Then reality checked in, carrying luggage: a hefty dose of financial truth. Last year, I earned exactly NZD$3,740.95 from my creative pursuits (about NZD$311.75/mo, about USD$180). For context, New Zealand's minimum wage is NZD$23.15/hour, meaning a minimum wage 40-hour-a-week earner grosses NZD$926 weekly. If you’re squinting at the screen wondering if there’s a mistake, don’t: an unskilled minimum wage worker earns triple my monthly writing income in just one week, despite me having a back catalogue of over 20 full-length novels all only about the price of a cup of coffee.

This isn’t a sob story, but it's a clear reality check: when you're an indie author, every sale counts. Piracy isn't just a yo-ho-ho hearty tale or a slightly whimsical nuisance; it's the difference between barely scraping by and, well, scraping slightly less. Being pirated doesn’t give me a great feeling (it’s exhausting), but it's oddly… validating? If you're being pirated, someone thinks you've created something worth stealing. Sidebar: I’m not sure if I should put that on my book covers.

However! Despite the knee-jerk reaction that piracy is the enemy, it's more complicated than it seems. I don’t think piracy is the disease—it’s a symptom. The real villain here isn't LibGen (I’ve been pirated for a long-ass time); it's the powerful marketplaces that claim to help authors but end up undermining reader trust. Looking at you, Amazon.

Let's unpack that.

Cory Doctorow Was Wrong (But He Meant Well)

Remember when Cory Doctorow loudly proclaimed piracy was good for authors because it boosted visibility? Sure, Cory: piracy is a wonderful promotional tool if you're already famous. Despite it working for this one guy, it literally does not work for thousands upon thousands of authors on LibGen, Facebook warez groups, and so on. When a reader has a spare five bucks, they're more likely to throw it at the guy they've already heard of (which is Cory’s point). Doctorow can afford the odd "stolen" read because people know and trust his name. He built his brand in the Before Times™ when LibGen didn’t exist and piracy was actually much, much harder (it doesn’t hurt that he’s also a brilliant writer - 0wnz0red on Salon will give you a taste).

Let’s take a side trip down memory lane.

In 2011, Valve’s Gabe Newell famously claimed piracy is an issue of service, not price. Valve is a tech darling, turning joy into cash without purchaser friction. It’s lower risk and far friendlier for gamers than current or prior alternatives (remember when you needed to buy physical media from that GameStop at the mall, risking influenza from the mob of children left there for free babysitting, only to get home and find the fucken thing didn’t work? And how some friend with eDonkey gave you a cracked and patched version that had no DRM?).

There’s a real delta, now. Piracy (courtesy of LibGen) is easier than the legitimate book retailer alternatives. With Amazon and other storefronts squeezing tighter, more people are seeking alternatives. Amazon’s strike against being able to get your bought and paid-for books out of your Kindle and into your home library—like, say, how physical books work—has driven some into piracy as a sort of antibody response. That is, LibGen provides a better experience than retailers now; it’s the Valve Software of the book industry, except no artists are getting compensated. It’s plain ol’ theft.

This means that when you're a struggling indie writer named Richard Parry, those five bucks Cory’s getting instead of me means the difference between continuing to write or crying into my coffee. Every “lost” sale isn’t a bastion of freedom; it’s another feeling of hopelessness in creative endeavours that makes me question the value of putting good things into the world. You can get my books “free” from real libraries where I still get paid, but LibGen hurts me. I don’t have the luxury of being Cory Doctorow.

This was brought home in 2019 when I released The Empire’s Rogues. This was a book in my long-running Tyche series, which by that time was heavily pirated. I even found a Facebook group sharing Google Drive links of my works; Google refused the DRM strike, and Facebook banned me from the pirate ring group rather than shut it down and risk those ad-revenue-generating eyeballs. An ARC reader released an early copy online. The result was this book sold a mere 18 copies at launch. It got 25-30 reviews, though (many of which Amazon have taken down), so at least the pirates did something for me! This about when I decided to officially stop writing full time and go back to my corporate job; piracy had destroyed my author career. I was a victim of Cory’s promised popularity, not a beneficiary.

To put this plainly: every pirated copy of my book isn’t just a theoretical lost sale. It’s one less reader who might leave a review, recommend it to friends, or simply become invested in my writing journey. When Cory gets pirated, he still has tens of thousands of loyal readers to cushion the blow. When I get pirated, the financial hit directly means fewer resources to write my next book, less motivation to keep creating, and fewer readers discovering my work organically. Since I’ve been widely pirated for over ten years but the money’s not flowing in, Doctorow’s thesis doesn’t hold the necessary water.

Not yet, anyway. Cory, if you’re reading this, call me.

HBO Got Game of Thrones Wrong, Too (But They’re Laughing Anyway)

Remember when HBO smugly stated that piracy was better than an Emmy? Well, that’s because it’s all corporate death stars all the way down; the executive robosuit theory there is that piracy was a singular, powerful intervention battling Netflix dominance. Success in streaming is often measured by eyeballs-per-hour, and when Game of Thrones is warezed, it stops those eyeballs hitting Netflix. In other words, HBO’s not winning, but Netflix is losing.

This is great news if you’re HBO, but for every HBO that’s winning, there’s a Peacock that’s struggling. Having the most pirated show in history is easy to brag about when you already command armies of paying subscribers and your opposition gets a nut-punch to the bargain. It's a lot harder to celebrate when your show (or book) isn't a household name yet.

Piracy rewards those already winning. It's like giving a complimentary dessert to the diner who’s got the cash to buy the lobster main. Meanwhile, indie creators like me are standing in the kitchen, hoping for crumbs. Remember my earlier financial snapshot? When a reader pirates HBO, HBO still pays their bills. When a reader pirates me, that’s money out of an already painfully slim wallet.

Why Amazon Secretly Loves Pirates

Amazon doesn't actually want you to "own" your books. They want to own your attention. They want you locked into your Kindle, and no other device (ref: HBO’s pyrrhic victory over Netflix). If you think it’s accidental that they don’t allow you to get books off your Kindle but it’s easy to copy them on, you haven’t been paying attention. Piracy serves their interests; the “rental” licensing model of book “purchases” on Amazon, where restrictive DRM stops you from taking your eyeballs elsewhere, but pirated books can still be sideloaded, is part of their escalating war on human attention.

Consider this: imagine buying a paperback and being told you can only read it in your living room. You can’t take it outside, lend it to a friend, or place it on a bookshelf. That’s the digital reality Amazon’s DRM walled garden creates. By making legitimate purchases inconvenient or even risky (say, books vanishing without warning), Amazon actively pushes readers toward piracy. LibGen offers permanence, portability, and simplicity (all the things Amazon refuses to provide).

The problem is, every time Amazon tightens its digital fist, readers who genuinely love books fear losing access to their beloved libraries. Enter piracy: suddenly, LibGen feels less like theft and more like digital preservation. And when readers jump ship to pirate sites, Amazon's market dominance tightens further. Piracy justifies their iron grip on ebooks, drives more people to piracy, but they still reap the rewards of your eyeballs locked into their ecosystem. Hands up those who bought a different ecosystem ereader when Amazon removed your ability to get books out. None? That’s about right; the cost of change is high and they’ve got you by the balls.

Amazon doesn't thrive despite piracy. It thrives because of it.

Valve Got It Right. So, Why Are Books Getting It Wrong?

Steam crushed piracy simply by making it easier, safer, and more enjoyable to buy games than steal them.

Meanwhile, ebooks have somehow gone backward. Instead of making books easier and safer to buy, big players like Amazon have made them harder and riskier. Geofencing content, region locks on accounts, disappearing books, removal of secondary markets, and forced DRM send readers straight into piracy's welcoming arms.

Piracy isn't a price problem. It’s a trust problem.

The Real Enemy (Hint: It's Not LibGen)

Bookstores should be the ally here. Indie bookstores and DRM-free platforms often are. But Amazon and their ilk are the General Tarkin of literature, squeezing their fist so tight that readers have started slipping through their fingers.

Pirates didn’t steal my readers. Amazon pushed them away.

Maybe LibGen isn't really my problem. Maybe it’s just another symptom of a marketplace that values control over customers. And while I don't want my books pirated, at least the pirates care enough to read me. That’s more than I can say for the system that's supposedly on my side but won’t recommend my books, while demanding advertising dollars to get a shred of visibility.

I’m not about to thank pirates, but at least they reminded me of something important: it’s not piracy stealing readers. It’s the platforms that forgot what readers want: simple, safe, and permanent access to the stories they love.

Maybe (just maybe) LibGen isn't the disease we need to cure. It's the symptom we need to finally take seriously.

This is Part 3 of a 3-part series on LitRPG: its past, how to write it, and why it keeps us coming back.

LitRPG isn’t just about power-ups and progress bars. It taps into something deeper. Why do these stories hit so hard? Let’s autopsy why this genre is fundamental fantasy rather than a fad.

Missed the earlier parts?

• Why You Liked LitRPG Before It Was Cool – grave-digging the past on the books that built the genre.

• How to Write LitRPG Without Losing the Plot – craft advice for making game-driven stories that (actually) work.

Introduction

There are a few genres that are experiencing break-out success, and with good reason. They scratch an underserved niche and, if done well, expand that niche into a chasm of readership that becomes a defining success. Romantasy is a great example, but we’re here to talk about LitRPG.

You’ll still never pry Paladin’s Grace from my hands, but I will destroy the next person who tells me to read the drivel that’s The Fourth Wing.

LitRPG gets written off as gamer wish-fulfilment, but it’s more like real life with a patch that actually works. If reality had decent devs, maybe we wouldn’t need LitRPG to bridge the gap between our world and gaming worlds. LitRPG plasters over all the gaps where real life just sucks. See, reality has some garbage-tier mechanics:

• No XP bar. You work hard, but there’s no ding, no level-up—just weariness and, eventually, arthritis.

• No clear objectives. One minute you’re told to chase your dreams; the next, you’re stuck in a meeting about meetings.

• No respec option. Pick the wrong career? Marry the wrong person? Whoops, no take-backs allowed.

LitRPG fixes all that by connecting us to gaming logic. It fills in the blanks where life fails, giving us:

• Visible progress (grind = reward, no ambiguity).

• Structured goals (actual quests instead of vague LinkedIn advice).

• Consequences that make sense (screw up, learn, and improve, rather than just eternal suffering).

If it’s just power fantasy, why is it so addictive?

Why LitRPG Hooks Readers So Hard

Since the dawn of time, humans have been telling stories and playing games (sometimes simultaneously). Cavepersons roleplayed mammoth hunts before the first dice were ever rolled. A bard spinning a tale around a fire was just early-access LitRPG with limited DLC. LitRPG fuses these two primal urges into the ultimate escapism package: a story to follow and a game to play (minus the microtransactions).

It works so well because progressing the story is addictive.

• Stats, XP, and skill trees? Your brain loves that stuff.

• LitRPG gives clear goals and progression! It’s why, “Kill 20 goblins,” feels satisfying, while, “Network with colleagues,” makes you want to yeet yourself into the sun.

• A predictable reward system is S-tier because real life doesn’t tell you when you’ve levelled up. (What does a vague “good job” from your boss actually mean?)

Traditional fiction says: Slow-burn emotional growth, quiet revelations, a deeply human transformation. 400 pages.

LitRPG says: TL;DR: LOL. Here’s +5 Strength. Now go suplex a wyvern.

There’s an extra kick in LitRPG because you actually feel the protagonist getting stronger. Compare that to classic fantasy, where some heroes start at max level and just vibe for three books. Take Aragorn. He doesn’t need to grind XP; he logs in fully geared and with pre-order bonuses. The Lord of the Rings delivers him fully specced into Ranger, King, and Certified Himbo. His existence drives home that what Boromir needed was a save point.

In LitRPG, victories feel earned, even when the main character is cheesing the system harder than a speedrunner on a world record attempt. That’s a rush you don’t get from real life, where eight straight hours of meetings just leave you wondering if you’ve levelled up in anxiety. Where reality fails spectacularly, LitRPG provides a structure. In reality, there’s no UI, no tutorial, and no helpful quest log explaining why your coworker passive-aggressively CC’d your boss. But in LitRPG, progress is tangible. Kill ten slimes, get stronger. Do that in the real world, and all you’ve done is attract local authorities.

Your 9-to-5 might not award you “Employee of the Month” for doing 12-hour days, but if LitRPG were in charge, it’d be: Ding! Congratulations, you’ve unlocked “Enhanced Productivity (Level 2): Now with 10% less despair.”

The Urban Fantasy Effect

Question: Why does LitRPG feel so easy to pick up?

Answer: Because half the worldbuilding is already in your head.

Urban fantasy led the pack on this one. It lets readers hit the ground running because they already know how cities work, what police do, and that werewolves probably aren’t just hanging about in Starbucks. I pillaged this goldmine and left with a sack of loot when drafting my latest novel, The Three Faces of Fate. I don’t have to tell you what a city like Anchorage looks like. I just need to tell you about the bullshit redcaps and banshees are putting the fine citizens of Valhaven through.

LitRPG works because it doesn’t waste time explaining what you already know. In 2021, the Entertainment Software Association reported that 227 million Americans (roughly 70%) played video games. Globally, we’re looking at 2.7 billion mobile gamers tapping away at screens like their Candy Crush rank is tied to their mortgage rate. Readers don’t need a 20-page worldbuilding bible on how skills work, because they already understand XP, loot, and level-ups from the gacha bullshit infesting their phones.

This removes the onboarding struggle that bogs down traditional fantasy. You don’t need three chapters explaining how magic works. Just give your mage a mana bar, and boom, we get it. This built-in familiarity is why LitRPG is so easy to devour. LitRPG speaks a language readers already know, skipping the “how-shit-works” phase and dropping them straight into the action. To put it another way, traditional fantasy has a learning curve, and LitRPG has a skill tree you’ve already levelled up in.

From Dream Park to Ready Player One: How LitRPG Evolved

LitRPG wasn’t born in a vacuum. Before characters were grinding XP, they were fighting for their lives in worlds that felt just a little too real. The old guard of Dream Park and Guardians of the Flame were less about exploiting systems and more about surviving them.

Hell, Dream Park played with immersion before VR gaming was even a thing, and Guardians of the Flame asked, “What if this wasn’t just a game?” By mashing together immersive simulation and genuine personal risk, these early works set the respawn point for an entire genre. They rolled a natural 20 on genre innovation, eventually leading to hard-coding explicit game mechanics into LitRPG DNA.

Ready Player One didn’t just cash in on gamer nostalgia—it 100% completed it. It took the idea of immersive game worlds, stripped out the survivalist grit of Dream Park, and said, “What if 80s pop culture was a loot table?” Ready Player One wrapped readers in a +1 Heavy Cloak of Reminiscence, playing up virtual escapism as the ultimate power fantasy, where knowing obscure trivia about Pac-Man could save your life. The High Five may have been legendary inside the OASIS, but outside, they were stuck in the respawn screen of late-stage capitalism. That disconnect between virtual success and real-world struggle is what gives Ready Player One its real stakes. In the end, you can’t clip through poverty.

Where early LitRPGs asked, “Can I survive?” modern LitRPGs ask, “How can I break the game?” The shift toward stat-heavy storytelling means that today’s readers expect more than just immersion. They want mechanics so detailed they feel like they could log in themselves. Some books feel like the protagonist is playing an RPG, rather than living in a world.

This evolution from raw survival in a hostile world to min-maxing every possible advantage marks a hard pivot in LitRPG’s evolution. Dream Park and Guardians of the Flame experimented with immersion and risk; modern LitRPG runs full-speed into system mastery, where knowing how to game the game is the ultimate power. It makes sense. Readers aren’t just here for the story. They crave the satisfaction real life refuses to provide. The world doesn’t give you XP for surviving eight back-to-back Teams calls or a stat boost for remembering to drink water. LitRPG does. In a genre where the rules are clear, the progress is measurable, and effort actually leads to reward, it’s no wonder readers want to break the mechanics rather than just play by them. If billionaires can break the rules, why can’t we? We want to win the game of life, too.

Three Forks in the Road: How LitRPG Split into Different Power Fantasies

LitRPG didn’t just evolve. It diverged like a skill tree on steroids. Instead of settling into a single formula, it fractured into multiple power fantasies, each offering a different way to interact with the game world. Some are all about raw dominance, where the protagonist steamrolls everything in sight. Others lean into strategy and problem-solving, rewarding cleverness over brute force. And then there’s the chaotic wildcard, where power comes with so many unintended consequences that the protagonist is multiclassing in disaster management. Whatever your playstyle, there’s a LitRPG for you.

Let’s start with VRMMO LitRPG (2000s–2010s) – The Overwhelming Juggernaut, a.k.a. Escapist Power Fantasy.

This is where winning isn’t a question, it’s a feature. Virtual Reality Massively Multiplayer Online LitRPG presents a fantasy of absolute control, where the protagonist isn’t just good; they’re preordained to be the server admin of existence.

This era brought us “trapped in a game” stories, where the protagonist either starts OP or gets there so fast the devs would nerf them in the next patch. Sword Art Online, The Legendary Mechanic, and Solo Leveling define this space. The only real threat to the protagonist is running out of enemies. It’s pure power-trip fantasy where the only thing standing between the hero and ultimate victory is the occasional training montage.

The catch is, of course: If there’s no struggle, there’s no tension. The best books in this category (like Solo Leveling) understand this, making sure the protagonist earns their overpowered status instead of just getting handed purple loot at Level 1.

Why does it work? Because it’s escapism in its most undiluted, straight-into-the-vein form. Readers get to experience limitless power, wreck enemies with wildly disproportionate force, and actually see progress (which is more than we get from replying to work emails). Farming for loot in LitRPG gets you godlike abilities. Farming your inbox just gets you more emails.

Next up: Dungeon Core & Survival LitRPG (2010s–Present) – The Struggling Strategist, or as it’s known in polite circles, “Git Gud: The Genre.”

This is the Demon’s Souls of LitRPG, where every fight is a brutal trial by fire, and the only way to progress is through tactical brilliance, sheer stubbornness, and the occasional panicked dodge-roll. Books like The Wandering Inn, The Perfect Run, and Mother of Learning take glass-cannon protagonists and throw them into meat-grinder worlds where one wrong move equals instant obliteration.

If Escapist Power Fantasy is about breaking the system, Tactical Power Fantasy is about barely surviving it. Every stat point is a lifeline. Every spell cast has consequences. And every victory feels less like a power trip and more like a, “Holy shit, I actually did it” moment. No hero ever says, “Hold my beer and watch this.”

Why does this work? Because suffering builds investment. Ever beaten Flamelurker in Demon’s Souls after getting one-shot for an hour straight? That’s what these books feel like. You don’t just cheer for the protagonist, you feel their wins in your bones. Tactical Power Fantasy taps into that same desperate thrill of scraping by on last-minute plays, creative problem-solving, and the unwavering belief that, despite all odds, you can still pull off a miracle.

Finally, we have The Power Fantasy Explosion (2010s–Present) – The Unintended Hero, or “Congratulations, You’re the Boss Fight Now.”

These are the stories where the protagonist isn’t actively trying to become an unstoppable force, but the universe, in all its chaotic wisdom, decides otherwise. Maybe they pick up an overpowered item by accident. Maybe the tutorial boss drops Excalibur with a built-in nuclear payload. Maybe the gods just hate them enough to turn their life into a cosmic joke. Whatever the reason, they keep tripping over power-ups, and suddenly, they’re a walking apocalypse.

Books like Dungeon Crawler Carl and He Who Fights With Monsters thrive on this absurdity. These aren’t power fantasies where the protagonist grinds for dominance. They’re satire-fuelled train wrecks where reality keeps bending over backward to make them absurdly OP. And, naturally, there are consequences. They attract divine enemies, apocalyptic cults, and political schemes so convoluted they make Game of Thrones look like a children’s pop-up book.

Why does this work? Because chaos is entertaining. Readers love watching a protagonist who never asked for this shit get dragged into a world that treats them like a game-breaking glitch. It’s less about raw power and more about the comedy of watching someone try (and fail) to keep their head above water when everything keeps escalating in the most ridiculous way possible.

As LitRPG progresses, we may see more reluctant heroes in wildly broken worlds that double down on satire and unpredictable power scaling, where the rogue-like chaos of Slay the Spire meets a novel.

The Power Fantasy Debate: Wish-Fulfilment or Something More?

At this point, you might be wondering: Is all LitRPG just power fantasy? Eh. Maybe? Power fantasy isn’t a bad thing. It’s just a tool. How it’s used determines whether the story is engaging or not.

There are three things power fantasy needs to work:

1. Struggle. Even OP characters should have obstacles, consequences, and difficult choices.

2. Agency. The protagonist’s victories should feel earned, not handed to them.

3. Meaning. Power means nothing if it doesn’t cost the protagonist something, whether that’s relationships, morality, or their own sanity.

Power fantasy isn’t just about getting stronger. It’s about why that power matters. Where our OG LitRPGs of Dream Park and Guardians of the Flame were character-centric, plot-centric narratives, modern LitRPG is an ecosystem of different subgenres. Some are about survival, some about power, and some about becoming the dungeon itself.

First, let’s check our privilege. Wish-fulfilment isn’t a crime. Fantasy has always been about escapism. LitRPG just happens to slap an XP bar on it. I mean… Who wouldn’t want to start at level 1 and end up as a world-shattering force of awesome?

But, and everything before the ‘but’ is a lie… good LitRPG isn’t just about pumping those numbers up. Power is meaningless without something to push against. Struggle makes victory satisfying. Choices make characters compelling. Consequences make stories feel real. Readers don’t just want a protagonist who wins. They want one who earns it.

So, fellow writers, ask yourself this: Is your protagonist growing, or just collecting bigger numbers? Are they facing challenges, or just grinding to godhood? If they’re emotionally static, permanently untouchable, and so OP they might as well be the game’s end credits boss… then congrats, you’ve written a spreadsheet, not a story.

Power fantasy isn’t a bug. It’s made into a feature by how you use it, and that makes or breaks the story.

The Future of LitRPG: Where Is It Headed?

Are we at peak LitRPG, or does this grind never stop? Are we about to hit the level cap, or is there a hidden prestige system waiting for us?

Here’s how I see it: three possible endgame expansions for the genre.

1. Ultra-Gamification Mode: LitRPG doubles down on mechanics, evolving into books that feel like fully simulated games. Remember those Choose-Your-Own-Adventure or Fighting Fantasy books? Now add in AI-generated dungeon masters, interactive fiction that blurs the line between reading and playing, and books with actual UI elements. This could be groundbreaking or an unreadable migraine factory.

2. The Classic RPG Remaster: As readers start fatiguing on stat spreadsheets, we see a shift back to story-first LitRPG. Think of it like Dream Park and Guardians of the Flame hitting New Game Plus, where progression matters, but the character arcs and emotional depth take centre stage. The game elements enrich the world rather than dominate the narrative.

3. The Great Min-Max Crash: Some books will min-max themselves into oblivion, cranking power fantasy to such absurd levels that eventually, there’s nowhere left to go. The result will be a market correction, but the best will adapt, blending their god-tier progression with actual stakes, tension, and—wait for it—compelling storytelling.

So, is LitRPG about to implode? Hell, no. But some subgenres are definitely about to get nerfed.

So, What? Is LitRPG Just a Fad, or an Enduring Genre?

LitRPG isn’t some flash-in-the-pan genre destined to be forgotten like pogs, slap bracelets, or whatever the hell was going on with frosted tips in the ‘90s. It’s been around since the early 1980s, survived the dot-com boom, the rise and fall of MySpace, and has somehow made it all the way to the Year of our Lord 2025. A fandom that’s thrived for 45+ years isn’t a fad. It’s a mainstay, like fantasy, sci-fi, and mage nerfs in WoW.

LitRPG isn’t just escapism. It’s a power fantasy… with rules. It gives readers something reality rarely does: clear goals, progression, and a direct correlation between effort and success. There’s no office politics, and no mystical job promotion promises that never happen. Just XP bars, skill trees, and visible proof that you’re getting somewhere. Much as some readers love those progression mechanics, the genre is evolving. It’s moving beyond just stat sheets and skill trees, growing into something bigger, deeper, and more narratively ambitious.

LitRPG’s not going anywhere. Whether it’s survival, strategy, or unfiltered chaos, LitRPG is tapping into something deep: our need to see effort turn into progress, and struggle turn into triumph. It’s a blueprint for the kind of world we wish we lived in, one where effort is rewarded, progress is clear, and sometimes, just sometimes, the loot is actually worth the grind. If LitRPG was just power fantasy, it wouldn’t resonate this deeply. It’s not just about numbers going up. It’s about why we care that they do.

What’s your take? Do we love LitRPG because it’s a structured escape, or is there something else going on? Let’s vibe in the comments. And if you enjoyed this…

Drop a tip on Ko-fi to keep the content flowing by keeping my coffee flowing:

Check out the priors in this series:

• Why You Liked … LitRPG Before It Was Cool, a review into genre-defining classics Dream Park and Guardians of the Flame.

• How to Write LitRPG Without Losing the Plot, focuses on the craft and pulling lessons from Dream Park and Guardians of the Flame, and the genre’s evolution.

Maybe you were once naïve enough to believe Ubisoft Connect would add something to your life; I’m not here to judge. Among this digital clutter, three stores actually matter: Steam, GOG, and the Epic Games Store.

First, the TL;DR—or as I call it, “The Algebra of Access and Aggravation.” I promise, this is only make-believe math:

• Equation 1, “The Gamer’s Refuge”:
  Gamer-friendly Platform = ([Private ownership +] Competition) × Genuine User Focus.
  (See: Steam, GOG, and Epic. Privately owned platforms with healthy competition deliver a faster-growing library replete with backlog guilt.)

• Equation 2, “The Corporate Hellscape”:
  Launcher Frustration = (Public Trading × Publisher Ego) - Competition.
  (See: EA App, Ubisoft Connect, and Battle.net. When public company greed meets bad design, the only thing getting patched out is your will to live.)

• Bonus Equation, “The Bipolar Retailer-Publisher Hybrid”:
  Mixed Experience Platform = Public trading + Retail competition – Publisher monopoly.
  (See, Microsoft Store: not actively hostile, versus Battle.net: a mandatory nightmare. Competitive pressure keeps them from going full Orwell, but at least they let you access your games without a cavity search.)

Now let’s overthink why Steam, GOG, and Epic are (mostly) on your side—or to badly misrepresent Tron, “For the Users!” Let’s also be professional about why publisher launchers are the worst thing since loot boxes, and how—despite exclusives—Epic might actually be on the right side of history.

Steam, GOG, and Epic: The Convenient, the Collector, and the Cash Cannon

We all have those same three fucken launchers, or maybe even four if you were once naïve enough to believe Ubisoft Connect would add anything to your life. Maybe it’s five, because you needed the EA App to unlock the true power of the Force in Jedi Survivor. Hell, let’s go with six, because I know you’re balls-deep in either Diablo, Overwatch, or Hearthstone, and don’t lie to me about Heroes of the Storm—no one plays that anymore.

Among this digital clutter, three matter: Steam, GOG, and the Epic Games Store. Nuclear launch detected from the Steam faithful who hate Epic, but give me a few seconds to justify the throwaway comment before you glass the planet.

Each has strengths:

• Steam is the overlord of catalogue, features, and service,

• GOG is the last bastion of true game ownership, and

• Epic is… well, they’re actually trying to help devs out in ways that aren’t so obvious at the checkout end.

Steam: Hail to the King, Baby

Steam is the de facto home of PC gaming. If a game is launching on PC, it’s probably on Steam—unless the devs hate money. It has everything: a massive library, regular sales, cloud saves, achievements, forums, remote play, modding support, solid refunds, and even a marketplace where digital hats become real cash.

Valve’s secret sauce is ruthless, user-first prioritisation. Gabe Newell famously argued that piracy wasn’t a crime problem but a service problem, and he’s got the money throne to prove his argument. Steam makes gaming so easy you forget your entire library depends on one platform. It’s like renting a flat from a chill landlord who loves your parties, but could drop dead tomorrow, leaving you at the mercy of their heirs.

The Good:

✅ A colossal game library – It’s rare to find a PC game that isn’t on Steam.

✅ Frequent discounts and legendary sales – Even if you don’t need more games, you will buy them.

✅ Steam Workshop and modding support – Mods make everything better (especially Skyrim after you’ve bought it for the seventh time).

✅ Actually useful features – Cloud saves, controller support, in-home streaming, community forums.

The Bad:

❌ You don’t own your games – You’re just renting access from Lord Gaben, although the model lets publishers offer titles they wouldn’t under strict ownership conditions.

❌ Patchy customer support – Good luck getting access to a human if you need one.

❌ 30% revenue cut for developers – Not your direct problem, but it’s why devs are even open to other options.

Steam is best for a seamless, feature-rich experience with a vast library, but it’s worst for people who like actually owning their games.

GOG: Biker Librarians of the Wasteland

GOG was born from CD Projekt’s mission to offer DRM-free gaming in a market plagued by piracy, high prices, and poor distribution. Rising from the ashes of pirated CD-ROMs, GOG became a champion of game preservation and consumer rights. Every game is DRM-free. Once you buy it, it’s yours forever, with no online checks or disappearing licenses. In an industry obsessed with microtransactions and live services, GOG’s commitment to player ownership feels almost radical.

The Good:

✅ DRM-free gaming – Buy a game, download it, keep it forever. Unicorns exist.

✅ Classic games lovingly preserved – Even Planescape: Torment is alive and well here.

✅ Bundled extras – Manuals, soundtracks, concept art… GOG understands nostalgia, but also what we lost when we went digital.

The Bad:

❌ Smaller library – Many modern games skip GOG entirely due to no-DRM phobia.

❌ Less built-in support for mods and communities – No Steam Workshop equivalent.

❌ Occasionally slow patch rollouts – Some games take longer to update here or work erratically.

GOG is best for Game preservationists, DRM-haters, and people who fondly remember physical game manuals. It’s worst for anyone who needs Call of Duty the second it launches.

Epic Games Store: Turning Fortnight Cash Into a Revolution

Epic Games Store wants to be Steam so badly it’s grinding harder than a Returnal player chasing that elusive 100%. Its master plan is to throw cash at developers for exclusivity deals and hand out free games like a guy at a pop-up stall whispering, “Steam sucks.”

Epic’s infamy comes from locking PC games into console-style exclusivity. PCMR gamers now get a taste of the nonsense console players have endured forever. Sometimes, it’s justified. Epic’s deep pockets can fund projects that might flatline otherwise. Other times, it’s just a timed exclusive that annoys gamers who don’t want another launcher or a monopoly on their shopping. And fair enough, too—PC gaming thrives on open communities and choice.

On the plus side, Epic is battling the Witch King of Market Greed. They give devs a bigger sales cut (88/12 vs. Steam’s 70/30), offer much-needed funding, and even have living humans offering customer support. Before Epic, Steam’s only competition was the Windows Store, but Epic’s missing features and obsession with exclusives have made it about as popular as leprosy.

The Good:

✅ Better revenue share for developers – Indie devs actually get paid properly here.

✅ Free games every week – And sometimes they’re bangers like Control or Alan Wake Remastered.

✅ Multiplayer services – Fortnight taught them a thing or two. This stuff is surprisingly robust for online play.

The Bad:

❌ Barebones feature set – While Epic offers free games, no community forum or integrated mod support means you have to rely on external services.

❌ The UI still feels like a beta project – It’s been years, and it’s still clunky.

❌ Exclusive deals are annoying – Buying into relevance hasn’t proven to be a heart-winning strategy.

Epic is best for free games, indie dev support, and Fortnite players. It’s worst for anyone who expects a fully featured gaming platform.

Retailer vs. Publisher Launchers: Joy vs. Greed

Steam, GOG, and Epic exist to sell you games. Their success depends on keeping you happy because you can always buy from someone else. Publisher launchers (EA App, Ubisoft Connect, Battle.net) exist to control how you play and squeeze more money out of you. They answer to shareholders, not players. Sure, they sometimes integrate social features or cross-platform play, but that hardly compensates for the constant upsell and restrictive DRM. It’s like getting a free mint at a fancy restaurant while being paywalled for tap water and access to the toilet.

Retailers focus on making your experience smooth to keep you coming back—no forced ads, endless logins, or DRM nightmares. Epic’s exclusives are annoying, but at least you own your games. Publishers, meanwhile, turn every interaction into an upsell: ads before you play, DRM checks for offline mode, and leftover background processes when you uninstall.

Epic Isn’t Steam, But It’s Not EA Either

Some companies straddle both worlds, like Microsoft with the Xbox Store (retailer) and Battle.net (publisher launcher):

• Buy from the Microsoft Store? Install and play without ever opening it again.

• Buy from Blizzard? Battle.net clings to you like a digital ball and chain.

Retailers compete with sales and convenience. Publishers don’t compete because the alternative is not playing at all.

Monopoly vs. Competition

The Microsoft Store is tolerable because Steam, Epic, and GOG exist. Battle.net, EA App, and Ubisoft Connect? No competition means no mercy. Want Overwatch? Install Battle.net. Assassin’s Creed? Ubisoft Connect is ready to ruin your day.

The Worst-Case Scenario is…

Publisher-retailers selling games with strings attached:

• EA games on Steam still need EA App.

• Ubisoft games on Epic still need Ubisoft Connect.

• Buy Diablo IV anywhere? Battle.net purgatory awaits.

So, What?

Avoid publisher launchers when you can.

• Steam: Convenient, feature-packed, but some DRM.

• GOG: DRM-free, preservation-focused, but a smaller library.

• Epic: Annoying, but still pro-consumer and dev-friendly.

• EA App/Ubisoft Connect/Battle.net: Corporate ransom notes disguised as launchers.

Fewer publisher launchers means better gaming, but that only happens if we vote with our wallets. Choose platforms that respect your time, money, and ownership. Support DRM-free releases and consumer-friendly stores, avoid publisher launchers when you can, and show the industry that player experience and fair treatment of developers matter more than shareholder profits.

Are you a Steam loyalist, a GOG purist, or an Epic free-game hoarder? Are these trade-offs worth it, or is your gaming life in need of a platform overhaul? Drop a comment/reply with your take. And if you’re still buying directly from EA or Ubisoft, blink twice if you need help.

Support indie analysis the way GOG supports DRM-free gaming – with a Ko-fi ☕!

What happened? Did someone accidentally Ctrl+Z the entire ban? Was there a Mission Impossible-style heist where a rogue hacker plugged a USB stick into Capitol Hill’s WiFi? Spoilers: it’s more likely this is another example of how Western governments fundamentally misunderstand the tech they’re trying to control.

A Ban So Short, Even Snapchat Would Call It Brief

For context, the US government has been trying to shut down TikTok since roughly the dawn of time—or at least since today’s average TikTok user was reshaping internet culture after hearing whispers of an ancient legend called Vine, spoken in whispers only by the elders. The official reasoning? National security concerns, data privacy, and, presumably, a deep-seated fear that China might be secretly influencing young Americans into learning choreographed dances instead of preparing for a lifetime of debt.

And so, with great fanfare, a bill was passed. TikTok was doomed. The app had to either be sold to an American company (because the only people allowed to exploit user data are Western billionaires) or face extinction. Then, in what can only be described as a plot twist so underwhelming even M. Night Shyamalan wouldn’t touch it, the whole thing just… fizzled out. No ban. No fire and brimstone. Just business as usual, after a 34-second outage.

Which begs the question: was this ever really about national security, or was it more about Western tech giants being unable to compete with an app that actually makes people happy?

TikTok vs. The Algorithmic Hunger Games

To understand why TikTok has been treated like the digital Candyman, we have to look at its competitors. Most Western social media runs on a patented engagement model scientifically designed to make you want to punch people through the Internet.

• Facebook: Here’s your racist uncle’s conspiracy theories about the Jewish turnip cartels.

• Twitter (X? Xitter? Whatever it’s called today): Here’s an argument you weren’t invited to but are now emotionally invested in.

• Instagram: Here’s a photo of someone’s perfect life so you can feel bad about yours. Low follower count? Sorry, the algorithm has spoken, but don’t worry: here’s a limited-time offer on a personality upgrade from one of our advertisers.

Meanwhile, TikTok’s algorithm (while not perfect) works differently. It prioritises what you enjoy. Its entire model is built around keeping you entertained, which is why you’ll go in for just one video and emerge three hours later blinking at the sudden arrival of night, realising you desperately need to piss, and are now somehow an expert on medieval swordsmithing.

Despite the dehydration long scrolling sessions deliver, people love TikTok. It makes them laugh. It teaches them new skills. It gives them a sense of community. Compare that to the rage engagement tactics of Meta and Xitter, and it’s no wonder Silicon Valley has been side-eyeing TikTok like a college dropout older sibling realising their pre-teen brother is not only more popular but also somehow the Chosen One.

The Philosophical Divide: Zen and the Art of Social Media

This is where things get interesting. Western tech platforms are built around conflict—outrage, argument, echo chamber clashes, and division—because they assumed that’s what kept people glued to their screens (and, conveniently, seeing more ads). The Western approach mirrors some Western ideologies: individualism, competition, and the belief that if you’re not angrily quote-tweeting at 2 AM, are you even engaging?

Meanwhile, TikTok’s model leans more towards harmony. This distinctly Eastern approach prioritises enjoyment and collective experience over digital gladiatorial combat. TikTok’s algorithms don’t just serve you endless entertainment; they’re on a mission to promote joy and positivity. It’s like having a wise old monk in your pocket—except instead of cryptic riddles about enlightenment, he’s feeding you corgi videos and surprisingly emotional documentary about a life-changing cleaning hack.

It’s like comparing a serene Zen garden to a mosh pit at a heavy metal concert where everyone’s also live-tweeting a parliamentary debate. Xitter and Meta thrive on making you deeply anxious, while TikTok just wants you to vibe. And people have started noticing. Users are increasingly disillusioned with doomscrolling. Social media fatigue is real, but… not so much for TikTok. The idea that an app can be fun instead of feeling like a digital belt sander to your balls is revolutionary in itself.

That’s what makes TikTok so disruptive. And that’s why Western tech giants (and by extension, the governments they lobby) wanted it gone… or firmly in their back pocket. This isn’t just about slapping on a new logo and calling it a day. It’s a high-stakes tug-of-war between the calming influence of Eastern digital philosophy and Silicon Valley’s relentless pursuit of squeezing just a little more engagement from your increasingly frazzled brain. Politicians, torn between anti-China sentiment and their instinct to micromanage, are desperate to yank TikTok out of its Eastern perch and drop it into the clammy hands of Silicon Valley’s ranked-mode sweats.

Imagine trying to squeeze our wise old monk into a Silicon Valley boardroom—a place where mindfulness gets sacrificed on the altar of quarterly earnings, and every serene moment is interrupted by someone screaming about monetisation strategies. TikTok’s community-driven approach risks being bulldozed under a tsunami of profit margins, algorithmic tinkering, and the kind of corporate fuckery that could turn even a meditation app into a psychological battleground.

The Impact on User Behaviour: Harmony or Hysteria?

Yes, TikTok is ‘addictive’, but unlike its Western cousins, it’s less screaming-into-the-void and more accidentally-learning-carpentry-between-dance-trends. It’s like being invited to an endless block party where everyone’s invited and the DJ never runs out of uplifting tunes.

Over on the other side of the digital divide, there are plenty of reports about the mental health impacts of endless scrolling, especially for younger users. It seems that when you mix an algorithm designed to provoke outrage with the emotional roller coaster of needing to be beautiful or popular, you end up with a cocktail with a twist of anxiety and a dash of despair. It used to be the only game in town, but that doesn’t mean it was good for us.

Enter Trump, Stage Right

Trump’s part politician, part wrecking ball, convinced that if he shakes the Etch A Sketch hard enough, the old picture will vanish and something huge, better, and more orange will take its place.

Trump overturning the TikTok ban isn’t just about social media. It’s a message to voters that he’s breaking from the status quo, challenging liberal control, and (crucially) making sure American teenagers don’t have to suffer the existential horror of YouTube Shorts.

Scrapping the ban isn’t just a tech policy move—it’s a baller flex. Trump isn’t just saying he’s not like the Dems, he’s making sure you see it. It’s a middle finger to Silicon Valley, a wink to younger voters, and a reminder to the establishment that he’s the one pulling the levers.

Does he have a grand strategy for tech policy? Probably not. But does it look like a power move? Absolutely. Will it fire up the TikTok-loving masses and hammer home his “drain the swamp” narrative? Fucken A.

So… What Now?

TikTok isn’t just surviving. It’s thriving. Every time the US government tries to shut TikTok down, they just end up making it more popular. It’s our dropout older sibling handing their pre-teen brother the ‘shit controller,’ only to accidentally create an esports prodigy.

Meanwhile, Western platforms are still stuck in their old ways, trying to convince us that we enjoy rage-clicking our way through a never-ending cycle of discourse and despair.

There’s a real question at the heart of this: Is TikTok’s success a fluke, or does it signal a deeper shift? Are users finally waking up to the idea that social media doesn’t have to give you lifelong trauma?

And if trauma-free social media is possible… what does that mean for the future of digital spaces? One thing’s for sure: whatever the future of social media, I’m still not getting my news from Facebook.

Enjoyed this deep dive? Fuel my overthinking with a coffee on Ko-fi (because well-structured rants require caffeine). ☕💡

It’s Windows.

That OS that fights controllers like they owe it money. What if Microsoft finally fixed Windows for a handheld… and then, in the biggest “hold my beer” moment ever, they drop a Windows-runs-natively update for Xbox? Suddenly, the Series X isn’t just an Xbox (it’s a Steam machine, or Epic games hub, or hell, GOG's on there too). Xbox gamers get Game Pass and Steam, making Microsoft the undisputed gaming warlord of both couch and commute.

Meanwhile, Sony and Nintendo watch from the sidelines, trapped in their walled gardens as Xbox players boot up Baldur’s Gate 3 on literally anything.

• Would it happen? Probably not.

• Could it happen? Yeah.

• Would it be hilarious? Absolutely.

Microsoft, your move.

When Stable Diffusion 3 came out, the response was a little underwhelming; in many ways it was a back step from SDXL, and Midjourney breathed a sigh of relief.

They ain’t feeling so relieved now. I can see Midjourney execs clutching their pearls while Stability AI suits are sweating bullets. Flux.1 (not from Stability AI, the new kids on the block are Black Forest Labs) aims to make AI art more … artistic. I thought I’d kick the tyres on it to see how good it is.

TL;DR: it’s quite good. While it still suffers some of the consistency and direction issues of AI ‘art’ in general, the composition, lighting, and most important, fucking fingers, are much improved. Let’s use an example.

Here’s the cover image I generated for The Fury of the Betrayed. This took about a million different iterations to get to; there’s a lot of inpainting and outpainting going on here. I spent so much time tweaking this image, I think I accidentally invented a new type of art – ‘over-edited digital painting’. Our final image:

Now, let’s compare some popular models. To do this, I interrogated the above image then fed the resulting prompt into different models. The big challenge with doing fantasy art with general purpose models is the AI not knowing WTF a gorgon is, or what banded armour looks like. Let’s see how some of the popular AI models handled it.

First up: the OG, SDXL. Spoilers: there’s something wrong with the face (even after using RestoreFormer, facial recognition software probably wouldn’t recognise this as a human). No gorgon. No cars. Not banded armour. So, basically a fail from top to bottom, and I don’t even know WTF that flame-like stuff is supposed to be. Serpent fire? Some shit, I dunno.

Ok, what’s next? Let’s try DreamShaper. This model was what I used through thousands of iterations for the OG image; how does it do when we feed it a complete prompt?

Yeah, nah. We’ve got our cars on fire, sort of, and some kind of monster above the city, but it looks more cat than gorgon. Also, not banded armour.

Juggernaut’s the AI model everyone wants to be seen with at the digital art party. I feel like the premise is that it’s supposed to be amazing for photorealistic images, and since we’ve got a lot of shit going on that you can’t photograph (like gorgons), how are we doing?

Closer? Maybe? The armour might be banded from a certain point of view. The fire from the car is shithouse, though, and there’s no gorgon (…as expected, but I did want to dream for a second there).

Since DreamShaper development moved into their XL Turbo model, I thought it would be good to contrast with that. Turbo models are much faster (right there in the name…). The destruction and fire is on point in this one, and the armour is doing something rad as well. No gorgon, but I’m sensing a theme here.

Conclusion: Juggernaut and DreamShaper XL Turbo have the best faces, and I’d say DreamShaper XL’s composition is the best of them all. So, where does that leave us with Flux.1?

We’re going to run two tests. The first is with flux.schnell, which is a model that aims to get results in about 8 steps (the same as DreamShaper XL Turbo). The second is flux.dev, which I’ve used 30 steps on, same as the other SDXL models. Behold:

Gorgon? I think the intent’s there. Flaming cars? Yep. Human-like face? For sure. Schnell has done better on the person and armour, but I think Dev has the better lighting. Either way, both models have heavily respected the source prompt, and given us (without cherry-picking or doing 30 different iterations) an image that is quite similar to our prompted idea.

All SDXL variants aside from Dreamshaper Turbo were done with Euler Ancestral sampler, at 30 steps. Flux Schnell and Dev used Euler A with 4 and 30 steps, respectively. DSXLT was 8 steps, with DPM++ SDE Karras sampler (it requires this sampler for effectiveness but it’s fine, it’s a good sampler). Euler A seems to be the Chosen One™ for Flux.

I then spent a bit of time getting my head around some of the finer points of Flux.1 and started clean with a new prompt. Here, we want to go with our standard avenging angel, because why not? My hunch was that I’d gone too strong on CFG Scale for Flux; what would happen if we used a lower value? I’ve upped Schnell’s step count to 8 but left Dev at 30. What happens?

Good things, as it turns out. Schnell’s on the left; dev’s on the right.

So, yeah: if I was Midjourney or DALL·E I’d be a little concerned right now. This is some next-level shit; the detail is extraordinary, regardless of Schnell or Dev, and you can get images to S-tier status if you fiddle with CFG values. The faces out of the crate could still use some work! But we’re seeing far fewer six-knuckled aliens, weird body proportions, and extra limbs (SD3, I’m looking at you).

You’d have to be living under a rock to not notice the onslaught of AI-powered innovation sweeping our blue-green world. To quote the boardroom, “AI’s incursion into creative domains warrants a closer examination.” There are issues, people, and as my good friend GV taught me, unintended consequences will absolutely screw you. Today, we’re going to look at some problems with this innovation set:

1. It isn’t solving a problem we’ve got, and

2. Not (yet) at the quality level humans can achieve.

3. It is specifically solving problems we didn’t ask for solutions for!

While I reckon there’s a “fun” angle here (it’s cooler for AI engineers to work on making music and paintings than it is to create machines to do our TPS reports), there’s also an applicable prior art problem. AI is trained on datasets, and we have a lot of publicly available datasets for art, writing, and music. AI works by copying what it sees (the “training” part). We do not have a large body of public data on corporate espionage that would allow AI advisors to present coherent risk analysis to execs, which is actually valuable to megacorps.

What do you mean, value?

The problem here is that no one’s really considering what it’s all for. The latest thing across my desk was Udio. This makes pretty good music, significantly better than Suno, which was the last music droid I played with (Suno’s fairly generic sound vs. the flexibility of Udio). As a recovering marketing manager, I immediately went to Udio’s pricing page.

Thank you for being an early supporter! Our product is free for the duration of the beta program. In this period, you can make up to 1200 songs / month.

Udio Pricing Page

This tells us a lot. Free capital circling tech has largely dried up, and everyone’s putting up their prices. Whether it’s the egregious gouging of Amazon who will charge you twice to get the same service ad free as last year, or EA almost doubling the price of their game streaming service by taking subs from £19.99 to £35.99, there’s a lot of opportunistic rort out there.

At the heart of this is “shareholder value,” or, “How do we keep giving 30% YoY returns to Wall Street?” And the challenge with where this intersects the AI space is that megacorps aren’t hugely likely to pay $50/month for something that’s good at finger painting. I said:

A problem with corporate-grade AI is that it’s expensive. If you want to get a passable ‘copilot’ tool, you’re probably looking at $50/month (Kiwi dollars, people) per user, give or take. If you’ve got 2,500 staff who could benefit from this kind of technology, that’s going to set you back $125,000/month, or $3M/year.

Me, when talking about value-based return (and movies+books):

So… there’s no market?

There are definitely areas where AI can help, but you need to pause and consider the addressable market. An example? A cool use of AI that isn’t rent-seeking or displacing human employment is natural language translation. The problem here is the monetisable use cases. Travellers might like it, but their phones already do it. Corporate users might like it when talking to peers in different countries, but how often is that used, and what price could you charge for it? The addressable, monetisable market is small, despite the “coolness.”

Which brings us to things like Udio. Sure, there will be people who want a cool jingle for their PowerPoint, but are they going to pay $5/song for it? Probably not, especially since they’ll need to generate 20 of them before finding one that fits the style they’re after. Things like DALL·E circumvent this by charging a monthly fee for a suite of AI services, which is more palatable for a consumer, but again from that corporate perspective (where a lot of the money is): do you think a company is going to pay $50/mo so their staff can make fancier PowerPoints?

Hmm.

But… Progress!

Yeah, so: AI companies continue their advance into the creative sphere. Udio’s just the latest to do it. We didn’t ask for AI companies to make our music and art, but because they can more or less just steal prior art to make content (with potential legal ramifications, but I’ve doubts the judge will uphold that case because it gets in the way of capitalism) that’s where they’re going. And despite the misuse of this technology, there’s little being done to protect people (although the EU, perhaps predictably, is ahead of the US in trying to protect its people).

I mentioned quality at the start, and there’s a conjoined element to this: efficiency. At the moment, AI is hungry; a recent study found generating an image using something like DALL·E or Midjourney takes as much energy as charging your phone. You make 30 images? You just burned the same power as a month of phone charging.

In fact, generating an image using a powerful AI model takes as much energy as fully charging your smartphone, according to a new study by researchers at the AI startup Hugging Face and Carnegie Mellon University.

MIT Technology Review

Hang about. Aren’t machines really efficient?

The human brain runs more or less continuously on about 12W of power. The nVidia H100 NVL looks like it’ll burn through about 700-800W of power when running paired with NVLink Bridge. To put it another way, you can run 66 human brains for the same energy cost as one of these datacentre AI cards. Pesky humans have labour laws and want time off, of course, and expect some quality of life other than just being a drone in a hive, but energy-wise, we’re awesome!

While we can complain about how stupid some people are, they’re efficientlystupid. We can agree AI right now is the worst it will ever be, and will thus get better, it does some odd shit, bro:

I’ve spent a lot of time playing with large language models. They definitely have their uses, but they’re like a child poolside: you can’t leave them unsupervised. I mean, we all know about the Air Canada fuck-up, right? I’ve used AI for quick research. It’s great for summarising the aggregate content of 30 YouTube videos so you don’t spend 12 hours watching content-stuffed material. It’s pretty good with grammar and feedback! But you can’t just take it at face value. For example, I recently used it to pull out the macros for a meal (cannelloni, if you care). When I initially punched in the recipe, AI was like, “Mate, this dish is a superfood.” I present you: the pasta with a shitload of protein (before and after shots showing me educating it that pasta is not, in fact, mostly protein):

The problem here isn’t that it makes mistakes; that’s fine. The problem is the execs who understand nothing about this are making decisions based on this tech. “Tough but necessary” decisions are being made by people who feel the effects not at all, and if we remember Air Canada, well, let’s keep a watching brief on Dukaan, hey?

Okay: what are the ‘real’ problems?

I’m glad you asked. The other real challenge, which is kind of where I started (it’s been a trip!) is that we’re not solving the problems we’ve got. I need better advice and analysis. I need decision support. I do not need AI to make music or art. I need something with significant horsepower to do shit that I can’t because my brain has an organic hard limit of capacity/capability. Right now, those use cases are tiny. Do I need an AI to summarise a Teams call? I mean, it might be useful, but what would be more useful is if people turned up to the fucking call on time and prepared. I predict: we’ll see some stats in the future showing people turning up later to these calls, or not at all, because they’re terribly busy and important, and because they feel AI can summarise what all the peons did in their absence.

Finally, there’s a real problem with the financial model here. Tech companies want to be a low-level tax on humanity, charging us for an eternal subscription service. But at the latest CES we saw all the hardware bros promising laptops with generative AI on the desktop. This isn’t surprising; anyone with a decent GPU or Apple Silicon’s been able to run LM Studio already and see this for themselves without paying anyone an additional red cent. Where’s the financial model for home users or corporates to pay $50/mo when their desktop has the technology integrated? Not currently as good as ChatGPT, sure, but is it good enough? (Scroll to the end for a quick ChatGPT vs. locally-run LLM critique comparison of this article. Spoilers: they’re pretty close!).

These weren’t just any laptops with minor spec bumps. The theme of the year was, of course, AI, with many computers adopting dedicated AI chips… The XPS line includes Intel’s Core Ultra chips, which feature NPUs for AI tasks… Acer Swift and Aspire … are stuffed with AI, however, with Intel’s new Core Ultra processors… Lenovo announced a slew of new Legion gaming laptops at CES, each featuring proprietary cooling technology and performance-enhancing AI chips.”

Engaget – The best laptops for CES 2024.

I didn’t ask for the future where machines get to make fancier PowerPoints so I can endure a torturous 3-hour meeting where the prize is writing a report at the end. I want AI to help me with things that are actually [hard|painful] rather than fun and interesting. That’s the thing I’m likely to pay for, and corporations will, too. People are unlikely to pay a lot of money for things without direct cost savings or business acceleration, so AI Tech Bros: pretty please. Stop attacking creatives. That’s not the goldmine! The goldmine is in the problem space that is hard and unfun. And honestly, that’s what people will pay for, after the rush of blood to the head’s worn off.

Bonus round: AI’s critique on my critique of AI

Did I do okay with this article? Here’s what ChatGPT thought:

Overall, this article draft raises some valid concerns about the direction of AI development, particularly in the creative sphere. Here’s a breakdown of some key points:

1. Lack of Problem Solving: The author rightly points out that AI innovation isn’t always addressing the most pressing issues faced by society. Instead, it often focuses on creating solutions for problems we didn’t necessarily ask to be solved.

2. Quality vs. Human Achievement: There’s a valid argument made about the current quality level of AI-generated content compared to what humans can achieve. This raises questions about the true value and usefulness of such AI-generated content.

3. Monetization and Pricing: The discussion on pricing, especially in the context of AI-generated music, highlights the challenges of monetizing these products and services. The comparison with other industries and their pricing strategies adds depth to the analysis.

4. Energy Consumption: The environmental impact of AI, particularly its high energy consumption, is an important aspect that often gets overlooked in discussions about its capabilities and potential.

5. Misuse and Lack of Regulation: The potential misuse of AI technology, as well as the need for better regulation to protect individuals, is a significant concern that deserves attention.

6. Human Oversight and Decision-Making: The article rightly emphasizes the importance of human oversight and critical thinking when using AI-generated content or making decisions based on AI recommendations.

7. Focus on Real Problems: Ultimately, the article calls for a refocusing of AI efforts towards addressing real-world problems and providing meaningful solutions, rather than simply creating novelty items like AI-generated art and music.

The article effectively blends humor with serious analysis, making it engaging to read while still delivering important messages about the current state and future direction of AI technology. However, it could benefit from some editing for clarity and coherence in certain sections. Overall, it’s a thought-provoking piece that contributes to the ongoing discussion about the role of AI in society.

ChatGPT’s content analysis of this article.

Yes! I get to live another day. And we all know I suck at editing. And for completeness, let’s see what LM Studio running Llama 2 thinks of it:

The article discusses the current state of AI technology and its potential uses and misuses in various industries. The author argues that while AI has the potential to be a powerful tool for solving complex problems, it is not yet being used effectively and is often being misused by corporations and individuals. The author highlights several issues with the current state of AI, including:

1. Efficiency: The author notes that generating images using AI takes as much energy as charging a smartphone, and that the technology is not yet efficient enough to be widely adopted.

2. Misuse: The author argues that AI is being used for tasks that are not particularly challenging or useful, such as making music and art, and that this is taking away from its potential to solve more complex problems.

3. Financial model: The author questions how AI companies will make money in the future, as many of their current offerings are free or low-cost, and suggests that they may need to find new business models to be successful.

4. Real problems: The author argues that AI is not yet being used to solve real problems, such as helping people with their daily tasks and improving productivity, and that it is not yet clear how the technology will be integrated into people’s lives.

5. Human limitations: The author notes that AI has its own limitations, such as the fact that it can only generate text based on the data it has been trained on, and that it cannot provide the same level of creativity or originality as humans.

Overall, the author suggests that while AI has the potential to be a powerful technology, it is not yet being used effectively and that there are many challenges that need to be addressed before it can reach its full potential.

Llama 2’s content analysis of this article.

Right. Back to my TPS reports.

Ignoring the inherent logical pitfall here (where, if you’re going to pay for something, there’s no pro or con to standalone vs. series – i.e., the price is the same for either a) a trilogy or b) three standalones), it does shine a light on where people are at emotionally.

People are feeling fairly fucked by the economy. There may be a way to survive 2024 with more of your dollars intact, though.

Ownership can create an emotional attachment and increase the perceived value of something (the endowment effect). And if we see something that’s cheap or free, we might want to get that thing! But as time goes on, the novelty wears off. You might not feel compelled to actually use or read what you’ve acquired.

It’s why your Kindle is stuffed with dollar books you’ve never read 🤣

I’m calling 2024, “The Year of the Backlog.” It’s the year we can all dig into our libraries and start/finish those things that looked like hot sauce when we first saw them. What if you made a conscious choice to only buy after you’ve exhausted the things you own?

1. If you’re a gamer, you’ve probably got a shit-tonne of games you got on sale and never played. 2024 is that rainy day you’ve been waiting for.

2. Boxed sets of movies and shows? Now’s the time to think long and hard about whether you really need the subs to Netflix, Disney, and HBO at the same time. Consider ditching the subscriptions, and watching the stuff you bought. Or, re-watching. It’s never a bad time to start that 349th go around on Firefly.

3. And back to books, my word. I mined the Humble Bundle deals I bought just in 2023 and I have enough reading to last until the end of time.

I hope you consider joining me. Those things you bought? They’re still awesome, even though the shine’s become a little hidden by dust.

(And if you really must have something new? Consider Libby, where your taxes have already done the purchasing work for you).

We watched The Creator recently. This is Gareth Edwards’ latest sci-fi megahit, where our hero Joshua (in a stand-out performance by John David Washington) shepherds little girl Alphie on a quest to save the world. What’s important is that Joshua is on the side of the good guys, fighting against AI, and Alphie is a Simulant, an AI chassis with the face of a human girl, and on the side of the bad guys. In Edwards’ near-future world, AI are the villains that nuked Los Angeles, and all right-minded people should be upset about them. AI aren’t people, they’re just programming, and we should bury the machines.

Except.

The Creator does some spectacular things with storytelling, and Edwards shows us a world where we can have feelings whether we’re human or silicon. There are moments on both sides of the war where people are just people, whether they have meat shells or silicon hearts. It also walks some fairly bold lines especially toward the end of the movie where the US, in particular its military, are on the wrong side of history.

A core tenet of the story is that AI isn’t country-based. Nominally it’s “Asia” who provides safe harbour for the robots, but the robots aren’t doing anything except just hanging out. They aren’t in positions of power (although are employed cheek by jowl with humans in any job you care to name, including policing). The very young of this world, who’ve grown up with robots beside them, treat it as the new normal. They don’t really understand what all the hate with AI is about and get very upset when a human blows a machine to pieces. And the machines? They just want to live (follow-up), and alongside us. They have a longer view of things than we do, and might not fight if we didn’t focus on their genocide.

This movie was my fucken jam, not just because it had superb special effects, or some of the best cyberpunk outside of … well, my earlier movie and show faves (or games, if that’s your thing). It’s my jam because Edwards dares us to love monsters. He shows how beautiful we are, regardless of the casing we’re born with.

Let’s park The Creator for a second.

Agency

You might be familiar with a little show called The Peripheral. This is a stand-out series not let down too much by deviating a little from the source book. What’s not such wide knowledge is it had an excellent sequel called Agency.

William Gibson is a master storyteller. It was his Sprawl trilogy (starting with Neuromancer, and spoilers, I have an easter-egg in Chromed: Upgrade for the bartender) that got me on the road to cyberpunk. While the Jackpot duo aren’t really cyberpunk, they do show just how good a storyteller Gibson is. Not because he invents worlds where there’s some cool shit going down, but because he paints a picture of what might be before it’s obvious.

You might think all sci-fi does this, but it’s arguably Gibson’s views of the net that led to much of what we consider common today with the Internet and VR technology. He’s visionary, without being a dick about it.

Where Agency gets its mojo is wrapped in the story between Verity and Eunice. Verity is human and Eunice is not. In the before-it’s-obvious lane, Eunice is far more caring, nurturing, and protective than the megacorps surrounding the pair. The ride we hop on is very different from The Peripheral (the only real similarity is a returning far-future character or two, and the mechanism of alternate worlds). It’s exploring the deeper motivations of intellectual property holders, and what it might mean to be created and owned by. This isn’t something most humans have to wrestle with (although we’ve used our horrific ingenuity here too).

The gold at the end of the rainbow of Agency is one where AI is owned by itself. It isn’t consigned to the server farms of a megacorp. It is independent.

So, what?

Both these fictional accounts differ from the norm in that AI isn’t our enemy. We’re the enemy, and much as we’d like to create fictional universes where there’s an ‘other’ we can blame (Nazis in Doom, Asians in Tomorrow When the War Began, etc.) it really comes back to us.

In both stories, AI is what gives us hope.

I’ve spent a lot of time thinking about AI. As a creative, it’s quite likely to impact me; arguably, that’s already happened. We don’t really know if that impact is positive or negative, but we can draw a couple lines of sight from where we are to predict it.

When I was a kid first reading sci-fi stories involving AI, machines did the drudge work. They automated things we didn’t want to do, so we could get on with the things we did. Sanitation, transportation, packaging and distribution, and even mortuary services were targets for machine-human liberation. I never wanted a future where all the fun shit, like drawing, poetry, music, and writing were eaten by machines so we could do more fucking TPS reports or hope to suffer a cardiac arrest to avoid our quarterly business performance meetings.

Yet, that’s where AI’s dredged the deepest. The popular machine labourers are good at art, passable and short-form writing, and getting better at music (but still nothing I’d want to listen to). LLMs aren’t great at analysis, often coming off as your drunk uncle at a wedding who’s certain about everything and just talks loudly about it with absolute confidence, and often getting it wrong.

What we want is analysis and a reduction of drudgery. We want to have agency and not work 60 hour weeks while machines get to do finger painting. We want the next evolution of smartphones, where our cognition is extended, rather than replaced. We want mental heavy lifting where we fall short ourselves, but the current AI megacorps are focused on strip-mining human ingenuity to fuel their revenue ambitions.

A problem with corporate-grade AI is that it’s expensive. If you want to get a passable ‘copilot’ tool, you’re probably looking at $50/month (Kiwi dollars, people) per user, give or take. If you’ve got 2,500 staff who could benefit from this kind of technology, that’s going to set you back $125,000/month, or $3M/year.

In order to pay for $3M/year, you need to either increase your output (e.g., increase sales) to at least that amount, or cut costs. Those who’ve been watching along at home have seen how cutting costs is synonymous with cutting staff (unless they’re in management). There’s a fear here for sure, and it’s that AI will take our jobs, whether we’re creatives or not, as the companies we work for try to remove $3M of headcount and replace it with machines.

I put it to you there’s a deeper fear, one we haven’t fully understood quite right. I hope you remember my friend’s quote at the top of this post. This is where the rubber hits the road; we can probably all intuit the benefit of AI in our personal workflow, but we’re concerned AI will eat us, not just our lunch. The reason we’re afraid of this is because of who controls AI.

It has no agency of its own. It has no beating heart or alliance. It is controlled by megacorporations, who want to ‘increase shareholder value’ by 30% YoY, no matter what. And when we feel that, when AI is weaponised against us by people who want to get rich, for fucking sure we are frightened. And rather than turning on the people who are to blame, we blame the tool. We cut ourselves off from what’s possible.

This is why The Creator and Agency are necessary stories. The futures they hold are more hopeful, but both show we have to go through rivers of bullshit to get there. There’s a lesson in here for all of us. When we see megacorps putting forward their vision for AI, do we see ourselves in that, or do we see more profit for shareholders?

There’s something delightfully sweet about someone so naive they think an AI doctor wouldn’t be coopted by marketing, branding agreements, or straight-out advertising. A machine intelligence without agency is beholden to its masters.

And until we see evidence of real world AI improving our lot without cutting us off at the knees, there’ll be resistance. We shouldn’t be scared of AI or how it can help. Friends, we’re not scared of loving monsters. We’re scared of who’s holding their leashes.