The thing about Minneapolis that scares me

I learned four things by living through covid. They are:

  1. Whatever the mainstream narrative tells you to believe (or not to believe), you should probably believe the opposite.
  2. Whatever the government tells you to do (or not to do), you should probably do the opposite.
  3. Accusation is projection is confession.
  4. At any given time, the most important story is the one that no one is talking about.

As the situation in Minneapolis continues to escalate, it’s not just the action on the ground that has me worried, but the rhetoric itself. Specifically, the one that has me worried is the accusation that ICE is somehow Trump’s Gestapo.

Obviously, this is ludicrous on its face—a wildly false accusation meant to rile up the useful idiots, many of whom received a public school education and thus know almost nothing about the actual Nazi Gestapo. But because accusation is projection is confession, it’s actually much more than that.

If there’s one thing that’s consistent about the left, it’s that they always accuse their enemies of doing the things that they are actually doing, or that they want to do. So when they say that Trump has some sort of Gestapo, that’s a very strong signal about their future plans, if they ever get power again.

The key question is this: by accusing Trump of setting up his own secret police force, are they confessing to something they hope to do, or to something that they are actually setting up right now? In other words, are they projecting something that’s purely aspirational, or do they already have the databases and surveillance infrastructure set up so that they can have a secret police force up and running the moment they come back to power in Washington again?

How about a book on AI writing?

For the last two and a half years, I’ve been reworking my creative writing process to incorporate AI in a way that doesn’t diminish my voice or humanity while taking advantage of all of the ways that AI can make my writing faster and more efficient. I’ve got it down to a point where my books only take weeks or months to write, instead of months or years, and I’d really like to write a writing book where I can share all of that.

As with the other non-fiction that I’ve done, I’ll probably post it all here on the blog before combining it into a book. But there are a lot of different directions I could take this. Should I write this more for an amateur hobby/weekend writer, or an aspiring professional kind of like I was 15+ years ago? Should I focus more on how to preserve elements of humanity like authorial voice, creative vision, etc, or should I focus more on the AI side like prompt engineering and common AI-isms? Should I go into depth about philosophical and ethical concerns, or ignore that stuff altogether and focus on what I’ve found works for me?

What I need is to come up with a rough chapter outline. Once I’ve got that, I can turn this into a weekly blogging thing, until I’ve got enough posts for a book. And while I can run this brianstorming exercise through ChatGPT to come up with a good outline (and I probably will, at some point), I’d like to throw it out there and hear from some of you.

So what do you think? What’s the angle you’d really like to see me take with this?

By the way, here’s a mock-up of the cover:

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?

Fisking 1-star reviews bashing AI

They say that authors should never respond to one-star reviews. That’s generally good advice, and for most of my career, I’ve studiously kept it. However, I’ve recently begun to get a new kind of one-star review that baffles me—reviews that essentially say: “the book was good, but it was written with AI so I hate it.”

Here’s an example:

This book is written with AI. Incredibly disappointing as a reader to give a book/author a chance and then to get to the end of the book only for the “author” to then announce the AI card. If I could give zero stars, I would for this alone. I also didn’t appreciate that this use of AI was not announced until the ending Author’s Note. If “authors” are going to cut corners and put their name to computer-generated mush, they should be willing to put that information on the front cover. The book struggled to find its pace, and some parts read as though they were written for a child’s short story competition while others felt as though the writer was snorting crushed up DVDs of Pirates of the Caribbean as they wrote.

Let’s break it down:

This book is written with AI. Incredibly disappointing as a reader to give a book/author a chance and then to get to the end of the book only for the “author” to then announce the AI card.

Yes… but I can’t help but notice that you got to the end of it. In other words, you finished the book. Also, from the way you tell it, it seems that you didn’t realize the book was written with AI until you got to the very end. So based on your own behavior, it doesn’t seem that quality was the issue.

I also didn’t appreciate that this use of AI was not announced until the ending Author’s Note. If “authors” are going to cut corners and put their name to computer-generated mush, they should be willing to put that information on the front cover.

Okay… but if my book was just “computer-generated mush,” why did you finish it? And why were you surprised when you learned that it was written with AI-assistance?

I can understand the objection to books that were written solely with AI, with little to no human input. But that’s not how I write my AI-assisted books. Instead, I outline them thoroughly beforehand, write and refine a series of meticulously detailed prompts (usually using Sudowrite), and generate multiple drafts, combining the best parts of them to make a passable AI draft. And then I rewrite the whole thing in my own words, using the AI draft as a loose guide with no copy-pasting.

Why would I go through so much trouble? Because of how the AI drafting stage gives me a bird’s eye view of the book, allowing me to identify and fix major story issues before they metastasize and give me writer’s block. Before AI, that’s where 80% of my writer’s block came from, and it often derailed my projects for months, so that it took me well over a year to write a full-length novel. But with AI, I’m no longer so focused on the page that I lose sight of the forest for the trees. So even though generating and revising a solid AI draft adds a couple more steps to the process, it’s worth it for the time and trouble that it saves.

That’s the way I use generative AI in my writing process. But there are many other ways—and I hate to break it to you, but most authors use AI in one way or another. If an author uses Grammarly to fix their spelling and grammar, should they disclose that on the cover? If they use MS Word? What if they used a chatbot to brainstorm story ideas, but went on to write it entirely themselves? Should that also be disclosed?

The book struggled to find its pace, and some parts read as though they were written for a child’s short story competition while others felt as though the writer was snorting crushed up DVDs of Pirates of the Caribbean as they wrote.

Yes… but again, I can’t help but notice that you finished the book. And after you finished it, you were surprised to learn that it was written with AI. So with all due respect, I’m going to call BS on your objections here. I think you only decided you hated the book after you learned it was written with AI, and you came up with these objections after the fact. Whatever.

I think a lot of the people who object to AI are really just scared and angry. They claim to have principled, ethical objections to the technology, but few of them follow through to implement that principled stance into every area of their lives. After all, if you use Grammarly, Google Docs, or MS Word, you are using generative AI just as surely as I am using ChatGPT and Sudowrite. For most people, the ethical objections are just a smokescreen for their general fear of change. They’re fine with embracing the convenience the technology offers them in their own personal lives, but they insist that everyone else—including me—live according to their principles, no matter how inconvenient or difficult it may be.

As an example of that, check out this one-star review:

The arts! Whether visual, performance, or literary—my haloed experience has been the act of creating and sharing a connection to the profound or sublime. Why, then, would any artist—musician, dancer, sculptor, painter, or author—offload (abdicate) the act of creation to AI? Process versus product. Mr. Vasicek included an afterword for this volume, describing his workflow and the efficiency of collaboration with AI: a 6,624-word day! another volume completed! Mr. Vasicek obviously owns the skills to weave rich character development and scenes. Perhaps Mr. Vasicek’s AI collaboration explains why these characters, the plot, the narrative—and subsequently, the entire story— are so flat and undeveloped. Although his lead male shows some undeveloped promise, the mother’s too-oft used “dear” and “my love,” and the daughter’s clutching at her mother’s apron are cringe-inducing. Perhaps Mr. Vasicek might eschew AI-assisted writing, seeking a future of quality over quantity.

Let’s break it down:

The arts! Whether visual, performance, or literary—my haloed experience has been the act of creating and sharing a connection to the profound or sublime. Why, then, would any artist—musician, dancer, sculptor, painter, or author—offload (abdicate) the act of creation to AI?

Because for some of us, writing is more than a “haloed experience”—it’s an actual job. It’s what we do for a living. And if you want to do your best work, you need to use the best tools. We used to build houses with plaster and lath and wrought-iron nails, using hand tools and locally-sourced lumber. But today, you’d be a fool not to use power tools and materials sourced from a building supply store, or your local Home Depot. If that makes your building experience less profound or sublime, so be it.

Process versus product. Mr. Vasicek included an afterword for this volume, describing his workflow and the efficiency of collaboration with AI: a 6,624-word day! another volume completed!

I’m not gonna lie: there is a certain degree of tension between art-as-product and art-for-art’s-sake. But the two are not mutually exclusive. A house can still be a beautiful work of art, without taking as long as a cathedral to build it. Likewise, a book can still be a beautiful work of art, without taking as long as Tolkien’s Lord of the Rings.

Again, you’re trying to pidgeon-hole me into your “haloed” idea of what a “true artist” should be. Which would make it absolutely impossible for me to make a living at this craft. If all of us writers followed that path, there are a lot of wonderful books that would never get written. And I doubt that the overall quality of the books that do get written would rise.

Mr. Vasicek obviously owns the skills to weave rich character development and scenes.

Now we get to the interesting part. I checked this reviewer’s history, and this was the only review they’ve written for any of my books. Therefore, I can only assume that this is the only book of mine that they’ve read. But if that’s the case, how do they know that I have “the skills to weave rich character development and scenes”? If the book I wrote with AI was pure trash, why would they say that I obviously have some skill?

Once again, we’ve got a case of “I enjoyed this book, but it’s written with AI so I hate it.” In other words, it’s not the book itself that you hate, so much as the way I wrote it. You object to the idea of authors using AI, not to what they actually write with AI.

Perhaps Mr. Vasicek’s AI collaboration explains why these characters, the plot, the narrative—and subsequently, the entire story— are so flat and undeveloped. Although his lead male shows some undeveloped promise, the mother’s too-oft used “dear” and “my love,” and the daughter’s clutching at her mother’s apron are cringe-inducing.

Finally, some specific and legitimate criticism. And while I do think there’s a degree of retroactively looking for faults after enjoying the book, I’m totally willing to own that these criticisms are valid. This particular book (The Widow’s Child) was one of my first AI-assisted books, and I was still learning to use these AI tools as I was writing it. I did the best I could at the time, but if I were to write it today, I could probably do a lot better, smoothing out the annoying AI-isms that you’ve pointed out here.

But the book is currently sitting at 4.4 stars on Amazon (4.1 on Goodreads). And the other readers do not share your objections. Here is another review, pulled from the same book:

Since waiting a year or more to read the next book in a sequel is hard on my stress levels, I’m liking this AI. It means talented authors like Joe Vasicek can churn out an outline faster. Then he can bring in his talented ideas, such as the content of this heart-stopping adventure of The Widow’s Child, to fill out the nitty gritty in record time.

Clearly, it’s not the case that all (or even most) readers feel the same way about AI as you do.

Perhaps Mr. Vasicek might eschew AI-assisted writing, seeking a future of quality over quantity.

Why can’t we have both? Why can’t we have quantity with quality? Why can’t AI make us more creative, instead of replacing our human creativity?

This is all giving me flashbacks to the big debate between tradition vs. indie publishing, back in the early 2010s. Back then, the debate was between purists who said that indie publishing would destroy literature by flooding the market with crappy books. Indies argued that removing the industry middlemen would create a more dynamic market that would give readers more choices and allow more writers to make a living. Both were right to some degree, and both were also wrong about some things. In the end, we reached a middle ground where “hybrid publishing” became the norm.

The same kind of debate is happening right now between human-only purists and AI-assisted writers. The biggest difference is dead internet theory. In the early 2010s, the ratio of bots to humans on the internet was still low enough to allow for a lively debate. Today, there’s so much bot-driven outrage on the internet that most of us are just quietly doing our own thing and avoiding the debate.

That same bot- and algorithm-driven outrage is driving a lot of peole to be irrationally angry or afraid of AI. With that said, I can understand why so many people are upset. And I do think there are a lot of valid criticisms about this new technology, including its environmental impact, copyright considerations, how the models were trained, and the societal impact it’s already starting to have. But if we don’t have an honest and good-faith debate about these issues, we can’t solve any of them. And we can’t have a good-faith debate if one side is coming at it from a place of irrational anger or fear.

In any case, I find it super annoying when readers who clearly found some value or enjoyment in my books turn around and give it a one-star review merely because they don’t like how I used AI. And at the risk of going viral and soliciting more one-star anti-AI reviews, I think its worth voicing my views on the subject and opening that debate. So what are your thoughts on the subject? How do you feel about using AI as a tool to help write books? Can we have quantity with quality? Can AI help us to be more creative, not just more productive? What has been your experience?

Fantasy from A to Z: X is for eXpectations

What sort of books are fantasy readers looking for today? What are the expectations that readers have for the genre?

Overall, the fantasy genre is growing. Sales are up, both in traditional and indie publishing, and the big names in the field (like Brandon Sanderson) are doing quite well. It’s clear that the fantasy genre as a whole is robust and healthy.

When you break it down by publishers and subgenres, however, things start to look a little different. Romantasy is dominating the traditional publishing world, but most of it is little more than pornography for women, dressed up with fantasy trappings. And because of how traditional publishing now relies on a few big blockbusters to make most of their earnings, romantasy is sucking all of the oxygen out of the room, making it much more difficult for debut and midlist authors in the other fantasy subgenres.

In the world of indie publishing, litRPG has begun to demonstrate some staying power. It was the new hot thing back in the early 2020s, but it’s attracted enough attention and developed enough of a following that it has become a major subgenre that is likely to endure for some time. I could be wrong about that, but from what I see, that’s where most of the innovative authors and whale readers (ie >1 book per week) are focusing their attention these days.

But because of the way that the algorithms tend to govern the indie publishing cycle (and the way that indie publishing has unfortunately turned into a zero-sum, pay-to-play game with online advertising), the rise of litRPG in the indie publishing world may very well be sucking all of the oxygen out of the room in the same way that romantasy is sucking it out of the traditional publishing world. 

Both subgenres are also very gender-biased, with women gravitating toward romantasy and men gravitating toward litRPG. This reflects the broader social and political trend of men and women going separate ways, across a whole host of different metrics. So as the gender divide continues to widen in society generally, that will probably reinforce the divide between romantasy and litRPG, creating a positive feedback loop (or death spiral, depending on how you look at it).

Sword and sorcery continues to do okay, and has probably been given a boost by the recent release of Conan the Barbarian into the public domain. But most of sword and sorcery got siphoned off into grimdark back in the 00s—in fact, you could say that sword and sorcery reinvented itself as grimdark. And while grimdark has resisted the feminization of literature, standing as one of the few remaining bastions where male readers continue to feel at home, I think grimdark has already passed its peak. In a post-pandemic, post-Trump world, I think most readers are hungry for books that are less nihilistic and more uplifting.

Which brings us to epic fantasy. While Brandon Sanderson continues to dominate this subgenre, with his massive kickstarters and huge book releases, it’s debatable whether his readers are hungry for more epic fantasy, or just for more Brandon Sanderson. He’s kind of a subgenre all to himself. Recent streaming adaptations like Wheel of Time and Rings of Power have failed miserably, and Game of Thrones has fallen almost totally out of cultural significance, with George R.R. Martin’s failure to finish the last book (and Patrick Rothfuss’s failure to finish his own series) becoming something of a meme.

In fact, the failure of these two big-name authors to finish writing their books may have struck epic fantasy a mortal wound. Because of how they have been burned, a large number of epic fantasy readers are now unwilling to commit to a series until after it is complete. But very few authors can afford to write a truly epic series and release the whole thing at once. It takes several years to write a series like that—and what are authors supposed to do if the first one flops? 

In other words, debut epic fantasy authors are damned if they do, and damned if they don’t. If they release the first book by itself, it will probably sink into obscurity before they can write and release the next book. And if by some measure of hard work and tenacity they manage to write a whole series and hold back from publishing until they’re ready to release it all at once, if the first book still fails to sell, they’re SOL and all that hard work was for nothing. 

This is also why traditional publishers are so unwilling to publish a new epic fantasy series from a debut or a midlist author. A bestseller like Larry Correia might be able to dip his feet in that pond (and do quite well—I highly recommend his Sons of the Black Sword series), they won’t do that for anyone else. Which is fine, except that indie publishing epic fantasy is just as hard—arguably more so.

For these reasons, I don’t think it’s an exaggeration to say that Patrick Rothfuss and George R.R. Martin have done more to kill epic fantasy than they have to grow it.

But this may actually have created an opportunity for those authors who are willing to drive into the smoke. After all, there’s much less competition if you can manage to break in and build a decent following. But how much hunger is there for epic fantasy, compared to other fantasy subgenres? And how can a newer/midlist author reach them, without a big push from a publisher or the algorithms?

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.

Thinking about switching Gunslinger books to J.M. Wight

Right now, I’m a science fiction writer who occasionally writes fantasy. I want to transition to being a fantasy writer who occasionally writes science fiction. But I also have a pen name (J.M. Wight) for more religious-themed books, since there are a lot of science fiction readers who have a serious ick with that.

As I set things up for this transition, I’ve been looking at the books I’ve already published and trying to decide what to do with them. The Gunslinger Trilogy is one series I’ve been looking at particularly hard. It’s kind of an edge case, because the religious themes become more pronounced as the series progresses. One of the more consistent themes in one-star reviews is that people don’t like the “Mormon” stuff in the later books, such as the part where the main character meets with the missionaries (and ultimately gets baptized), or the alien twist in the last book that’s pulled right out of the Books of Enoch/Jasher/Moses.

If I’d planned out the whole series before I wrote the first book, I probably would have published them under my J.M. Wight pen name for that reason. But the first book was a straight-up space opera, with minimal religious themes. It was only after I’d published the first book (under my main Joe Vasicek name) that I wrote the next two books and decided to throw in the more religious stuff. And while I was careful to write it in such a way that the books never come out and say whether all that religious stuff is actually true, the fact that it’s in there at all has turned off some readers who weren’t expecting it.

The trouble is that the first book has a lot of profanity in it, and religious readers tend to be just as icky about profanity as sci-fi readers are about the religious stuff. Even more so, in fact. So before I make the switch, I will probably have to make an extensive rewrite to tone down the swearing and make it more palatable for that audience.

It’s a fairly common mistake, especially among inexperience writers: you write the first book for a certain audience, but as the series progresses, the later books appeal to a different audience, betraying some of the expectations of the first audience. When taken to extremes, it’s the sort of thing that torpedoes careers and forces writers to reinvent themselves. So given that fact, I’m kind of surprised that these books have done as well as they have.

What do you think? Should I switch them to my J.M. Wight pen name, editing them to remove the profanity and lean into the audience that isn’t turned off by religious themes in their science fiction? Or should I keep them as they are?

Making some changes

I’m thinking very seriously about changing my email newsletter to a monthly digest, as opposed to the (mostly) weekly thing that it is right now. Last month, I saw a severed drop in my open rate, and I’m not sure why, but I suspect it’s a combination of sending newsletters too frequently, getting too many of them flagged or left unopened (though my spam rates have always been quite low), and not being very careful about what I put in the subject lines, as apparently the ISPs will flag you if you use words like “free” or “sale.” So that’s going to be a joy to figure out.

So that’s why I’m planning to turn my newsletter into a monthly thing, as opposed to a weekly thing. To make up for that, I plan to turn this blog into more of a daily thing, engaging with it more and being more open about my writing and everything else. I’d also like to bring on some guest bloggers from time to time, and I have some interesting ideas for that. Here are just a few of the things I’d like to post more of:

  • Guest posts & interviews
  • Book reviews
  • “Best of” genre tropes
  • Writing updates
  • Family/life updates
  • WIP excerpts
  • Interesting long-form podcasts
  • “How I Would Vote Now,” maybe for more than just the Hugos (or Hugo: Best Novel)
  • SF&F news reactions
  • Books/games/movies that inspired some of my books

etc etc, as well as the occasional just for fun post.

It’s funny, because I started this blog back in 2007, just as the iphone and social media were really starting to take off. Those technologies led to the “death” of the blogosphere, but I kept on blogging through the social media era, just because I enjoy blogging. Now, it turns out that AI grabs most of its data from blogs, and the best way to improve your AI optimization is to have a prominent blog and post often to it.

So that’s another big reason why I plan to post a lot more. But I don’t plan to churn out any AI slop, though I may use AI for help brainstorming blog topics or breaking down my thoughts for a good blog post. I actually do enjoy keeping this blog, even if only a handful of people read it, so I’m not going to go too crazy with the AI optimization. If anything, that’s more of a side benefit.

What sort of stuff would you like to see me post more of?

Five things I did at work last week (and a question–wanna read a free e-arc?)

Things have been so busy around here that I forgot to do this on Monday! But here it is, just a day late.

Last week, I:

  • Wrote about 4k human words in Bloodfire Legacy,
  • Revised about 18k words in The Soulbond and the Sling,
  • Generated another 10k words for The Soulbond and the Sling,
  • Used AI to revise through another 56k words of The Soulbond and the Sling, and
  • Started the outline for the second book in the Rise of the Soulbound King Trilogy, The Soulbond and the Lady.

I am super excited about The Soulbond and the Sling, though I will not release it until the first three books are out. Maybe I’ll post the AI draft to my blog? I think it’s good enough that I can do that. Or maybe I’ll release a free e-arc or something. Still need to think that through–but I would really love to find a way to share this book with people, because it is really a lot of fun. Also, my most ambitious book to date. The final draft will probably clock in somewhere between 150k and 200k words–a solid epic fantasy. And that’s just the first book in the trilogy!

Anyhow, I will try to be better about posting this week, but I am really trying to make as much progress on this WIP over the summer as I can. When the fall comes around, things are going to be crazy busy insane, with our family moving back to Orem, my wife starting a new job, and having a new baby. I may not be able to do any more writing from September to the end of the year, so I’m trying to do as much now as I can!