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. 

Must you do on-site research for your novel in order to be “authentic?”

Melissa posted this question on my “Ask A Question For My Blog” page:

I’m currently reading a book on writing historical fiction in which the author strongly emphasizes researching on location. While I agree with him 100% that on-site research will enrich your story, it’s not always feasible to travel to your stories physical location to do so. What would you say is the second best option available to a writer who wants to authenticate the physical location of a place that he/she has never been?

This question is a good one, whether you’re writing historical fiction or any other kind of fiction. Must you do on-site research?

I remember years ago reading an interview with Tom Clancy in Writer’s Digest. I don’t have that interview anymore, but one thing stood out to me. If my memory is correct, in that interview, Tom said that he had never been on a submarine until after he wrote his book THE HUNT FOR RED OCTOBER. But he had talked to lots of people who had.

Since THE HUNT FOR RED OCTOBER was notable for its highly authentic feel of life on a nuclear sub, this surprised a lot of people. How did Tom make his readers believe that they were experiencing life on a sub, if he hadn’t experienced it himself?

The answer is not merely that Tom talked to a lot of people. Tom also asked those people the right questions. His books are packed with details — things that make you believe you’re right there. I’ve never been on a sub, so I can’t speak from experience on whether those details are right. But the very fact that the details are there makes you FEEL like they’re correct. In principle, a writer could make it all up, and yet make it feel real by simply showing lots of details of the environment. But more importantly, the writer must make it matter to the reader by finding the emotive impact those details have on the characters.

I’ve never been to Mars, and yet I wrote two novels set on Mars with my co-author John Olson. John and I studied up on what Mars is like, based on the best information we had. Then we imagined what it would be like living in a small habitation module on Mars, recycling the water, dealing with the peroxide-laced Martian dust, getting on the nerves of the other astronauts, living in constant fear of a depressurization event that would mean certain death, and suffering the effects of hypervigilance as a result. Then we took that imagination and made it real in the form of sensory details and everyday actions in the lives of our astronauts. In the end, the physical details were less important than the emotive impact those details had on our characters.

I’ve never been to ancient Jerusalem, but I wrote three novels set there. I have been to modern Jerusalem, and I spent an entire day studying a model of what the ancient city looked like. I also wandered around the old city, getting a feel for the color of the stones, the blue of the sky, the size of the city. I also spent absurd amounts of time reading the writings of people who lived in that time and place, learning the way they expressed ideas and how they interacted with each other. I tried to imagine what they cared about and what they feared and hoped for. Then I took all that and put it into concrete details. Again, the actual details were less important than the emotive effect they had on my characters.

Are there factual errors in my novels? Almost certainly. The evidence available for both Mars and ancient Jerusalem is fragmentary. But you can’t write a novel using fragmentary descriptions and details. You have to fill things in as best you can to create a coherent picture. Some of what you fill in will be wrong. That is one of life’s little tragedies, and the smart writer will accept that and not worry about.

Create an imaginary world that fits the facts as best you know them, but which fills in the holes in such vivid detail that the reader can’t tell the difference between what you know and what you imagine. Remember, it’s a novel you’re writing, not a documentary.

I won’t go into all the tools you have at your disposal for doing research. That depends a lot on what time and place you’re writing about, what information exists, and what form the information is in. It can be very helpful to find experts who know the world of your novel better than anyone else. Don’t be surprised, though, if you ask 3 experts and get 4 opinions. That’s the nature of the beast. It’s better that you form a coherent picture in your own mind of the world of your novel, and that you create that world in vivid detail for your reader. Then translate that coherent picture into an emotional impact on your characters.

Repeat after me: It’s a novel, not a documentary. It’s a novel, not a documentary. It’s a novel, not a documentary.

If you’ve got a question you’d like me to answer in public on this blog, hop on over to my “Ask A Question For My Blog” page and submit your question. I’ll answer them in the order they come in.