ChatGPT writes a sword and planet novel for the modern age

Last week, I posted the AI-generated synopsis for a trashy romantasy novel that hits all of the hottest current tropes. This week, I thought it would be fun to do something similar, but to pick a genre that has fallen out of favor in the last 50 years and see if we can’t update it for modern tastes.

So I asked ChatGPT to list some subgenres that were popular 50+ years ago but have fallen sharply out of favor in our current time, then list some of the tropes that define that genre, and combine those tropes with more popular tropes today. The subgenre we went with was sword and planet, and after going back and forth a few times, I think we came up with something decent, if not great.

(FYI, I went back and forth with the AI a lot more times with this one than with the trashy romantasy novel. As a result, it has a lot more of my own fingerprints on it, which you can probably tell if you read it closely enough. But I did rely heavily on the AI.)


Star-Crowned

Ava Mendoza is a brilliant but shy engineering graduate student who has never once seen herself as important, beautiful, or heroic. She prefers equations to people, and predictable routine to anything resembling danger. So when a late-night experiment catastrophically collapses into a quantum anomaly and a wormhole drags her out of her own world entirely, she has no idea she is about to become the center of another world’s prophecy.

She wakes in a burning red desert beneath a sun that flickers like a faulty light—sometimes blinding, sometimes dim, always unstable. Before she can orient herself, the sand erupts into a crystalline predator that hunts using refracted solar flares. Death seems certain until sky-clan warriors descend on insect-wing gliders and drag her to safety through a blur of heat and blade-light.

The moment they spot the battered silver watch on her wrist, everything changes. To Ava it’s a sentimental relic from her father; to the sky-clans it is the legendary “Clock of Worlds,” the unmistakable sign of their prophesied Star-Crowned Princess. She insists they’re mistaken, but the hope in their eyes is too hungry, too desperate. And their leader, Kade Thorne—scarred, disciplined, unexpectedly gentle—treats her with a respect she doesn’t know how to process.

Aelion is a world in collapse. Its red sun flares unpredictably, unleashing radiation storms capable of wiping out whole regions. Long ago, a lost civilization built the Aureole Shield, a planet-spanning defense lattice meant to regulate the sun’s tantrums. But now the shield is failing, and only a tyrant thrives in the chaos.

High Imperator Veylor—ruthless, brilliant, and dying slowly from radiation poisoning—has convinced many that only he can save the world. He sees in Ava the perfect weapon: a beautiful, exotic woman whom the people already whisper about in half-remembered prophecy. If he enslaves her, he doesn’t just possess her; he possesses their hope, their fear, their future. It’s not her power he wants. It’s her image. Her symbolism. Her body as a banner of conquest.

Ava flees with Kade and a small fellowship—Syrin the guilt-stricken telepath, Pira the razor-tongued scout, and Talen the scholar-priest whose fascination with Earthborn oddities borders on worship. Their journey across Aelion is lush, terrifying, and breathtaking: crystal forests humming with ancient data, floating citadels trembling on failing grav-cores, ruins haunted by swarming nanites humming like ghosts of the old world.

And between dangers, Ava and Kade move closer. They share warmth on freezing nights; they exchange glances that linger too long; he corrects her sword stance with hands that hover at her hips longer than necessary; she teases him about his old-fashioned courtesy. When Veylor’s hunters ambush them and Kade draws a battered Colt Peacemaker revolver—an impossibly out-of-place Earth weapon—Ava realizes he’s been hiding a truth as wild as her own.

He came from Earth too. Born in 1887, swept through a wormhole in a lightning storm, stranded here decades before she was born. The admission ties them together in ways neither is ready to voice.

But Veylor’s net tightens. He spreads word that Ava is his destined bride, his divine right. The Aureole Shield’s core is sealed behind defenses only his personal slaves and prisoners may pass. No army can storm it. No warrior can break in. And no other path leads to saving the world.

Ava understands the truth with terrible clarity: if she wants to reach the shield, she must let Veylor take her.

It is the most frightening decision she has ever made, and the bravest. She and Kade plan her “capture” together. He hates it—nearly breaks when she touches his cheek in reassurance—but he promises he will come for her. Not as a hero rescuing a damsel, but as her partner fulfilling the dangerous, brilliant plan she created.

When Ava surrenders to Veylor’s forces, the tyrant is ecstatic. He displays her like a trophy. He mistakes her trembling for fear, not strategy. He believes she is broken. He believes he has won. And because he assumes she is powerless, he brings her into the holy of holies: the Aureole Shield’s control chamber, a throne of living metal and starlight older than memory.

He demands she activate the shield for him.
Instead, she rewires it beneath his nose.

Ava uses her engineering expertise—her intuition, her quick thinking, her Earthborn perspective—to sabotage his takeover, reroute the shield’s systems, and trigger a hard reset that locks him out permanently. When Veylor lunges at her in rage, Kade storms into the chamber, fighting the tyrant in a brutal, desperate duel while Ava works to bring the shield back online.

The Aureole Shield ignites in a cascade of radiance. Aelion’s sun stabilizes for the first time in centuries. Veylor dies screaming that only he deserved its power.

And then—unexpectedly—the energy surge tears open a new wormhole. A shimmering, perfect doorway home.

For the first time since the desert, Ava falters. Earth calls to her with familiar, safe monotony: her graduate program, her half-finished research, her tiny apartment filled with loneliness she once endured without question. Returning would be easy. Predictable. The life she knew.

But she is no longer the woman who left. Aelion has carved her into something new—braver, bolder, desired, seen. She wants Kade. She wants the sky-clans. She wants to live vividly, fiercely, unapologetically. She wants to be what she has become.

She turns away as the wormhole closes on its own.

In the days that follow, she embraces her destiny fully. Ava dons the ceremonial finery of the sky-clans—not as a costume, but as her true skin: elegant, powerful, sensual. She becomes the Star-Crowned Princess by choice, not prophecy. Kade bows to her not out of submission, but devotion. She takes his hand as an equal, radiant and unafraid.

The shy engineer is gone.
In her place stands the woman who saved a world—and claimed her own heart in the process.

Ava Star-Crowned, Princess of Aelion.
A warrior’s beloved.
A world’s hope.
A legend just beginning.


What do you think? Is it something you might want to read? I’m not gonna lie: there’s a part of me that’s tempted to write AI slop, and a novel like this is something I could happily run with.

Or maybe… what if I wrote a book of interesting novel prompts for generative AI, designed for someone to copy-paste into ChatGPT (or their AI model of choice) themselves and have the AI write the story for them? The AI could then adapt the story to the reader, based on their reactions and what they like about it. What do you think? Would you buy a book like that?

ChatGPT writes a trashy novel that fits all the current market trends

So just for fun, I asked ChatGPT to list the post popular tropes in science fiction and fantasy literature right now, pick the most popular subgenre, and write up a novel synopsis that mashes up all of those tropes.

To no one’s surprise, the subgenre it chose was romantasy, but it also threw in dragons, dark academia, and time magic. Here is the complete synopsis:


Here is a tighter, sharper, more compelling 1000-word synopsis that follows the same outline but sells the story harder—maximizing emotional hooks, character stakes, and the high-heat romantasy appeal. Spoilers intact.


The Hundredth Life of the Dragon-Bonded

Rina Ashvale has always been ordinary—poor, unnoticed, unimportant. But on the morning of the Day of Choosing, she wakes with the unshakable feeling that she’s lived this day before. And died in it. Images flash behind her eyes: burning skies, a dragon’s scream, a prince’s hand dripping with blood. None of it makes sense.

Everything changes when Sereth, the most ancient and aloof of all dragons, chooses her as his rider. The bond hits like a lightning strike: thousands of half-formed memories, shards of forgotten lives, and a sense of wrongness in the fabric of the world. Sereth refuses to explain, and Rina finds herself thrust into the elite dragon war-college—completely unprepared, utterly overwhelmed, and lodged in the same wing as the kingdom’s most dangerous cadet: Prince Kael Vorian, heir to their nation’s long-time enemy.

Their first interaction is a disaster. Kael—brilliant, beautiful, and infuriating—sees Rina as an unworthy upstart bonded to a dragon she doesn’t deserve. Rina sees him as an arrogant elite who’s never had to fight for anything real. But whenever they clash in the skies, sparks fly far beyond anger. Something in the dragon bond won’t let them ignore each other.

As Rina trains, she slowly forms a found family with three other misfit cadets—gentle Jory, fierce Thalia, and quick-tongued Marek. Life at the academy carries surprising warmth: late-night mess hall confessions, shared exhaustion after flight drills, stolen pastries in the city. For the first time in her life, Rina feels like she belongs.

But then the déjà vu returns—harder, sharper. She predicts an ambush drill seconds before it happens, saving Kael’s life in a maneuver she can’t explain. When she confronts Sereth, the dragon finally admits the truth:

The world is trapped in a time loop. Ninety-nine times, humanity has fallen to the Void. Ninety-nine times, reality has reset to the beginning of this academy term. Dragons remember. Humans do not.
Except Rina.

Her growing memories mean one thing: she may be the first human in a hundred loops capable of breaking the cycle.

But the moment Rina begins changing events—saving lives that used to be lost, altering training outcomes—the Void adapts. Darker monsters appear. Missions that were once safe become fatal. Jory loses his arm. Marek nearly dies. And Rina realizes a horrifying truth: every change she makes doesn’t erase suffering—it only shifts it onto someone else.

Through it all, Kael remains her fiercest rival and most dangerous ally. Their tension spikes during a magical mishap that amplifies emotion, throwing them into a breathless near-scene neither can forget. During the annual Festival of the First Flame, in the chaos of a Void creature attack, they end up pressed together in a narrow alley, clinging to each other with equal parts fear and longing. When they finally give in to the desire they’ve been denying—an explosive, passionate moment in the dragon stables—they can no longer pretend what’s between them is merely conflict.

But Rina’s growing memories deliver an unbearable blow: in one of the previous loops, Kael burned her village to the ground to slow the Void’s advance. He admits it. He regrets it. He would do it again if it meant saving the world.

Their fragile connection shatters.

As the loop destabilizes, the world begins to tear. Rina slips into the Twilight Reach, the dream-realm dragons inhabit between deaths. There she meets the Hollow King, a godlike Void entity who has been feeding on the loop for centuries. He offers her a seductive bargain: sever the dragon bonds and the loop will end forever—no more death, no more suffering. But it would also mean the extinction of dragons, the world’s only memory-keepers.

Rina refuses. She will not save the world by erasing its heart.

Meanwhile, Kael uncovers a devastating truth: his father, the emperor, is planning a military strike to seize the academy’s dragons, a move that could break the loop catastrophically and hand victory to the Void. Kael offers to kill his father to prevent it. Rina stops him. Instead, she proposes a desperate ritual to jump the timeline forward—getting ahead of the emperor’s plan.

The ritual fails spectacularly.

Time fractures.

The academy splits into two overlapping timelines—the unchanged past loop and the altered timeline Rina and Kael created. Students flicker in and out of existence. Some have duplicates. Others appear as ghosts of who they were meant to be.

Rina’s squad members are caught between versions of themselves. With Sereth’s help, Rina merges their memories, giving each friend the best parts of both lives—even if it costs Sereth more of his dwindling strength. Every memory he surrenders feeds the growing collapse of the loop.

Rina finally understands: dragons carry the burden of memory, but they cannot change it. That’s why the loop always resets. Only a human mind—someone capable of holding all ninety-nine lives at once—can force time forward for good.

She volunteers to carry the full weight of the loop. Kael refuses to let her do it alone.

Together, in the Twilight Reach, Rina and Kael confront the Hollow King. Sereth sacrifices himself to shatter the loop, unleashing all his stored timelines in one final blaze. The Hollow King retreats—but not before warning that breaking the cycle will unleash consequences no one can predict.

Rina and Kael awaken in a world that has never existed before: one without resets, without second chances, without dragons except for a few younglings who survived the collapse. The academy is in ruins. Their nations have fractured. Rina’s village is gone in every timeline. Kael is disowned. The world is raw and wounded—but real.

With their surviving squadmates, they build a small dragon-rider outpost beside a river. Half refuge, half academy, it becomes the first place Rina has ever chosen for herself. Kael stays with her—not as a prince, not as a rival, but as the man who shared a hundred lifetimes of pain and desire with her.

For the first time, dawn breaks on a future that isn’t written.

Standing together in the new light, Rina and Kael speak the vow that binds them:

“We will be the dragons who remember.”

The loop is broken.
The world is reborn.
And their love—forged across a hundred lives—has finally outrun time itself.


So what do you think? Does it sound like something you’d actually want to read? Like something that might even be better than most of the trashy, trendy novels out there, even if it’s total AI slop?

I have no intention of actually writing this book, so if you feel like writing (or generating) it, knock yourself out. Just send me a link if you actually publish it.

How I Would Vote Now: 1993 Hugo Awards (Best Novel)

The Nominees

China Mountain Zhang by Maureen F. McHugh

Red Mars by Kim Stanley Robinson

Steel Beach by John Varley

A Fire Upon the Deep by Vernor Vinge

Doomsday Book by Connie Willis

The Actual Results

  1. A Fire Upon the Deep by Vernor Vinge
  2. Doomsday Book by Connie Willis
  3. Red Mars by Kim Stanley Robinson
  4. China Mountain Zhang by Maureen F. McHugh
  5. Steel Beach by John Varley

How I Would Vote Now

(abstain)

Explanation

I didn’t hate any of these books, but I didn’t love any of them either—which is fairly typical for me of 90s era Hugo Awards. Let’s go down the list.

Doomsday Book is often held up as Connie Willis’s best, but I thought it lost the plot a bit when the time travelers had to simultaneously face a pandemic in their own future time while also having to rescue the lost apprentice time traveler from the black death in medieval England. If you’re reeling from a pandemic, what the heck are you doing sending time travelers back as if it’s a normal day on the job? Also, Connie Willis really has no love for the medieval era, and it shows. Blackout and All Clear were much better, partially because of how much Connie Willis clearly loves WWII-era Britain.

If there’s one book in this list that I should try again, and probably will, it’s A Fire Upon the Deep by Vernor Vinge. It’s the kind of science fiction that’s right up my wheelhouse, and I’ve enjoyed Vernor Vinge before (Rainbows End is the best so far). But this book is so freaking huge, and I never latched on to any of the characters… oh, and the central conceit of the aliens, that the small collective packs form a hive mind that thinks and acts like an individual—that didn’t really work for me either time I attempted to read this book.

I screened Steel Beach and China Mountain Zhang through ChatGPT for objectionable content and decided to skip both of them. Here is what ChatGPT said about China Mountain Zhang that made me decide to skip it:

The story engages deeply with themes of intersectional identity, including race, sexual orientation, and societal roles. Zhang’s struggles as a gay man in a conformist society are a significant part of the narrative. The book also critiques authoritarianism and explores social dynamics through a progressive lens. While these themes are integral to the story and handled with subtlety, they align with a modern “woke” perspective.

And here’s what it said about Steel Beach that made me decide to skip it:

Language: Strong language is used throughout, reflecting the irreverent tone of the protagonist and the society depicted.

Gender and Identity: Steel Beach explores themes of gender fluidity and personal identity in a society where individuals can easily change their biological sex. This aspect of the world is presented as normalized rather than contentious.

As for Red Mars, I read this one way back (way way back) when I was a freshman in college. At the time, I was still working out what I believed politically, so most of KSR’s leftism went right over my head. However, there were a few sexually explicit scenes that weirded me out, especially the one where the colony team’s depressed psychiatrist discovers—and joins—the bizarre sex cult and their group orgies in the farm module. I still finished the book, but I declined to read the rest of the series.

What is it with crunchy leftist authors and bizarre, explicit sexual content? Why do they always seem to feel a need to fill their books with weird and pointless sex? There are so many books I’ve read for this series that started out strong, but ultimately devolved into sexual degeneracy that added nothing to the story. It’s almost like they felt a compelling need to add the degeneracy for its own sake. Maybe it’s a boomer thing? A “spirit of the age” possession of some sort? I honestly don’t know.

What if it’s all hallucination?

I’ve been thinking a lot recently about something my wife said about AI. She’s finishing up her PhD in computer science, and knows more about generative AI and computational linguistics than just about everyone I know IRL (and most people I follow on the internet, too). So when she speaks on the subject, I do my best to listen.

Ever since OpenAI and ChatGPT took the world by storm, she’s been telling me that she doesn’t think the hallucination problem (where LLMs make stuff up) will ever be solved. Indeed, she doesn’t think it’s a “problem” in a technical sense at all, because every response from a generative AI is a hallucination—and that’s kind of a point. These aren’t really thinking machines, they’re hallucinating machines, replicating patterns in human language and thought. What difference does it make if the answer is false or true?

We call it “artificial intelligence,” but that’s really a misnomer, because these machines have no “intelligence” at all—at least, not in the human sense. Instead, they are like mirrors of our own intelligence, parroting back things that sound like they involve real thought, when really it’s all just pattern replication. They aren’t trained to recognize truth, they’re trained to recognize patterns. So, in reality, everything an AI generates is a “hallucination.”

This is why she thinks that we will never fully solve the hallucination “problem.” Indeed, the whole effort is a bit like trying to turn a lion into a vegan. And until we can train an AI on absolute truth—a thing that humanity has never been able to agree upon, much less reduce to zeroes and ones—then all we will really be able to do is create better and better plumage for our stochastic parrots.

What are the implications of this? First of all, we can safely ignore the worst of the AI doom porn, because a machine that cannot fundamentally recognize truth from falsehood is probably not capable of taking over the world and exterminating or enslaving humanity, even if it does qualify as a “general” intelligence.

We can also lay aside the fear (or the pipe-dream) that AI will 100% replace humans in all or most or really any fields. Even if they can do 90% of the work, recognizing truth is still an essential part of just about everything we as humans do. We can give it jobs and tasks—perhaps even some genuinely complex tasks—but so long as these machines cannot fundamentally distinguish between truth and falsehood, we will still need a human to oversee them.

That doesn’t mean that most humans are safe from being replaced by AI, though. If an AI-augmented person can accomplish the work of 10x or 100x the number of other human workers, we’re still going to face a massive disruption in the labor market and society as a whole. The question, then, is one of ownership and distribution. Who owns the AI? How do we distribute the productivity gains from AI? These are some of the difficult problems we need to solve in the next few years.

But the real problem—and the scariest implication of all of this—is the question of truth itself. After all, if AI is fundamentally incapable of recognizing truth, and all AI output is hallucination on some level, then who determines what is true and what is not? Sam Altman? OpenAI? Congress? Some three-letter government agency?

I think this is going to be the defining question of the rising generation, which is growing up in an AI-native world. What is truth? How can we recognize it? How do we distinguish between what is true and what is false? Increasingly, we are going to find that these are questions that AI cannot answer. And in a world saturated by deep fakes, bots, and sock puppets, where the internet is dead and all the most powerful players are constantly fighting a 5th gen war with each other, truth will be the thing we are all starving for.

The tragedy of the millennial generation is that everything in our world conspired to starve us of the three things we needed most. More than anything else, we hungered for meaning, authenticity, and redemption—and for the most part, we never got it. You can blame social media, the boomers, capitalism, student loan debt, the Republicans, the Democrats—it really makes no difference. All of those things and more came together to hobble our generation and make it almost impossible for us to launch.

Will the same thing happen with the zoomers and gen-alpha over the question of truth? It appears that things are moving in that direction. In a world saturated with AI, truth becomes a scarce and valuable commodity.

So what do we do? First, I think it’s important to recognize that AI cannot and never will be an authority on truth. At best, it only mirrors our own thoughts and ideas back to us—and at worst, it feeds us the thoughts and ideas of those who seek to control us. But AI itself is neutral, just like a gun or a knife lying on a table is neutral. What matters is how it is used.

Beyond that, I don’t really know what to say. Only that this is something I need to think about a lot more. What are your thoughts?

What do you think of these covers?

I’ve been playing around some more with ChatGPT, working on cover art for the Falconstar Trilogy. The best way to do it, I’ve found, is to make the art with AI, but to do the typography myself.

Anyhow, here are the test covers. What do you think?

The one that I feel most ambivalent about is Queen of the Falconstar. I really like how Zlata turned out, and the Falconstar looks pretty cool too, but the background… let’s see if I can fix that:

Anyhow, what do you think?

Epic Fantasy vs. LitRPG: 20 more principles that set them apart from other genres

So building on yesterday’s blog post, after asking ChatGPT to contrast litRPG against epic fantasy, I asked the AI to come up with twenty more principles that show how litRPG and epic fantasy are more similar to each other, by contrasting them against other genres. In other words, I asked for another twenty principles that either 1) hold true for both litRPG and epic fantasy, but not other genres, or 2) do not hold true for litRPG or epic fantasy, but do hold true for other genres. This was what the AI came up with.

What do you think? Do you agree with the list, or do you think the AI doesn’t know what it’s talking about? I mean, of course the AI doesn’t know what it’s talking about—it’s a pattern-matching stochastic parrot incapable of actual thought—but does the list itself hold true, or not? I’m interested to hear what you think!


✅ Ten Principles That Work in Both Epic Fantasy and LitRPG (but not as well elsewhere)

1. The Long Form Is an Asset

  • Epic Fantasy: Readers expect doorstoppers; sprawling stories add gravitas.
  • LitRPG: Readers binge long series to follow progression.
  • Other genres: Overly long novels (romance, thrillers) often feel padded or indulgent.

2. Worldbuilding as a Core Pleasure

  • Epic Fantasy: Intricate maps, languages, and histories enrich immersion.
  • LitRPG: Detailed mechanics, systems, and economies are part of the appeal.
  • Other genres: Too much worldbuilding bogs down the story (e.g., in mystery or romance).

3. Reader Dedication Is Assumed

  • Epic Fantasy: Readers accept investment to reap the mythic payoff.
  • LitRPG: Readers accept grindy arcs to enjoy progression.
  • Other genres: Casual readers often want quick satisfaction.

4. Hero’s Journey as Central Skeleton

  • Epic Fantasy: Growth from obscurity to legend is the core arc.
  • LitRPG: Growth from level 1 to overpowered is the core arc.
  • Other genres: Often resist the monomyth (slice-of-life, literary realism, etc.).

5. Community/Ensemble Casts

  • Epic Fantasy: Multiple POVs enrich the tapestry.
  • LitRPG: Party dynamics (tank, healer, mage) reflect RPG roots.
  • Other genres: Large casts risk confusing readers who want intimacy.

6. Spectacle as Payoff

  • Epic Fantasy: Climactic battles or magical revelations awe readers.
  • LitRPG: Dungeon raids and boss fights provide thrill.
  • Other genres: Spectacle without intimacy or brevity (like in romance) falls flat.

7. Maps and Charts Enhance the Experience

  • Epic Fantasy: Maps show kingdoms, trade routes, and lost ruins.
  • LitRPG: Stat sheets, skill trees, and quest logs scratch the gamer itch.
  • Other genres: Appendices and diagrams often feel extraneous.

8. Bingeability

  • Epic Fantasy: Readers want to sink in for weeks.
  • LitRPG: Readers tear through serialized arcs like binge-gaming sessions.
  • Other genres: Shorter, self-contained experiences dominate (rom-coms, thrillers).

9. Immersion Requires Internal Consistency

  • Epic Fantasy: Magic systems, politics, and cultures must feel internally real.
  • LitRPG: Mechanics and progression must follow consistent rules.
  • Other genres: Small cheats or contrivances are forgiven more easily.

10. The Fantasy of Escape Into Another Life

  • Epic Fantasy: Readers escape into a mythic, larger-than-life destiny.
  • LitRPG: Readers escape into a game avatar, empowered and free.
  • Other genres: Escapism is more muted—characters often mirror real-world constraints.

❌ Ten Principles That Work in Other Genres But Not in Epic Fantasy or LitRPG

11. Economy of Length

  • Epic Fantasy: Truncated stories feel shallow.
  • LitRPG: Short books cut off progression.
  • Other genres: Brevity (novellas, short novels) often thrives in romance, literary fiction, thrillers.

12. Standalone Closure

  • Epic Fantasy: Readers expect series and arcs across volumes.
  • LitRPG: Readers expect sequels and continuous leveling.
  • Other genres: Standalone novels dominate many markets (romance, crime).

13. Minimal World Detail

  • Epic Fantasy: Sparse settings break immersion.
  • LitRPG: Thin systems or game mechanics disappoint.
  • Other genres: Often better to focus tightly on character or conflict.

14. Immediate, High-Speed Pacing

  • Epic Fantasy: Readers accept gradual build-up.
  • LitRPG: Readers accept grind loops before climax.
  • Other genres: Quick, relentless pacing (thrillers) is a selling point.

15. Subtlety Over Spectacle

  • Epic Fantasy: Readers want grandeur, not quiet minimalism.
  • LitRPG: Readers want flashy abilities, loot drops, boss fights.
  • Other genres: Subtle slice-of-life or understated literary fiction works well.

16. Ambiguous Endings

  • Epic Fantasy: Readers want resolution—wars won, empires reshaped.
  • LitRPG: Readers want progression arcs to complete.
  • Other genres: Literary realism thrives on ambiguity.

17. Everyday Banality

  • Epic Fantasy: Mundane routine (work, school, dishes) feels like filler.
  • LitRPG: Grinding without purpose or progress feels like padding.
  • Other genres: Slice-of-life, contemporary drama thrive on the ordinary.

18. Romance as the Core Engine

  • Epic Fantasy: Love enriches but rarely drives the whole tapestry.
  • LitRPG: Love plots are secondary to leveling and quests.
  • Other genres: Romance is often the primary driver.

19. Prose Minimalism

  • Epic Fantasy: Readers want at least some richness, tone, and weight.
  • LitRPG: Readers want clarity and detail in mechanics, not Hemingway sparsity.
  • Other genres: Minimalist prose shines in lit fic or thrillers.

20. Compressed Timelines

  • Epic Fantasy: Readers want generations, years, or at least a long journey.
  • LitRPG: Readers want long campaigns and layered arcs.
  • Other genres: Stories that span a weekend or a single evening work beautifully in mystery, romance, lit fic.

⚖️ Big Takeaway

  • Shared Strengths (1–10): Both genres embrace immersion, scope, detail, and reader investment. They reward readers who want to live in another world for a long time.
  • Shared Weaknesses (11–20): Neither does well with brevity, minimalism, ambiguity, or everyday mundanity. Those principles thrive in other fiction but undermine the immersive, long-game experience of epic fantasy and LitRPG.

Epic Fantasy vs. LitRPG: 20 principles that work in one but not the other

So I was doing some genre research using ChatGPT, comparing epic fantasy (which I write) to litRPG (which I do not write—at least, not yet). After going back and forth for a while, I had ChatGPT list a bunch of principles that set each subgenre apart from each other. In other words, each of these principles holds true only for the one subgenre and not for the other.

It’s an interesting list. But being AI-generated, I’m not sure how much I can trust it, so I’d be interested to get your feedback. How true do you think these principles holds? Is it a pretty solid list, or are any areas where the AI got it wrong?


✅ Works in Epic Fantasy but Not LitRPG

1. Slow, Majestic Pacing

  • Epic Fantasy: Readers savor patience, waiting hundreds of pages for payoffs.
  • LitRPG: Readers expect regular “level-ups” or stat reveals—slow burns feel like stalling.

2. World as a Living, Breathing Character

  • Epic Fantasy: Setting is alive, with cultures, histories, and myth shaping events.
  • LitRPG: Worlds are often coded, constructed systems; too much “world-agency” risks breaking the conceit of “game mechanics.”

3. Archetypal Myth and Destiny

  • Epic Fantasy: Readers love prophecy, ancient bloodlines, and cosmic fate.
  • LitRPG: Players expect agency and control; prophecy undercuts the appeal of player choice.

4. Elevated, Poetic Language

  • Epic Fantasy: Slightly archaic or grand prose enhances the mythic atmosphere.
  • LitRPG: Readers expect clear, modern, accessible prose—too much ornament feels like “lag.”

5. Moral and Philosophical Depth

  • Epic Fantasy: Readers enjoy wrestling with justice, faith, and power.
  • LitRPG: Too much moral philosophizing slows down what should feel like gameplay and strategy.

6. Earned Heroism Through Suffering

  • Epic Fantasy: Heroes rise through sacrifice, scars, and loss.
  • LitRPG: Heroes rise by optimizing builds and winning battles. Too much suffering without progression feels like poor game balance.

7. History as Weight

  • Epic Fantasy: Ancient wars, dynasties, ruins, and forgotten myths enrich immersion.
  • LitRPG: History matters less than mechanics; world “backstory” is often secondary to the system’s function.

8. Layered Political Intrigue

  • Epic Fantasy: Kingdoms, councils, conspiracies—slow, strategic plotting excites readers.
  • LitRPG: Readers may skip political detail to get back to quests, loot, or progression.

9. Villains as Ideologies

  • Epic Fantasy: Antagonists often embody philosophies or cosmic balances.
  • LitRPG: Readers want enemies to be challenges, bosses, or rival players—not treatises on ideology.

10. The Reader Must Feel Small

  • Epic Fantasy: The awe of mountains, empires, or gods dwarfs the individual.
  • LitRPG: Readers want to feel powerful, not humbled—progression fantasy is about growth and mastery.

✅ Works in LitRPG but Not Epic Fantasy

11. Constant Tangible Progress

  • LitRPG: Frequent “dings,” new skills, and stat boosts scratch the gamer itch.
  • Epic Fantasy: Constant visible gains feel artificial—growth should be slow, hard-won, and often invisible.

12. Game-Like Structure

  • LitRPG: Clear quests, dungeons, XP, and loot tables create satisfying loops.
  • Epic Fantasy: Too much structure breaks the illusion of a living world—life doesn’t hand out quests so neatly.

13. Crunchy Mechanics

  • LitRPG: Readers relish stat blocks, skill trees, and optimization discussions.
  • Epic Fantasy: Overly mechanical explanations kill immersion—magic should feel mysterious, not like a spreadsheet.

14. Frequent Combat Encounters

  • LitRPG: Battles are core gameplay; readers expect frequent fights.
  • Epic Fantasy: Endless combat risks exhausting readers who want battles to feel rare, costly, and decisive.

15. Player Agency Above All

  • LitRPG: The protagonist must feel like a player making choices.
  • Epic Fantasy: Fate, prophecy, or the “burden of destiny” often guide characters beyond their control.

16. Meta Awareness

  • LitRPG: Characters can reference game mechanics, genre tropes, or player logic.
  • Epic Fantasy: Meta jokes break immersion—characters can’t wink at the audience about being in a story.

17. Loot and Rewards as Story Fuel

  • LitRPG: New gear and loot drops are story progression.
  • Epic Fantasy: Magical swords and treasures matter, but they’re rare, symbolic, and usually secondary to inner growth.

18. Episodic, “Grindable” Arcs

  • LitRPG: Dungeon runs, quests, and side missions can be modular and satisfying.
  • Epic Fantasy: Too episodic undermines the long-arc gravitas; the story must feel like a single tapestry.

19. Power Fantasy at the Forefront

  • LitRPG: Readers want to imagine themselves growing invincible.
  • Epic Fantasy: Too much power fantasy feels hollow—readers want awe and cost, not invincibility.

20. Immersion Through Familiar Systems

  • LitRPG: RPG tropes are comforting—readers enjoy seeing familiar mechanics at play.
  • Epic Fantasy: Familiar mechanics feel derivative—immersion comes from originality, history, and myth.

⚖️ The Big Picture

  • Epic Fantasy: Offers immersion in a mythic, awe-inspiring legend, with patience, gravitas, and weight. It humbles and uplifts.
  • LitRPG: Offers immersion in a game you can read, with momentum, mechanics, and constant progression. It empowers and energizes.

They share world immersion as a value—but diverge in what kind of immersion the audience craves: awe vs. agency, myth vs. mechanics, destiny vs. progress.

How I Would Vote: 2025 Hugo Awards

The Nominees

The Tainted Cup by Robert Jackson Bennett

The Ministry of Time by Kaliane Bradley

A Sorceress Comes to Call by T. Kingfisher

Alien Clay by Adrian Tchaikovsky

Service Model by Adrian Tchaikovsky

Someone You Can Build a Nest In by John Wiswell

The Actual Results

TO BE DETERMINED

How I Would Vote Now

  1. No Award
  2. Service Model by Adrian Tchaikovsky

Explanation

As if yesterday’s post wasn’t controversial enough, I’ve decided to jump feet-first into this particular tempest (though thankfully, it appears to be a tempest in an ever-shrinking teacup). And I suppose the thing that makes this particular post so interesting is that I could actually cast this vote, if I had no qualms about giving the clowns who run the Hugo Awards any of my hard-earned money. But I do have qualms, so I won’t give them my money, which still makes this a hypothetical exercise, even though I’m posting this three weeks before the 2025 Hugos are awarded.

To be perfectly honest, I have not read any of these books all of the way through. I’ve read enough of two of them to DNF them, and one of them enough (including the epilogue) to know that I will eventually read the whole thing. And I screened all of them first with AI, which told me enough to know that three of them were not worth reading at all.

First, Someone You Can Build a Nest In. According to ChatGPT (and frankly, the back cover description itself), this book is chock full of body horror, trauma, abuse, and sexual depravity. It is also quite possibly the wokest book on the ballot, which means that it probably has the best chance of actually winning. Which also means that you couldn’t pay me enough money to read it. So much for that.

The Ministry of Time also appears to be woke, with anti-colonial and LGBTQ themes. However, the thing that really turned me off were all of the content issues that ChatGPT listed, such as frequent strong language, lots of F-bombs, and several erotic “open-door” sex scenes. So yeah, I’ll give a pass on that one too.

It’s much the same story for The Tainted Cup. A few woke elements, a subtle M/M romance (which I’m sure plays into the “All True Love is LGBTQ Love” trope that I cannot abide), and a lot of explicit profanity, with some prostitution to round it out. Not interested.

I forget why I DNFed A Sorceress Comes to Call. All I remember was that when I tried to read it, I felt repelled from it like a magnet. Since that has been my experience with basically everything else that T. Kingfisher has written, I didn’t feel compelled to try again.

Which brings us to the two books by Tchaikovsky. I really enjoyed his Children of Time, though I didn’t really get into the sequel (just didn’t feel compelled by any of the characters). He is a good writer, and specifically a good science fiction writer, though his scientific materialism strikes me as outdated.

Alien Clay didn’t appeal much to me, though—honestly, I found it difficult to believe that a government that would expend so many resources to transport their prisoners halfway across the galaxy wouldn’t also spend the tiny fractional cost to make sure they all got there alive. So right from the start, it felt like a melodramatic parody of all the left’s fears about “fascism.” And skipping to the end, it basically turns out the way Halo would have ended if the Flood had won. So I decided to DNF it, even though it wasn’t the worst book I’ve ever DNFed. And also, I don’t think that any one author should have more than one book on the ballot in any given year. So that’s why I’d put it under No Award.

Service Model, though, is pretty good. The best way I can describe it is Murderbot meets Kafka. It’s sort of an absurdist comedy in a post-apocalyptic world where the humans have (mostly) vanished, and the robots are malfunctioning in hilarious (and sometimes disturbing) ways. Not my favorite kind of book, and it probably could be improved by ruthlessly editing it to half the length, but I was enjoying it right up to the point where someone else put the library copy on hold, and I had to return it without renewing it. Skipping to the epilogue, I found nothing particularly objectionable, so I will pick it up again, and will likely finish it.

Which is more than I can say of most Hugo-nominated books in the last ten years.

[ETA 23 Feb 2026: I’ve decided to DNF Service Model after all, not because of anything objectionable that I read, but because I just couldn’t bring myself to pick it up again and finish it. It just wasn’t compelling enough for me to want to finish it more than I want to pick up something new. I could be persuaded otherwise if I heard someone really gush about it, but right now, I’m just not going to bother.]

The dangers of relying too much on AI

I saw this really interesting video last week, and it made me think: am I relying too much on AI?

In my personal life, this probably isn’t an issue. I do occasionally ask ChatGPT to make me a recipe, or to advise me on a particular topic, but I always do a gut check and assume that it’s hallucinating if it doesn’t pass. If it gives me something that I can quickly and easily verify, I always do that… and half of the time, it turns out to be a hallucination to some degree. So yeah, I don’t rely on it nearly as much in my personal life as some of the characters in this video.

What about blogging? Don’t be too scandalized, but with my new blogging schedule, I have experimented a bit with using ChatGPT to write some of these blog posts. It’s not like I’ve been copy-pasting everything straight from the chatbot, but I have relied on it a little more heavily than I do in my own writing.

After trying that a couple of times, though, I decided to cut that out and write all of these blog posts by hand. Why? Because I felt like it was creating too much distance between myself and the people who read this blog, and the purpose for writing this blog is to foster a human connection. So it kind of defeats the purpose to rely on a chatbot to generate most of the content I post here. For that reason, I plan to keep writing all these blog posts entirely myself, with only minimal AI input.

So what about my fiction? This is where things get a little tricky. While I totally agree that simply copy-pasting from AI is a piss-poor way to write a book, I do think that AI can be a very useful tool in writing and crafting a novel, provided that you understand the limitations of the AI and don’t rely on it too much. But how much is too much? That is the question.

The biggest way that AI has helped to enhance my own writing is in giving me a birdseye view of the story as I generate a “crappy first draft.” This birdseye view allows me to see and fix major story issues before they metastatize and give me writer’s block, which is what tends to happen if I write these drafts out entirely by hand. When I’m focused on the page, I tend to lose sight of the forest for the trees, so I don’t notice that there’s a problem with the story until I’m several chapters in and find that I just can’t write.

This has happened with basically every project that I write on my own, and is the main reason why it took me anywhere from six to eighteen months (or longer) to write even a short novel, before I started using AI. However, since I began incorporating AI into my writing process, this problem has basically gone away, and I no longer experience this form of writer’s block at all.

However, while I do rely on AI to help me to craft my “crappy first draft,” that isn’t the draft that I publish. Once the AI draft is as good as I can make it, I will then go through scene-by-scene and rewrite the entire book in my own words. The purpose for this step is to make sure that I’m telling the story in my own words, and to make the story my own. I will still have the AI draft open on another screen, and refer to it as I write out the story, but I don’t do any copy-pasting. It’s all written out by hand.

Is this enough, though? Or do I need to add more steps to make sure that I’m not relying too much on AI, and thus losing my own voice? Recently, I’ve been spending a lot more time on the AI draft, generating multiple iterations and combining the best parts to (hopefully) boost the quality. I’ve also been doing a revision pass over the AI draft, tweaking it to smooth over some common AI-isms and (hopefully) adding a bit of my own voice before I move on to the human draft and rewrite the whole thing to make sure it’s all in my voice.

But while this might be enough to keep the book in my own words, is this enough to keep my own writing skills from atrophying? Or do I need to occasionally pick up a WIP that is 100% human writing, with no AI at all, just to make sure I don’t lose these writing skills? That is the question that I’m currently pondering. Perhaps this is the sort of thing that short stories could serve really well to help with. Perhaps I should go back to writing short stories again, just as a way to keep my writing skills sharp.

If I were starting out right now as a new writer, I would definitely avoid writing with AI until I’d written enough to find my own voice. And I would also make sure to write at least one novel 100% without AI-assistance, just for the experience, and to prove to myself that I could do it. Otherwise, I think there would be a very real danger in becoming over-reliant on AI to write my books, and thus risk losing my own unique voice, so that none of the books that I write ever truly become my own.

Anyhow, those are some of my current thoughts on the subject. What do you think of this problem?

Gearing up for another family road trip

We’ve spent the last couple of days getting ready for another cross-country road trip as a family, this time to Arkansas. My side of the family is going down there, mostly because my youngest sister works at a national park, so it’s more convenient for us to come to her (and it should be fun as well).

The plan is to drive to Omaha, spend a couple of nights with my brother-in-law and his wife, then drive down to Arkansas and spend the week with family. Once we’re done, we’ll just drive straight back to Utah, hopefully in two days, but more likely in three. After all, we’ve got a five year-old and a two year-old with us.

This is the first big road trip we have this summer. The second one is at the end of July, and we’ll be going up to northern Alberta for a reunion with my wife’s side of the family. Her grandmother passed away earlier this year, and this was the soonest everyone could get together (getting passports for the kids was a little tricky).

I’ve already schedule blog posts through the next week and a half, so those should be coming up each day. I’ve also been writing more Fantasy from A to Z posts, and I hope to write the rest of them while I’m out there, though I’m not stressing out too much about that. If they get done, great, if not, I’ll just finish them when I get back.

The big reason why I’m blogging daily now is because of some major problems I’ve been having with my email list. I used to send out a newsletter approximately every week, but over the last couple of years, my open and click-thru rates have been creeping ever lower, until just last month they suddenly dropped by more than 50%. Turns out there’s a whole lot of backend stuff that changed in the last year, most of which I barely understand.

But ChatGPT has been a huge help in figuring out what’s wrong, and how I need to register DMARC and SPF and all the other stuff that I still don’t understand. My wife has also been a huge help in sorting through it all. I think it’s all set up properly, but I haven’t sent out a newsletter yet, and probably won’t until I get back from Arkansas. I also need to update my newsletter template. ChatGPT should be really good for that.

So the email newsletter is turning into a monthly thing, and the blog is turning into a daily thing, at least for the forseeable future. All of that might get thrown out the window when the new baby comes along, at least temporarily.

In the meantime, I’m working on Fantasy from A to Z and the rough AI draft of Lord of the Falconstar, both of which are coming along quite well. I’m going to experiment with having one human WIP and one AI WIP active at the same time, because ChatGPT suggested that this would be the best way to maximize by writing time and productivity.

I fed ChatGPT my accountability spreadsheet and the daily project journals I’ve been keeping for the past year, and it came back with some fascinating insights into my writing process. It’s amazing how you can feed it a bunch of raw, barely-formatted data, and get a genuinely insightful analysis.

Is this taking away jobs from a data analysis / writing coach? Not really, at least in my case, because I doubt I would have hired one. But the results sure are useful. I’m also experimenting with feeding my entire book into ChatGPT and asking it to write a book description or generate a cover. It’s amazing how it can “read” a whole novel in a fraction of a second, and spit back answers that show (or at least simulate) a genuine understanding of the material.

But one thing ChatGPT can’t do is convert a short story into a screenplay—at least, not without significant human input. I tried uploading “What Hard Times Hath Wrought” and told it to turn it into a screenplay, and the results were hilariously bad. Maybe Sudowrite has a plugin, though…