Created by Randy Ingermanson - "the Snowflake Guy"
America's Mad Professor of Fiction Writing

Advanced Fiction Writing Blog

Your One-Sentence Summary

by 1 Comment

in Fiction Writing

It’s never too late to write the one-sentence summary for your novel. Or rewrite it.

The one-sentence summary is the first step in my wildly popular Snowflake Method of writing a novel. But even if you don’t use the Snowflake Method, you still need a one-sentence summary.

What is a One-Sentence Summary?

A one-sentence summary is a sentence of up to 25 words that sets up the Story Question in your reader’s mind. Please note that the one-sentence summary usually is not the Story Question itself. The one-sentence summary causes your reader to ask the Story Question.

And what is the Story Question? That’s easy. The lead character of novel has some goal that they want to achieve by the end of the novel. Either they want to get something, or do something, or become something. The Story Question asks whether the lead character will achieve their goal. 

An Example One-Sentence Summary 

Let’s write an example one-sentence summary for one of my favorite spy novels, The Eye of the Needle, by Ken Follett. A little background is in order. 

It’s the spring of 1944, and World War II is anyone’s war to win—or lose. The German army is defending Europe, and the Allies have captured much of Italy. Everyone knows the Allies are going to attempt an invasion of France by crossing the English Channel. But nobody knows where the attack will land. Calais is the closest point on the French coast for an attack, but Normandy is less well-defended.

The German armies must defend both Calais and Normandy against attack, but they have limited forces. Their job would be much easier if only they knew where the attack would land. 

The Allies intend to attack Normandy. To fool the Germans, they create a large fake military camp on the ground in East Anglia, making it appear that they will attack Calais. The camp can easily be seen from the air and has thousands of fake tanks, airplanes, and buildings. The Allies generate fake radio messages from the camp, and run a bombing campaign against Calais.

The ruse works, and the Germans focus their defense on Calais. The Allies attack Normandy and create a foothold in Europe that eventually leads to victory. 

All of the above is standard history. What could have gone wrong? Suppose a German spy had investigated the fake military camp and discovered the ruse? Suppose the spy notified the Nazi high command? Then the Germans might have shifted their defenses to Normandy, and the war might have ended differently. We’ll never know, because it didn’t happen. 

But Ken Follett decided this possibility would make an exciting novel. Here’s my one-sentence summary of the storyline: “Shortly before D-Day, the only German spy in England discovers that the Allied invasion force threatening Calais is a fake.” 

That’s it. Just 20 words. I’ve left out all the story background. I’ve left out the names of all the characters. I’ve left out the Story Question. The one-sentence summary leaves out almost everything. But what goes into it? 

The Ingredients of a One-Sentency Summary

  These are the usual ingredients I use for cooking up a one-sentence summary. I don’t always use all of them, but I usually use most of them:

  • Time or place information to establish the setting. 
  • A paradoxical description of a major character.
  • A surprising event that suggests the Story Question. 
  • At least one emotive “kicker” word. 

In my example one-sentence summary, the phrase “shortly before D-Day” tells us the time, and the words “in England” tells us the location. We don’t need to be more precise than that. 

The paradoxical description of a major character is “the only German spy in England.” This is paradoxical because it’s rather shocking to hear that there might be just a single spy in the entire country. The reader probably won’t know for sure if it’s true, but it’s possible. And this fact massively raises the stakes on the story. This is the only spy who can inform the German high command, so everything is riding on him! 

The Story Question is obvious: Will the spy be able to warn his superiors about the fake invasion force, or will he not? The one-sentence summary doesn’t “tell” the reader the Story Question. It “shows” the reader enough information to figure out the Story Question. And having figured it out, the reader is now engaged in the story. 

The “kicker” word is the last one in the sentence—“fake.” The first 19 words of the story appear to be about an invasion force, and everyone knows there was an invasion. So the first 19 words make it seem like this is just another war story. Then the word “fake” turns everything around. Readers who know the history of the Normandy invasion will realize that this must be FUSAG—the famous fictitious First United States Army Group, under the command of George Patton. Readers who don’t know the history of the invasion will wonder what’s going on—and if they care about World War II, they’ll want to know more. 

Why Do You Need a One-Sentency Summary?

There are many reasons you need a one-sentence summary. Here are some of the most important:

  • It keeps you focused when you’re writing your first draft, potentially shaving months off the time it takes to get it written. 
  • It helps you edit your manuscript, because it tells you what to leave in, and what to take out. 
  • It sells your book to your agent, who now knows how to sell it to your editor.
  • It sells your book to your editor, who now knows how to sell it to their publishing committee. 
  • It sells your book to the publishing committee, who makes the final decision on whether your editor will be allowed to publish your book. 
  • It sells your book to your marketing team, because when you hand them a great one-sentence summary, you’ve done half their job. 
  • It tells your cover designer how to create the perfect cover for your book. 
  • It sells your book to potential readers in your target audience. In ten seconds, they know your book is exactly what they’ve been dying to read. 
  • It scares away potential readers who are not in your target audience. You absolutely don’t want them reading your book and then leaving a review explaining why it’s not the book they were expecting. 

What if You Don’t Have a One-Sentency Summary?

There’s no better time than yesterday to write one. If that didn’t work out, there’s no time like the present. If that’s not in the cards, then tomorrow still works.

Some writers know their one-sentence summary from the get-go, before they even write the first word of their novel. Other writers like to discover their one-sentence summary as the story unfolds in their mind, bit by bit. They may need to write the whole first draft before they know what their story’s about. And that’s fine. 

The truth is that even writers who planned their story in advance will find some surprises while writing the first draft. By the time the manuscript is written, the story has usually evolved. In that case, it doesn’t hurt to refine the original one-sentence summary—or scrap it altogether and write a new one, a better one. 

I like to write a one-sentence summary before I start writing. But then I refine it after I’ve written the first quarter of the first draft. Then I refine it again when the book is half done, and again when it’s three-quarters done. And (hopefully) one last time when the first draft is complete.

There’s no harm in revising your one-sentence summary several times. It’s a bit like a fine wine—it gets better with age. 

Homework

  • Do you have a one-sentence summary for your novel? If not, would you like one?
  • What is the time and place where your novel is set? 
  • What is the most important goal of any of the characters in your story? (It doesn’t need to be your protagonist who has the goal.)
  • How can you define that character in a paradoxical way? 
  • What is the “kicker” you can put at the end of the sentence that makes the story special? 
  • Give yourself one hour and write the best one-sentence summary you can within that time limit. It can be awful, if that’s the best you’ve got, but it needs to be 25 words or less. Less is more.

Some Example One-Sentence Summaries

What makes each of the following one-sentence summaries work? Can you do better?

  • A 17-year-old girl pretends to fall in love with another contestant in the arena where she and 23 other teens must fight to the death. (The Hunger Games, by Suzanne Collins.)
  • A young English woman with little prospect of marriage must fend off a rude young aristocrat who thinks he loves her. (Pride & Prejudice, by Jane Austen.) 
  • At the height of the cold war, a Russian submarine captain decides to turn over his latest-generation nuclear sub to the Americans. (The Hunt for Red October, by Tom Clancy.)
  • A rogue physicist travels back in time to kill the apostle Paul. (My first published novel, Transgression.)

How to Interview Your Characters

by 42 Comments

in Craft

Most novelists don’t know their characters well enough when they start writing their novel. The problem is that you get to know your characters by writing about your characters. 

If you get to know your characters by writing the first draft of your novel, you’ll write the first 200 pages before you really know your characters. And that may mean you need to thoroughly rewrite the whole book.

That seems inefficient. Isn’t there a faster way? 

Yes, there is. If you use my Snowflake Method, you’ve already got a nice tool for getting to know your characters. But not everyone’s brain is wired to use the Snowflake Method. 

So what if you’re not a Snowflaker?

If you’re not a Snowflaker, you can interview your characters. That’s a great way to get to know them. And in fact, even if you are a Snowflaker, you can also interview them, and it’s a great way to fill in some of the missing details in your Snowflake document.

How To Interview One Character

First, let me thank one of my very first friends in the writing business, John DeSimone. I met John at a writing conference in 1990, and we quickly became writing buddies. We talked on the phone often over the years. John introduced me to my first agent. And he also was the first person to tell me about interviewing his characters. 

John later got an MFA in creative writing, and he taught writing for years. He’s organized writing conferences, worked as an editor, and worked as a ghostwriter. And of course he’s published some novels. You can see what he’s up to at his website.

Interviewing a character is extremely simple. Here are the steps:

1) Decide which character in your novel you want to get to know better.

2) Open up your word processor and start a new document. 

3) Ask your character any question that comes to mind. A good one is, “What’s your main problem at the start of this novel?”

4) Let your character answer, however long or short they want to go. 

5) Ask another question based on that answer. You can be friendly or antagonistic, or both, or neither. Pretend you’re writing a feature article for your favorite news outlet. Make your character talk. Listen to how they express themselves. Continue until you’re done. 

Which Characters Should You Interview?

I find it useful to interview any character who gets significant air time in my novel. 

Definitely interview your lead character. One of the hardest parts of writing a novel is figuring out where your story is going. When you interview your lead character, ask them where they think they’re going. Then in your story, force them to go somewhere else. 

I think it’s even more important to interview your villain. Why? Because it’s all too easy to make your villain a two-dimensional bad guy with no redeeming features. When you interview your villain, you have a chance to dive deep, to figure out why they’ve gone bad. And how they justify their actions. How they convince themselves that they’re actually the good guy, the hero of the story. When you know that, you’ll automatically have a better story. 

It also makes sense to interview any viewpoint characters. If you’re writing even one scene from any character’s point-of-view, it really helps to know how they think. And you learn how they think by listening to them talk. You get them talking by asking them questions.

An Example Character Interview

OK, enough theory. Here’s the beginnings of a character interview with a guy most of you are familiar with, Luke Skywalker, from Star Wars. This is not an official interview. Luke is not my character, and I had nothing to do with the Star Wars movies. This is purely for educational purposes. 

This is how I imagine I’d get to know Luke if I was just starting out to write the very first Star Wars movie, and if I didn’t really have a good idea where the story was going. 

In this interview, I’ll use my initials (RI) and Luke’s initials (LS). And away we go…

RI: Hi Luke, you’re a young guy working on a farm. Tell me what you’d like to be doing in five years. Where do you see your life going?

LS: Don’t get me started! I’m going nowhere. I hate working on this farm. This is the most boring planet in the galaxy. And I’ll probably die of boredom before I’m thirty. 

RI: Why don’t you just leave? You’re not helpless.

LS: I can’t leave! I owe it to my Uncle Owen and Aunt Beru. They raised me when I was an orphan, and now I have to help them keep the farm going. Even though I hate it. 

RI: I don’t get it. Yes, you owe them something, but you’re not an indentured servant. You’re an adult, and farming isn’t in your blood. Can’t they hire somebody? Or get a few droids to help out?

LS: They can’t afford to hire anybody. And droids are expensive. So I’m stuck here. My best buddy went off to join the rebels last year, but I’ll be here forever. 

RI: Explain to me about the rebels. Is there something going on I don’t know about?

LS: What cave did you crawl out of? Don’t you know? The whole galaxy’s in revolt. The evil Emperor has finally gone too far. There are whole planets that have rebelled. There’s something called the Rebellion, which I’m not supposed to talk about, but it’s real. And it’ll be over before I ever get off this planet to join. 

RI: That sounds great! The Rebellion will knock off the evil Emperor, and you’ll be safely here, away from danger—

LS: What are you talking about? The Rebellion hasn’t got a prayer of winning. There’s this new thing called the Death Star. It can knock out a planet with one giant zap. And then on to the next one. Everyone’s terrified of it, but nobody’s doing anything about it. 

RI: Well, then obviously you don’t want to get involved. If the Rebellion has no chance of winning, you’d just get yourself killed, and that would be—

LS: NO!!!! I can’t just do nothing. That’s stupid and lame and wrong. I could help. I’m a good flyer. I could go to battle and fight the Evil Empire. 

RI: With all due respect, you’re just one guy. I’m sure you fly very well for a farm boy, but you’re not military-trained, and anyway one guy against the Death Star doesn’t sound like a fair fight. If you want my advice, don’t get involved.

LS: I don’t care! I’ve got to do something! You make me sick, talking about running and hiding. 

RI: Hey Luke? Chill, OK? Frankly, you sound a little childish. You talk big about fighting the evil Emperor and taking on the Death Star, but you can’t even stand up for yourself and tell your uncle you need to get off the farm. I think you’re all talk, no action. 

LS: You don’t talk to me like that, you hear? Cause if you do, I’ll … um … 

RI: You’ll do what, Luke? Throw milk on me? Tell the teacher I called you names? I don’t think you’re the violent type. I don’t see you using force to get what you want. 

LS: Wait, what did you say? 

RI: Are you going to throw milk on me?

LS: No, after that. The part about using force. How do you know about that?

RI: I have no idea what you’re talking about. 

LS: You never heard of The Force?

RI: No, what’s The Force?

LS: Well, I’m not supposed to talk about it. Uncle Owen would be really mad. But I heard a rumor that there used to be these amazing guys called the Jedi Knights. And they mastered something called The Force. And they were like, unbeatable in battle. 

RI: Sounds like an old wives tale, Luke. Maybe you should get back to milking cows, or whatever you farm boys do on a desert planet. Because look, I already told you what your real problem is, and—

LS: My problem is I’m stuck here on the farm!

RI: Sorry, no. Luke, your real problem is that you think you’re stuck here on the farm, and you can’t see that there’s absolutely nothing holding you here except your own scaredy-cat self. You say you want to leave, but you don’t really. You’re a bratty little kid, Luke. You don’t want to leave bad enough to just do it, and consequences be damned.

LS: Not true! I should … punch you for that!

RI: Yes, you should. But you won’t. Because you’re just a whiny do-nothing kid, and you’re never going to amount to—ouch! That hurt! Hey, come back here, and I’ll punch you right back! Where do you think you’re going?

LS: I have no idea. But I’m out of here.

What Are You Waiting For?

Are you itching to start your first interview with one of your characters? What are you waiting for? You have a whole universe of potential characters waiting to be discovered. 

Go to it. And may the … 

No, no, I’m not using that cliche. It’s been done to death. But remember one thing. At one point in time, nobody on the planet had ever said, “May the Force be with you.” 

Until George Lucas met Obi-Wan Kenobi. I like to think they met in a smoky bar, had a bunch of drinks, talked about life and war and philosophy and love and power and fear and hopes and dreams. And about two hours in, working on their fifteenth beer, Obi-Wan Kenobi said something about the Force. 

And George was listening. 

The Problem With Zingers

by 86 Comments

in Dialogue

Writing fiction is all about creating conflict. Putting your characters in a crucible. Raising the temperature. This shows your reader what your characters are made of. And one reason we read fiction is to learn how to deal with the conflict in our own lives by living out conflict in somebody else’s skin. 

Dialogue is one of your best tools for creating conflict in your fiction. It’s not your only tool. You’ve also got action, interior monologue, interior emotion, and (sometimes) description. 

And one of the quickest ways to raise the temperature using dialogue is with a zinger. Let me define what I mean by a zinger. It’s a short, pithy remark that makes some other character look stupid or exposes their lie. 

That’s all fine in fiction. In your novel, you have good people and bad people. They’re clearly defined. Your protagonist is (usually) one of the good people. Your villain is (almost always) one of the bad people. Your protagonist stands for the right, and your villain stands for the wrong, and a well-aimed zinger is a shot for justice.

So What’s Wrong With That?

Nothing’s wrong with that, if you have all the facts. If you know exactly who’s right and who’s wrong. And you do know that in a novel, because you created the storyworld. You are the God of your storyworld; you are omniscient; you can set things up so there is a clear right side and a clear wrong side. 

And you control how high the temperature goes in your novel. You can set things up with a zinger, and maybe a counterzinger, and maybe even a final countercounterzinger. But when the temperature has risen to just to the right point, you get to decide when to drop it down again. Because you’re God. It’s your story, so you set the limits. You choose how much mud will be slung, and then you stop the action. 

Real life is a little more complicated than that. In real life, you and I are not God. We’re not omniscient. We sometimes make mistakes. (At least I do; I’m betting you do too.) 

In real life, when we get into an argument, it’s likely that both sides actually have some valid points to make. Because both sides bring different life experiences to the table. You know stuff I don’t. I know stuff you don’t.

Now let’s suppose you and I get into a zinger fight. Let’s say that I simplify your position to make it sound as dumb as possible, and then I shoot a zinger at you. You very rightly get angry that I misrepresented your case, so you respond in kind. You simplify my position to make it sound as dumb as possible, and then you fire a zinger back at me. Maybe you even escalate it a bit. Then I escalate it more with my own zinger. 

The problem now is there’s no limit. We can keep escalating it until everyone’s furious. God doesn’t usually step in to lower the temperature. Everyone keeps slinging mud until they’re all covered with it, and they’ve forgotten what the argument was about in the first place. 

Zingers raise the temperature without limit. Zingers kill rational discussion. Zingers make real life worse, not better. 

Zingers on Social Media

One major problem with social media is that it promotes zingers. The social media algorithms reward and amplify outrage.

Here’s how it works.

Somebody posts a zinger on a social media platform. It’s often about religion or politics, and it’s often a meme that simplifies and misrepresents somebody else’s beliefs into something ridiculous. Then it skewers that misrepresentation. 

If nobody responded to the zinger post, it would just die. But if it’s outrageous enough, somebody on the other side will get angry, and they’ll respond with their own zinger. The algorithm notices this and shows it to more people. Then the original poster responds with a new zinger. That’s more juice for the algorithm, and it shows the post to more people. And so it escalates.

The more the temperature rises, the more responses the post gets, and the more the algorithm shows it around, and the more people get angry. 

Is this sounding familiar? 

The social media platforms love outrage, because outrage means engagement, and engagement means eyeballs, and eyeballs mean advertising dollars. 

But all that outrage just turns social media into a toxic pit that nobody likes. A place where everyone is angry. Where everyone’s blood pressure is up. Where the only winner is the billionaire who runs the social media platform. 

Yeah, But There’s Nothing We Can Do About It

It’s easy to think that we have no control here. Zingers are gonna zing, and we can’t stop them.

Actually, we can do something about it. Anyone can choose to opt out of the zinger lifestyle. Anyone can quench the zingers in their own personal world. Anyone can help make the world a better place. 

Anyone can do that by adopting a few simple rules. Here are the ones I’ve adopted recently, which you might find useful.

Rules For a Zinger-Free World

  1. Don’t post zingers. If you can simplify somebody else’s beliefs down to just a few words that could be zinged, then you probably don’t understand their beliefs. Real beliefs of real people have nuance. Your beliefs have nuance. Mine do. Everybody’s do. 
  2. When you see a zinger on social media that enrages you, ignore it. If you have an option to hide it, do so. (This will release one of those feel-good chemicals in your brain, so it’s actually good for you.) The algorithm will take note and show you fewer zingers likely to enrage you. And it will also take note that the post got negative engagement, so it may actually show the post to fewer people. 
  3. If you post something on social media, and somebody responds with a zinger, ask yourself if you did something to enrage them. If so, then apologize. If not, then delete the zinger. If you know them, send them a message that you don’t allow zingers on your page. If you don’t know them, post a short message saying that you deleted a zinger because you don’t allow zingers on your page.
  4. If you’re really committed to eliminating zingers, declare your page a zinger-free zone. You may be able to post your own personal rules for a zinger-free world somewhere on your page or your profile. Then you can refer violators to your rules when they complain that you deleted their zinger.

Will Going Zinger-Free Actually Make a Difference?

If you and I are the only people who adopt zinger-free rules, then we’ll each benefit personally.  Our blood pressure will be lower. We’ll sleep better. We’ll feel happier. These benefits kick in immediately. 

But imagine a world in which most people adopt their own personal set of zinger-free rules. Then the world would become a less hateful place. We’d all be better off. The more people who go zinger-free, the better the world would be. These benefits would take time, because it takes time for new ideas to spread. But the early adopters would benefit most. 

Please note that I am not saying nobody should ever discuss controversial ideas. Of course we should. That’s how we learn. That’s how we change. But you can talk about tough subjects without using zingers. And you can refuse to engage with people who want to zing you.  

There’s one group who won’t like the idea of a zinger-free world—the billionaires who profit from the outrage. I’m not too worried about them. I bet you aren’t either. 

Are you in? Or do you like things the way they are?

Zinger-Free

Researching Your Novel With ChatGPT

by 12 Comments

in Research

AI tools burst onto the public consciousness last year with a new release of ChatGPT that seems pretty smart to most people. It’s not yet smarter than a human. But it’s surprisingly good. And it’s fast. And it’s cheap. 

I have no interest in writing my novels using AI. My novels should be mine, not somebody else’s. 

But a lot of people use AI as a research tool. As a better version of Google. 

What Could Possibly Go Wrong?

You’ve probably heard that ChatGPT and other tools that use “large language models” are prone to hallucination. Meaning they tend to make up an answer when they don’t know. 

What’s the story here? True or not true? 

I recently had a research question that I took to ChatGPT to see how it would do. As some of you know, I write historical novels, and I’ve read the works of many historians over the years. I’ve read so many, it’s sometimes hard to remember who exactly said what. 

I had a vague recollection that one particular historian (we’ll call him Fred) had written on a particular topic. But I wasn’t sure. A search on Google didn’t bring up anything. So I asked ChatGPT what “Fred” had said on this subject. 

ChatGPT replied with a general high-level summary of Fred’s thoughts on this subject, which it organized as five bullet points. I am very familiar with Fred’s writings, and these certainly sounded like things Fred would say, but I was looking for references, exact quotes.

I asked ChatGPT for a specific reference for bullet point 4. It immediately referred me to one of Fred’s well-known books, which I have in my library. I bought it many years ago, the fifth edition of the book. ChatGPT referred me to the sixth edition of the book, and it said I could find Fred’s thoughts explained well in Chapter 9. It even gave the title of Chapter 9. 

I opened my copy of the fifth edition and found that the title of Chapter 9 was not the one ChatGPT had given. So I went to Amazon and bought the e-book version of the sixth edition, just so I could drill down to the actual words of Fred.

When I opened the sixth edition, I found that the title of Chapter 9 in this edition was the same as in the paper copy I bought 40 years ago. ChatGPT had gotten the chapter title wrong. It wasn’t close.

Worser and Worser

I told ChatGPT it had made a mistake, that it had given the wrong title for Chapter 9, and in fact that chapter had nothing to do with the question I’d asked in the first place. 

ChatGPT immediately apologized for the confusion. It told me the actual material I wanted was found in Chapter 8 and Chapter 10 of the book. And it again gave me the titles of these chapters. 

But both titles were wrong, and those chapters also had nothing to do with the original question. It seemed that ChatGPT was simply digging itself in deeper and deeper. 

I was getting impatient. I told ChatGPT that neither chapter title was correct, and I asked for a direct quote of Fred’s own words. I figured I could then do an electronic search for any prominent words in the quote, and that would take me to the passage where Fred dealt with my question.

ChatGPT again apologized for the “confusion” and gave me a direct quote from Fred. It was two full sentences, about 70 words long. I’ve read enough of Fred’s books to know his voice. The quote sounded exactly like what he would have said. So I searched for several words in the quote. 

They weren’t there. ChatGPT had invented a direct quote from Fred. When people talk about hallucinations of ChatGPT, this is what they mean. 

I challenged ChatGPT again, telling it that I have the book, and the quotation it had given me was NOT in the book anywhere. 

More Apologies

ChatGPT apologized again. I will say this for it—ChatGPT is good at apologizing. I’ve known many people who make up stuff but never apologize for their mistake. ChatGPT at least will admit it’s wrong when you confront it. 

ChatGPT did more than apologize though. It gave me a shorter quotation from Fred’s book, giving me the page number on which the words could be found. I checked. Another hallucination.

My response to ChatGPT was very terse: “I have the book. This quotation is not found in it.”

You can guess what happened next. ChatGPT apologized again, and gave me another quote that sounded exactly like what Fred would say. This time, ChatGPT attributed it to Chater 8. 

But once again, the quote was not in the book. So I challenged ChatGPT yet again, and again it apologized and gave me another quote that sounded perfectly authentic, but wasn’t.

The Bottom Line

By the end of the session, ChatGPT had given me five apologies for incorrect statements. But I never did find out what Fred thinks on the particular topic. 

Let’s be clear. When I started the session, I had a vague recollection that Fred had written something once on this topic, but I couldn’t remember exactly what he said or where it was found. I knew that I didn’t know the answer. 

During the session, ChatGPT confidently gave me five answers that were no better than my vague recollection. They were no worse, but I was looking for better, and ChatGPT was just as bad at pulling up the actual quote as I was. But ChatGPT didn’t know that it didn’t know.

There’s a saying that’s been going around for awhile, that “You don’t know what you don’t know.” This is often associated with the Dunning-Kurger effect, which says (very roughly) that people who are very ignorant of a subject often overestimate their level of understanding of it, whereas highly informed people accurately estimate their level of understanding. 

Or in other words, ignorant people don’t know that they don’t know something. But competent people know when they know, and they also know when they don’t know. 

I am pretty well-read in my chosen time period of history, but there are many things I don’t know. And I’m at least competent enough to know that I don’t know something. 

ChatGPT does not know when it doesn’t know something. And there’s our hazard. 

Because ChatGPT was trained on information scraped from the internet. And now many people are using it to write articles to post on the internet. That’s much easier than doing the hard word yourself. In a morning’s work, you could use ChatGPT to write dozens of articles. 

Which means that future variants of ChatGPT and other large language models will probably be trained on information that was hallucinated by their own previous versions. That can’t end well. 

Should You Use ChatGPT for Research?

Yes, of course you should. I recently asked ChatGPT a math question which I’d been puzzling over for a couple of hours. It instantly suggested a possible solution. That wasn’t quite what I needed, so I pointed out some flaws in its suggestion. It immediately suggested an improvement. That was also not quite what I needed, but it was close. And I solved the math problem. 

The moral is this: Trust, but verify. (That’s an old Russian proverb that Ronald Reagan learned about and repeated often. John Kerry later updated it to “Verify and verify.”) 

Use ChatGPT for ideas. It can be very creative. But verify everything. If ChatGPT gives you a direct quote, with references and page numbers, look it up and make sure. 

Human sources are fallible too, but good human sources written by experts in their field have a huge advantage over ChatGPT—they know when they don’t know. 

Privacy Policy Cookie Policy
Terms and Conditions
>