinforce the underlying logic of your paper’s organization by providing the reader with essential information regarding the relationship between your ideas. In this way, transitions act as the glue that binds the components of your argument or discussion into a unified, coherent, and persuasive whole.

Types of transitions

Now that you have a general idea of how to go about developing effective transitions in your writing, let us briefly discuss the types of transitions your writing will use.

The types of transitions available to you are as diverse as the circumstances in which you need to use them. A transition can be a single word, a phrase, a sentence, or an entire paragraph. In each case, it functions the same way: First, the transition either directly summarizes the content of a preceding sentence, paragraph, or section or implies such a summary (by reminding the reader of what has come before). Then, it helps the reader anticipate or comprehend the new information that you wish to present.

Transitions between sections: Particularly in longer works, it may be necessary to include transitional paragraphs that summarize for the reader the information just covered and specify the relevance of this information to the discussion in the following section.
Transitions between paragraphs: If you have done a good job of arranging paragraphs so that the content of one leads logically to the next, the transition will highlight a relationship that already exists by summarizing the previous paragraph and suggesting something of the content of the paragraph that follows. A transition between paragraphs can be a word or two (however, for example, similarly), a phrase, or a sentence. Transitions can be at the end of the first paragraph, at the beginning of the second paragraph, or in both places.
Transitions within paragraphs: As with transitions between sections and paragraphs, transitions within paragraphs act as cues by helping readers to anticipate what is coming before they read it. Within paragraphs, transitions tend to be single words or short phrases.

Transitional expressions

Effectively constructing each transition often depends upon your ability to identify words or phrases that will indicate for the reader the kind of logical relationships you want to convey. The table below should make it easier for you to find these words or phrases. Whenever you have trouble finding a word, phrase, or sentence to serve as an effective transition, refer to the information in the table for assistance. Look in the left column of the table for the kind of logical relationship you are trying to express. Then look in the right column of the table for examples of words or phrases that express this logical relationship.

Keep in mind that each of these words or phrases may have a slightly different meaning. Consult a dictionary or writer’s handbook if you are unsure of the exact meaning of a word or phrase.

You may reproduce it for non-commercial use if you use the entire handout and attribute the source: The Writing Center, University of North Carolina at Chapel Hill

Make a Gift

190 Good Transition Words for Essays

August 23, 2023

good transitions words for essays, college

Essay writing consists of two primary procedures: coming up with the content we want to include and structuring that content. These procedures might take place in either order or they could occur simultaneously. When writing an essay it is important to think about the ways that content and structure complement one another. The best essays join these two elements in thoughtful ways. Transition words for essays (including for college essays) are some of our most primary tools when it comes to structuring a piece of writing.

When beginning an essay it is often recommended to begin with a messy first draft. The purpose of this draft is to get everything out on the page. You should put down as many ideas and trajectories as you can without worrying too much about phrasing or whether they will make it into the final draft. The key here is to be loose—to get ahead of our self-editors and expel everything we can from our minds.

List of Good Transition Words for Essays (Continued)

While this is a good strategy for beginning an essay it will likely leave you unsure how everything fits together. This is where transition words come in. As you will see in this list (which is necessarily incomplete) the range of transition words for essays is vast. Each transition word implies a different relation, often in subtle ways. After accumulating content, the next step is to figure out how the elements fit together towards an overall goal (this could be but is not necessarily an “argument”). Consulting this list of transition words for essays can provide a shortcut for determining how one piece might lead into another. Along with transition words, rhetorical devices and literary devices are other tools to consider during this stage of essay writing.

Transition Words for College Essays

While this list will be a useful tool for all types of essay writing it will be particularly helpful when it comes to finding the right transition words for college essays . The goal of a college essay is to give a strong overall sense of its author in the tight space of 650 words. As you might imagine, it’s not easy to encompass a life or convey a complex personality in such a space. When writing a college essay you are working with a huge amount of potential content. Students often want to squeeze in as much as they can. To this end, transition words for college essays are essential tools to have at our disposal.

Here is our list of transition words for college essays and other essays. It is organized by the different types of transition words/phrases and their functions. While this organization should be convenient, keep in mind that there’s plenty of overlap. Many of these words can function in multiple ways.

1) Additive Transitions

These words function in an additive manner, accumulating content to build upon what has already been stated. They can be used to construct an argument or establish a scene through the accumulation of details.

Additionally
In addition to
Furthermore
Not to mention
In all honesty
To tell the truth
Not only…but also
As a matter of fact
To say nothing of
What’s more
Alternatively
To go a step further

2) Comparative Transitions (Similarity)

These transition words draw a parallel or bring out a similarity between images or ideas. They can be used not only in a straightforward sense but also to establish relations of similarity between objects or ideas that might appear to be dissonant.

In the same way
In a similar vein
Along the lines of
In the key of

3) Comparative Transitions (Difference)

While also functioning comparatively, the following words demonstrate difference between ideas or images. These transition words are useful when it comes to establishing contrasting points of view, an important component of any argument.

On the other hand
On the contrary
In contrast to
In contradiction
Nevertheless
Nonetheless
In any event
In any case
In either event

4) Sequential Transitions

The following are particularly effective transition words for college essays. They will allow you to order ideas chronologically or in a sequence, providing a sense of continuity over time. This is particularly useful when an essay leans into something more creative or involves telling a story.

Subsequently
At the same time
Concurrently
In the beginning
At the start
At the outset
Off the bat

5) Spatial Transitions

Rather than organizing ideas or images in regards to sequence, these transitions indicate spatial relationships. They are particularly useful when it comes to painting a scene and/or describing objects, but they can also be used metaphorically. Consider, for example, how you might use the transition, “standing in […’s] shadow.”

Standing in […’s] shadow
In front of
In the middle
In the center
To the left
To the right
On the side
Adjacent to
Around the bend
On the outskirts
In the distance
On the horizon
In the foreground
In the background
Underground
Through the grapevine

6) Causal Transitions

These transition words for essays indicate cause and effect relationships between ideas. They will be particularly useful when you are structuring a logical argument, i.e. using logos as a mode of persuasion . Causal transitions are an important element of academic, legal and scientific writing.

Accordingly
Resultingly
As a result
Consequently
In consequence
As a consequence
For this reason
So much that
Granting that
That being the case
Under those circumstances
With this in mind
For the purpose of
For all intents and purposes
In the event that
In the event of
In light of
On the condition that
To the extent that

7) Examples/Illustration/Supporting Transition

These transition words for college essays can be used to introduce supporting evidence, emphasis, examples, and clarification. There is some overlap here with additive transitions and causal transitions. These transitions are also useful when it comes to building an argument. At the same time, they can signal a shift into a different linguistic register.

For example
For instance
In other words
As an illustration
To illustrate
To put it differently
To put it another way
That is to say
As the evidence illustrates
It’s important to realize
It’s important to understand
It must be remembered
To demonstrate
For clarity’s sake
To emphasize
To put it plainly
To enumerate
To speak metaphorically

8) Conclusory Transitions

These transition words for essays serve to bring an idea or story to a close. They offer a clear way of signaling the conclusion of a particular train of thought. They might be followed by a summary or a restatement of an essay’s argument. In this way they also provide emphasis, setting the reader up for what is about to come.

In conclusion
To summarize
To put it succinctly
To this end
At the end of the day
In the final analysis
By and large
On second thought
On first glance
That’s all to say
On the whole
All things considered
Generally speaking

List of Good Transition Words for Essays (Final Thoughts)

Even when elements appear to be disparate on first glance, transition words are a great tool for giving your essay a smooth flow. They can also create surprising juxtapositions, relationships, and equivalences. The way a reader will understand a transition word depends on the context in which they encounter it.

Individual words and phrases can be used in a wide variety of ways, ranging from the literal to the figurative to the colloquial or idiomatic. “Through the grapevine” is an example of the colloquial or idiomatic. When we encounter this phrase we don’t interpret it literally (as hearing something “through” a grapevine) but rather as hearing news secondhand. There are, of course, a vast number of idioms that are not included in this list but can also function as transitional phrases.

This list of transition words for college essays (and really any form of writing you might be working on) is a resource that you can return to again and again in your life as a writer. Over years of writing we tend to fall into patterns when it comes to the transition words we use. Mixing things up can be exciting both as a writer and for your readers. Even if you don’t choose to stray from your trusted transitions, considering the alternatives (and why they don’t work for you) can offer a deeper understanding of what you are trying to say.

List of Good Transition Words for Essays (An Exercise)

As an exercise in self-understanding, you may want to try highlighting all of the transition words in a piece of your own writing. You can then compare this to the transition words in a piece of writing that you admire. Are they using similar transitions or others? Are they using them more or less often? What do you like or dislike about them? We all use transition words differently, creating different tonal effects. Keeping an eye out for them, not only as a writer but also as a reader, will help you develop your own aesthetic.

College Essay

Emmett Lewis

Emmett holds a BA in Philosophy from Vassar College and is currently completing an MFA in Writing at Columbia University. Previously, he served as a writing instructor within the Columbia Artists/Teachers community as well as a Creative Writing Teaching Fellow at Columbia, where he taught poetry workshops. In addition, Emmett is a member of the Poetry Board at the Columbia Journal , and his work has been published in HAD , Otoliths , and Some Kind of Opening , among others.

2-Year Colleges
Application Strategies
Best Colleges by Major
Best Colleges by State
Big Picture
Career & Personality Assessment
College Search/Knowledge
College Success
Costs & Financial Aid
Dental School Admissions
Extracurricular Activities
Graduate School Admissions
High School Success
High Schools
Law School Admissions
Medical School Admissions
Navigating the Admissions Process
Online Learning
Private High School Spotlight
Summer Program Spotlight
Summer Programs
Test Prep Provider Spotlight

“Innovative and invaluable…use this book as your college lifeline.”

— Lynn O'Shaughnessy

Nationally Recognized College Expert

College Planning in Your Inbox

Join our information-packed monthly newsletter.

33 Transition Words and Phrases

Transitional terms give writers the opportunity to prepare readers for a new idea, connecting the previous sentence to the next one.

Many transitional words are nearly synonymous: words that broadly indicate that “this follows logically from the preceding” include accordingly, therefore, and consequently . Words that mean “in addition to” include moreover, besides, and further . Words that mean “contrary to what was just stated” include however, nevertheless , and nonetheless .

as a result : THEREFORE : CONSEQUENTLY

The executive’s flight was delayed and they accordingly arrived late.

in or by way of addition : FURTHERMORE

The mountain has many marked hiking trails; additionally, there are several unmarked trails that lead to the summit.

at a later or succeeding time : SUBSEQUENTLY, THEREAFTER

Afterward, she got a promotion.

even though : ALTHOUGH

She appeared as a guest star on the show, albeit briefly.

in spite of the fact that : even though —used when making a statement that differs from or contrasts with a statement you have just made

They are good friends, although they don't see each other very often.

in addition to what has been said : MOREOVER, FURTHERMORE

I can't go, and besides, I wouldn't go if I could.

as a result : in view of the foregoing : ACCORDINGLY

The words are often confused and are consequently misused.

in a contrasting or opposite way —used to introduce a statement that contrasts with a previous statement or presents a differing interpretation or possibility

Large objects appear to be closer. Conversely, small objects seem farther away.

used to introduce a statement that is somehow different from what has just been said

These problems are not as bad as they were. Even so, there is much more work to be done.

used as a stronger way to say "though" or "although"

I'm planning to go even though it may rain.

in addition : MOREOVER

I had some money to invest, and, further, I realized that the risk was small.

in addition to what precedes : BESIDES —used to introduce a statement that supports or adds to a previous statement

These findings seem plausible. Furthermore, several studies have confirmed them.

because of a preceding fact or premise : for this reason : THEREFORE

He was a newcomer and hence had no close friends here.

from this point on : starting now

She announced that henceforth she would be running the company.

in spite of that : on the other hand —used when you are saying something that is different from or contrasts with a previous statement

I'd like to go; however, I'd better not.

as something more : BESIDES —used for adding information to a statement

The city has the largest population in the country and in addition is a major shipping port.

all things considered : as a matter of fact —used when making a statement that adds to or strengthens a previous statement

He likes to have things his own way; indeed, he can be very stubborn.

for fear that —often used after an expression denoting fear or apprehension

He was concerned lest anyone think that he was guilty.

in addition : ALSO —often used to introduce a statement that adds to and is related to a previous statement

She is an acclaimed painter who is likewise a sculptor.

at or during the same time : in the meantime

You can set the table. Meanwhile, I'll start making dinner.

BESIDES, FURTHER : in addition to what has been said —used to introduce a statement that supports or adds to a previous statement

It probably wouldn't work. Moreover, it would be very expensive to try it.

in spite of that : HOWEVER

It was a predictable, but nevertheless funny, story.

in spite of what has just been said : NEVERTHELESS

The hike was difficult, but fun nonetheless.

without being prevented by (something) : despite—used to say that something happens or is true even though there is something that might prevent it from happening or being true

Notwithstanding their youth and inexperience, the team won the championship.

if not : or else

Finish your dinner. Otherwise, you won't get any dessert.

more correctly speaking —used to introduce a statement that corrects what you have just said

We can take the car, or rather, the van.

in spite of that —used to say that something happens or is true even though there is something that might prevent it from happening or being true

I tried again and still I failed.

by that : by that means

He signed the contract, thereby forfeiting his right to the property.

for that reason : because of that

This tablet is thin and light and therefore very convenient to carry around.

immediately after that

The committee reviewed the documents and thereupon decided to accept the proposal.

because of this or that : HENCE, CONSEQUENTLY

This detergent is highly concentrated and thus you will need to dilute it.

while on the contrary —used to make a statement that describes how two people, groups, etc., are different

Some of these species have flourished, whereas others have struggled.

NEVERTHELESS, HOWEVER —used to introduce a statement that adds something to a previous statement and usually contrasts with it in some way

It was pouring rain out, yet his clothes didn’t seem very wet.

Word of the Day

See Definitions and Examples »

Get Word of the Day daily email!

Games & Quizzes

Play Quordle: Guess all four words in a limited number of tries. Each of your guesses must be a real 5-letter word.

Usage Notes

Prepositions, ending a sentence with, is 'irregardless' a real word, 8 more grammar terms you used to know: special verb edition, point of view: it's personal, 31 useful rhetorical devices, grammar & usage, 7 pairs of commonly confused words, did we change the definition of 'literally', more commonly mispronounced words, the tangled history of 'it's' and 'its', more commonly misspelled words, 10 bird names that sound like insults (and sometimes are), eavesdrop, fiasco, and 8 more words with surprising origins, 'when pigs fly' and other barnyard idioms, the words of the week - mar. 29, 10 scrabble words without any vowels.

Online Course

45 Best Transition Words and Phrases For Essays

Your essay needs to be coherent and written in a way where one idea flows naturally to the other, and for that, you need transition words.

But how to make sure that everything ties together, and that you present your arguments in a logical, smooth manner? It’s simple. You do it by using transition words and phrases, which can turn your scattered thoughts into a well-organized, and neatly looking piece of prose. “Look on every exit as being an entrance somewhere else.” – Tom Stoppard It is common knowledge that the ability to write a great essay is tremendously helpful to those who are pursuing higher education. So, it wouldn’t hurt to add all the weapons you can find to your essay-writing arsenal, like these transition words.

What are transition words?

Transition words and phrases are a part of speech , and they’re used to create coherent relationships between ideas in the text. The ones you might be familiar with are ‘and’, ‘but’, ‘so’, and ‘because’. They’re applied to maintain a logical, uninterrupted stream of thought and a smooth flow of paragraphs and sentences. Their goal is to show your reader the relationship between phrases, sentences, or even paragraphs. When you use them, you make it easier for your readers to understand how your thoughts and ideas are connected. There are around 200 of them in the English language. Example: Regular exercise leads to improved cardiovascular performance. It improves the function of the brain.

Here are the main rules for the usage of transitional words:

Using transitional words in essays

Your regular essay will comprise five paragraphs – an introduction, three paragraphs to present your points, and a conclusion. Your job is to make the prose consistent, and that’s why you need words and phrases to create links between the ideas. The words and phrases below are mostly used in persuasive (argumentative) essays where you need to convince the readers of your opinion confidently. But in fact, they’re useful in almost any type of writing (such as expository essays ) simply to keep the structure intact. If you use them well, they can emphasize contrast, highlight a similarity, and solidify your conclusion. Transition, a formal definition: the process of changing from one situation, form, or state to another.

Transition words are used at the beginning of each new paragraph. For Example:

To begin with
In the first place
To summarize

They can also be used when you present a new point in the same paragraph. For Example:

There’s a multitude of transition words that will contribute to a sleeker essay.

Many students make the mistake of repeating the same words repeatedly. This causes them to lose impact and meaning. Among grammarians, this phenomenon is called grammar saturation. The important thing to know is that there are several categories to transition words depending on the type of impact you’d like to create in your writing . Often, there are several words suitable for one transition. Just remember that they don’t always mean the same and you might need some practice to recognize the subtle differences between them. To avoid this, look up synonyms and never use the same transition word more than once in a single piece of prose (especially in the same paragraph). If you need a more in-depth course on this topic, you may read A Writer’s Guide To Transitional Words and Expressions.

Here’s a list of the best transition words that’ll come to your rescue:

When you want to indicate similarity or addition:.

Incidentally
More important
For instance
Furthermore
In addition
In the same fashion

Examples of use:

A diet based mostly on carbohydrates can cause massive weight gain. Furthermore, it can cause mental fog and a lack of energy in adult humans.
Small steps can lead to huge gains. For instance, if you write one page a day, you’ll have a whole book within one year.

When you want to indicate dissimilarity, contrast, or contradiction:

By contrast
On the other hand
On the contrary
All the same
At any rate
At the same time
Nonetheless
Despite this
By comparison
In comparison
In place of
Nevertheless
Notwithstanding
Unfortunately
A ban on the possession of firearms would vastly improve the safety of the civilian population. In spite of this, the politicians won’t push it through because of the powerful gun lobby.
Everyone knows that eating excessive amounts of sugar causes health problems. Yet, the consumption of “white poison” is higher than ever.

When you want to indicate similarity:

In the same way
In like manner
Learning computer languages serves as a competitive advantage in the job market. Likewise, the ability to speak Chinese or Japanese can be beneficial.
The cost of mobile devices around the world dropped significantly. In the same manner, laptops and TVs became more affordable.

When you want to indicate cause, effect, purpose, consequence, or result:

Accordingly
As a result
Knowing this
With this object
With this end
To this end
With this in mind
In many cases
In this way
Consequently
For this reason
Fortunately
In any case
Provided that
Excessive time spent at the desk at work can lead to coronary disease. Sitting for a long time is more harmful than the regular consumption of fast foods.
Becoming a self-employed digital nomad isn’t easy. Fortunately, there are many guides and forums on this topic.

When you want to emphasize something:

Specifically
In particular
More specifically
In other words
To illustrate
Drinking a lot of water raises your levels of energy. In particular, filtered and purified water is the best thing to drink.
The player dropped the ball at the very last moment. Truly, this was the reason the team was defeated.

When you want to indicate the time or sequence of events:

In the meantime
Immediately
In the same instant
Subsequently
At that point
The children were starving and without water. Finally, the international convoy came to help them.
The politician angered the crowds. Immediately, you could hear boos from every direction.

When you want to indicate spatial order or reference:

On the opposite side
On the right
On the left
In a corner
In front of
The huge mountain covered the horizon. Beneath it, there were kilometers of caverns.
The table stood in the center of the room. On the right, you could find a few scattered pieces of furniture.

How do these words relate to the format of your essay?

If you focus on academic writing you’ll need to adhere to a specific essay format. Use the following words to create comprehensive transitions between paragraphs:

Introductory transitions

These come in handy when you craft your first supporting paragraph (the one after the introductory one). Here you usually start building on your thesis and start giving arguments in its favor.

Words to use in an introductory paragraph:

The first reason

Connecting the second paragraph to the third:

Additionally
Another reason why
Pursuing this further

Connecting the third paragraph to the fourth:

Yet another reason why
One last reason why

Connecting the body to the conclusion:

In conclusion
To sum it all up
In the final analysis
You can see why
To wrap it all up

Pro tip: Words like ‘for’, ‘and’, ‘nor’, ‘but’, ‘or’, ‘yet’, and ‘since’ shouldn’t be used at the beginning of a sentence if you’re writing a formal essay. “The best part of your story is when it changes.” – Bella Bloom Bonus material – a printable PDF chart with link words (always keep it beside you): A complete list of transition words and conjunctions.

Now it’s your turn to use these transition words

Starting an essay is always challenging, even for advanced writers. Hopefully, by reading this article, I made your task easier by adding a valuable tool to your writer’s toolbox. Just remember to use these phrases originally, and without repetition. The last thing you want to do is to sound mechanical as if you’re writing from a template. Next up, you may want to check a list of amazing short pretty words in English .

Digital marketing course: Join my full AI Marketing course, with over 6h and 30 minutes of video lessons and 5 bonuses and learn the skills necessary to thrive as a marketer in the digital era.

Rafal Reyzer

Hey there, welcome to my blog! I'm a full-time entrepreneur building two companies, a digital marketer, and a content creator with 10+ years of experience. I started RafalReyzer.com to provide you with great tools and strategies you can use to become a proficient digital marketer and achieve freedom through online creativity. My site is a one-stop shop for digital marketers, and content enthusiasts who want to be independent, earn more money, and create beautiful things. Explore my journey here , and don't miss out on my AI Marketing Mastery online course.

Down and Dirty Tips: Persuasion Essay: Adding Transitions

Getting Started
Adding Transitions

Persuasion Transitions

<< Previous: Persuasion
Last Updated: Oct 23, 2023 11:28 AM
URL: https://spcollege.libguides.com/persuasion

My Speech Class

Public Speaking Tips & Speech Topics

A List of Transition Words to Use for Argumentative Essays

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

Writing an argumentative essay requires a lot of effort aside from research. Besides grammar and structure, you definitely need to make sure your essay is coherent by using transitions.

Argumentative essay transition words allow you to wrap up a piece of evidence to support your main point and then move on to another. Keep reading for tips and an exhaustive list of transition words I put together for your argumentative essays.

What Is a Transition Word?

A transition word is critical to producing quality content. Also known as linking words, transition words make basic connections between sentences and paragraphs to show a relationship between ideas.

A strong transition is crucial when writing an essay. It’s not enough that you provide complete information about your main points and supporting details. You also have to make your argument attractive and logical by using transitions in your academic essay.

The absence of transition words will make your paper less readable and understandable. But too many transitions can also ruin your piece. Use them in moderation to avoid confusion about your document.

Function and Importance of Transitions

The goal of transition words is to convey ideas clearly and concisely to your readers. If you’re writing an argumentative paper, you want to make logical connections in your document to prove your central point.

Transitional phrases and words help you produce a logical flow from one sentence or paragraph to another. In other words, they introduce what the following information will be. Some transitions come in single words, while others come in complete phrases and sentences.

Can We Write Your Speech?

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

There are many categories of transitions, including those that present counterarguments and others that build on your arguments. Be careful about using the wrong transition. Otherwise, you won’t achieve your goal of clarity and conciseness. Consider these examples.

“ For instance , an anonymous TikTok user reports having a shorter attention span because of its over-swiping feature.” (In this sentence, for instance is used to provide an example).
“ Here’s an exception to my previous point. ” (This entire sentence is a transition, showing a logical connection between the previous and following sentences).

Transition can also be a sentence to a paragraph long. I’ll show you an example.

Paragraph A: A point that supports co-sleeping as a parenting method.

Transition: Despite this, there are many reasons that prove co-sleeping leads to sleep-related accidents.

Paragraph B: Points that oppose co-sleeping.

Types of Transition Words

There are several types of transitions you can use for making high-quality essays.

Transition Between Paragraphs

A type of transition required for a well-written essay is one you can find between paragraphs. Once you’ve arranged each paragraph according to your outline, it’s important to start each with an effective transition. This word or phrase is usually present in the topic sentence of the body.

Some examples include however, similarly, and for example. But these transition expressions cannot be a single sentence long. The initial sentence of every paragraph should be clear and substantial instead of simply connecting ideas.

Transition Within Paragraphs

Creating a powerful transition within every paragraph of your academic papers avoids choppy sentences. It provides a sense of connection between complex ideas to help readers anticipate what is coming.

These are usually single words or short phrases like in addition, since, and if.

Transition Between Sections

The last type of transition phrases and sentences are those between sections. You’ll find them all over the entire paper to summarize the information. They can be restatements of arguments or a short closing sentence to ensure the flow of ideas.

What Is an Argumentative Essay?

It’s a type of essay that requires you to research a subject matter and establish a position for or against it.

Aside from researching and evaluating evidence, showing a relationship between sentences and sections is essential when writing a paper. This will allow you to wrap up an idea and then start another. You must cite different sources to support your point of view, then show counterarguments.

The entire essay should include an introduction, a conclusion, and at least three body paragraphs.

How Do You Start an Argumentative Essay?

Every type of paper starts with an introduction, which usually includes a hook, background, and thesis statement.

The common essay introduction piques the reader’s interest through a surprising statistic or an interesting question. Provide readers with a background of your entire content piece, then state your main argument in a clear sentence.

Transition expressions are not yet essential in this stage of essay writing. Focus on setting up your point and discussing how you will argue it throughout the paper.

Common Transitions for Argumentative Essay Writing

Take a look at this list of transitional words and phrases commonly used to make strong arguments.

Additionally
In addition
Not only… but also
In the same way
Comparatively
Furthermore
Equally important

Counterargument Transition Words

Here’s a transition word list for essays showing different sides of an argument.

While it is true that
Nevertheless
Despite this
On the other hand
Be that as it may
Even though
Although this may be true

Transition Words and Phrases for Comparing and Contrasting

Here’s a breakdown of transition words and phrases you can use when comparing and contrasting.

In spite of
On the contrary
Different from
In contrast

Transition Words to Include in Your College Essay

Here are some examples of transition words you can use when applying for college admission or scholarship.

To put it in another way
To demonstrate
As an illustration
By all means
In other words

Transition Words for Cause and Effect

Consider this transition word list when showing cause and effect.

As a result
For this reason
Consequently
Accordingly
Under those circumstances
Because the

Transition Words for Essay Paragraphs

At the present time
In due time
To begin with
All of a sudden
Immediately
In a moment

Transitions to Emphasize a Point

Most of all
The main problem/issue is
Without question
More importantly
Most important of all

Transition Words for Additional Support or Evidence

Transition words for sequence or order, transition words for space or place.

In the middle of
In the distance
In the background
Here and there
On the side

To Cite a Source or Paraphrase

According to
This means that
Put it more simply

Transition Words to Begin a Body Paragraph

What is more
Beyond that

Transition Words to Introduce Details

For example
As an example
For instance
A case in point
Specifically
In particular
More specifically

Transition Words for Conclusion

As can be seen
By and large
On the whole
To summarize
In the final analysis
Generally speaking

More Transition Words

With this intention
In order to
In the hope that
With this in mind
For the purpose of
Provided that

Tips for Using Argumentative Essay Transitions

Follow these tips to improve your use of transitions in your essay.

Know What the Transitions Mean

Non-native speakers may need help knowing the meaning of every transition expression, so research every term before using it.

There are also many categories of transition words. You can use them to summarize points, show contradictions, express sequence, or begin a paragraph.

Start Your Essay with an Outline

Writing an outline will make it easier to map your ideas and move them around. This strategy will help you transition between paragraphs.

Don’t Overuse Transitions

The last mistake you shouldn’t make is overuse. Instead of making connections between sentences, you’ll make your paper more difficult to read. It creates more incoherence and distraction in your writing, contradicting its intended purpose in your paper.

Use Transition Words Properly

Now you know how to use transition words and phrases for your argumentative essay through this guide and list. These expressions will help you produce a coherent relationship between every idea.

Mastering transitions for your essay may not be a piece of cake, but practice makes perfect. Don’t forget to revise and proofread your argumentative before submitting it to your professor.

Mother of the Groom Speech – Best Tips & Examples

How to Write the Best Commencement Speech – Tips & Examples

I accept the Privacy Policy

Reach out to us for sponsorship opportunities

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

Using Persuasive Essay Transition Words to Craft a Perfect Piece

In academic writing and persuasive essays, transition words are used extensively. These transition words connect not only two paragraphs but two different concepts as well. Students must learn how to use persuasive essay transition words to make a perfect essay writing .

Table of Contents

What are Transition Words Anyways?

In the ultimate guide of persuasive essay , the main emphasis of the debate is to provide supporting information and connect them with each other. The task of connecting two paragraphs, two concepts, or two arguments is done with the help of transition words. You often read words like ‘next’, ‘accordingly’, ‘therefore’, and more in an article or an essay. Most of the time, they are used at the beginning of a new sentence which tells that they are being used to connect this sentence with the previous one.

Hence the reader’s concentration is not compromised. For your understanding, these are essential transition words you can use in your persuasive essay. These include “and,” “but,” and “but also,” as well as therefore, however, and more.

Persuasive Essay Transition Words That You Must Use

The point of a persuasive essay is to persuade a reader to your point of view. To do this effectively, you need to transition from one topic to another elegantly and logically. Transition words are those words that help move from one idea to the next. Transition words have their particular place of usage and you need to determine where to put them according to your persuasive essay outline that defines a path for content delivery. Let’s look at common transition words and how they are used in essays.

Here’s how you can use sum up in the persuasive essay. To sum up, the conclusion is different from the summary. Summarizing does not mean repeating what you have already said in your essay but rather summarizing it by stating the main points and how they relate to each other to make sense of your ideas.

Secure Your Custom Essay Writing Solution

Summarizing the main points of your essay is a great way to end it. This can be done in several ways:

Use a transition at the end of each paragraph, such as “In summary…” or “Finally….”

Use a transition at the end of each section, such as “In conclusion…” or “And so on….”

Use a transition at the end of your entire essay (such as “Conclusion”)

As has been said

As has been said, the above statement is a quote from an author.

In this transition, you can use the exact words in a typical sentence: “As has been said” or “As has been written.” You can also add other things like “according to” or “in accordance with.”

The better way to understand how you can use ‘therefore’ is with an example like this. Suppose you are writing a persuasive essay on why bacterias are not the main reason for tooth decay. This is how you will use this transition word along with ‘however.’

‘Therefore, as you can see, I have no intention of advocating such a policy. But what about my response to your assertion that “bacteria cause tooth decay”? Well, I will say this: bacteria indeed cause tooth decay; however, the fact that they do so does not mean we should do anything about it.

Consequently

Consequently means “as a result.” As in, “Consequently, if you don’t do this, then I’ll be angry with you.” This can be used to connect two ideas. Mostly used in a cause and effect relationship essay. For example:

Suppose you are trying to say that if your audience is bored during the presentation, you will walk out of there.

Consequently, if my audience is bored during my presentation, I will walk out of there.

‘Thus’ is a good transition word to use if you want to introduce a conclusion. It’s also helpful if you are writing about a cause-and-effect relationship, as it can help readers focus on the main point of your essay. However, this word should never be used as part of an introduction because it can feel like an attempt at persuasion rather than simply stating what happened in your story.

In conclusion

In conclusion, you should reiterate the main idea of the essay. Writers need to make sure that the end conclusion is achieving the primary purpose of a persuasive essay .

Suppose you are writing a persuasive essay on education as an essential factor for economic growth. Here’s how you will use this transition word. Education helps individuals attain higher levels of knowledge and develops their talents and skills. In conclusion, it is essential for people who want careers in these fields to finish high school or college at least.

To conclude

The final sentence of a persuasive essay should be the strongest, most powerful one. It should be short but also powerful and convincing. It could be a summary statement summarizing all the information you’ve presented in your argumentative essay (or maybe just one part). Or it could be a conclusion that ties everything together: This is how you can use the transition word here. “To conclude, I think this is what we can learn from this conversation about love and friendship.”

For this reason

This transition tells what has made you act in such a way. Or what has made you decide this? For example, you can say. For this reason, the best way to move forward is through education.

It is used when the writer wants to conclude a paragraph or an essay.

This is how it is used:

Finally, I would like to conclude by stating that the main points of my essay are:

Persuasive writing is an art form.

It requires skill and creativity to be done correctly.

Get Your Custom Essay Written with 50% Discount Act Now!

This blog uncovers some of the best examples to use as persuasive essay transition words. Students need to learn and use them to enhance the writing effects of their persuasive essays. By doing this, they have a good chance of taking top grades. Students can also use an affordable college paper writing service to awestruck their professors with their creative skills.

First Time Order? Get Custom FREE ESSAY

No Plagiarism & No AI Content

Timely Deliveries

Premium Quality

Unlimited Revisions

Assignment Writing Service
Biography Writing Services
Opinion Essay Writing Service
Cover Letter Writing Service
Critical Analysis Essay
Romeo and Juliet
Admission Essay
Analytical Essay Writing Service
Personal Statement
Research Paper Writing Service
Dream Essay
Annotated Bibliography
Dissertation Writing Services
Contrast Essay
Argumentative Essay
College Essay Writing Service
Application Letter
College Paper
Thesis Statement

We are a team of professional writers providing quality-assured essays, research papers, and assignments. We bring the most affordable services for you with multiple revisions. Get plagiarism-free content with Turnitin pass and on-time delivery. We Create Great Content, Value, & Reliability!

Opinion Essay Writing
Cover letter writing service
College Essay Writing
Our Writers

How To Write An Essay

Transition Words For Essays

Transition Words for Essays - An Ultimate List

12 min read

Published on: Jan 1, 2021

Last updated on: Jan 30, 2024

What are Transition Words?

Transition words are linking words used to connect sentences and ideas in the content. They help the audience move from one idea to another, building a coherent relationship within the document.

When writing an essay , it is essential to make sure that the information provided is readable and understandable by the readers. For this purpose, explicit language, transition words, and phrases are used.

Moreover, these words set a base for the idea that is going to be discussed next.

Transition words can either make or break the entire essay. It is mandatory to keep in view that not every sentence in your essay needs a transitional phrase.

Types of Transitions

Generally, there are three types of transitions that are used while drafting a piece of document. Depending on the length, complexity, and kind of text, transitions can take the following form:

Transition Between Sections - When your document is lengthy, transition paragraphs are used to summarize a particular section for the readers. In addition to this, it also links the information that is to be shared next.

For example:

"In the following section..." "Moving on to..." "Now, let's explore..." "Turning our attention to..." "To delve deeper, we will now examine..."

Transition Between Paragraphs - The transition between paragraphs is when you logically connect the two paragraphs. This connection summarizes the paragraphâs primary concern and links it to the next idea of the other paragraph.

"Furthermore..." "On the other hand..." "Similarly..." "In contrast..." "Moreover..." "Additionally..." "In addition to..." "Conversely..." "Likewise..." "In a similar vein...

Transition Within Paragraphs - They act as cues for the readers to prepare them for what is coming next. They are usually single words or small phrases.

"For instance..." "In particular..." "To illustrate..." "Additionally..." "Moreover..." "Furthermore..." "On the contrary..." "However..." "In contrast..." "In other words..."

Paper Due? Why Suffer? That's our Job!

Types of Transition Words

Here's a table showcasing different types of transition words and their corresponding functions:

Transition Words For Different Types of Essays

Transitional words depend on the relationship you want to convey to the audience about the ideas and paragraphs. Below is a list of words and phrases that can be used to link different sentences, paragraphs, and sections.

Identify which transition expression you want to share for your logical relationship.

Transition Words for Argumentative Essay

In the same way
Equally important
Furthermore
Comparatively
Additionally
In addition
Not only...but also

Transition Words for Compare and Contrast Essay

In contrast
Different from
On the contrary
In spite of

Transition Words for Informative Essay

Provided that
With this in mind
For the purpose of
In the hope that
In order to
With this intention

Transition Words for College Essays

In other words
By all means
To demonstrate
As in illustration
To put it another way

Transition Words for Cause and Effect Essay

As a result
For this reason
Because the
Under those circumstances
Accordingly
Consequently

Transition Words for Expository Essay

Not long after that
Specifically
To begin with
Without doubt
Undoubtedly
Due to circumstances
In similar fashion

Transition Words for Different Parts of Essay

Here's a table listing transition words for different parts of an essay:

How Transitions work

Transitions work by creating a bridge between ideas, sentences, paragraphs, or sections in your essay. They help to establish logical connections and guide the reader through the flow of your writing.

Here's how transitions work:

Coherence : Transitions create smooth connections between ideas, ensuring a coherent flow in your writing.
Signal Relationships: Transitions clarify how ideas are related, such as cause and effect, comparison, contrast, or sequence.
Guide the Reader: It acts as signpost, guiding readers through your essay and indicating the direction of your thoughts.
Enhance Clarity: Transitions improve clarity by organizing ideas and helping readers understand logical progression.
Improve Flow: It ensures a seamless flow between sentences, paragraphs, and sections, preventing choppiness.
Emphasize Key Points: Transitions can be used strategically to highlight important ideas and make them more impactful.

Let's consider an example:

In the above example, transitions like " one such source " connect the idea of solar power to renewable energy sources. " Similarly " then introduces the concept of wind power, creating a logical progression. These transitions help readers follow the flow of ideas and understand the relationships between different energy sources.

Tips to Use Transition Words in your Essay

Here are some tips to effectively use transition words in your essay:

Understand the Purpose: Familiarize yourself with the different types and functions of transition words, phrases, or sentences. Recognize how they connect ideas, provide structure, and indicate relationships between different parts of your essay.
Plan your Essay Structure: Before you start writing, outline the main sections, paragraphs, and points you want to cover. Consider where transition words can be used to improve the flow and coherence of your essay.
Use Transition Words Appropriately: Ensure that the transition word you choose accurately reflects the relationship between ideas. Don't force a transition where it doesn't fit naturally.
Vary Transition Words: Avoid repetitive or excessive use of the same transition word throughout your essay. Use a variety of transition words to maintain reader interest and enhance overall readability.
Pay Attention to Placement: Place transition words at the beginning, middle, or end of sentences, depending on the desired effect. Consider the logical flow of your ideas and choose the appropriate placement for each transition word.
Use Transitional Phrases: Instead of using single transition words, consider incorporating transitional phrases or clauses. These can provide more context and clarity, strengthening the connection between ideas.
Revise and Edit: After completing your essay, review it for the effectiveness and smoothness of transitions. Ensure that they serve their purpose in guiding the reader and enhancing the overall coherence of your writing.
Seek Feedback: Share your essay with others and ask for feedback, specifically on the use of transition words. Others' perspectives can help you identify any areas that need improvement or where transitions could be strengthened.

To sum it up! While mastering transition words may require time and practice, it is a skill well worth developing. These words are crucial for creating coherence and flow in your essays. Throughout this blog, we have explored various transition words and phrases that can greatly enhance your writing.

Remember, practice makes perfect, so don't hesitate to apply these newfound skills in your future essays. You can utilize an AI essay writer to enhance and refine your writing skills.

If you still need assistance or have further inquiries, our team at CollegeEssay.org is available to provide legit essay writing service .

Barbara P (Literature, Marketing)

Barbara is a highly educated and qualified author with a Ph.D. in public health from an Ivy League university. She has spent a significant amount of time working in the medical field, conducting a thorough study on a variety of health issues. Her work has been published in several major publications.

Paper Due? Why Suffer? That’s our Job!

Keep reading

Privacy Policy
Cookies Policy
Terms of Use
Refunds & Cancellations
Our Writers
Success Stories
Our Guarantees
Affiliate Program
Referral Program
AI Essay Writer

Disclaimer: All client orders are completed by our team of highly qualified human writers. The essays and papers provided by us are not to be used for submission but rather as learning models only.

Transition Words and Phrases

Transitions are connecting words or phrases that strengthen the internal cohesion of your writing. Transition words tell the reader how one idea relates to another. Using them appropriately makes your argument more convincing because the reader is able to understand the flow between and within paragraphs, including the relationship between different ideas, evidence, and analysis.

Types of Transition Words and Phrases

additionally
coupled with
furthermore
equally important
in addition

Cause and Effect

accordingly
as consequence
as a result
at that time
concurrently
consequently
followed by
for this purpose
for this reason
subsequently
comparatively
correspondingly
in the same way
on the one han
together with

Contrast/Exception/Concession

a different view is
alternatively
despite/in spite of (+ noun)
differing from
even though
in contrast
it could also be said that
nevertheless
notwithstanding (+ noun)
nonetheless
on the contrary
on (the) one hand
on the other hand
regardless of (+ noun)
in particular
particularly

Example/Illustration

as an example
as an illustration
for example
for instance
illustrated by
in the/this case
on this occasion
specifically
to demonstrate
to illustrate
all things considered
at the same time
in other words
on the whole
that is to say
to put it differently
first, second, third, etc.

Summary/Conclusion

by and large
in any case
in any event
in conclusion
to conclude
to summarize
at that/this point
at that/this time
immediately
in the future
in the meantime
in the past
simultaneously

Sample Transition Words

While (1) qualitative data is helpful in gauging graduate student responses to Boot Camp, it is also crucial that we undertake data-driven analysis to support the value of the four-day writing event. Currently (2), quantitative measures of satisfaction of Dissertation Boot Camp participants are tracked in two ways: through a formal survey posted through SurveyMonkey and an informal survey that is handwritten at the end of the Camp. In fact (3), to ensure reliable data for analysis, the SurveyMonkey questionnaire is filled out by students at three different times: before Camp, on the first day of Camp, and 30 days after Camp. The decision to send the survey at three different times was made in order to ensure that attitudes prior to Camp matched attitudes on the first day, and to then compare that to results after Camp. However (4) the current survey questions are somewhat informal, and none have been psychometrically tested. In order to improve the reliability and usefulness of the collected data, we will need to revise some of our Likert-scale based questions using currently-available test questions from other indices. Ultimately (5) , this combination of quantitative and qualitative data will help us to make decisions about the program as it is offered in subsequent semesters.

(1) Comparison

(3) Emphasis

(4) Contrast/Exception/Concession

(5) Summary/Conclusion

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.

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.

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.

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 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.

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.

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.

IMAGES

Transition Words and Phrases: Useful List with Example Sentences
Persuasive writing word mat (SB10598)
List of Transitional Words for Writing Essays
Transition Words for Essays: Great List & Useful Tips • 7ESL
Opinion / Persuasive Writing
The 8 Elements of an Argument Posters (CCSS)

VIDEO

Transitional Devices || English Grammar || By Sir Mubarik A.Raza
Transition words for Essay, Part 1
برنامج الإنقاذ
PERSUASIVE ESSAY Part6 Transition Sentences
Writing_Persuasive_S9-Expert & Powerful Words
Transition Words for Essay, Part 2

COMMENTS

70+ Transition words for essays with examples
Transition words for essays with examples. Master the art of transitions! Explore a treasure trove of transition words with examples, and learn how to craft a smooth, logical flow of ideas in your essays. This blog post empowers you to write persuasive and well-structured essays that leave a lasting impression.
Transition Words for Persuasive Essays
Transition Words for Persuasive Essays. #persuasive essay #tips for writing good essay #how to write persuasive essays. posted by Andy Preisler 20 May 2015. Table of contents: Persuasive essays are those in which you must convince a reader that your position on an issue is the correct one. Thus, you may want to convince an audience that animal ...
Transitions
Transitions. Transitions help your readers move between ideas within a paragraph, between paragraphs, or between sections of your argument. When you are deciding how to transition from one idea to the next, your goal should be to help readers see how your ideas are connected—and how those ideas connect to the big picture.
Transition Words & Phrases
Example sentence. Transition words and phrases. Addition. We found that the mixture was effective. Moreover, it appeared to have additional effects we had not predicted. indeed, furthermore, moreover, additionally, and, also, both x and y, not only x but also y, besides x, in fact. Introduction.
A List of 200+ Transition Words For Essays
Transition Words for Argumentative Essays. 4. Transition Words for Persuasive Essays. 5. Transition Words for Compare and Contrast Essays. 6. Transition Words for Informative Essays. 7. Transition Words for Expository Essays.
Transition Sentences
Clear transitions are crucial to clear writing: They show the reader how different parts of your essay, paper, or thesis are connected. Transition sentences can be used to structure your text and link together paragraphs or sections. Example of a transition sentence for a new paragraph. In this case, the researchers concluded that the method ...
Transitions
A transition between paragraphs can be a word or two (however, for example, similarly), a phrase, or a sentence. Transitions can be at the end of the first paragraph, at the beginning of the second paragraph, or in both places. Transitions within paragraphs: As with transitions between sections and paragraphs, transitions within paragraphs act ...
100+ Transition Words and Phrases to Use in Essays
Transition words for persuasive essays. Persuasive essays are written to convince the reader of an author's point of view. To make a persuasive essay flow, it is important to use transition words or phrases to move from one idea to another in a smooth and logical way. Here are some highly effective transition words for persuasive writing:
190 Good Transition Words for Essays
In addition, Emmett is a member of the Poetry Board at the Columbia Journal, and his work has been published in HAD, Otoliths, and Some Kind of Opening, among others. Transition words for essays can help improve flow and enhance the quality of your writing. Includes transition words for college essays.
Master Transition Words for Argumentative Essay Writing
151 Transition Words for An Argumentative Essay. Compiling a comprehensive list of transition words for argumentative essays can dramatically improve your writing. Here are some categorized ...
33 Transition Words for Essays
33 Transition Words and Phrases. 'Besides,' 'furthermore,' 'although,' and other words to help you jump from one idea to the next. Transitional terms give writers the opportunity to prepare readers for a new idea, connecting the previous sentence to the next one. Many transitional words are nearly synonymous: words that broadly indicate that ...
Transitional Words and Phrases
Transitional words and phrases can create powerful links between ideas in your paper and can help your reader understand the logic of your paper. However, these words all have different meanings, nuances, and connotations. Before using a particular transitional word in your paper, be sure you understand its meaning and usage completely and be sure…
45 Best Transition Words and Phrases For Essays
All in all. Pro tip: Words like 'for', 'and', 'nor', 'but', 'or', 'yet', and 'since' shouldn't be used at the beginning of a sentence if you're writing a formal essay. "The best part of your story is when it changes.". - Bella Bloom Bonus material - a printable PDF chart with link words (always keep it ...
Down and Dirty Tips: Persuasion Essay: Adding Transitions
Transitional expressions can help tie ideas together and show relationships. They also reveal organization patterns to help your reader follow along. Try out a few in your paper. Be sure that any transition you use makes logical sense. To add an idea: first, second, third, next, in addition, moreover, furthermore, besides, as well.
A List of Transition Words to Use for Argumentative Essays
Transition can also be a sentence to a paragraph long. I'll show you an example. Paragraph A: A point that supports co-sleeping as a parenting method. Transition: Despite this, there are many reasons that prove co-sleeping leads to sleep-related accidents. Paragraph B: Points that oppose co-sleeping.
Persuasive Essay Transition Words To Use In Essay
In the ultimate guide of persuasive essay, the main emphasis of the debate is to provide supporting information and connect them with each other.The task of connecting two paragraphs, two concepts, or two arguments is done with the help of transition words. You often read words like 'next', 'accordingly', 'therefore', and more in an article or an essay.
A Complete List of 200+ Transition Words for Essays
Vary Transition Words: Avoid repetitive or excessive use of the same transition word throughout your essay. Use a variety of transition words to maintain reader interest and enhance overall readability. Pay Attention to Placement: Place transition words at the beginning, middle, or end of sentences, depending on the desired effect. Consider the ...
Transition Words and Phrases
Transition Words and Phrases. Transitions are connecting words or phrases that strengthen the internal cohesion of your writing. Transition words tell the reader how one idea relates to another. Using them appropriately makes your argument more convincing because the reader is able to understand the flow between and within paragraphs, including ...
Transition Words for Essays: Great List & Useful Tips • 7ESL
Nevertheless. On the contrary. Example: Still, it would be a terrible waste of tomatoes, so we won't pelt the politicians. Along with the argument for or against something, is the expansion of an idea. These transitions help lay the foundation for taking an idea or thought, then adding more to it.
English Transition Words 101: Everything You Need to Know
Sequential transition words. Sequential transition words are useful when outlining a step-by-step process or a sequence of events. They help readers understand the time, order, and sequence of your ideas. Some good examples include "then," "first," "in addition," "subsequently," "afterward," "to begin with," "second ...
PDF Transition, Persuasive, and Descriptive Words
PERSUASIVE WORDS Recall: Persuasive Essays will ask you to PERSUADE or CONVINCE your audience to believe in you, in your side of the argument. Reread this familiar Persuasive Prompt: Some experts believe that television has a negative impact on society. Think about the television and how it affects you. Now write to convince the reader to
Transcript: Ezra Klein Interviews Ethan Mollick
I couldn't do a transition. Give me 30 versions of this sentence in radically different styles. ... outline the problem, you know, the essay you're going to write. Second, give me the first ...

70+ Transition words for essays with examples

List of Transition words for essays

Transition words for essays with examples

Related Posts:

Leave a Reply Cancel reply

Download the Word coach App on your Android phone

Transition Words for Persuasive Essays

Good Transitions to Improve Logical Flow

Primary Uses for Transition Words and Phrases of Essays that Attempt to Persuade

Transitions Can Be Tricky

Andy Preisler

Sentence pair #2: Effective Transition

Transition Words For Essays - The Ultimate List

What are Good Transition Words for Essays?

Purpose of Transition Words

Examples of Different Types of Transition Words

Addition Transitions

Comparison Transitions

Contrast Transitions

Cause and Effect Transitions

Time Transitions

Illustration Transitions

Emphasis Transitions

Summary Transitions

Sequence Transitions

For Showing Exception

For Proving

Transition Words for Argumentative Essays

Transition Words for Persuasive Essays

Transition Words for Compare and Contrast Essays

Transition Words for Informative Essays

Transition Words for Expository Essays

Transition Words for Cause and Effect Essays

Transition Words for Synthesis Essays

Transition Words for Analysis Essays

Conclusion Transition Words for Essays

Beginning Transition Words for Essays

Paragraph Transition Words for Essays

Transition Words for Essay’s First Body Paragraph

Transition Words for Essay’s Second Body Paragraph

Transition Words for Essay’s Last Body Paragraph

Transition Words for Quotes in Essays

Transition Words for Essays Middle School

Transition Words for Essays High School

Transition Words for Essays College

Do’s and Don’ts of Using Transition Words

Keep reading

Have a language expert improve your writing

Transition Sentences | Tips & Examples for Clear Writing

Instantly correct all language mistakes in your text

Table of contents

Placement of transition sentences

Prevent plagiarism. Run a free check.

The known-new contract

Transition words and phrases

Grouping similar information

Cite this Scribbr article

Is this article helpful?

Jack Caulfield

Transitions

The function and importance of transitions

Signs that you might need to work on your transitions

Organization

How transitions work

Types of transitions

Transitional expressions

190 Good Transition Words for Essays

List of Good Transition Words for Essays (Continued)

Transition Words for College Essays

1) Additive Transitions

2) Comparative Transitions (Similarity)

3) Comparative Transitions (Difference)

4) Sequential Transitions

5) Spatial Transitions

6) Causal Transitions

7) Examples/Illustration/Supporting Transition

8) Conclusory Transitions

List of Good Transition Words for Essays (Final Thoughts)

List of Good Transition Words for Essays (An Exercise)

Emmett Lewis