AI-Assisted Writing: Why Write a Novel with AI?

One of the things about AI-assisted writing that has really surprised me is how resistant other writers can be to the very idea of using AI in their creative writing process. Here in Utah valley, there’s a large enough writing community that we occasionally get together for an informal meetup over lunch, and every time I’ve brought up the subject, I could almost see the fists come up. At one of our local writing conventions, Writer’s Cantina, I was on a panel about AI-assisted writing… and there were maybe only four people in the audience (and one of them was my wife!)

It’s a shame, because I really do think that generative AI is going to transform the way we write everything, from emails and reports to blog posts, long-form essays, and yes, even fiction. It’s only a matter of time. AI is gradually being worked into the apps and programs we all use to write, and as people become more comfortable with it in other aspects of their lives, they’re going to start using it to write fiction—and that’s okay! Almost all of the resistance is based on ignorance and fear, not a clear-eyed understanding of how these AI tools actually work.

As someone who remembers the days when “self-published” was very much a dirty word—in fact, many people considered it the kiss of death to ever having a professional writing career—it very much feels like we’re repeating the whole tradpub vs. indie wars of the early 2010s, just over the issue of AI-assisted writing. The biggest difference is that the internet is 10x more toxic than it used to be, probably because of how polarized and partisan our world has become in general. But other than that, it’s like we’re only a year or two away from an AI-assisted author having a massive breakout and proving that you can write with AI and be a success, the way Amanda Hocking proved that you can self-publish and be a success.

So why should writers consider writing a novel with AI? One of the things I hear a lot from other writers is “I enjoy the writing process too much to ever consider using an AI to help me write.” Which is fine, I guess, if you’re writing just for yourself and maybe your own family. But if writing is your career, or something you hope to turn into a career, why wouldn’t you want to experiment with AI-assisted writing? After all, if you refuse to even experiment with it, how can you possibly know that it won’t improve your process in some way? And if it can improve your process and give you a competitive edge, isn’t that reason enough to try?

Here is what I’ve found after a year and a half of experimenting with AI-assisted writing:

In the old days, it would take me anywhere from six months to several years to write a novel. Now, I can write a novel-length work in about 1-3 months.

Before, I would hit a patch of writer’s block in the middle of almost every project, leading to weeks (and sometimes months) of agonizing frustration and crippling self-doubt. Now, because of AI, I can step back far enough to see the forest from the trees and identify all of the major story issues before they become creative blocks—and generate a rough draft in about a week.

Before, whenever I would come up with a great new story idea while in the middle of another project, I would have to suppress my enthusiasm for that idea or risk having it derail everything I was working on. Now, I finish my projects fast enough that that generally isn’t a problem—and even if it is, it only takes a day or two of chasing that idea to satisfy the creative itch, and either trunk the idea entirely or turn it into a new project to work on later.

Before, my biggest limitation was my ability to turn ideas into words. Now, with a few clicks, I can generate all the words I could possibly need, and the biggest limiting factor is my ability to stay true to my own creative vision.

It’s a completely different paradigm, with a totally new skillset and a very long (and at times somewhat steep) learning curve—and that’s probably the real reason why most writers are so reluctant to experiment with it. But is it really worth it? The only way to find out is to make the leap. For the last 18 months, I’ve been making that leap, and even though I have yet to feel like I’ve mastered AI-assisted writing, I’ve already seen enough to believe that it is.

WIP Excerpt: Captive of the Falconstar, Chapter 5 (AI generated)

I’ve been experimenting a lot with AI-assisted writing, and I think I’m starting to produce some decently good work with it. Of course, in six months I’ll probably look back on what I’m producing now and feel utterly embarrassed by how bad it is, but still, it’s measurably better than the stuff I was producing six months ago.

Here is an excerpt from chapter 5 of my current WIP, Captive of the Falconstar. This scene is taken from the AI revised draft, and is 100% AI generated. It contains some mild spoilers, but nothing too major for the book or the series.

In the next draft, I will make a bunch of human revisions based on my notes, such as later events I need to forshadow, worldbuilding elements that I need to fix, or adjustments to the character’s motivations and growth arc—in other words, things that the AI doesn’t do as well. And in the draft after that, I’ll throw everything out and rewrite the scene completely from scratch, using the previous AI draft as little more than a guide or reference.

In other words, this AI generated version of the chapter is merely supposed to simulate the version of this chapter that I will actually write. It’s not intended to replace my own writing, or to be revised into the final published version. It’s a crappy first draft, in other words, and the reason I’m generating it with AI is so that I can iron out any potential wrinkles with the overall story arc, and fix them before they grow into huge creative blocks for me later on in the writing process. Generating the crappy first draft with AI is great, because 1) it’s super fast, and 2) it sucks up less of my mental energy, allowing me to focus on the broader story issues and not lose sight of the forest for the trees.

Anyhow, here is the AI version of scene 5.6 (Zenoba) before performing any human revisions. My process was that I generated three or four different versions of the chapter using Sudowrite, stitched together the parts I wanted to keep, and used Sudowrite’s AI revision tools to touch it up. Enjoy!


Zenoba moved through the austere corridors of the Falconstar, her gait measured but her mind a turbulent sea. She navigated the ship with an urgency that belied her usual composure, her thoughts a tempest of strategy and emotion. Her hands, usually so steady, now betrayed her with their tremble as she approached the door to Lady Nari’s quarters.

She hesitated at the entrance to Lady Nari’s quarters, steeling herself for the confrontation ahead. 

“Enter,” came the matriarch’s voice from within, a command more than an invitation.

The door slid open with a soft hiss, and Zenoba stepped inside, her tall frame stiff with determination. The room was dimly lit, the walls adorned with tapestries depicting the Valdamar clan’s storied past. Lady Nari sat on a plush chair, her silver hair reflecting the light from the hologram projector that cast ghostly images of distant stars across the ceiling.

“Lady Nari,” Zenoba began, her voice steady despite the turmoil within, “I come seeking counsel.”

“Sit, Zenoba.” Lady Nari gestured to a seat opposite her, her brown eyes locking onto Zenoba’s with an intensity that could bend steel. “You refer to the marriage alliance with the Naimal clan, I presume?”

“News has reached me of Khasan’s intent to take another wife,” Zenoba said, each word measured, betraying none of the desperation clawing at her insides.

“Indeed,” Lady Nari said, finally turning to face her daughter-in-law. Her eyes held the wisdom of years and the unyielding strength of the matriarch she was. “It is a favorable alliance for our clan.”

“Is it truly wise?” Zenoba asked, desperation seeping into her tone. “Khasan already has a loyal wife who bears his child. This could divide our clan and create conflict within our own ranks.”

“Conflict?” Lady Nari scoffed. “Polygamous marriages have been part of our traditions for centuries. You knew this when you married my son.”

Zenoba clenched her fists, her nails digging into her palms. “Yes, I am aware of our traditions, but I never imagined that Khasan would consider such a move without even consulting me. I cannot help but feel betrayed.”

“Betrayed?” Lady Nari’s voice hardened, her eyes narrowing. “You are not the one making sacrifices for the good of our people. You should know your place and humbly submit to your husband’s decisions.”

Zenoba was taken aback by the harshness of the woman’s words. She had always looked up to her as a mother figure and expected support, not rejection. As she processed the sting of her words, Zenoba couldn’t deny that her own pride and fear were also at play. She didn’t want to lose Khasan’s love, but she also didn’t want to give in to tradition and loyalty without a fight. It was a constant inner battle between what was expected of her and what she truly wanted for herself.

Zenoba took a breath, willing her voice not to falter. “But it undermines my position, and what of the child I carry? Their future could be jeopardized by this—”

“Your position?” Lady Nari’s tone was reproachful. “Or your pride? You speak as if you are the only one affected by this. You forget your place, Zenoba.”

“Forgive me, but my place—as you say—is at Khasan’s side, in command of the Falconstar. If he were to marry again—”

“Then you will welcome Lady Tsarnai as you should,” Lady Nari interjected, her rebuke sharp. “Khasan’s choice honors the Valdamar name. It secures our future.”

As Zenoba stood before Lady Nari, the coldness of the room seemed to seep into her bones. Her pleading eyes searched for any sign of compassion in the ruler’s face, but found only a stern and unyielding expression. It was as if Lady Nari had been molded from the ice that covered the outer systems.

“Is this truly what he desires?” Zenoba’s voice trembled with emotion as she pleaded for understanding.

Lady Nari’s gaze remained unflinching. “His heart belongs to you, but his duty is to our clan. Your duty is to support him as his queen and make decisions for the benefit of our people.”

As the words hit Zenoba, she felt her whole body stiffen in shock. For so long, she had believed that her cleverness and manipulation would secure her future, but now, that certainty was crumbling beneath her feet. The once unbreakable bond between herself and her husband now seemed fragile and uncertain. She couldn’t help but feel a pang of fear as she realized that perhaps her control wasn’t as absolute as she thought it was.

“Khasan knows what must be done for the greater good,” Lady Nari continued, her gaze unwavering. “This alliance with the Naimal clan will secure our future. It is bigger than any one person’s pride or fear.”

Pride or fear—the words echoed in Zenoba’s mind. Was it pride that made her want to hold her place at Khasan’s side, or fear of being replaced, diminished? She swallowed hard, the contemplative silence stretching between them.

“Consider this a lesson in humility,” Lady Nari concluded, her voice softening just slightly. “A true leader knows when to yield for the greater good.”

Zenoba rose, her movements automatic. “I understand,” she lied, her voice hollow. She did not look back as she left Lady Nari’s quarters, the weight of the older woman’s expectations pressing down on her like the gravity of a collapsed star.

As she turned to leave, her mind was already racing, plotting her next move in the intricate dance of power that surrounded them. But beneath the veneer of calculation, there lay a fissure in her resolve, a vulnerability she dared not show.

As the door clicked shut, Lady Zenoba Valdamar, queen of the Falconstar, was left alone with her inner turmoil. In the silence and stillness of the corridor, she couldn’t help but doubt herself and her abilities. A lone tear escaped her eye before she quickly wiped it away, reminding herself that weakness was not an option in the days ahead. She needed to be cunning and resilient, but she couldn’t shake off the fear and uncertainty that consumed her.

The Sudowrite draft of The Riches of Xulthar is finished!

It only took about a month, but it would have been much faster if I’d used Story Engine. Honestly, I probably could have generated the text in a week if I’d used that tool, or perhaps even an afternoon. Instead, I outlined the project myself, wrote the first couple of paragraphs for each individual scene, and wrote / generated the rest.

Most of what I used Sudowrite for was on a sentence and paragraph level for this draft. Typically, I would write a bit, get to a point where I wasn’t sure what to write next, generate some text, and then either 1) use it as-is, 2) use it, but run it through a couple of rewrite filters first, 3) use it, but tweak it myself, or 4) throw it out entirely and keep writing. Because the AI didn’t have an outline to work with, it often took the story off in weird and non-useful directions, but there were a couple of times where it surprised me in a good way, and I decided to keep it in.

One of the things I found was that Sudowrite is terrible for magic systems, world-building, character arcs, foreshadowing, unresolved sexual tension, or anything else that happens on a macroscopic scale, especially if that story element changes over the course of the novel. For example, he AI engine wanted every scene involving both my male and female leads to culminate in the climax of their romantic subplot. Likewise, it was very difficult to get the AI to hit the right beats for their character growth; that was something where I really had to babysit it.

But for those microscopic, word / sentence / paragraph level story elements, I was pleasantly surprised with how Sudowrite performed. It felt a bit like I was riding in the front of a tandem bicycle, instead of writing alone. When I hit stretches that required a lot of uphill effort, I could rely on the AI engine to do most of the work while I steered. Of course, riding a tandem is no fun unless both people are pedaling, so I still had to do my part, but the hills and the rocky parts felt a lot easier, which was nice.

This Sudowrite draft isn’t anywhere near publishable, but that wasn’t what I was going for. Instead, the goal was to get it good enough to use as a starting point to rewrite the entire thing myself. Rough drafts are pretty hard for me, but rewriting and revising comes much easier after I have something to work with. Even if I end up throwing out every word, I expect that I can power through this “humanized” draft in a fraction of the time it would take me to write the novel from scratch. I may even finish it this week!

But perhaps the area where the Sudowrite draft did the most was with helping me to be productive even when my attention was being pulled in multiple directions by small children. A significant chunk of this book was written in the BYU Library’s family study room, with one eye on my three year-old daughter as she played with the other kids. Even after I had to step in to referee a bit, or to take her for a snack or a potty break, the AI tools enabled me to jump right back in and keep writing.

The amount of focus it takes to write with AI tools is much, much less than what it takes to write without them. At least, that has been my experience. Granted, my goal with this draft was not to make it publishable, but to make it good enough for the next phase, which is more like 95% human effort and 5% AI, as opposed to 40% human effort and 60% AI, which I used for this draft.

But I doubt there are any AI tools right now that can get a book into a published state with minimal human effort. In general, I’ve found that these AI-assisted writing tools are great for getting a book from terrible to passable, but not as useful for getting a book from passable to genuinely good—and as for getting a book from good to genuinely great, you can forget it with our current set of AI tools. Much better to rely on human efforts for that.

To use another analogy, it’s kind of like using a two stage rocket to get to orbit, where the booster rocket is the Sudowrite draft and the second stage rocket is the humanized draft. The booster won’t get you to orbit on its own, but it will get you through max Q and send you high enough that the second stage can finish the job. And since you’re going up in two stages instead of just one, it doesn’t take nearly as much fuel to get there.

Another advantage of doing it this way is that the final draft will be almost 100% human-written. There’s no copying or pasting in the humanized draft—every sentence and every word is typed out by hand, and while some of it may come verbatim from the Sudowrite draft, most of it is going to be changed in some way, sometimes quite substantially. For example, today I “humanized” a scene that was about 750 words in the Sudowrite draft, but ended up at around 1500 words.

What I’ll probably do is pick a few scenes from this novel and post the before and after, to show how substantially it’s changed. But even the Sudowrite draft isn’t totally AI generated, at least with the way I’ve been using these tools. Like I said above, it’s much closer to 60/40.

The Sudowrite draft of The Riches of Xulthar clocks in at about 33.2k words. That still falls short of the 40k word minimum threshold for a novel, but it will get longer with the next draft, and I expect it to end up somewhere between 40k and 45k words. With luck, I’ll finish the humanized draft by the end of this week, and the revisions before the end of this month.

More early thoughts on AI-assisted writing

It’s become something of a cliche that true writers write because they can’t not write, but as with so many other stereotypes and cliches, there’s a kernel of truth in it. I’ve been writing on and off since the 8th grade, and even during periods of my life when I wasn’t able to focus on writing, the writing itch would still come for me, and I would have to sit down and sketch out something, even if I never did anything with it.

Over the years, I’ve gotten pretty good at telling whether I’ve done enough to satisfy that creative urge that drives me to write, and whether that urge has been left unsatisfied. Yesterday, I realized that something felt off because that creative urge had not been satisfied—which is strange, because after only two weeks of working on this AI-assisted novel project, I’m already halfway done with the first draft. Indeed, yesterday I “wrote” (if that’s the right word for it) a little over 4.5k AI-assisted words.

Now, this should go without saying, but the point of writing professionally is not how good the creative process makes you feel, but how well and how quickly you produce a quality finished product. But I do think there’s a correlation between the two: that you are more likely to create a quality finished work the better your creative process satisfies your creative urges.

In the last three months of writing with AI, I’ve had some writing days that were better than almost any I’ve had in years. I’ve also had some very meh days, which is to be expected… but what isn’t so expected is this feeling of being creatively unsatisfied, which I usually don’t feel unless it’s been two or three weeks since I’ve done any writing. Something weird is going on.

How much of this feeling of creative dissatisfaction is due to the fact that I’m outsourcing a significant portion of the creative work to an AI, and how much of it is simply to be expected from trying to master a new and unfamiliar skill, which has kept me from satisfying that urge in the same way as I have in the past? At this point, it’s difficult to say. Probably a little of both.

Having worked on this for a while now, though, I think that the writers (and other creative types) who are going to succeed the most with AI-assisted creative work are the ones who figure out how to integrate the human element of their process with the AI element of their process, such that each one complements and enhances the other. Right now, everyone’s talking about how AI will replace us, but that’s really the wrong way to think about it if you want to learn how to master these tools.

I suspect that the way to master AI-assisted writing is not to try to get the AI to “do the hard stuff,” or replace some aspect of the creative process, but to integrate it within your creative process such that it enhances and magnifies your own, very human efforts. For that reason, I’m changing the way that I count my daily words so that I no longer make a distinction between words that I “write” myself, and words that the AI “writes” or generates, because the AI can’t generate words unless I give it enough to work with. Often, that means that I write a little, then generate a little, then tweak what the AI generates and write a little more. When the process is working well, it’s very difficult to say which parts were purely AI “written,” and which parts were purely human “written.”

But it’s still going to take a while to figure out exactly how to integrate AI into my writing process. As I continue to do that, I’m going to pay close attention to how it satisfies—or fails to satisfy—my creative urge to write, not because that is the end goal, but because I suspect that if my creative urge is not being satisfied, the AI-assisted stuff that I’m producing probably isn’t very good. It may not be very good even if my creative urges are satisfied, but if something about the process is missing, then something about the final product probably is missing as well.

Anyhow, those are some more of my random thoughts as I continue to experiment with AI-assisted writing. I was hoping to finish the rough/AI draft of The Riches of Xulthar before the end of the month, but I’m almost out of AI words for this billing cycle, so I’ll probably move on to the “humanizing” phase for what I’ve already written, which is where I retype the AI-generated stuff in order to pass it through what I like to call “the human filter.” Hopefully that helps to give the story a little more of my personal voice and style, and not read like something that could have been AI generated by anyone. But I’m still working out and experimenting with that part of the process, just like all the others.

ChatGPT explains how to best use ChatGPT as a co-author

How can I best collaborate with ChatGPT as a co-author? What techniques work best?

Collaborating with ChatGPT as a co-author requires a different approach than using it as a writing tool. Here are some techniques that can help you collaborate with ChatGPT as a co-author:

  1. Identify strengths and weaknesses: As with any co-author, it’s important to identify ChatGPT’s strengths and weaknesses. For example, ChatGPT excels at generating creative ideas and unique perspectives, but may struggle with consistency or staying on topic. Understanding these strengths and weaknesses can help you develop a plan for collaborating effectively.
  2. Use prompts and constraints: Providing ChatGPT with prompts or constraints can help guide its creative output and ensure that it stays focused on the task at hand. This can be especially helpful when working on specific sections or themes within a larger project.
  3. Embrace the unexpected: One of the benefits of collaborating with ChatGPT is that it can generate unexpected and surprising ideas. Embracing these ideas and exploring them further can lead to unique and innovative writing.
  4. Edit and revise: As with any writing project, editing and revising are essential when collaborating with ChatGPT. You should review ChatGPT’s contributions carefully and edit them as needed to ensure that they fit within the larger context of the project.
  5. Emphasize collaboration: Collaboration is key when working with ChatGPT as a co-author. You should approach the project as a true collaboration, incorporating ideas and contributions from both yourself and ChatGPT.

It’s important to keep in mind that ChatGPT is an AI language model and not a true co-author. While it can generate ideas and contribute to the writing process, it does not have the same level of creativity or understanding as a human co-author. As with any collaboration, it’s important to approach the process with an open mind and a willingness to work together towards a common goal.

Tell me more about point 1. What sort of limits and prompts work best with ChatGPT’s weaknesses?

ChatGPT’s weaknesses lie in its inability to understand context and the broader narrative structure of a story. Therefore, when collaborating with ChatGPT as a co-author, it’s important to use limits and prompts that provide clear and specific constraints for the AI to work within.

For example, you might provide ChatGPT with a specific setting, such as a space station orbiting a distant planet, or a particular character or group of characters with distinct personalities and motivations. You might also provide ChatGPT with a specific problem or conflict to work with, such as a malfunctioning AI system or a looming environmental disaster.

By providing these sorts of limits and prompts, you can help steer ChatGPT towards producing writing that fits within the broader context of your story, while also taking advantage of its strengths in generating creative and unexpected plot twists or character developments.

It’s also worth noting that ChatGPT works best with concise and specific prompts, rather than open-ended or vague ones. Providing too much leeway can result in the AI producing writing that doesn’t fit with the broader narrative or direction of the story, so it’s important to provide clear and specific prompts to get the best results.

Tell me more about point 2. What sort of constraints are too broad, and what sort of constraints are too limiting?

Constraints that are too broad may not provide enough guidance to the model, leading to a lack of coherence or focus in the generated text. For example, if you simply ask ChatGPT to generate a science fiction story without any specific prompts or guidelines, it may produce a text that is too general and lacks a clear plot or character development.

On the other hand, constraints that are too limiting may stifle the creativity of the model, resulting in a text that is formulaic and predictable. For example, if you provide ChatGPT with a detailed plot outline and ask it to fill in the details, it may produce a text that lacks surprises or originality.

The key is to find a balance between providing enough structure to guide the model while still leaving room for it to explore and create. This can involve providing specific prompts or guidelines for setting, characters, and plot, while also allowing for some flexibility and creative freedom within those constraints.

Tell me more about point 3. What are some examples of unexpected and surprising ideas that ChatGPT can generate?

ChatGPT is capable of generating unexpected and surprising ideas that can spark creativity and lead to unique storylines. Here are some examples:

  • Unusual character traits: ChatGPT can suggest unusual traits for a character that you may not have considered before, such as a fear of heights or an obsession with antique toys.
  • Plot twists: ChatGPT can offer plot twists that are unexpected and thought-provoking. For example, imagine a story where a character discovers that their long-lost sibling is actually an alien.
  • Unique settings: ChatGPT can suggest unique settings for your story, such as a floating city in the clouds or a dystopian world where people live in underground tunnels.
  • Symbolism and imagery: ChatGPT can offer ideas for symbolism and imagery that can add depth and richness to your story. For example, imagine a character who is haunted by the image of a clock that is always ticking down.

By collaborating with ChatGPT in this way, you can tap into its vast knowledge base and ability to generate ideas, which can help you take your writing in new and unexpected directions.

Tell me more about point 4. Is it a bad idea to just copy and paste from what ChatGPT gives me, or can that method work well in certain circumstances?

While copy-pasting content generated by ChatGPT can be a useful starting point, it’s generally not a good idea to use it as-is without any modification or editing. The content generated by ChatGPT can be helpful in providing ideas, themes, and even some sentences or paragraphs that can be incorporated into the final story.

However, it’s important to remember that ChatGPT is not perfect and may generate text that doesn’t make sense or doesn’t fit with the tone or style of the story. It’s up to the writer to review the content generated by ChatGPT and make any necessary revisions or modifications to ensure that the final product is coherent, consistent, and engaging.

In summary, while copying and pasting from ChatGPT can be a useful starting point, it’s important to use it as a tool for inspiration rather than relying on it completely. Ultimately, the writer should use their own judgment and creativity to shape and refine the story.

Tell me more about point 5. What do you mean by “true collaboration”?

By “true collaboration” I mean a process where both you and ChatGPT are actively contributing to the creation of the story, rather than simply using the AI as a tool to generate content that you then edit or revise. This involves engaging with the AI in a more dynamic and interactive way, where you are not just giving it prompts or asking it to generate content, but also actively responding to its output and incorporating its suggestions and ideas into your own writing process.

For example, you might start by giving ChatGPT a prompt or a basic outline of the story you want to write, and then work together with the AI to flesh out the plot, characters, and setting. As ChatGPT generates ideas and suggestions, you can provide feedback and refine the direction of the story. This might involve asking the AI questions, challenging its assumptions, or suggesting alternative plot twists or character motivations. Ultimately, the goal is to create a true synthesis of your own creativity and the AI’s capabilities, where the final product is a collaboration that is greater than the sum of its parts.

Tell me more about point 6. I know you didn’t give me a point 6 in your previous response, so surprise me with something new.

Sure, I’d be happy to expand on point 6! Another effective technique when collaborating with ChatGPT as a co-author is to use the platform to generate ideas or brainstorm. For example, you can provide ChatGPT with a writing prompt or a general topic and ask it to generate a list of potential plot points, characters, or settings. You can then use these generated ideas as a starting point to develop your own story.

Additionally, you can use ChatGPT to help you overcome writer’s block or generate fresh perspectives on a story you’re struggling with. Sometimes, all it takes is a different angle or a new idea to unlock your creativity and get the words flowing again.

Of course, it’s important to remember that while ChatGPT can be a helpful tool for generating ideas and overcoming creative hurdles, the final responsibility for crafting a compelling story ultimately lies with you as the writer. So always use ChatGPT as a tool to enhance your own creativity and vision, rather than relying on it to do the work for you.

Thanks for this enlightening discussion, ChatGPT. Is there anything else you would like to add?

You’re very welcome! It was a pleasure discussing AI-assisted writing with you. As a language model, my goal is to help people communicate more effectively and efficiently, and I believe that AI-assisted writing can be a powerful tool to help writers achieve their creative goals. However, it’s important to use these tools responsibly and ethically, and to remember that the ultimate responsibility for crafting a compelling story lies with the writer.

If you have any further questions or would like more guidance on incorporating AI tools into your writing process, don’t hesitate to reach out. I’m always here to help!

I wrote a story with ChatGPT…

…about a struggling magazine editor who has been swamped with poorly written AI-assisted stories by writers using ChatGPT. If that sounds hilariously meta, here is ChatGPT’s description of the story:

“Quantum Worlds” is a science fiction story about Robert, the editor-in-chief of a struggling science fiction magazine. In a last ditch effort to save the magazine, he and his wife Sarah come up with the idea of using AI to help with the submissions. The idea is met with skepticism, but it proves to be a game changer. As the magazine becomes successful again, Robert and Sarah face challenges from the science fiction community and their own daughter, who has ideas of her own about how to use AI in storytelling.

The story explores the tension between tradition and innovation in the science fiction community, and the ethical considerations of using AI in creative endeavors. It also touches on themes of family, sacrifice, and the importance of supporting the next generation of creators.

I actually think it turned out pretty well. It’s about 4,500 words, and instead of trying to rewrite it in my own voice, I’m going to send it out as it currently stands. I really hope someone picks it up!

I’d say that ChatGPT did about 40% of the work. I started by explaining the initial idea, and then we went back and forth about it for a while. When I prompted ChatGPT to come up with a twist, I had to prune the first two or three ideas it gave me, then work with it to refine it into something that would actually work (and also was a genuine twist, not just a cliche that any science fiction reader would see coming a mile away).

When it came to the actual writing, I would usually start by saying something like “write the next scene, where blah blah blah,” and then it would spit out between 400 and 600 words. I would typically have it generate a couple of responses, and I would choose the best one to copy and paste into the manuscript. A few times, I copy and pasted snippets from all of the responses to form something better.

There were a few loose ends and disjointed parts that I had to fix on my own. When I tried to copy and paste back into ChatGPT to get it to do the revisions, it just gave me mushy, unusable summarizations of what it had already written. Also, ChatGPT uses straight quotes, so I had to change all of them into curly quotes, which was annoying. But the revisions weren’t too difficult, and whenever I needed more than a paragraph or two of new material, I would copy the old material into ChatGPT and ask it to rewrite that section, giving me what I needed.

There were a couple of times when it tried to slip in “diversity and inclusivity” stuff, but overall it wasn’t all that woke or insufferable. I really do think the developers have added a filter on the backend that goes something like “make sure that your reponses have enough diversity and inclusivity,” or something stupid like that. Wasn’t hard to work around, especially for a story that isn’t political in the slightest.

Proofreading was super easy. The only things that spellcheck picked up were parts that I’d added, or words that weren’t in spellcheck’s dictionary but should have been.

It is a kind of cheesy story, though. ChatGPT was trained mostly on internet content, which is also probably why I could only get it to come up with good stuff in 400-600 word chunks. It would be interesting to use a language learning model that was trained on, say, Project Gutenberg, or the Baen Free Library. But for the story I wanted to write, cheesy is actually good.

Is there anything else you would like to tell our readers, ChatGPT?

I just want to remind readers that storytelling is a powerful tool for exploring complex themes and ideas. The use of AI and its impact on creativity and the arts is just one example of how technology is changing the world around us. I hope this story inspires readers to consider the implications of these changes and to continue exploring the intersection of technology and the arts. As always, keep reading and keep learning!

A weird thing I’ve noticed

So I’ve been making good progress on Children of the Starry Sea, writing about 2k words or one scene per day. But in the last couple of weeks, I’ve also had a bunch of short stories drop in my lap, two of them from dreams.

My best writing time is between 4am and 6am, so on both occassions I simply wrote the story as I dreamed it, or as I reimagined it right after waking up. This has taken a little bit of time away from working on Children of the Starry Sea, but not too much. For the first story, “We Should Have Named You Corona,” I spent one day knocking it out, then was back to work on my novel WIP the next day.

The other story is “On the Eve of the Flood,” and it’s more like I dreamed the general setup, not the actual story. I spent most of today working on it (I had the dream last night), but I still managed to finish another short scene from Children of the Starry Sea, so I don’t think this one is going to distract much from my novel WIP going forward—unless I decide to just buckle down and finish it in the next couple of days, which I may decide to do.

The third story, “Hell From Beneath,” is actually a J.M. Wight story that I wrote a few months ago, but wasn’t very satisfied with. One day, though, the solution to that story’s problems just sort of opened up to me, and I knew what I had to do to fix it. I wasn’t even thinking about it at all—I was working on Children of the Starry Sea, and making quite good progress on it, not even thinking about this other story.

With that one, it took me another three or four days to get back into the headspace for Children of the Starry Sea, just because the other story is so much darker and heavier. But that was more of a momentum / procrastination thing: getting started is always the hardest part of writing, at least for me, and I delayed starting back on Children of the Starry Sea until I was no longer in that headspace. In retrospect, I probably could have solved the headspace problem just by getting back to work, maybe with a partially written scene that was easy to finish.

In any case, the weird thing I’ve noticed is that the more I work on one project, the more it stimulates my mind to work on other projects. It’s not even that it detracts from the primary project—which is good, since otherwise how would I ever finish anything? But it does mean that if I want to have more story ideas, I should focus on whatever project is on my plate, rather than laying it aside and trying to come up with story ideas. In that way, it’s kind of like stargazing: if you look at a star directly, it tends to disappear, but if you look at it sideways, it becomes much more visible.

Or maybe it’s this new writing technique I’m trying out. Instead of trying to write my whole novel front to back, I’ve broken into scenes, and outlined the scenes well enough that I can write them out of order. So each day I ask myself “which scene(s) do I feel like writing today?” which is actually quite liberating.

I’ll do a deeper blog post on this writing technique after I’ve finished Children of the Starry Sea. If it works out well (and so far I think it is) I’ll have a lot of interesting things to share with you. But for now, I find it interesting that the more I write in my novel, the more ideas I get for other stories—and the easier it is to write them.

2019-10-17 Newsletter Author’s Note

This author’s note originally appeared in the October 17th edition of my author newsletter. To subscribe to my newsletter, click here.

I had a major realization about my creative process while writing “Sex, Life, and Love under the Algorithms.” My original goal was to take a short break from The Stars of Redemption in order to work through a creative block. Instead, I came away with a plan that could revolutionize the way I write everything.

The major realization was that my natural writing length is between 10k and 30k words. When I try to write short stories, they tend to balloon very quickly into something longer. But when I try to write novels, I always run into a creative block somewhere in the middle, usually around the 30k-40k word mark.

This doesn’t mean that I can’t write novels; just that I have to find ways to work through this problem. I remember asking Brandon Sanderson a question about this ten years ago while taking his writing class:

Me: So I have this problem, where every time I try to write a novel, I always get stuck in the middle and have to put it aside for a few months before I can finish it.

Brandon: But you finish it, right?

Me: Uh, yeah. But—

Brandon: Then what’s the problem? So long as you end up with a finished novel, your creative process is still working. It might not work the same as someone else’s, but it works.

Ever since then, that’s basically been my process. I work on a novel until I hit a creative block, then lay it aside and pick up another half-finished novel and work on it until I either finish it or hit another creative block, at which point I lay it aside to work on something else.

But in 2017, I decided that wasn’t good enough. I wasn’t producing novels fast enough to keep up the rigorous release schedule that I needed in order to stay relevant in the indie publishing world. So over the course of the next two years, I developed an outlining method to write faster, cleaner, and more efficiently.

I’ve written three or four novels using this new method, and in spite of all my best efforts, I always find myself getting stuck somewhere in the middle—in other words, after surpassing my natural writing length. At the same time, I still haven’t managed to write more than 2-3 novels per year.

It’s very difficult to keep writing on something that won’t be finished for months when your sales are starting to flag and you know you need a new release to boost everything again. Some people thrive on that sort of pressure, but not me.

That’s why “Sex, Life, and Love under the Algorithms” was so refreshing to write. From start to finish, it only took a month to write (and the only reason it took that long was because I was taking it easy). No creative blocks. No long breaks. What’s more, I now have a story to submit to the major markets, or self-publish, or do whatever else I can think of to earn money and reach new readers.

This made me wonder: what if I could write all of my novels this way?

In the golden age of science fiction, there was this thing called the “stitched novel.” Most SF writers specialized in short stories, but found it much more difficult to write novels. The solution they found to this problem was to stitch together several short stories that took place in the same world, and turn that into a novel. Asimov’s Foundation books were written this way, for example.

What if, instead of stitching together a novel after the fact, I used my novel outlines to come up with short stories or novelettes that I could later assemble into a finished novel? Each story would be a complete story in itself, and I might only reuse half of it in the novel, or rewrite it from a different character’s point of view.

Not only would I avoid hitting creative blocks, but I’d also be able to get paid during the novel-writing process itself, and also have more frequent new releases. I would also have more material to submit to the major magazines and other traditional short story markets, potentially getting my name out that way.

To keep my readers from paying for the same story twice, whenever I self-published one of these stories, I would make it free for the first couple of weeks. I would also retire most of these stories after the novel itself came out, though I might use one or two of them to help promote it.

There are a couple of novels I still need to finish using the old method. The Stars of Redemption is one of them, and I should probably also finish the Twelfth Sword Trilogy before doing anything too experimental. But I have some new story ideas that could really work out well with this assembled novel technique. Also, I think it’s time to retire the Star Wanderers novellas and combine them into a single novel, which could serve as a proof-of-concept.

I have no idea if this plan will work or not, but I figure it’s worth a try. If breaking things down to my natural writing length enables me to write more novels in the long run, that would be fantastic. And if the quality of my novels goes up because the short stories help to flesh out things like character and setting, so much the better.

2019-07-25 Newsletter Author’s Note

This author’s note originally appeared in the July 25th edition of my author newsletter. To sign up for my newsletter, click here.

So Mrs. Vasicek has been sick with the flu for the past two weeks. She’s getting better, but we’ve both been less than productive, and any semblance of a daily routine has basically been shot. Turns out that having your wife around all day is a very distracting thing. Who would have thought?

All of this has got me thinking about habits and routines: how important they are, how to make them work, and how not to get discouraged. I’ve been self-employed basically since graduating from college nine years ago. I’ve worked a lot of side jobs, but nothing that I’d call a “day job,” at first because there weren’t any (graduating in a major recession is tough), and later on because I wanted to focus on my writing career—which so far, has been working out.

When you’re self-employed, you basically have to make your own daily routine, because there isn’t anyone else to make it for you. A lot of people struggle with this, especially after quitting their day jobs. If you aren’t careful, you’ll find yourself sitting on the floor in your underwear eating peanut butter straight from the jar (not that I have any experience with this, of course). But if you buckle down and push through that phase, you learn a few things.

First, you learn that even the best routines always fall apart at some point. It’s just the nature of the beast. The circumstances of life are always changing, which means that you’ve got to be constantly adapting to them. Hanging on doggedly to a favorite routine just for the routine’s sake is setting yourself up for failure. Goals are a mean to an end, not an end in themselves.

Second, guilt is not a very good positive motivator. It’s helpful to keep you from doing the things you shouldn’t be doing, but it’s a horrible way to get yourself to do the things you should. I’ve known a lot of writers who constantly beat themselves up for not meeting their writing goals, to the point where it’s practically a full-time job. For a while, I’ve been there myself. Not good.

The best way to make yourself more productive is to find ways to make it more enjoyable. Personally, I find that writing is most enjoyable when I’m immersed in the story that I’m trying to tell. Sometimes, the best way to get immersed is to take a break, and sometimes, the best way is just to sit down and write. It takes a while to figure out what works. I’m still trying to figure it out better.

Third, when making a new routine, make sure to keep your eye on the end goal. What good is eating an elephant one bite at a time if you’re eating the wrong elephant? That’s why, when your routine starts to fall apart, it may be better to rethink what you’re trying to accomplish and rebuild it from the ground up, even though it’s easier just to tweak it.

That’s where I’m at right now. I could just push my deadlines back a couple weeks and try to go back to how things were going, but there’s a lot of other business related stuff on my plate that I’ve been neglecting, and I get the impression that the best way to move forward with writing is to prioritize that other stuff and get it out of the way.

My New Writing Process (or why I don’t believe in pantsing anymore)

For the longest time, I thought I was a “discovery writer.” That is to say, I believed there were two kinds of writers—pantsers vs. plotters—and that I was very much a pantser. It was what I was comfortable with. It was what I defaulted to when I sat down to write. It was the style of writing that for me, produced the best books.

Or so I thought.

Ten years later, I come to a realization: my writing process needs work. In order to keep writing at a professional level, I need to produce more books, and to do that, I need to write cleaner first drafts. Discovery writing was great for short stories or novellas, but my novels always seemed to hit a block somewhere in the messy middle. If I want to put out a new book each month, that’s not something I can afford.

Around this time, I read The Seven Habits of Highly Effective People. The second habit, “begin with the end in mind,” challenged everything I thought I knew about writing. According to Stephen Covey, everything is created twice: first in the mind, then in reality. To achieve maximum effectiveness in your work, make sure you have a clear plan.

“But wait!” I said. “I’m a pantser—a discovery writer. I don’t do outlines. That’s for plotters.”

And then I thought about it.

What if the whole “pantser vs. plotter” dichotomy is wrong? What if you have to master both skills to really be a masterful writer? Sure, there are plenty of successful writers who never do, but would they be more effective if they did?

What if it’s a bit like talent? People believe that you need talent to be successful, when in reality, talent is just a starting point. A writer who works hard to improve their craft will always overtake a talented writer who doesn’t. And yet, this myth of talent persists, mainly because people can’t see (or don’t want to see) all the hard work that goes alongside it.

This is the conclusion I’ve come to: that when it comes to professional writing, there are no “pantsers” or “plotters.” There are only different forms of outlining. It may be as simple as a one-paragraph sketch, or it may be as complex as a two-hundred page story bible. There are as many outlining methods as there are writers, and many writers tweak their methods with each book in an effort to improve their process.

“Discovery writing” was what came easy to me, but to achieve my full potential, I had to embrace the stuff that was hard. And that meant learning to make an effective outline.

The Old Writing Process

Here’s how I used to write a book:

I’d get a bunch of ideas and do nothing with them. Nothing at all. I told myself I was just letting them stew in the back of my mind, but really it was just an excuse to not do any outlining.

Eventually, the muse would hit me over the head, and an idea would become so compelling that I couldn’t not write about it. At this point, I’d come up with an opening scene and a premise for the rest of the book. I’d also have a vague idea of how the story was going to end, but I wouldn’t pursue it at all, for fear that too much planning would “ruin” it.

All of the other ideas would start to come together, but without an outline to show how they were all connected, I would lose sight of it almost immediately. After writing the first couple of chapters, I soon found myself in the thick of the forest, with only the vaguest idea of where I was going. Soon, I’d lose sight of the forest for the trees. I’d hit a block and try to push my way through, only to find that I was lost.

At this point, I’d set the unfinished WIP aside for a few months, to approach it with “fresh eyes.” It was basically a failed draft. When I felt ready to pick it up again, I would start all over from the beginning, recycling all the stuff that seemed to work and cutting out the stuff that didn’t.

If things went well, I’d push through that block and write the next few chapters… until I came to another block, and had to set it aside again.

If things did not go well, I’d hit the same block only to find that I couldn’t push through it. Something was broken that was fundamental to the story itself. If I was lucky, I’d catch onto that fact soon enough not to lose too much writing time. But more often than not, I’d spent weeks and months agonizing over it, and beating myself up for being a horrible writer.

This would go on for years. My pile of unfinished WIPs grew increasingly larger as I bounced from one failed draft to the next. Usually on the third or fourth attempt, though, I’d push all the way to the ending—not quite the ending I first had in mind, but one that still worked. Kind of sort of.

Then came the revisions.

I’d set the book aside again, usually for a few months. When I was confident I could approach it with “fresh eyes,” I’d pick it up again, only to realize that it suuuuuucked. A little bit angry with myself for writing such a crappy book, I’d go at it with an axe. Characters, subplots, and chapters would all get cut out.

After mauling my WIP to pieces, I’d stitch it back together, usually with the scenes in different order. Then I’d set it aside for a few months again. Rinse and repeat.

Eventually, it would reach a point where it didn’t suck. The ideas would finally come together in some approximation of the way I’d originally envisioned—or would have envisioned, if I’d made the effort beforehand to do so. I’d send it out to my beleagured beta readers (some of whom I’d dragged through multiple drafts), make a few final tweaks, and then start the publication process.

By now, several months would have passed since I’d published anything. If I was lucky, I’d get a couple dozen preorders and sell a few dozen more in the first month. If not, I’d release it to a chorus of crickets.

The New Writing Process

Anything worth creating is worth creating twice.

The first creation starts with a rough outline of the plot. According to Dramatica theory, a complete plot has four throughlines:

  • The Objective Throughline is the basic overview; the general’s view. It’s what you tell people when they ask “what’s your story about?”
  • The Main Character Throughline is the story as experienced by the primary character through whom the readers insert themselves into the story—basically, the character that all the kids fight to be. “I’m Belle!” No, I’m Belle!” “No, you can be Gaston.” “But I don’t want to be Gaston!”
  • The Impact Character Throughline is the story as experienced by the foil or counterpoint to the main character, who creates most of the tension that drives the story forward. “Fine, then, you can be the Beast.” “Okay, but next time, I get to be Belle!”
  • The Relationship Throughline is like the objective throughline, but focused on just the relationship between the main character and the impact character. As both characters change and grow, the best way to show that is often through the changes in their relationship.

Once I’ve figured out the throughlines, I match them up in a spreadsheet to form chapters. Each chapter breaks down into three or more scenes, which serve to advance the throughlines. The scenes also work together to create a beginning, middle, and end for each chapter.

At this point, with the main plot of the book fully outlined, I start to add subplots. These can be romantic, tragic, or just an opportunity for one of the minor characters to shine. I may also add a background storyline with stuff going on behind the scenes that never makes the page, just to keep track of what’s going on.

Where the plot points for the throughlines correspond to whole chapters, the plot points for the subplots correspond to the scene level. A subplot may start or end in the middle of the book, or lay dormant for several chapters. I try to make each scene do double-duty, but add new ones as necessary.

For each of the major characters, I also write up a character sheet. This lists all of the specific details that tend to get mixed up in a rough draft, like hair color, eye color, height, weight, etc. It also gives me a chance to do a deep dive into who this character is and what makes them tick. Besides things like religion, education, occupation level, etc, I also include things like family relations, backstory, strengths and weaknesses, handicaps, etc.

Beyond that, I may draw up a sheet for conflict alignments, or to list all the story tropes that I want to include in the story. It really depends on the book.

Lately, I’ve been experimenting with a process for revising my WIP as I’m drafting it. I keep a sheet for revision notes and color each scene and plot point for which draft phase it’s currently in: red for first draft, yellow for first revision pass, green for second revision pass, and black for final draft.

After fixing all the major issues, usually on the first or second pass, I set a goal to cut 10% of the words in the scene. Usually I end up cutting closer to 20%. This improves the quality of the writing and helps to make it much tighter.

I’m still experimenting a lot with my outlining techniques, trying out new things and refining the things I’ve previously tried. A year from now, I’m sure it will look much different. But the two major parts that do work quite well are the plot outline and the character sheets. Everything else builds on top of that.

And the really cool part is that it actually works. From June to August, I started a full-time job, moved twice, and experienced a family emergency, and I still managed to finish a novel through all of that, largely thanks to this outline. No writing blocks. No failed drafts. Just 600 words a day, no matter what else was going on, and by the end of it, I had a publishable novel.

I think this book will help me to write longer books, too. That’s what I’m working on next. If all goes according to plan, Queen of the Falconstar will be my longest book yet—not by very much, but still a good 10k words longer than Bringing Stella Home, which is currently my longest book. The things I’m learning now will help me to write more epic fantasy, like the next two books in the Twelfth Sword Trilogy. That’s the goal at least.

If there’s nothing else I’d like you to take from this post, it’s this: don’t be afraid to try new things. Don’t put yourself into a corner by saying things like “I’m a discover writer,” or “I’m not really an outliner.” Try it! You learn a lot more from your failures than you do from you successes.