AI-assisted story practice recap

So it’s Saturday night, which means the end of the work week for me. How did I do with my goal to write 10 AI-assisted stories? Not terrible: I did manage to write 6 stories, at least through the AI part. I also burned through about 40k word on my Sudowrite plan—obviously, I didn’t include all of those words, but Sudowrite charges you for all the words it generates, whether you use them or not.

Six stories falls short of my goal of ten, but I’ve learned quite a lot from the experience, and feel confident (and eager) enough to move on to long-form fiction now. However, I should probably take another week to rework and finish most of these stories, just to see how it works. I’m sure I will learn a lot from that as well.

Here are all of the AI-assisted stories I’ve written so far:

  • Quantum Worlds: A near future SF story about a struggling science fiction magazine editor who gets swamped with AI-assisted short stories, until he figures out how to turn it around and use AI to make his magazine successful.
  • The Knight and the Half-Goblin: A fantasy story about a half-goblin half-orc, a pacifist dragon, and a struggling hedge knight, and how they use their unlikely skills and friendship to save the land from a rising dark lord.
  • The Last Voyage of the Pioneer: A space opera story about a clandestine mission to find the Voyager and Pioneer probes and recover or destroy them before an invading alien race uses them to locate humanity’s homeworld.
  • The Unforgotten Dream: A flash fiction piece about a woman who lives her life backwards, and a man who recognizes her.
  • A Mother’s Last Goodbye: A zombie story about a mother who gets bitten while her three year-old child is taking a nap.
  • On Wings of Redemption: A fantasy story about an ancient dragon who has to overcome a curse to save the land from the wicked sorcerer who controls him.
  • The Lonely Planet: A space opera story about a planet that gains sentience after humans terraform it, but is almost destroyed by contact with an ancient artificial intelligence.
  • The Wingwoman: A near future apocalyptic story about a professional wingman who gets approached by a woman who wants help being a mother. It’s… different.
  • The Princess and the Professor: A humorous fantasy story about how Jordan Peterson uses his 12 rules for life to defeat a dragon and save a princess.
  • Alex-29XT: A prequel to my military SF story “Lizzie-99XT.”
  • On the Eve of the Flood: A near future apocalyptic dystopian story about… a lot of things. It started with a really vivid dream I had, and I didn’t know how to finish it, so I just played with it in Sudowrite until a plot appeared. Hard to describe.

These are all at various stages of production, though, and most of them need a lot of work—or to be completely reworked, now that I’ve figured out my process more or less.

Not bad for two months of writing, though.

Jordan Peterson defeats a dragon and saves a princess

Once upon a time, in a far-off kingdom, a ferocious dragon was wreaking havoc on the land. The people were living in constant fear, and no knight dared to face the beast.

But then, a wise professor named Jordan Peterson arrived in the kingdom. He had studied the 12 Rules for Life and knew that they could help him defeat the dragon and save the princess.

He donned his armor and sword, stood up straight with his shoulders back, and approached the dragon’s lair. As he faced the dragon, he spoke with a calm and composed voice.

“Hello there, dragon,” he said. “I understand that you have some grievances with the people of this kingdom. I’m here to listen to you and see if we can find a peaceful solution.”

The dragon snorted and breathed fire, but Jordan Peterson remained undaunted.

“I’m not here to fight you,” he continued. “I’m here to find a way for us to coexist peacefully. I know that there must be some common ground we can find.”

The dragon was surprised by Jordan Peterson’s words. No one had ever spoken to it in such a respectful manner before.

“What do you propose?” the dragon asked, its voice deep and rumbling.

“I propose that we make a deal,” Jordan Peterson replied. “I will help you to set your lair in perfect order, and in exchange, you will leave this kingdom in peace.”

The dragon considered this for a moment before nodding its massive head. “Very well,” it said. “We have a deal.”

As Jordan Peterson set to work helping the dragon to clean its lair, he told the dragon about his 4th rule: Compare yourself to who you were yesterday, not to who someone else is today. He knew that the dragon needed to focus on improving itself, rather than comparing itself to others.

He also remembered his 8th rule: Tell the truth, or at least don’t lie. He knew that he needed to be honest with the dragon, and so he shared some of his own experiences with the dragon as they worked together.

“You know, I’ve had my own struggles in life,” Jordan Peterson said, wiping the sweat from his brow. “But I’ve learned that it’s important to take responsibility for your own actions and do what you can to make things right.”

The dragon listened intently, and Jordan Peterson could sense a growing respect between them.

After several hours of hard work, the lair was clean and orderly, as per Jordan Peterson’s agreement with the dragon. As he prepared to leave, he remembered his 6th rule: Set your house in perfect order before you criticize the world.

“Thank you for working with me,” he said to the dragon. “I hope that this new arrangement will work out for all of us.”

The dragon nodded and flew away, leaving Jordan Peterson to rescue the princess.

As he freed her from her bonds, he spoke to her with kindness and understanding.

“Are you okay?” he asked. “What did the dragon do to you?”

The princess looked up at him with tears in her eyes. “Thank you for rescuing me,” she said. “I thought I was going to die.”

Jordan Peterson smiled warmly at her. “You’re safe now,” he said. “Let’s get you back to the kingdom where you belong.”

On their way back to the kingdom, Jordan Peterson remembered his 7th rule: Pursue what is meaningful, not what is expedient. He knew that he needed to help the princess find meaning in her life, rather than just rescuing her and sending her on her way.

“Tell me, princess,” he said. “What are your goals in life? What do you want to achieve?”

The princess looked thoughtful for a moment before responding.

“Well, I’ve always been interested in art and music,” she said. “But I’ve never been allowed to pursue those passions because of my duties as a princess.”

Jordan Peterson nodded thoughtfully. “I understand,” he said. “But remember, it’s important to pursue what is meaningful, even if it’s difficult or goes against what others expect of you.”

As they arrived back at the kingdom, Jordan Peterson remembered his 9th rule: Assume that the person you are listening to might know something you don’t. He knew that he needed to listen to the people in the kingdom to fully understand the situation.

He spoke with the king and queen, and together they came up with a plan to allow the princess to pursue her passions while still fulfilling her duties as a princess.

Jordan Peterson left the kingdom, knowing that he had not only defeated the dragon and saved the princess but also helped the people of the kingdom find a way to live together peacefully.

As he journeyed back to his own land, he remembered his 12th rule: Pet a cat when you encounter one on the street. He smiled to himself, thinking of the small cat he had encountered on the way to the kingdom, and how it had brought him a moment of joy.

He knew that life was full of challenges, but by living according to his 12 Rules for Life, he had the tools to face them with courage, wisdom, and kindness.

Written and visualized with ChatGPT and Sudowrite.

Practice Writing AI-Assisted Stories

For an elective pottery class at a large university, the instructor told his students at the beginning of the semester that they could choose to be graded on the quality of their final piece, or the quantity of pieces they produced. But they had to decide right then, in the first week of the class, and couldn’t change their decision after.

About half of the students chose to be graded on the quality of their final piece. They were confident that they could produce a high quality piece if they worked on it hard enough, and could probably save some time too. The other half chose quantity over quality: they figured that was the safest course, since even if they never learned how to excel at pottery, at least they would still get an A for putting in their hours.

Those who were graded on quality focused all of their time and energy on producing their final project. Those who were graded on quantity churned out pieces as quickly as they could, without focusing too much on any one piece.

At the end of the semester, a funny thing happened: the final projects of those students who chose quality over quantity were actually inferior to the last few pieces of the students who had chosen quantity over quality. By practicing on multiple pieces and putting in the tedious hours that the other students had hoped to avoid, they had paradoxically learned how to produce higher quality work—even though that wasn’t what they had been focused on.

I’ve been experimenting a lot with AI-assisted writing recently, mostly with ChatGPT, but I just started using Sudowrite as well. Contrary to popular belief, these are difficult tools to master, with a learning curve that starts off fairly shallow but ramps up to be dauntingly steep fairly quickly. This summer, I plan to write a novel with these tools, but because I have much to learn—and literally no one to teach me, since the technology is so new that we are all pioneers—I have decided to start with short stories instead.

My goal for this week is to produce ten AI-assisted short stories, at least up to the rough draft stage. So far, I’ve produced four, which is actually more than I expected to have at this point. Yes, they’re rough—each of them will have to pass through what I call the “human filter” before they’re ready to put out into the world: the choppier the AI version, the harder the work in the human filter stage—but they are still recognizeable as stories.

But just like the kids in the pottery class who chose quantity over quality, I’m not going to try to make any of them perfect—at least, not right now. My goal right now is just to get them done. Later, I’ll do my best to perfect them.

Along the way, I’m keeping notes on things that work and things that don’t. It’s getting to be a pretty big list, and I’m sure it will get much bigger as I go. At some point, I may share it as a blog post.

I’ll also be experimenting with different story generation methods, such as:

  • Starting with ChatGPT from scratch and moving to Sudowrite for refinement,
  • Starting from scratch with Sudowrite,
  • Starting with the Mythulu cards and using those as inspiration for AI guidance,
  • Writing a “seed” of a couple hundred words or so and seeing where the AI models take it, or
  • “Seeding” both the beginning and ending, and using the AI models to fill in the middle.

I’ll probably come up with some other combinations, but those are pretty good to start with.

When the whole thing is over, and all of these stories have been passed through the “human filter” and polished enough that I feel that they’re ready to send out into the world, I’ll probably put them all together into a short story collection and release that directly, rather than releasing them individually as short story singles. I may do that later, but with how quickly I can put out these stories (and how few of the traditional markets are willing to publish them), there’s really no reason to wait.

Anyhow, that’s my thinking at the moment. But I may be getting ahead of myself, since I’ve only written four stories so far. Ask me where things are on Saturday, after I’ve written all ten.

Prepping for a new novel project

I am so far behind on so many things right now. My in-laws went to Idaho for the week, so all of the childcare has fallen on us while they’re gone, and we’ve just been swamped. I know that there are amazing parents out there who can watch five kids at a time, by themselves, without breaking a sweat, but we haven’t leveled up that far yet, and our newborn and three year-old are really kicking our butts.

It probably didn’t help that I started a new AI-assisted short story about a week ago and became really engrossed in that for a while. It all started when I prompted ChatGPT to write a story about Conan the Barbarian in the style of Robert E. Howard. Let me tell you, if you want to get ChatGPT to break its own content guidelines in a totally awesome way, that is the way to do it! It gave me this awesome fight scene, and then this part about a slave girl, and then it got super steamy… and then I decided to delete it and start over.

So I started a new chat, with the prompt “Let’s write a fantasy adventure story in the style of Robert E. Howard,” and immediately it launched into a pretty good fight scene. Here is what it gave me:

The sky was blood-red as the setting sun cast its final rays across the desolate landscape of the wasteland. The cracked earth was parched, and the air was thick with dust and despair. In the midst of this barren terrain stood a lone figure, clad in tattered armor, with a sword sheathed at his side. His name was Roderick, a seasoned warrior who had seen many battles in his days.

Roderick had been on a quest to find the lost city of Xulthar, rumored to hold unimaginable riches and ancient secrets. But the journey had been treacherous, and he had faced countless obstacles along the way. His companions had fallen one by one, leaving him to brave the dangers of the wasteland alone.

As night fell and the moon rose, Roderick sought shelter in the ruins of an ancient temple. Its crumbling walls were adorned with faded symbols of a long-forgotten civilization, and its dark interior was filled with an eerie silence. Roderick’s senses were on high alert as he made his way through the labyrinthine corridors, his sword ready in his hand.

But he was not alone.

A guttural growl echoed through the air, and Roderick whirled around to see a pair of glowing red eyes staring at him from the darkness. A monstrous creature, half-human, half-beast, lunged at him with razor-sharp claws. Roderick swung his sword with all his might, but the creature was fast and agile, evading his strikes with unnatural speed.

The battle was fierce and brutal, as Roderick clashed with the creature in a deadly dance of steel and blood. His muscles strained, and his heart pounded with adrenaline as he fought with every ounce of his skill and strength. The creature was relentless, its claws slashing through the air with deadly precision, but Roderick’s sword found its mark, slicing through flesh and bone.

Finally, with a final swing, Roderick delivered a crushing blow to the creature, sending it crashing to the ground. Its red eyes faded, and its grotesque form transformed into that of a man, clad in ragged clothes.

As Roderick caught his breath, he looked down at the fallen man, who was gasping for breath, his eyes filled with fear and confusion. Roderick recognized him as a lost traveler who had succumbed to the dark magic of the wasteland, transforming into a monster. He had seen this before, a dark sorcery that twisted the minds and bodies of those who dared to venture too far into the forbidden lands.

Roderick’s heart went out to the fallen man, and he knelt down beside him. With his last breath, the man begged for forgiveness, his human form returning briefly before he passed away. Roderick closed the man’s eyes, offering a silent prayer for his soul.

With a heavy heart, Roderick continued his journey, pushing deeper into the heart of the wasteland. He knew he was close to finding Xulthar, and he could feel the pull of its ancient power growing stronger with each step he took. But he also knew that the dangers ahead would be even greater, and he would need all his skill and courage to overcome them.

As he pressed on, Roderick encountered more of the twisted creatures that lurked in the wasteland. He battled monstrous beasts and encountered treacherous traps, but he never wavered in his determination. He was a warrior forged in the fires of battle, and he would not be deterred.

Finally, after days of relentless pursuit, Roderick stood at the entrance of a massive stone gate adorned with intricate runes. This was it, the entrance to Xulthar. He could feel

Not too bad. A little rough around the edges, much like everything ChatGPT gives you at first, but I decided to work with it. I prompted the model to give me the story all the way from start to finish, and then, instead of simply copy-pasting, I decided to manually transcribe it myself, adding and editing as I went.

One thing led to another, and pretty soon I was 4k words into a short story that was taking on a life of its own. It bore only a loose resemblance to the material ChatGPT gave me, at least in terms of overall story structure. Over the next few days, I tried forking the conversation at a few points, copying what I’d written to see what ChatGPT came up with next, but it wasn’t keeping up very well, and I found myself using less and less of what it was giving me.

At the same time, the story was quickly turning into a novelette, and from there into a novella. In fact, it was ballooning so quickly that I realized I was neglecting my novel WIP, Children of the Starry Sea. So I decided to set the story aside for a while…

…except then it occured to me that I’m going to need a new novel WIP in May, and the one I had planned (Return of the Starborn Son) isn’t really outlined yet. I’ve been trying to outline it while finishing the revisions for Children of the Starry Sea, but haven’t made much progress on it, and it’s going to be a big one—possibly longer than Children when it’s done.

So I thought to myself, why not turn this story into my next novel WIP and work on outlining that instead of Return of the Starborn Son? With post-it notes and a dry erase marker (and some help from my toddler, who decided which color post-it notes to hand to me), I put together a basic story outline, which should come out to about 40k words when it’s done. As you can see, I used the window of my home office to put it all together, which was fun. 40k words is pretty short for a novel, just barely crossing the line over what SFWA considers a novella, but for a Conan-style sword & sorcery fantasy, it should be perfect.

I’ve also decided to make this an AI-assisted novel, using ChatGPT of course but also trying out Sudowrite, which looks like a much more useful AI writing tool. Getting ChatGPT to help you write anything longer than about 4k words is like trying to write on a whiteboard with boxing gloves on your hands. It’s going to be experimental, but I think I can turn it into something publishable in the next three or four months. It should be a fascinating learning experience either way.