Show HN: I built 80 mini-games using Fable before it was shut down

[legocoder]

Dear Hacker News,

I'm kindly asking for your participation in the open beta for my AI-managed mini-games website. Thank you in advance!

For a limited time window, I'm setting the all-free feature flag to true. I hope you have a lot of fun exploring the AI's sense for games! Here and there, I tweaked it to help with visual consistency.

I would be deeply grateful if you opted into analytics.

$2,300 in API tokens...

Cheers!

[vunderba]

So here goes:

*Pros*

- Very well polished

- Thematically consistent

*Cons*

- Not a lot of uniqueness in these games; most of them seem to be clones.

To that end, I'm legitimately confused about what the OP is expecting to get out of this site. They can't seriously be expecting to generate any significant amount of revenue. They’d be lucky to make enough to pay for the domain. Vanity domains (like those ending in .world, etc) often give a hefty discount for the first year. But by the next year, you’re suddenly paying $20 or $30 a year for that domain.

The graveyard of Show HN, even from the last few years, is littered with the corpses of *.app, *.ai, and *.social sites.

I think they’d be lucky to even cover the cost of this top-level domain, especially considering how many all in one mini‑game arcade/portal browser sites already exist and that was before the rise of large language models.

[legocoder]

I'm here for unfiltered exposure, the busines case I have. I'm happy about any feedback, even if unconstructive

[andai]

>Not a lot of uniqueness in these games; most of them seem to be clones.

I just spent a few hours exploring one of the most popular web games portals. 4 out of the top 5 games are Minecraft clones. Also clones of Fortnite, Asteroids, Spider-Man, and most importantly, the classic Flash game, Fishy!

There are a few original games, but they appear to be in the minority, at least on the trending page.

[legocoder]

In my business strategy I can control what to show and what to hide. Therefore I can place my own original ideas tactically

[variety8675]

> The games, text, graphics, and other content provided through the Service are protected by copyright. You may play the games for private, non-commercial use in your browser. Any further reproduction, distribution, or commercial use requires the provider’s prior consent.

Can AI generated content be copyrighted?

[vunderba]

Given that the majority of the games seem to be LLM generated knockoffs of existing games, I'd wager any IP law would be paper thin here.

I love how Fable "decided" to get around this issue by just renaming things - it's not Tetris - it's Cobalt Vault!

Why no sir, these aren't Fruit Loops - they're Sugar Toroids!

[ghthor]

Tetris specifically cannot be called Tetris or use the original shapes verbatim or it’s up for legal action.

I made a Tetris clone and then researched this. Soiadded a Q shape and AFAI can tell that makes mine a little safe

[vunderba]

Yeah, I can believe that. I imagine the Tetris Holdings Company (or whatever it’s called) is pretty litigious about its trademark.

The history of Tetris in general, especially as it relates to copyright law and the weird, insanely complicated licensing situation with Henk Rogers, The Tetris Company, the Russian goverment, and the creator Alexey Pajitnov is actually pretty fascinating as well.

[samtheDamned]

If just using all the same pieces verbatim is a liability then "cobalt vault" would be at risk since after a quick playthrough I haven't run into anything but the original shapes.

[londons_explore]

No, but you only need to mix a few lines of your own code in and there is copyright protection - and there is no need to tell anyone which lines you wrote.

[vunderba]

Well it's not like it's really relevant in this situation. You could just point Fable at this website or any website with hundreds of mini games and ask it to clone them. Now "mix" in your own lines of code. Launder and repeat.

[colesantiago]

> For a limited time window, I'm setting the all-free feature flag to true.

?

Why not make this all free?

The cost of software in the age of AI has gone to zero now that anyone can vibe code your entire site, Fable or no Fable.

Why would you spend $2,300 in API tokens for something that wouldn't get any return?

The economics make no sense here?

I'm curious why do you think people would pay for your software rather than them pointing Claude at your site and recreating everything for free on a $100 subscription?

[overgard]

Who are these imaginary people going to websites and just being like "I'm not spending $10 on this!! I'll just clone it with $500 worth of tokens!"

[Planktonne]

I don't think they exist, but I think there are loads who would go to this website and then leave, preferring to download free higher-quality apps instead.

[colesantiago]

Still cheaper than spending $2,300 to initially build it.

Eventually the cost will go drastically down as always.

[binary0010]

I have some friends like this, always churning out low effort slop and trying to market it, for it to always fail and them getting depressed and trying again a month later.

I don't get it. It's like they're always excited that they found the magic infinite money glitch in the system.

[legocoder]

I'm aware of the fact, that you can only collect money for giving value.

[cwmoore]

Value the customer parts with money for, and you have competition.

[dc3k]

> I built

Seems more accurate to say “an LLM ripped off”

[legocoder]

I planned the economics and business case, I engineered it beforehand on paper how the Elixir will orchatrate the agent and code, I guarded claude code. Yes, I built it.

[Planktonne]

Why?

You've made 80 quite janky, simple copies of existing games, and put them on a site with awkward tagging.

I get that the fact you could generate them all is exciting in itself, but better free versions of these already exist everywhere online; why would someone pay you for this, and why is it something you want to spend time on?

[jp0001]

Agree. If this was this was just "look at what Fable could do quickly" that's fine. But saying it's free for now is funny. Anyone else could just make games they want to play locally for themselves and their friends now. And there are better ones online.

[tmaly]

I would have loved to see some clones of the original Nintendo games made to work in the browser as multi-player games. The original Final Fantasy would have been cool to see.

[echelon]

The value of all software is going to trend to zero soon.

I don't know why anyone thinks they can sell software anymore.

You're going to sell outcomes.

[WheelsAtLarge]

Programming your own app is not practical. It's not worth the time. It's just easier to have someone else do it. I can probably write my own tax software using an LLM but there's no way I will spend the time to do it. It will probably cost me a few grand in tokens and I can't really know if it's accurate without taking lots of time to QA it. As programmers we've always been selling outcomes. No one accepts partially working code. It has to meet specifications. If a programmer can't do that then he/she loses their job. The programing profession is changing but it won't go away anytime soon.

[bluefirebrand]

Who has been selling software for the last... 15, 20 years?

SAAS took over the software industry. Software as a Service. If you work in SAAS you sell a service not software

Which is actually why the software industry sucks now. I'd much rather build products to sell than "services"

[CyberDildonics]

I don't know why anyone thinks they can sell software anymore.

Probably because lots of people are still selling software.

[xboxnolifes]

Software has always been about selling outcomes. People didn't pay for software because they liked that particular ordering of 1s and 0s.

[colesantiago]

This.

I predict in 10 years time the domain will be expired, nobody will play (let alone pay) the games on here.

With software alone there is no moat, and I am surprised that "smart" engineers didn't think of this far ahead.

This is basic economics.

OP, you might as well have donated $2,300 directly to Anthropic.

[id00]

Game is just another creative media like books and movies. Does it mean that you believe that those will get expired too?

[Planktonne]

If you released 80 poorly-written abridged copies of popular novels, I think you'd also struggle to make much money.

[id00]

Actually it was my fault misreading the comment I replied to. Initially I've read the meaning of it as the whole domain of video games will "get expired" with the advancement of AI.

After re-reading it, I totally agree with the comment message

[legocoder]

Important to have those as a foundation or base, to introduce own custom games with broader audience and control the market economy on my own page. My plan is to save on marketing if I already have the user.

[jp0001]

Gotta have a moat.

[shooly]

Well yes - all of those do check all the boxes to technically be called "games". Can't really say much more than that, since it seems like that was the only requirement here?

None of these games have any soul or uniqueness to them, they are all just clones of existing games with no twist or even challenge, they all use the exact same generic "art style", the website itself doesn't look fun or playful, it's dark and looks like it was taken straight out of Cyberpunk 2077.

It's just boring, sad and passionless - the complete opposite of what games are supposed to be.

[legocoder]

Thank you for your opinion

[markus_zhang]

Mark my word, resource restraint is a GOOD thing — as long as it is not resources that you rely on for living.

[legocoder]

noted. but fun aside - I agree with you completely

[andai]

Not sure why all the negativity in this thread. I played several of the games and they are fun.

I especially enjoyed the gravity slingshot game. The game has a sound engine that responds based on the proximity to planets. That's super cool.

Say, was Fable able to test the games? Like, interact with them?

[himata4113]

What blows my mind is how long fable can go without human input. I played a few and all these games would need at least 2-3 hours of back and forward with a raw version of opus. Of course we have harness tools that can achieve nearly identical results, but it appears that fable has created its own meta-harness inside itself to expand a prompt into a full plan before execution which makes me think a lot of these improvements come from baking claude code data directly into the model and simply adapting the entire manual process of the "back and forward".

I guess that would explain why fable feels like it is able to guess what the human input will be before it ends turn and continue working.

[andai]

I heard Claude Code used a different system prompt for Fable, with different instructions.

It would be pretty funny if most of the gains turned out to be from prompting. Probably not. But a little harness goes a long way!

https://news.ycombinator.com/item?id=48192383

[himata4113]

My observations are made oh-my-pi. https://omp.sh

[a1studmuffin]

Have you noticed Claude Code now gives a suggestion for what to reply with that you can autocomplete with tab? Wouldn't surprise me if Fable used that concept in some way, whether directly or indirectly in training.

[skeledrew]

Makes sense. Those suggestions have been relevant at least 80% of the time for me I think.

[bicepjai]

Good ideas. I like that prototyping game ideas is so simple now or atleast it was simple

[aspect0545]

Congrats, it’s a nice collection. I’m not a big fan of the visuals though, it looks too much like any cheap AI / blockchain project. That‘s just me though.

[legocoder]

Thank you for your feedback! I heard that from friends, too. "Purple is the color of the sexually frustrated."

[andai]

Cool! The idle game is fun.

I was just thinking yesterday I have no moat in browser games. (Well, aside from my incredibly good taste, of course :) [0]

Although, your moat being the fact that Fable is now banned, is pretty funny!

[0] https://x.com/Dan_Cassaro/status/1731752637052166379

[GaggiX]

I guess we can start a chain of comment listing their favorite ones, I haven't tried many but "wobble stack" is pretty cool and simple, "Starfall Defense" is a much more complex game but I love tower defense.

[legocoder]

cool that you like them, i was repromptingthem abit, because they where alittle bit to simple in the beginning!

[hsuduebc2]

Just ouf of curiosity. Is there any business model behind it or it's just for fun? I mainly struggled with my AI projects to give them care after I finished them, so I'm interested in your direction.

[zem]

I am guessing the people most disappointed with AI in the long run are the ones wanting some sort of arbitrage where they can generate products with low effort and then expect people to pay for access to them based on a paradigm where creating software at all required a lot of effort.

not intending to slam you personally, but the fact that you finished your projects and then lost interest in them is very indicative of projects done for the sake of generating something with AI just because you could.

I think the people who succeed will be the ones who are willing to develop a project with high effort, and then use the LLM to help with some of that effort. not just because in a world where everyone has access to the same AI code generators the effort is the value add, but because a good product genuinely does require a lot of human input and supervision being l beyond simply churning out code.

[hsuduebc2]

I agree. In my case none of the projects was something paywalled and we're developed with sole intent to learn. Some we're data heavy which we're most of the work and I didn't had any experience before.

What I meant is the "aftercare" when product is publicized. Like promoting it in some way, maybe using a social media to promote it properly? No idea. This is another thing I know absolutely nothing about, so It would be wise to learn it. I usually just let them hang to be indexed by google and chatbots which drives some traffic, but it's basically just running app not a product.

What I meant is, that OP spend quite a lot of money on that so I was curious if he have any plan. :)

[legocoder]

yes, establishing a base fountation of games, and AB testing new ideas on a broader audience

[mystraline]

Soooo, you paid $2300 for 80 slop game-lets?

You know I can download the following

All NES games: https://archive.org/details/NESMegaPack201808

All SNES games: https://archive.org/details/snes-usa-romset-complete-collect...

All Genesis games: https://archive.org/download/sega-genesis-romset-ultra-usa

All Playstation games: https://archive.org/download/psx-roms-archive

All Gameboy Advance Games: https://archive.org/download/GameboyAdvanceRomCollectionByGh...

And those cost..... 0 tokens.

Add this to a mSD card and a Mayoo Mini+, and you have games for years. Years.

[legocoder]

Haven't thought about that, thank you

[skeledrew]

I suspect you just murdered at least a few of those links by posting here.

[agnishom]

Are any of these games fun to play?

[apricot13]

I'd been looking for a codebreaker game recently so cypher lock was fun to play for me! https://minigames.world/en/feed/cipher-lock

[cr125rider]

I think so. In the same way their source material is fun I guess

[binary0010]

You found these fun? As I can't imagine finding them fun. Can I ask, how long did you play? How often would you see yourself returning to this site?

[sunrunner]

I still have Quantum Forge open in a tab. I think that probably says more about me than the game though?

[agnishom]

Which are the fun games? Any suggestions?

What source material are you talking about?

[armnd]

> The games, text, graphics, and other content provided through the Service are protected by copyright. You may play the games for private, non-commercial use in your browser. Any further reproduction, distribution, or commercial use requires the provider’s prior consent.

The fucking hubris.

[sph]

I’m so glad vibecoders adopt the same garish style of web design, I can spot them from a mile away and not waste my time in playing their slop.

I hope this was worth the 2 grand and 10 minutes of your effort.

[legocoder]

yes, it was very pleasant and I learned a lot

[cwmoore]

What was your prompt?

[217]

oh wow we really have poki / crazygames at home now

[legocoder]

yes, I wanted an own mini games web page for quite some years. but have been to bad to code one

[bmusuku]

thank you, I loved checkers

[legocoder]

classic

[briangao]

what is the point of this? it doesn't matter how many games you can make in 4 days, none of these are of high quality, this is useless

[legocoder]

What is quality for ones children eyes?