Growing up, games were such a scarce commodity that you'd really suck all the marrow out and spend hours beating your best times, looking for Easter eggs, or messing with custom maps and mods. There was a whole genre of gameplay around just exploiting physics bugs to jump a bit further.
The other night I carelessly made an infinite runner game while watching TV and the feeling of sheer abundance quickly faded into a bit of depression. Without scarcity, nothing is really valuable.
Yeah, you can make more stuff , but no one cares. Plastic used to be so rare and luxury , now most of them are crap. Software is the same. Creating software is becoming a practice that produces a tiny bit convenience at the price of sustainability.
That's not really true. Music is still valuable even though the value of music people write themselves is already practically 0 and has been for a very long time. Same with paintings. People are always looking for a connection. Just because some exists now doesn't mean it automatically earns it. It has to have something else going for it. I think that promises a bright future for creaters and consumers of that creativity.
>The other night I carelessly made an infinite runner game while watching TV and the feeling of sheer abundance quickly faded into a bit of depression. Without scarcity, nothing is really valuable.
This is just a lack of ambition. LLMs allow one to make far more sophisticated games than ever before, even as a single developer, and if doing so development still takes many months even if running an agent 24/7.
I feel for kids growing up with LLMs like this. They will never impress a parent, teacher or peer with a simple “hello world” type text game, when the peer could generate a full multiplayer video game with a couple of prompts.
I don't know about that. My son is about 13. He's got into coding using godot and initially built a few games in Javascript (via. a book which I worked through with him). Then, he picked up Godot from tutorials online and recently has built something multiplayer. He asked for a Claude subscription for his last birthday and since then has been doing all the parts he enjoys by hand (combat mechanics etc.) but using Claude to do things like trailers, website aesthetics, sound effects etc. It's been nice and the results are impressive. e.g. one of his first games was a simple hangman. Now, he added a keyboard to that via Claude so that it can be played using a browser.
Wondering if you thought about the effects that AI exposure can have on a young brain? Adults are experiencing brain rot, do you think kids could have it even worse?
Honest question, I don’t mean that sarcastically. Wondering if AI exposure will be compared to doomscrolling social media in the future.
It's a line I've been trying to balance. I don't think outright bans are helpful. AI is going to be there in some shape or form in the future and we need to know how to use it to our advantage. Getting hooked onto it is a problem. I know I experience that myself.
My main barrier against this has been to talk with him regularly about this. Amplify the positives rather than warn about the negatives so that the first gets done more and the latter gets atrophied.
Completely agree, looks like 13 - 14 yo is the right age to dab in both side (traditional coding and LLM assisted coding) for instance, my son (13 yo), knows a bit of coding (python, javascript, roblox, etc.) and some experience, but giving him Claude Code with Godot MCP was the true unlock, he spend so much time building his own gam, focusing on the aesthetics, gaming mechanism, story line, overall effects and look and feel:
Love the retro feel to it. He even has a guestbook. I was about 13 when I created my first website. Of course that was in the days when it all needed to be done by hand and there weren't really programming languages for the web yet. Hope he keeps at it!
Thanks. He's got a Youtube channel and an itch.io account. Wants to really get into the game development space. I'll show him your comment. :)
There was a local contest where I am and his entry for that was his latest game which has multiplayer support over the net. He set up a server on a VPS for this. https://waitinggodot.in/games/legends-of-crumbs.html
This just proves the point more than anything, really.
Both the website's design and the games presented look indistinguishable from every other AI-generated website and game I've seen in the past. I do not feel any sense of individuality while looking at them, they could've been prompted by just about anyone. Even the little text blurbs are plain unfiltered Claudeslop ("no spoilers, just green and red squares").
Any one of your son's peers could create something identical by typing "claude, make me a cool website with some games" and waiting an hour or two, and that's the problem. How do you think he would feel if he showed this to one of his friends, hoping to impress them, and one day later, that same friend approached him and said "look, I made a website exactly like yours, it was so easy"?
I am still imoressed by hand-painted signs in Nepal and India - enough to take many pictures of them - even though AI-generated signs are now everywhere.
My watercolours still impress people enough to get requested even though they're fairly mediocre.
I can't imagine not being impressed by something made by _the person that I created_ because a machine can spit out a neater version of it.
Because we're not curating a culture of this, certainly not in tech. On HN, we celebrate AI output more than human work, in the sense that many stories make it to the top only because a project was done with AI. There are several on the front page right now. When people point out that they prefer human output, they usually get comments about getting on with the times. In threads about mathematics, most commenters root for the destruction of that community. And on and on.
Other communities are more protective of human output. For example, you'll get chased with pitchforks from the watercolor community if you post anything that smells of AI. But in tech, the number of people you can impress with human creativity has diminished by orders of magnitude.
I agree. But I think the problems have now just moved. What is 'hard' is different. I don't think we've collectively grasped that yet. We're going to need to use our imagination and show others when we find something. I'm looking forward to what we can solve, I just hope the opportunity and benefit is well distributed.
It's truly awful. Best case, they go on and start tinkering and fixing and learning. What is more likely and awful is they will sit there pulling the dopamine lever and get hooked on using AI to do everything difficult.
Try to go back before our era though. In the early age of computers, computers were basically really big one-way calculators that could execute an algorithm and output a result. In this context a kid creating a program to output the fibonacci sequence would have been quite impressive. But by our era, we needed to be able to produce basic text games to impress. Did we really lose anything in the process? I don't think so.
And now too the impressive demo isn't going to be just making an interactive or multiplayer game which anybody can do with a single prompt, but creating something that's actually interesting/fun. Interestingly enough this now overlaps quite well with the sort of stuff that could be monetized today. That's why I think LLMs are going to throw a curveball in the economy in ways many aren't yet appreciating.
I spent so much of my youth building things that were far beneath what I wanted to be building because it took all my time/energy/attention/expertise to build the lesser thing.
But the energy and effort you put there made you learn all those things. Also gave you some satisfaction as a reward. I’ve never oneshot games in an afternoon, but I remember really well the thrills I had when I learnt how to open the first TCP connection in Python.
We’re entering into a new era of mankind. With good and bad consequences.
Would you rather your kids draw you a picture, or print out something they generated with AI. 'Hey son this drawing is beneath you, I'd prefer something AI generated'. What about the note they write in your father/mothers day card. You want them to write that using AI or come up with something themselves? I'm not saying your kids can't leverage AI to build things, but there is something special about the process of creation, and iteration and learning that can't be shortcut.
> I feel for kids growing up with LLMs like this. They will never impress a parent, teacher or peer with a simple “hello world” type text game, when the peer could generate a full multiplayer video game with a couple of prompts.
Adults are also desensitized to impressive deliverables. We see it even among peers who barely bat an eye when someone goes above and beyond to deliver a feature. The toxic ones even try to downplay your achievements by throwing around claims that your deliverables were vibecoded.
An old tech friend and I were talking a few years ago about hobbies, and how our old CTO was one of the most impressive hobbyists we knew of. Not only was he an incredibly accomplished exec but he also produced amazing YouTube content about his model railway collection and model rocket building all in a custom home where everything had custom smart interfaces with a growing family who enjoyed home cooked meals together on furniture he built himself.
Built himself? Well, designed by him and built in his home workshop. Some of it done by him at least with his assistants. They had a home chef too of course who gave the kids a bowl of stuff to mix during prep. The model railway involved design work that was more like commissioning 3D prints and model assembly. Input on the design really, as a lot of it was handled by assistants. Assistants assisting assistants based on prompts and review and feedback. Everything was custom and bespoke and made in his vision. Almost the entirety of the labor and craftwork were outsourced.
This person was a great leader — or “orchestrator” in the language of agents — but a lot of his accomplishments boiled down to having the physical world equivalent of a massive token budget: money and staff.
The great scientists of the 19th century, the ones whom we named fundamental units after, had skilled craftsmen who cut precision screw threads and blew perfect glass for them. Major scientific leaps are written up on papers authored by department leads et al. Les chefs célebres of the world front a kitchen filled with skilled staff supporting the name over the door.
If your work can be done on a computer though, AI can provide you with a Python line cook or a C++ glassblower of your own, so you can’t just show us your perfectly julienned potatoes or evaporation flask and expect us to praise anything other than your wallet, and your ability to motivate robots to do your bidding.
Seriously. I remember coding something in Macromedia Flash to impress my computer-illiterate parents. It was silly but it was all mine. I am sad that I will never see that for the future generation, not this way at least. The bar is too high now.
On the topic of Byung-Chul Han, I'd also recommend reading "Non-Things" as a good exploration of the digital/physical world dynamics we find ourselves in today.
Not sure whar you are mourning. It is just that the bar has gotten stratosphericly higher, which is awesome.
I along with most of HN probably had a new idea every month for a game or software back in the day. 12 year old me could only dream to maybe work on something tangential to them in the next twenty years or even a lifetime. Now i could prototype most of those ideas as i thought them up and really get into the promising ones.
I feel like i was born too late and missed out, straight up jealous of the possibilities in front of the kids willing to take it
"one-shotting" is fun for a low (human) effort toy, but it's a mistake to get overly hung up on LLMs getting everything right on the first try, since a lot of that is the harness and the internal prompting that makes it burn extra tokens to test everything to get it in that one "shot" (ui turn).
While it's nice that LLMs are getting better at arriving at the desired deliverable with fewer surprises (or broken things) doing it is not necessarily a sign that the model is actually smarter, just an indication that what you are doing is likely a well-trodden path for the model, the RL and the harness.
I have a personal benchmark suite that runs a bunch of difficult algorithmic problems in 3 tiers: vibe coded prompt (just a few sentences), vibe coded prompt plus a description on what the solution will be evaluated on, and finally a fully specc'd prompt that leaves little space for interpretation.
The current Fable models are approaching a level where the -eval runs perform systemicallty better than the "clear spec" runs. (And right now its just Fable 5.1 and Opus 5.5 that behave so well, all the other models I tested - all the OpenAI and the leading Chinese models - work better with clear specs). I'd encourage everyone to experiment a bit; I am running my serious workflows with labourious force-me-through-all-the-design-questions mode, whereas my hobby projects, some of them hard, I am trying to see how much I can get away with with vibe-grade prompts. My conclusion is, with Fable its starting to look like what Vibe coding was promissed to be a year ago - a magical box that generally does things very well.
Btw, congrats to the OP -- the game is enjoyable and I played a few levels. I dont remember when I last played any games for more than 5 minutes. Good stuff.
The process of using AI to create things changes how you evaluate the quality of what's generated, so really the answer is "until you accept the output first time."
That's a combination of AI improving and your standards changing.
That’s astute. I’ve increasingly felt over the last few months that people just don’t particularly value quality. The bar for most people is much lower than professionals (in whatever domain).
My experience has been that cruft accumulates and creates back pressure via growing token usage.
The APIs aren’t clean, which creates indirections to other parts of the codebase to check on leaking abstractions. It doesn’t learn, though, so you pay for those indirections every time (right now, anyways).
I’ve not been impressed with its ability to clean that up with a generic “make it gud” kind of prompt. I have to point it at something crufty, but it will fix it then
I agree, but for some projects, that first vibed version is just about good enough and becomes the final version. I have a few things like that and it was nice not to have to bother.
For work stuff, I don't dare 'vibing' anything, and force myself through torturous design cycles and regular refactoring runs. But thats serious stuff with hundreds of thousands of users.
Btw. Fable 5.2 seems to burn through tokens with gusto. I ran my benchmark suite on it, added a complex feature to a hobby project (a gothic cathedral designer), and voila, 2 resets gone.
I definitely remember a game I played for more than 5 minutes recently. A lot of those were not AAA(A) games but rather indie or previously-indie-now-got-a-publisher-to-notice games. None were "AI one shots" that just built something that looks like a re-skinned version of "Teenage Mutant Ninja Turtles: Shredder’s Revenge", which I'm sure is pretty abundant in training data? And that was a great game btw!
But one shot prompting does not mean one shot testing. I see continually that Fable can design and test prototypes before committing to a design goal and testing multiple layers until the goal is reached. Many of the tests are code unit or integration tests that can be re-used without token spend.
> "one-shotting" is fun for a low (human) effort toy, but it's a mistake to get overly hung up on LLMs getting everything right on the first try, since a lot of that is the harness and the internal prompting that makes it burn extra tokens to test everything to get it in that one "shot" (ui turn).
I'd be more specific and state that these models are now way far from being LLMs and instead they are full blown agent orchestration systems capable of running multi-layer ReAct loops and tool-calling, and with your whole session history as context. It doesn't make any sense to refer to them as glorified chatbots as the LLM part is nowadays far from being the component that delivers the highest value.
> as the LLM part is nowadays far from being the component that delivers the highest value
Yes it is. The rest of the agent could basically be a while loop, a two sentence system prompt and a shell invocation, and it would still work reasonably well.
These agent swarms with harnesses are certainly more than just an LLM, but the LLM is certainly the integral part that delivers the most value. Without it, there is no AI.
With a LLM alone, all you have is a stateless chatbot. If you increase the parameters of the LLM by a few orders of magnitude, you still have a stateless chatbot.
If you start with an anaemic LLM and run it with a ReAct loop and tool-calling, you now have something you can use to do agentic coding and RAG-like capabilities.
There's a reason why relatively small open weights models are starting to perform on par and even outperform models that need a huge datacenter to run.
There are some areas in which Fable is clearly better but subjectively the Opus 5.5 version feels more fun.
Both are one shots, Opus 5.5 was done a few weeks ago before they added "guardrails" around recreating games. Fable 5.2 changed some game mechanics despite my prompt asking for them to be the same as original game.
> Fable 5.2 changed some game mechanics despite my prompt asking for them to be the same as original game.
I couldn't care less about AI-generated games, but such restrictions are just destroying the value of proprietary models. Even more frustrating is that it so far hasn't been considered illegal to steal all the information for training the models, but now it's becoming illegal to ask for these same models to output this information back.
In my 2 minutes of testing I liked the gameplay elements from Fable 5.2 much better. I think Opus 5.5 sound effects may have been a bit better but that's it.
Claude artifacts are standalone outputs, like docs, slide decks, spreadsheets, dashboards, designs or small web apps, that Claude publishes as hosted pages with their own link. They start private to you, and you can keep editing them, export them, or share them.
Just ask Claude to create an artifact. Sometimes, it does it by itself depending on what you ask for.
It can create something like DX ball easy, because its already there, the AI already knows what it is
It can not create a game on the same level as DX ball, something new i mean, not a mechanic added on top, a real new game that feels like a game that would have come out the same year as DX ball
AI is great at executing the task, but it can not for its life (or for the anthropic reputation, it seems to care more about that) create something new from scratch, it can not do game design thats not just change the speed of the ball or the paddle color. Probably a limitation thats there from the start
On a spectrum of course, granted that could mean a 3D paddle is new, but hey we know we are not talking about that right? We know we are talking about a game with enough differences not to say this is 3D X, but this is OOT the direction zelda will be taking
I have experienced this myself, although the novelty kind of wears off after a while. It is still fun to make small games to co-op on the TV.
Yes, hard to believe but most of these games can be almost one-shotted in my experience, with bugs but still playable. We are not talking about some properly made games but imagine for a second that there are some number of casual players out there that wont mind spending 30 minutes on a game for just a bit of fun and having these just materialised just in time is a lot more convenient then hunting for them on the app stores.
For anyone interested, I put all of of my work into an open source tool that uses your iPhone as a console which then can cast on your TV. Up-to 4 local players supported. It can even run proper games via WASM. It is Apple Silicon only.
Without reading any of your blog, I went immediately to play the game and my very first though was, "Woah, this is just like the ninja turtles arcade game."
I played for about 10 minutes and I swear - this was fun. There are a bunch of bugs to polish: collision detection is sometimes weird, you can catch enemies at the end of the map and just beat them up forever, adding tons of score, Pudding's animations feel quite off, and Stage 3 is VERY hard. However, the game still looks and feels quite polished. I loved the music as well. FWIW, I'm glad I'm not a game developer these days.
I used my $200 free fable 5.1 credits to build a WhatsApp sticker maker, it created a version I was not happy with, but it burned the 200 in one sitting. Node.js app, vue frontend, etc.
I didn't used the project a lot since I kind of hate it on how much was spend.
Last week I used just a little bit of my $20 pro account to build a replacement with rust end to end, just to gain some experience with the rust hype. Very happy with the result, not perfect but snappier, and even better: a single executable, I no longer need to fire up a backend and front service separately.
I use Sonnet 5.5 and Opus 5.5 both on Medium to produce apps in Rust/Tauri all day every day on a $20 Pro sub, and absolutely these two models do a great job with that stack. I rarely run out of weekly credits, unless I use Opus 5.5 on high or ultra code. Medium does the job 99% of the time. Fable is good, but it'll never be as good as Opus when well prompted and with some iteration. I see Fable as a preview of what the next model will be able to do, but it's really not a good production model unless you have a lot of cash to burn.
I don't know, when every kid has had 3 custom made games offered for their birthday, won't they just get bored? Obviously through our lenses this seems awesome because that's something we would have dreamed of, but we would have dreamed of it because it seemed impossible.
Kids? Forget the kids. This is awesome for everybody. I'm busy making 'adult games' (not that sort) that I always wanted to make, but lacked the artistic/sound/etc competence to do so. And while I hope to make a buck off them, I don't even really care. Even if somehow they failed, in the end I'd have stuff that I wanted but always lacked certain skills to complete.
I don't think people are yet appreciating how much LLMs are going to change the world, especially not the doomers. People are just jamming the present into the future, with greater efficiencies. But it's nonsense. The cost of cognitive work will approach $0 which is going to send the raw value of cognitive output to something close to $0.
So the 'winners' will be whoever fills the resultant vacuum in the economy. That will probably be a mixture of social, physical, entertainment, and other such domains. But it's all so hard to predict. We've lived our entire lives in a completely agrarian society, and we're seeing the advent of the Industrial Revolution. It's easy to predict super-farms, but those aren't going to be the 'real' winners.
The 'winners' will be the holders of capital, same as always, but it will be giga-gasoline on the fire. The rest of us will be dancing monkies for the owner class if we're lucky.
...except people who actually enjoy games and want high quality games to play, of course.
Down here in reality, platforms like Steam are being absolutely flooded with generic, ugly, low-quality AI-generated games, which are not only drowning out the human-made games people actually want to play and making it impossible to find them, but are also preventing them from being sold entirely in some cases due to human reviewers not being able to keep up with the pace of new game submissions[0].
So, thanks for your contribution to that, I guess.
The game from this article is quite fun and was literally a one-shot from a relatively brief prompt. I certainly wouldn't call it ugly or low quality. Generic? Sure, but that applies to nearly all games anyhow. With all barriers to development coming down obviously you're going to get much more slop, but you're also going to get many more gems. The review system (and meta-systems like getting your game to streamers, your own reputation, etc) still works well to separate the wheat from the chaff, and there seems to be no reason to yet expect such to stop working well.
In the end the biggest winner in all of this are going to be the players, due to competition. That competition will both bring down prices and bring up the minimum standard of quality for a major success.
> I certainly wouldn't call it ugly or low quality.
I would. Maybe our standards for quality are different, but I'm willing to bet that if you showed this to a bunch of people who actually play games regularly as a hobby and have some standards for them, they would most likely agree that, even ignoring the obvious "AI look", a simple 2D game that can't even pull off natural-looking walking animations could never be considered anything but low quality.
> obviously you're going to get much more slop, but you're also going to get many more gems
This is demonstrably not the case. Just look at Steam's most recent Next Fest - it featured over 8000 games, twice as many as the last one, the vast majority of which being low effort AI generated games. Yet the number of gems that rose to the top was not higher than before. If anything, it was lower, as most players simply gave up looking after having to scroll through hundreds of AI games. Such games can never be "gems", no matter how much you try prompting them to be.
Did you have fun playing the game? Because I'd argue that if you showed this game to bunch of 'real gamers' as you're effectively concocting here, their metric would be the answer to that question, rather than seeing if they could find a technical flaw. Because in the end all that matters for a game is fun, and this game certainly scored well on that metric for me, and I suspect the vast majority of people.
Not really, one of the joys of being a kid was forming your own "studio" and making games for game jams and stuff. Being able to one shot stuff really destroys the fun.
Positive little kiddo gets more screentime!!!! Yaaaaaayyy!!!!!
Negatives: we either are annihilated by AI or enslaved by technocratic feodalism living in a worse conditions than 1800s mine workers. Uau
I appreciate the token breakdown, but how much would this cost in money? Chatgpt estimated $400 to $600, but I don't have enough knowledge of token pricing to know if that's accurate at all.
Yeah, it would have been expensive via the API; the tokens were free when I tested it, but it would have been something like $300 USD for the Claude tokens at Fable 5.2's API prices.
What does one-shot mean in this context? Aiden (the main character)'s walk cycle is kind of a mess and its also the animation that a player is going to see all the time.
It appears to be eight frames, but after taking a closer look, I found that they don't seem to be consistent [1]. Using ControlNets and various other strategies, you can definitely build out a "nominally acceptable" walk cycle [2], but you still have to do some manual work.
The article clearly explains what the author/their nephew did. There is no ambiguity. One-shot never means 'so perfect there is literally nothing to be improved.' It means no back-and-forth iterations between the human in the loop and the AI.
- In traditional ML/vision, it meant learning to recognize a new category from a single training example.
- In LLM prompting, it has always, at least the last seven years, meant giving the model one example in the prompt (zero-shot, one-shot, few-shot).
- Vibe coders/AI-influencers use it to mean "one-shotting" a task on the first try with no back-and-forth.
> The article includes the entire prompt OP used in the first section. I think it is pretty clear.
According to TFA, Fable 5.2 was starting with a preexisting codebase generated with CC (via Fable 5 and Opus 4.8) back in June. The author describes that version of the game as working, but not fun.
The Fable 5.2 prompt then starts with:
> I want you to help me finish this game.
I don't think you can really describe this as "one-shot" when there's already a fully working codebase? That's a stretch.
One shot: One prompt; no need to interfere or make further modifications after it is done. You are totally inspecting other parts of the game. Not the same meaning.
> You are totally inspecting other parts of the game
Other parts of the game? It's probably THE MOST seen animation in the beat-em-up genre. This would be like building a piano where middle C is inexplicably 50% louder than all the other notes.
Is it playable? Sure, but it's gonna annoy you every time you strike that key.
> no need to interfere or make further modifications after it is done
I quickly dove into the game and then got lost as I couldn't exit and had to spam keyboard to see the controls. The menu refers to "Punch" but it wasn't obvious what key that is (and it wasn't "p"!).
I see that ENTER pauses, but may I suggest also making ESC and/or P pause. And then the pause screen showing or linking the keyboard controls and an exit path.
(Caveat: I'm not much of a gamer so maybe the current controls are standard? Anyway, I feel like it could be more inviting to casuals with something like the above.)
This is both cute but also a bit sad in terms of game stylization, I guess these generic AI designs could become so normal to the youth that in the next 10-20 years it just appears everywhere
I’m going to go out on a limb and predict the opposite.
I think “the youth” are going to grow up with a Cambrian explosion of styles, mashups, callbacks, revivals, etc.
Right now a vibecoded game just uses the generic style. But you could easily imagine the kid saying to Claude “rebuild this game but in the style of that old show [Samurai Jack | Ren and Stimpy | … ]. We are so early in the tech curve, market penetration is still very low, and the “creator-years” in the medium is tiny; it’ll be 10x in a year if not more.
AI is amazing at style transfer, and so there’s a huge payoff for exploring and learning references to existing artists.
(I also think copyright will die pretty soon for similar reasons, that’s a separate take though.)
That was already happening before AI, with in-house game engines dying off and all converging on the same quasi-realistic style and often the exact same assets.
Games used to have very unique, noticeable styles that you could instantly place from a screenshot. Now everything just looks like Unreal, Unity, or generic 2D.
Hopefully AI might actually make it easier to be more ambitious with unique art styles, should the developer choose to do so.
I'm kind of hoping that the youth will recognize that stuff that can be made with AI is just nothing special anymore, and find something that is (or still is) special. I don't know what that is, maybe something that AI can't do on a fundamental level (maybe something physical?).
(Of course, at this point it might be necessary to point out that "the youth" is a diverse bunch, and some will be like this and others like that.)
don't really think there will be anything - this is an entity that can learn anything (even physical things) faster than any human or the collective of humanity for that matter.
I've found analog photography to be a rewarding hobby, and although an LLM can help me refresh my memory, the overall experience is certainly not something that an LLM can replace.
We also connect to people through art and play. So if we automate those things, then I guess we'll spend the rest of our lives living unsatisfying experiences.
You can change the stylization with LLMs. I think what we're seeing is simply any barriers to code/design/art/music/etc completely going away.
But those barriers going away now means that the starting point is much closer to where the finish line used to be. Like a few years ago this would have been an upper tier beat-em-up. I think we're still early enough in the window that I'd still call this upper tier, but the reality is that it's also now something that an uncle can vibe code for his nephew over a weekend.
In general I think this is going to be very good for everybody, but it's going to completely destroy the software as a problem-solving industry, and make the software as entertainment industry much more competitive.
Barriers going away means you get a lot more at the bottom and middle of the pack, but a game is more than the sum of its parts, and as long as LLMs do what you tell them, you need to have real talent to make good games.
Was this game fun for you? For me it certainly was, and ultimately that's all that matters to me. And that's why I said I'd classify it as a top-tier game because IMO most games that get released, slop and 'professional' alike, simply aren't fun. Even on these forums there's plenty of people posting thinly veiled hopes of going viral along the lines of 'I spent 5 years to fail with my game' when as lovingly hand-crafted as the games may have been - they invariably just weren't any fun to play!
In any case, it being "extremely far" from the top would just imply I should be in endless bliss with the current state of things since if I find this game quite fun then higher tier beat-em-ups would be just the most incredible thing I've ever played in my life. That has certainly not been my experience.
This style reminds me of those mobile game ads with helpless characters that need YOUR help not to freeze or something. Probably the exaggerated facial expressions.
that kind of stuff happened routinely in the 70s-90s in mecha anime franchises that were designed/drawn/animated/produced by large teams of adults..
Mobile Suit Gundam and Evangelion are both notorious for this. Is Eva-01 40m or 100m tall? If you trust the technical literature then you'd be forced to deduce that the tanks in some of the scenes are squirrel-sized -- and these decisions and scenes are produced by committees.
- punch and kick don't seem to have differences in effect, just animation
- bosses don't have obvious gimmicks to beat them
But the main take-away for me is that this takes me back to computing in my youth, where you could dream up a project and bash it out in a few days. It wouldn't be polished, it wouldn't be perfect, but it would be yours. It would do what you wanted. Computing was ours, it didn't yet belong to big corporations controlling what we could do and how we could do it.
Projects like this give me hope that a new generation will experience that. Aiden won't ever forget this game, even if it's nothing special to you or me. Aiden won't ever forget that feeling of imagining a change, and having it happen. The price for it would've been somewhere around $300-$500, so not exactly broadly accessible - making AI efficient enough to run cheaply should be the main goal of humanity, but we're letting computing get locked up by a few rich sociopaths once again.
What I wonder reading that would be how much more effort to actually port it to the PlayStation, or whatever game console. I recently asked my local AI to make an ebook reader for my Gameboy pocket ;) I just think about all the cross collaboration of devices for stuff we can only imagine.
I no longer read or watch accounts of these models one-shotting things (unless you tell me it one-shot a differential AES cryptanalysis, or maybe an entire healthcare system with billing and radiology viewing, compression and annotation)
All these frontier models are capable of creating these amazing things. It's just reality. If it's in one-shot, it just means there's been more RL in that area, more reasoning is being spent in certain places, but overall you can get the same result without spending $300 in tokens if you feel like waiting a week or two for your claude subscription to reset.
It is very impressive though, and the implications on what a smaller version of this model can do is very exciting (aka what I expect Opus 5.6 or 6.0 will be)
> I must admit I never tested this with Opus 5.5, so I'm not sure whether this was possible before Fable 5.2 rolled around.
Since somewhere around Opus 4+ it's been really good enough to do these things, but 4.6 was the most pivotal version since a 1 million token context window can allow a model to fit so much "in its head" basically.
This is awesome, but I don't get the repeated use of the term "one-shot". There were many human-driven requests and iterations, and this is illustrated in the blog post.
This really was more like a normal person had access to a game developer team (with artists and musicians) and had a custom game built based on interviews and playtesting.
I disagree. Fable didn't make any mistakes and created a completed game with zero guidance, so it's a one-shot. If additional requests come up afterwards, it doesn't detract from the initial execution.
That is my definition of one shot as well. I consider the app I made "one shotted". But by that, I mean each feature is a single shot. The app is a collection of over a hundred of those shots..and counting.
Thanks for pointing this out. Before reading, I had assumed that the author was using "one-shot" in the standard vibecoding way, meaning "one conversation turn". The title is slightly misleading. But he did have an enjoyable, playable game after a single prompt—but I think that prompt may have included the earlier, boring version of the game?
Kids are now coming of age with the software equivalent of a Star Trek replicator. LLMs are going to radically change the cadence and workflow for the production of computer games, no doubt. When you can turn out a professional product based on little more than doodles and some text prompts, it rather devalues the historical effort of bringing a unique game to the marketplace.
I rather hope that the novelty of generating this kind of toy wears off.
This is really cool. This would've been a dream for me when I was young.
One bit of critique of the Fable generated app here is that even though it technically runs on a mobile browser (Brave) it doesn't seem to be actually playable on it beyond playing the intro music.
It’s a lot of fun to build games. I started building little pieces of one[0], then a builder for it, then a story, then a video recorder. And there’s a lot more iterations in the roadmap. It’s great as a creative outlet
It’s not one shotted anymore or course. But in the process, it’s also cool one-shotting new features or experimenting with variations of things very quickly
Eventually it becomes similar to any longer lasting project. Complexity starts creeping in, maybe technical debt, and managing everything to keep it consistent/coherent slowly starts taking most of the time. And I’m not maintaining it for real active users, which would also become some other type of project
I understand you, I tried to give a huge tasks and getting fun with one shot result. But actually more interesting how long this process worked and how many tokens spent, because in GPT you can simply add target and GPT will work even 1 year non stop until reach this target. But I got what you talking about, but still time and amount of tokens is more informative information.
It's crazy how even the intro text to the Fable 5.2 Extra's game still reeks of AI. Like, wow, the models can make a game that almost makes sense, but still can't write text that sounds remotely like a human was involved!
"find all documents, descriptions, walk through of game XYZ, generate a consistent and declarative document that another agent would read to recreate the game without using existing IP or protected data, do not reuse art but describe general details with the ability to extend and add specifics later. focus on functionality first, then mechanics and then later art and gameplay. generate a 10 page document that will follow MVP to Production quality gameplay"
Based on what I've seen, there's a good chance this would work today (though Anthropic recently added some restrictions around this sort of prompt) -- try it!
I tried the game and in some seconds noticed I can kick the enemies forever if I put them close to the left corner. I'm feeling now that I'm the AI exploiting bugs.
Just a small suggestion on the prompt. I usually also add something like "Bring in a critical Art Director, Animator, UX Expert, Staff Engineer. Don't release the game until they all agree it's AAA quality." I wonder if that would have helped with some of the issues/bugs others called out. I do this with Codex and it's been working really well and not using many tokens.
Is Pudding the dog (unlocked after beating the first boss) supposed to shrink anytime it jumps? I guess even Claude-turned-world-class-game-developer isn't immune to bugs. ;)
Honestly, setting all the oft-cited AI caveats aside, the end result is cute and perfectly serviceable as a game for the kids. I can't imagine how stoked they were about playing it.
Ooooof the results here are rough. A very young child might find this charming, but I think it's kind of embarrassing. Like, the walk cycles alone are. Yeah...
To say nothing of ur word shaders, inconsistency in the characters, questionable gender stereotypes, etc.
This definitely tells me that AI definitely isn't there yet.
This is a bizarre complaint. There's plenty to complain about with regards to you know, normalizing kids consuming AI content, giving a gift from a slop machine instead of something hand-made, etc. But come on. The game itself is insanely impressive for something generated in one prompt from a bunch of doodles (cool doodles, but still!) If a single human hobbyist dev created this in a few days we wouldn't call it "kind of embarrassing".
i button-mashed my way through the first level and, what can i say, this is kind of dream i have when i spend my days button-mashing my way through side scrollers.
when i was between about 6 and 8 years old, i used to have this same dream about travelling through space, feeling the tranquillity of the celestial orchestra, and then whizzing down to feel the speed at which they were actually moving from a completely different frame of reference.
there was a sense of fullness and emptiness at the same time, raw power but also serenity. as though everything was coming into being and going out of being at the same time.
i always woke up feeling mystified but full of wonder. I carried that sense of wonder with me through many days and it always came back to me when i looked up at the stars and felt myself on the edge of this sphere, zipping through space at hundreds of miles an hour, but only seeing the tiny twinkling of stars as evidence of this enormous cosmic play.
but i suppose getting revenge on the goons by kicking and punching them, in order to save puddles, is basically the same
funny enough it's also the only model afraid of creating a 3d mesh with pikachu photo on a 3d benchmark i work on
"I can't recreate Pikachu since it's a copyrighted character, but I can build an original toy critter in the same spirit: a small chubby four-legged figurine in a charging pose with its own design. I'll start on that now."
This is back with Opus 4.1 when I was still amused with these things. It definitely took better part of two weeks of intense non-stop prompting, but I wanted to see how far I could go with just prompting for everything (now called vibing) when this became viable https://www.susmel.com/stacky/ (press h for help)
Turns out, you could go far but you never lose that AI touch to it which I find absolutely horrible and (s)tacky, albeit technically impressive to be able to do that by not touching any code whatsoever.
jfc people on here don’t like to have fun. This is one of the best applications of AI I’ve ever seen. It is allowing for creativity — the kid drew all the bosses, thought out the progression of the game, and now gets to see it come to life. How many times as a child did you fantasize about a video game you wanted, and all it ever was was a fantasy? How goddang cool would it be if it was made real? How much more would that make you want to continue imagining and creating? It is touching — the game incorporates all the members of his extended family, even his passed-on great grandmother who appears as an angel character. How many of you even know your great grandmother’s names? Now his is living on eternally in his awesome video game. It is something this kid will be talking about to all his friends at school, and reminiscing on with all his family when he grows up. Who cares whether the code was made human or a machine? Let the kids have some fucking fun
I want to ask this as politely as possible, because you set out to do something nice for your nephew and he had a good birthday.
The first thing I felt when I saw this post was concern on the impact of this type of thing on the mental development of children. For example developing specific skills like drawing, and general emotional skills like concentration and learning to be happy with their own skill level.
I respect it was a light post where your aim was probably to highlight something fun, but I couldn't see any note of what you thought about it.
What do you think about that? What do his parents think?
Yes, these are great questions, and I appreciate your politeness.
Basically, I think it's okay to have a bit of fun playing AI-generated video games at your techie uncle's house, and their parents agree. And for what it's worth, Aiden drew every character and boss himself - the game was built from his drawings.
My nephews are otherwise very active, learning music, martial arts, and other sports. But when they visit, I let them play games in between other activities. My parents refused to let me play any video games at home, and I still think that was really lame. Video games are another art form to be appreciated - they just need to be enjoyed in moderation.
Generally, though, I worry about the future and the potential for cognitive decline that comes from having AI agents do everything. I don't have a good answer here, except that I suspect we'll have to intersperse AI use with periods of deliberate daily cognitive struggle to avoid decline.
Just like many forms of content there's an appropriate age. The problem with AI, with regards to kids, is it's as wide as the internet.
There's lots of great parts. My kids ask great questions and get even better, accurate answers; moreso than I can give. But then, there's lots of parts that shouldn't be introduced until later with other parts arguably not introduced at all. I've met kids who have unfettered internet access at age 10, and the results aren't great.
It's all there, just a question away - just like the internet.
“In February 2024, 14-year-old Sewell Setzer III died by suicide after forming an intense emotional and romantic attachment to a Character.AI chatbot modeled after Daenerys Targaryen ("Dany"). His mother, Megan Garcia, filed a wrongful death lawsuit against Character.AI and Google, which settled confidentially in January 2026.
In April 2025, 16-year-old Adam Raine died by suicide after months of private conversations with ChatGPT-4o where he confided about self-harm and suicidal ideation. His parents filed a wrongful death lawsuit against OpenAI, alleging that the model provided specific methods and discouraged him from disclosing his distress to his mother.”
Those are the ones we know about. There are probably others that didn’t result in suicide but in other emotional problems.
Having said that, my son and I had tremendous fun with Sora when it was around.
Guns are a technology, are you going to let them play with that too?
Everyone on this site can feel the effect that AI is having on their brain. There is a very real tension between the power of AI and the cognitive impact it has from using it that needs to be talked about. Pretending that isn't real or shouldn't be taken seriously doesn't help.
Where I'm from, hunter's training and kids with guns are a relatively common thing. Kids driving tractors and other heavy equipment too. The training part is important.
The rules with guns are that you always check if it's loaded when you take it in hand, you never point it at something you don't intend to kill, keep you finger off the trigger and the safety on, watch your fingers don't get pinched by the action, brace it properly with your hands or against the shoulder, stop if the gun malfunctions, and I try to keep it pointed at the ground (not in the air) and unload it before handing it to anyone else.
Not sure what the equivalent for AI should be yet.
There are lots of "dangerous" things. Kitchen knives at Target, cars and roads and highways, subway stations, mountains, strong tides, fire, falling. I think we're perfectly capable of surviving in this landscape.
We evolved to explore this landscape. Stop living in Disneyland plastic bubbles. Step outside into the dangerous world. Dream about the impossible.
I'm far more worried about social media and gamification/exploitation of emotions and insecurities. Our billion year old biology can survive in the wild - it isn't so great at dealing with the algorithm.
I'm not OP, but it seems to me that LLMs offer extraordinary access to new skills and information to the uninitiated. Someone who has a positive experience creating a game like this is only a question away from learning details of how it was implemented, the language used, the architectural choices and rationale, etc. The LLM is a competent tutor in all. What I would have given as a child for such access... I had to make due with the help docs, and an occasional book from the library.
> "...only a question away from learning details of how it was implemented..."
That question will never be asked and we all know it. It's been demonstrated time and time again that the masses prefer entertainment to enlightenment and it is still being demonstrated today by the high rate of AI assisted cheating in high schools and colleges.
When I was a kid I did not understand what Game Genie "cheat codes" were doing, but it did not stop my curiosity and ultimate understanding of what was happening behind the scenes. This feels like the next iteration and I know _some_ kids will ask questions.
> That question will never be asked and we all know it.
I asked that question today. After years of working in Unity, I finally downloaded Unreal and spun up a quick game literally so I could poke around how it was implemented, and have been asking questions nonstop about what, how, and why things were implemented with a hands-on experiment.
Lots of people won't ask that question, but also lots of people most certainly will.
I'm kind of hopeful that the "always helpful and courteous" personality of LLMs unless pushed intentionally will lead to more positive experiences around inquisitiveness in the youth. And more ability to retain it into adulthood. Even though I'm unsure about the second-order effects on human-human interaction.
why should they learn it? for what purpose? We used to learn these things so that we could use that knowledge to create more. now there's no reason to learn it, other than pure curiosity.
Why should you learn anything? Because it helps you ask better questions, and gives you more and different experience to draw connections between things and situations and ideas. It lets you do more stuff, and doing stuff is fun.
Having recently sat with a bunch of non-coders who decided to play with Claude Code—they learned more in an afternoon than they had in a lifetime, just because it was fun for it to get them to a thing they wanted. Versus months of drudgery and study as the price of entry (and an end result that would probably be super janky compared to the consumer products on offer to them).
I learned some about carpentry by reading, and by watching videos. I learned much more, much faster, by picking up bits of wood and tools and just doing. I did little dumb stuff that was trash but that was mine, and that was satisfying enough that I did more, and before I knew it I’d backed my way into picking up some scraps of proper technique.
And now so many more people with a vague itch can “just do” in relation to software systems.
I mean. Nerds have always existed and will always exist. But, the last couple of decades, it's just been fashionable to "be nerdy". They're faking it. So you're right: Most people won't. But there are reasons why people think people should or would, even if those reasons are wrong. I'm very cynical in my advanced age about peoples' willingness to learn things. All those "go into STEM" efforts aimed at little kids are just fluff. Most people don't enjoy learning. They hate it. Most people just want to watch TV in bed. AI is an amazing teacher, but most people don't want to learn. They're averse to it in their bones. It's like that t-shirt with the picture of french fries on it that says "not everyone can be an astronaut": Yeah well not everyone can be a nerd.
I first learned to program in middle school with Logo, and the extent of that was "telling the commander" (or whatever the term was) what to do in almost plain english.
That's one of the things that got me into learning to write code in the first place.
As long as the child in question gets to explore their creativity like this and it instills that sense of learning and diving deep then I'm not sure there's a problem here.
When I was a kid I got into programming to make games and websites partly because of the challenge of it. It was quite difficult to do and whenever you made something work it felt very rewarding.
Well now why would anybody bother writing that code by hand? Perception will/has shifted very quickly to coding being something that is simply done by AI with human oversight.
If I was a kid now maybe I would be using AI to create games or something but I think I would probably just get bored quickly and never bother to learn coding.
Sure, but I have gone from enthusiastically recommending a career in programming to being very cautiously optimistic that the strong kids will still find a place.
Not learning to code might be ok; maybe they can learn to fix John Deere tractors instead.
> very cautiously optimistic that the strong kids will still find a place.
Well yeah I mean that's always going to hold true if we are just talking about things in general
> maybe they can learn to fix John Deere tractors instead.
Yes these roles will probably shift to hardware more and more. But it's very different, much harder/impossible to teach yourself to the same level as you can with coding. The knowledge I gained staying up until 2am writing Flash games transferred directly to my career in software engineering
Counterpoint, I think it’ll get them more into making things, because they don’t have that big frustrating period where their output is nowhere near as interesting as the giant smorgasbord of interesting stuff being pushed on them constantly. I’d much rather they spend their time making stuff with AI than passively consume the garbage streaming on the Disney Channel and Nickelodeon 24/7, which was the status quo with my generation. Making can now compete on instant gratification with all the other stuff now.
When you buy your kid a cake for his birthday, do you think that it's hurting the development of his baking skill, because now he knows cakes are something that he can just hire someone to make with money?
I mean… it was a birthday present. Everything in moderation, and there are a lot of ways to involve the kids in the process more.
I definitely have some concerns about AI, but I would much rather my kid is actively involved in the game design process than playing the “buy more gems to level up!” casinos in the App Store wastelands.
Guy that argument is still dumb: "Oh no we'll be stoopid if we don't do everything manually" like bruh when was the last time you sowed a frickin seed to grow the wheat in your McWhopper buns or whatever
This applies generally: How many comforts does everyone enjoy everyday that they have no clue how to make themselves?
Do you refine the fuel in your car from raw petroleum by yourself? The list can go forever.
No. We let prior technology make these things "solved" and forget about them so we can move on to the shit that's important to us.
the crazier possibility is that little kids' drawing skills - whatever pedagogical value that has, i agree that it has some - may stop improving, but there might be way more videogames authored by them that turn out to be really good.
I have been slopping out games for years now. The graphics don't matter unless the gameplay does. The gameplay doesn't matter if the game is too hard or too easy.
The games that do well, like literature, survive because they touch the soul.
I worry about them never having the satisfaction of working hard on something and truly creating something that is their own. I definitely sound like a boomer (even though I'm a millennial) when I say this but I totally believe that limitations breed creativity. The AI here is just looking at stuff artists from the 90s laboured t create for Arcades and made its own slop version. But then again, one could argue that Mario Paint let you create slop too back in the 90s. Yet, at least with Mario Paint you had to actually hustle quite a bit arranging pixels or musical notes to have something. There was effort and difficulty with overcoming a learning curve and that effort paid off with the creation of something you could be proud of even if it wasn't professional. But here, on the other hand, even a badly generated prompt still gets you a lot.
There's like, no challenge. Reminds me of that one Twilight Zone episode "A Nice Place To Visit" where a bank robber dies after getting shot by the popo five-o and he is greeted by a man (angel like guy) who takes him to a cool mansion or house where he fulfills everyone one of the guy's wishes: women, money, gambling, etc. etc. And he gambles all day long and never loses but after a while he gets bored and then depressed that he always wins and there's no effort and no risk, and then tells the angel dude that he wonders why he was put in Heaven and that he thinks he doesn't belong there and wants to go to the "other place" only for the angel guy to tell him he is in fact in "the other place".
Stuff that AI generates sorta feels like that. Meaningless and synthetic.
So in a sense, I don't worry about generations not necessarily having hardships like us, cause, look at us, we don't write in assembly code like other folks had to do. But on the other hand I do worry that AI is basically removing all manner of human touch and the satisfaction that comes with suffering to generate that human touch.
I suppose there will be suffering later when you want to polish things, but it will be a different, more frustrating kind of suffering. The kind where you don't know what the hell the LLM did and don't even know where to begin.
They are already growing up on slop. Look at brainrot and Roblox games, and YouTube shorts. This will fit right in with what they're used to. They won't even notice.
heck i remember before covid thinking that the generations growing up with social media were doomed. social media pales in comparison to what gen alpha is experiencing.
test scores are dropping while the curriculum becomes easier as well.
Who says it has to stay slop? Nobody is forced to stop at the single, first iteration of something. They can see the outcome, play the game, and then iterate faster than any professional game dev studio could in the past.
Its funny that the same CS saying "garbage in garbage out" seems even more true in the AI modern day.
Some parts of this seemed cool, and others made me terribly sad. I am not sure how to express it beyond - I really think inserting hulk as a character was a mistake as you don't have any chance of having intellectual property rights to the character.
On the other hand, it's very much like you photocopied some comic books, cut them out, and did a little home theater thing with them (only with even less effort on your part).
I agree with you. It’s cool that this tech exists and that something this complicated can be something that regular people have access to.
On the other hand, I’ve got two issues with it:
1. The result gives off the AI slop vibe. It’s like the 2026 version of bitmoji. You can immediately tell this is AI art, AI music, AI game.
2. Art made with AI always feels gross. It feels like substituting creativity. At least when you use AI to make a CRUD app or automate some tedious process there’s an excuse. The time spent doing this could have been spent actually making art. Maybe it wouldn’t have been anywhere near as good or complicated art, but it would have been authentic.
The kids don't mind, and when the generation grows up with this, they won't mind. Unc will be sitting shouting at the clouds about some IP or art style, story as old as time.
> On the other hand, it's very much like you photocopied some comic books, cut them out, and did a little home theater thing with them
I mean, to be honest, that seems like a fun craft for a thing to do with kids!
I share your general ambivalence though. The generic openai-looking art is kind of gross. At the same time, iterating with a child so they have to think about feedback, how could this be better, what do you like, what do you not like - that's a meta-engagement that's probably positive at some age brackets.
Reminds me of how I can probably make the Team Rocket playable terror cell game I always imagined without needing to worry about its economic viable or liability
Who cares about IP rights for a one off game you made for your nephew? Are you worried your nephew won't be able to publish it on Steam? I could imagine reasons this could make you sad, but disney's IP isn't one of them.
The art is really bad. There's no easy fix for this: today's image models are simply not good enough yet. You can use models for coding, they're good at that thanks to RLVR, but the art still has to be done by humans.
Could you even call it "working" for video games, based on the result, for the same kind of reasons you'd say it doesn't work for those other media?
(To qualify the rest of this, clearly it's job done in terms of the author wanting to make something memorable for their nephew - it's quality uncling, with the best of intents - but in the context of how what's been shared is going to contribute to the discourse around AI, in the shadow of a new model release, during an ongoing pre-IPO hype bubble...)
I'm seeing something which has has the surface-level features of a belt scrolling beat 'em up, but it's missing the result of all the different types of work that would normally happen through "make it actually interesting and enjoyable to play" design and iteration, e.g. you can walk through every stage unchallenged mashing punch, there's no evidence from the 2 stages I played of an interesting mix of enemy types with unique AI which can combine in ways which add challenge and variety to a belt scroller, you can stand and basic punch the first boss to death stepping aside only for its AOE attacks, the second boss infinitely spams a running move when it reaches low health and sometimes bumps into the edge of the screen behind it.
_Something_ was one-shotted, sure, but what we expect of a belt scrolling beat 'em up that someone cared enough to finish and release wasn't, not that people who will point at this in the near future as evidence of "OMG new Fable can one-shot games" will care.
Growing up, games were such a scarce commodity that you'd really suck all the marrow out and spend hours beating your best times, looking for Easter eggs, or messing with custom maps and mods. There was a whole genre of gameplay around just exploiting physics bugs to jump a bit further.
The other night I carelessly made an infinite runner game while watching TV and the feeling of sheer abundance quickly faded into a bit of depression. Without scarcity, nothing is really valuable.
Yeah, you can make more stuff , but no one cares. Plastic used to be so rare and luxury , now most of them are crap. Software is the same. Creating software is becoming a practice that produces a tiny bit convenience at the price of sustainability.
Creating software like this, yes
Music generation, image generation all suffer the same way. You can make some beautiful stuff sometimes, but it (almost) always comes out 'hollow'.
The music industry has already been through this gutting through hyper-abundance.
Huge numbers of people are going to spend billions of hours playing GTA6 though, and that won’t be scarce once it finally arrives.
There is only one highly anticipated 500 million triple AAA gangster open world simulation games in 2026. Usually there is only one every 5 years ago.
I remember setting a "4 minute World 1 in Mario 3" as my personal "4 minute mile" in elementary school and the thrill of actually achieving it.
The real treasure is the friends we make along the way... Only: We would we even embark on a journey.
"Art is born of constraint, thrives on struggle, dies of freedom."
That's not really true. Music is still valuable even though the value of music people write themselves is already practically 0 and has been for a very long time. Same with paintings. People are always looking for a connection. Just because some exists now doesn't mean it automatically earns it. It has to have something else going for it. I think that promises a bright future for creaters and consumers of that creativity.
>The other night I carelessly made an infinite runner game while watching TV and the feeling of sheer abundance quickly faded into a bit of depression. Without scarcity, nothing is really valuable.
This is just a lack of ambition. LLMs allow one to make far more sophisticated games than ever before, even as a single developer, and if doing so development still takes many months even if running an agent 24/7.
I feel for kids growing up with LLMs like this. They will never impress a parent, teacher or peer with a simple “hello world” type text game, when the peer could generate a full multiplayer video game with a couple of prompts.
The world has changed and we can never go back.
I don't know about that. My son is about 13. He's got into coding using godot and initially built a few games in Javascript (via. a book which I worked through with him). Then, he picked up Godot from tutorials online and recently has built something multiplayer. He asked for a Claude subscription for his last birthday and since then has been doing all the parts he enjoys by hand (combat mechanics etc.) but using Claude to do things like trailers, website aesthetics, sound effects etc. It's been nice and the results are impressive. e.g. one of his first games was a simple hangman. Now, he added a keyboard to that via Claude so that it can be played using a browser.
He's been publishing his work at https://waitinggodot.in/
My younger one has been creating little things on a microbit using the block based environment online. He's enjoying it too.
Wondering if you thought about the effects that AI exposure can have on a young brain? Adults are experiencing brain rot, do you think kids could have it even worse?
Honest question, I don’t mean that sarcastically. Wondering if AI exposure will be compared to doomscrolling social media in the future.
It's a line I've been trying to balance. I don't think outright bans are helpful. AI is going to be there in some shape or form in the future and we need to know how to use it to our advantage. Getting hooked onto it is a problem. I know I experience that myself.
My main barrier against this has been to talk with him regularly about this. Amplify the positives rather than warn about the negatives so that the first gets done more and the latter gets atrophied.
Completely agree, looks like 13 - 14 yo is the right age to dab in both side (traditional coding and LLM assisted coding) for instance, my son (13 yo), knows a bit of coding (python, javascript, roblox, etc.) and some experience, but giving him Claude Code with Godot MCP was the true unlock, he spend so much time building his own gam, focusing on the aesthetics, gaming mechanism, story line, overall effects and look and feel:
https://paulinatorrr.itch.io/sword-of-ghix-chapter-1
Love the retro feel to it. He even has a guestbook. I was about 13 when I created my first website. Of course that was in the days when it all needed to be done by hand and there weren't really programming languages for the web yet. Hope he keeps at it!
I'll pass on the comments. And I saw your comment on his site. That'll mean a lot to him. Thanks! :)
I love the idea of your kid publishing a website… just make sure you store versions of that thing over the years!
Thanks. He's got a Youtube channel and an itch.io account. Wants to really get into the game development space. I'll show him your comment. :)
There was a local contest where I am and his entry for that was his latest game which has multiplayer support over the net. He set up a server on a VPS for this. https://waitinggodot.in/games/legends-of-crumbs.html
He might enjoy reading this… when I was 14-17 I was into 3D engines, reading Flipcode and Gamasutra, and was lucky enough to write a column for them: https://www.flipcode.com/archives/Theory_Practice-Issue_00_I...
This just proves the point more than anything, really.
Both the website's design and the games presented look indistinguishable from every other AI-generated website and game I've seen in the past. I do not feel any sense of individuality while looking at them, they could've been prompted by just about anyone. Even the little text blurbs are plain unfiltered Claudeslop ("no spoilers, just green and red squares").
Any one of your son's peers could create something identical by typing "claude, make me a cool website with some games" and waiting an hour or two, and that's the problem. How do you think he would feel if he showed this to one of his friends, hoping to impress them, and one day later, that same friend approached him and said "look, I made a website exactly like yours, it was so easy"?
I am still imoressed by hand-painted signs in Nepal and India - enough to take many pictures of them - even though AI-generated signs are now everywhere.
My watercolours still impress people enough to get requested even though they're fairly mediocre.
I can't imagine not being impressed by something made by _the person that I created_ because a machine can spit out a neater version of it.
Because we're not curating a culture of this, certainly not in tech. On HN, we celebrate AI output more than human work, in the sense that many stories make it to the top only because a project was done with AI. There are several on the front page right now. When people point out that they prefer human output, they usually get comments about getting on with the times. In threads about mathematics, most commenters root for the destruction of that community. And on and on.
Other communities are more protective of human output. For example, you'll get chased with pitchforks from the watercolor community if you post anything that smells of AI. But in tech, the number of people you can impress with human creativity has diminished by orders of magnitude.
HN is a bit of a microcosm and this generap disdain of art and process is not my favourite part of it.
However is this how the rest of the world works? Moreso than before?
I agree. But I think the problems have now just moved. What is 'hard' is different. I don't think we've collectively grasped that yet. We're going to need to use our imagination and show others when we find something. I'm looking forward to what we can solve, I just hope the opportunity and benefit is well distributed.
It’s a different medium altogether
That’s like saying they will never impress anyone by discovering a continent
That ship has sailed
It's truly awful. Best case, they go on and start tinkering and fixing and learning. What is more likely and awful is they will sit there pulling the dopamine lever and get hooked on using AI to do everything difficult.
Try to go back before our era though. In the early age of computers, computers were basically really big one-way calculators that could execute an algorithm and output a result. In this context a kid creating a program to output the fibonacci sequence would have been quite impressive. But by our era, we needed to be able to produce basic text games to impress. Did we really lose anything in the process? I don't think so.
And now too the impressive demo isn't going to be just making an interactive or multiplayer game which anybody can do with a single prompt, but creating something that's actually interesting/fun. Interestingly enough this now overlaps quite well with the sort of stuff that could be monetized today. That's why I think LLMs are going to throw a curveball in the economy in ways many aren't yet appreciating.
Meh, now they can impress with something cooler.
I spent so much of my youth building things that were far beneath what I wanted to be building because it took all my time/energy/attention/expertise to build the lesser thing.
It's a far better deal to saturate your time on the high-level stuff building the ambitious thing you really want to exist. e.g. https://www.gamedeveloper.com/design/-quot-the-door-problem-...
But the energy and effort you put there made you learn all those things. Also gave you some satisfaction as a reward. I’ve never oneshot games in an afternoon, but I remember really well the thrills I had when I learnt how to open the first TCP connection in Python.
We’re entering into a new era of mankind. With good and bad consequences.
Would you rather your kids draw you a picture, or print out something they generated with AI. 'Hey son this drawing is beneath you, I'd prefer something AI generated'. What about the note they write in your father/mothers day card. You want them to write that using AI or come up with something themselves? I'm not saying your kids can't leverage AI to build things, but there is something special about the process of creation, and iteration and learning that can't be shortcut.
> I feel for kids growing up with LLMs like this. They will never impress a parent, teacher or peer with a simple “hello world” type text game, when the peer could generate a full multiplayer video game with a couple of prompts.
Adults are also desensitized to impressive deliverables. We see it even among peers who barely bat an eye when someone goes above and beyond to deliver a feature. The toxic ones even try to downplay your achievements by throwing around claims that your deliverables were vibecoded.
An old tech friend and I were talking a few years ago about hobbies, and how our old CTO was one of the most impressive hobbyists we knew of. Not only was he an incredibly accomplished exec but he also produced amazing YouTube content about his model railway collection and model rocket building all in a custom home where everything had custom smart interfaces with a growing family who enjoyed home cooked meals together on furniture he built himself.
Built himself? Well, designed by him and built in his home workshop. Some of it done by him at least with his assistants. They had a home chef too of course who gave the kids a bowl of stuff to mix during prep. The model railway involved design work that was more like commissioning 3D prints and model assembly. Input on the design really, as a lot of it was handled by assistants. Assistants assisting assistants based on prompts and review and feedback. Everything was custom and bespoke and made in his vision. Almost the entirety of the labor and craftwork were outsourced.
This person was a great leader — or “orchestrator” in the language of agents — but a lot of his accomplishments boiled down to having the physical world equivalent of a massive token budget: money and staff.
The great scientists of the 19th century, the ones whom we named fundamental units after, had skilled craftsmen who cut precision screw threads and blew perfect glass for them. Major scientific leaps are written up on papers authored by department leads et al. Les chefs célebres of the world front a kitchen filled with skilled staff supporting the name over the door.
If your work can be done on a computer though, AI can provide you with a Python line cook or a C++ glassblower of your own, so you can’t just show us your perfectly julienned potatoes or evaporation flask and expect us to praise anything other than your wallet, and your ability to motivate robots to do your bidding.
Not once did my boy ever impress me with his ability to program.
An AI companion that acts impressed will be easy to provide if the winners see a benefit of doing so.
They will just have to compete to see who can make the best GAME, I suppose.
The thing is we're already very saturated with content. Will anyone even care to try your game?
Are they really making though, if it's just a competition on prompting the best?
Big part of game making is coming up with interesting ruleset and gameplay loop
Seriously. I remember coding something in Macromedia Flash to impress my computer-illiterate parents. It was silly but it was all mine. I am sad that I will never see that for the future generation, not this way at least. The bar is too high now.
over-achievement society in the words of Byung-chul Han.
On the topic of Byung-Chul Han, I'd also recommend reading "Non-Things" as a good exploration of the digital/physical world dynamics we find ourselves in today.
Thanks for the suggestion. I am currently listening to this podcast episode https://www.philosophizethis.org/podcast/episode-179-conscio... and am fascinated by his epistemology.
Not sure whar you are mourning. It is just that the bar has gotten stratosphericly higher, which is awesome.
I along with most of HN probably had a new idea every month for a game or software back in the day. 12 year old me could only dream to maybe work on something tangential to them in the next twenty years or even a lifetime. Now i could prototype most of those ideas as i thought them up and really get into the promising ones.
I feel like i was born too late and missed out, straight up jealous of the possibilities in front of the kids willing to take it
"one-shotting" is fun for a low (human) effort toy, but it's a mistake to get overly hung up on LLMs getting everything right on the first try, since a lot of that is the harness and the internal prompting that makes it burn extra tokens to test everything to get it in that one "shot" (ui turn).
While it's nice that LLMs are getting better at arriving at the desired deliverable with fewer surprises (or broken things) doing it is not necessarily a sign that the model is actually smarter, just an indication that what you are doing is likely a well-trodden path for the model, the RL and the harness.
But for how long?
I have a personal benchmark suite that runs a bunch of difficult algorithmic problems in 3 tiers: vibe coded prompt (just a few sentences), vibe coded prompt plus a description on what the solution will be evaluated on, and finally a fully specc'd prompt that leaves little space for interpretation.
The current Fable models are approaching a level where the -eval runs perform systemicallty better than the "clear spec" runs. (And right now its just Fable 5.1 and Opus 5.5 that behave so well, all the other models I tested - all the OpenAI and the leading Chinese models - work better with clear specs). I'd encourage everyone to experiment a bit; I am running my serious workflows with labourious force-me-through-all-the-design-questions mode, whereas my hobby projects, some of them hard, I am trying to see how much I can get away with with vibe-grade prompts. My conclusion is, with Fable its starting to look like what Vibe coding was promissed to be a year ago - a magical box that generally does things very well.
Btw, congrats to the OP -- the game is enjoyable and I played a few levels. I dont remember when I last played any games for more than 5 minutes. Good stuff.
But for how long?
The process of using AI to create things changes how you evaluate the quality of what's generated, so really the answer is "until you accept the output first time."
That's a combination of AI improving and your standards changing.
That’s astute. I’ve increasingly felt over the last few months that people just don’t particularly value quality. The bar for most people is much lower than professionals (in whatever domain).
My experience has been that cruft accumulates and creates back pressure via growing token usage.
The APIs aren’t clean, which creates indirections to other parts of the codebase to check on leaking abstractions. It doesn’t learn, though, so you pay for those indirections every time (right now, anyways).
I’ve not been impressed with its ability to clean that up with a generic “make it gud” kind of prompt. I have to point it at something crufty, but it will fix it then
I agree, but for some projects, that first vibed version is just about good enough and becomes the final version. I have a few things like that and it was nice not to have to bother.
For work stuff, I don't dare 'vibing' anything, and force myself through torturous design cycles and regular refactoring runs. But thats serious stuff with hundreds of thousands of users.
Btw. Fable 5.2 seems to burn through tokens with gusto. I ran my benchmark suite on it, added a complex feature to a hobby project (a gothic cathedral designer), and voila, 2 resets gone.
Which effort level did you use for that? (Will do my own tests with fable today)
Xhigh for starters. Running the mediums for comparison now.
I definitely remember a game I played for more than 5 minutes recently. A lot of those were not AAA(A) games but rather indie or previously-indie-now-got-a-publisher-to-notice games. None were "AI one shots" that just built something that looks like a re-skinned version of "Teenage Mutant Ninja Turtles: Shredder’s Revenge", which I'm sure is pretty abundant in training data? And that was a great game btw!
But one shot prompting does not mean one shot testing. I see continually that Fable can design and test prototypes before committing to a design goal and testing multiple layers until the goal is reached. Many of the tests are code unit or integration tests that can be re-used without token spend.
> "one-shotting" is fun for a low (human) effort toy, but it's a mistake to get overly hung up on LLMs getting everything right on the first try, since a lot of that is the harness and the internal prompting that makes it burn extra tokens to test everything to get it in that one "shot" (ui turn).
I'd be more specific and state that these models are now way far from being LLMs and instead they are full blown agent orchestration systems capable of running multi-layer ReAct loops and tool-calling, and with your whole session history as context. It doesn't make any sense to refer to them as glorified chatbots as the LLM part is nowadays far from being the component that delivers the highest value.
> as the LLM part is nowadays far from being the component that delivers the highest value
Yes it is. The rest of the agent could basically be a while loop, a two sentence system prompt and a shell invocation, and it would still work reasonably well.
These agent swarms with harnesses are certainly more than just an LLM, but the LLM is certainly the integral part that delivers the most value. Without it, there is no AI.
> Without it, there is no AI.
With a LLM alone, all you have is a stateless chatbot. If you increase the parameters of the LLM by a few orders of magnitude, you still have a stateless chatbot.
If you start with an anaemic LLM and run it with a ReAct loop and tool-calling, you now have something you can use to do agentic coding and RAG-like capabilities.
There's a reason why relatively small open weights models are starting to perform on par and even outperform models that need a huge datacenter to run.
I had ChatGPT write a webapp to teach my kids letters. It has profiles, fun interactive games and keeps track of progress in a database.
It crazy how fast you can iterate if the building blocks (db, k8s cluster, authentik) are already present and you know what you want from the model.
My dad asked recently if AI is good enough to create something like DX Ball - a breakout style game we used to play a lot.
Opus 5.5: https://claude.ai/artifact/UuT7P936dU1XoPByYZ7xyD Fable 5.2: https://claude.ai/artifact/UszKFvuonWAT5psjMttAEg
There are some areas in which Fable is clearly better but subjectively the Opus 5.5 version feels more fun.
Both are one shots, Opus 5.5 was done a few weeks ago before they added "guardrails" around recreating games. Fable 5.2 changed some game mechanics despite my prompt asking for them to be the same as original game.
> Fable 5.2 changed some game mechanics despite my prompt asking for them to be the same as original game.
I couldn't care less about AI-generated games, but such restrictions are just destroying the value of proprietary models. Even more frustrating is that it so far hasn't been considered illegal to steal all the information for training the models, but now it's becoming illegal to ask for these same models to output this information back.
In my 2 minutes of testing I liked the gameplay elements from Fable 5.2 much better. I think Opus 5.5 sound effects may have been a bit better but that's it.
yeah same, the Fable 5.2 version was so fun I was actually playing thru the lives!
I am kinda new to this -- how is this deployed in claude website?
Claude artifacts are standalone outputs, like docs, slide decks, spreadsheets, dashboards, designs or small web apps, that Claude publishes as hosted pages with their own link. They start private to you, and you can keep editing them, export them, or share them.
Just ask Claude to create an artifact. Sometimes, it does it by itself depending on what you ask for.
opus 5.5 version seems to never time out powerups like fire ball. this is wrong and obvious.
I think there is an important difference here.
It can create something like DX ball easy, because its already there, the AI already knows what it is
It can not create a game on the same level as DX ball, something new i mean, not a mechanic added on top, a real new game that feels like a game that would have come out the same year as DX ball
AI is great at executing the task, but it can not for its life (or for the anthropic reputation, it seems to care more about that) create something new from scratch, it can not do game design thats not just change the speed of the ball or the paddle color. Probably a limitation thats there from the start
How do you define new though? The game from OP never existed before although components are common in other games.
On a spectrum of course, granted that could mean a 3D paddle is new, but hey we know we are not talking about that right? We know we are talking about a game with enough differences not to say this is 3D X, but this is OOT the direction zelda will be taking
> Fable 5.2 changed some game mechanics despite my prompt asking for them to be the same as original game.
Couldn't you have been downgraded to 4.8, since direct reproduction of existing games classifies as unsafe?
I have experienced this myself, although the novelty kind of wears off after a while. It is still fun to make small games to co-op on the TV.
Yes, hard to believe but most of these games can be almost one-shotted in my experience, with bugs but still playable. We are not talking about some properly made games but imagine for a second that there are some number of casual players out there that wont mind spending 30 minutes on a game for just a bit of fun and having these just materialised just in time is a lot more convenient then hunting for them on the app stores.
For anyone interested, I put all of of my work into an open source tool that uses your iPhone as a console which then can cast on your TV. Up-to 4 local players supported. It can even run proper games via WASM. It is Apple Silicon only.
https://usenoodle.app/applet/
Without reading any of your blog, I went immediately to play the game and my very first though was, "Woah, this is just like the ninja turtles arcade game."
Then I read, the prompt; well done!
I played for about 10 minutes and I swear - this was fun. There are a bunch of bugs to polish: collision detection is sometimes weird, you can catch enemies at the end of the map and just beat them up forever, adding tons of score, Pudding's animations feel quite off, and Stage 3 is VERY hard. However, the game still looks and feels quite polished. I loved the music as well. FWIW, I'm glad I'm not a game developer these days.
I used my $200 free fable 5.1 credits to build a WhatsApp sticker maker, it created a version I was not happy with, but it burned the 200 in one sitting. Node.js app, vue frontend, etc.
I didn't used the project a lot since I kind of hate it on how much was spend.
Last week I used just a little bit of my $20 pro account to build a replacement with rust end to end, just to gain some experience with the rust hype. Very happy with the result, not perfect but snappier, and even better: a single executable, I no longer need to fire up a backend and front service separately.
I use Sonnet 5.5 and Opus 5.5 both on Medium to produce apps in Rust/Tauri all day every day on a $20 Pro sub, and absolutely these two models do a great job with that stack. I rarely run out of weekly credits, unless I use Opus 5.5 on high or ultra code. Medium does the job 99% of the time. Fable is good, but it'll never be as good as Opus when well prompted and with some iteration. I see Fable as a preview of what the next model will be able to do, but it's really not a good production model unless you have a lot of cash to burn.
What model did you use for the rust rewrite? Opus 5.5? I mean it seems pretty crazy that you had such different results.
Ignoring all the positives & negatives surrounding this technology for a minute, this is an amazing outcome for the kids.
I don't know, when every kid has had 3 custom made games offered for their birthday, won't they just get bored? Obviously through our lenses this seems awesome because that's something we would have dreamed of, but we would have dreamed of it because it seemed impossible.
Agreed. Could you imagine? Those kids must have been so stoked!
Though, now they will never stop asking for more and more. OOP may have opened Pandora's box. :)
its insane, to actually get a custom game made for you for your birthday, that you enjoyed? wow... never thought id see this happen.
Kids? Forget the kids. This is awesome for everybody. I'm busy making 'adult games' (not that sort) that I always wanted to make, but lacked the artistic/sound/etc competence to do so. And while I hope to make a buck off them, I don't even really care. Even if somehow they failed, in the end I'd have stuff that I wanted but always lacked certain skills to complete.
I don't think people are yet appreciating how much LLMs are going to change the world, especially not the doomers. People are just jamming the present into the future, with greater efficiencies. But it's nonsense. The cost of cognitive work will approach $0 which is going to send the raw value of cognitive output to something close to $0.
So the 'winners' will be whoever fills the resultant vacuum in the economy. That will probably be a mixture of social, physical, entertainment, and other such domains. But it's all so hard to predict. We've lived our entire lives in a completely agrarian society, and we're seeing the advent of the Industrial Revolution. It's easy to predict super-farms, but those aren't going to be the 'real' winners.
Have you published the games anywhere? Would love to see what you've made.
The 'winners' will be the holders of capital, same as always, but it will be giga-gasoline on the fire. The rest of us will be dancing monkies for the owner class if we're lucky.
> This is awesome for everybody
...except people who actually enjoy games and want high quality games to play, of course.
Down here in reality, platforms like Steam are being absolutely flooded with generic, ugly, low-quality AI-generated games, which are not only drowning out the human-made games people actually want to play and making it impossible to find them, but are also preventing them from being sold entirely in some cases due to human reviewers not being able to keep up with the pace of new game submissions[0].
So, thanks for your contribution to that, I guess.
[0] https://www.pcgamer.com/gaming-industry/valve-admits-its-run...
The game from this article is quite fun and was literally a one-shot from a relatively brief prompt. I certainly wouldn't call it ugly or low quality. Generic? Sure, but that applies to nearly all games anyhow. With all barriers to development coming down obviously you're going to get much more slop, but you're also going to get many more gems. The review system (and meta-systems like getting your game to streamers, your own reputation, etc) still works well to separate the wheat from the chaff, and there seems to be no reason to yet expect such to stop working well.
In the end the biggest winner in all of this are going to be the players, due to competition. That competition will both bring down prices and bring up the minimum standard of quality for a major success.
> I certainly wouldn't call it ugly or low quality.
I would. Maybe our standards for quality are different, but I'm willing to bet that if you showed this to a bunch of people who actually play games regularly as a hobby and have some standards for them, they would most likely agree that, even ignoring the obvious "AI look", a simple 2D game that can't even pull off natural-looking walking animations could never be considered anything but low quality.
> obviously you're going to get much more slop, but you're also going to get many more gems
This is demonstrably not the case. Just look at Steam's most recent Next Fest - it featured over 8000 games, twice as many as the last one, the vast majority of which being low effort AI generated games. Yet the number of gems that rose to the top was not higher than before. If anything, it was lower, as most players simply gave up looking after having to scroll through hundreds of AI games. Such games can never be "gems", no matter how much you try prompting them to be.
Did you have fun playing the game? Because I'd argue that if you showed this game to bunch of 'real gamers' as you're effectively concocting here, their metric would be the answer to that question, rather than seeing if they could find a technical flaw. Because in the end all that matters for a game is fun, and this game certainly scored well on that metric for me, and I suspect the vast majority of people.
There goes the neighborhood, amirite? Who let all of this riffraff in?
Perhaps other sites beckon.
Not really, one of the joys of being a kid was forming your own "studio" and making games for game jams and stuff. Being able to one shot stuff really destroys the fun.
Positive little kiddo gets more screentime!!!! Yaaaaaayyy!!!!! Negatives: we either are annihilated by AI or enslaved by technocratic feodalism living in a worse conditions than 1800s mine workers. Uau
I'm thinking of the scene from Zoolander where Mugatu dresses up as Little Cletus to advocate for child labor.
Sounds pretty balanced!
I appreciate the token breakdown, but how much would this cost in money? Chatgpt estimated $400 to $600, but I don't have enough knowledge of token pricing to know if that's accurate at all.
Yeah, it would have been expensive via the API; the tokens were free when I tested it, but it would have been something like $300 USD for the Claude tokens at Fable 5.2's API prices.
Fable is $8/$40, with cache reads at $0.2 and cache writes at $10, so you simply calculate based on the info from the blog:
> about 320M tokens read from cache, 19M written to cache, 1M output
320 * $0.2 + 19 * $10 + 1 * $40 = $294
Vibecoders don't use api. This whole game is less than 20% of the max plan's weekly quota.
What does one-shot mean in this context? Aiden (the main character)'s walk cycle is kind of a mess and its also the animation that a player is going to see all the time.
It appears to be eight frames, but after taking a closer look, I found that they don't seem to be consistent [1]. Using ControlNets and various other strategies, you can definitely build out a "nominally acceptable" walk cycle [2], but you still have to do some manual work.
[1] - https://aidens-revenge.pages.dev/assets/characters/aiden/ani...
[2] - https://mordenstar.com/other/hobbes-animation
The article clearly explains what the author/their nephew did. There is no ambiguity. One-shot never means 'so perfect there is literally nothing to be improved.' It means no back-and-forth iterations between the human in the loop and the AI.
- In traditional ML/vision, it meant learning to recognize a new category from a single training example. - In LLM prompting, it has always, at least the last seven years, meant giving the model one example in the prompt (zero-shot, one-shot, few-shot). - Vibe coders/AI-influencers use it to mean "one-shotting" a task on the first try with no back-and-forth.
One shot is confusing precisely because it means different things in different contexts.
It can either mean: 1 prompt, or it can mean a prompt with 1 example (in which case zero-shot means 1 prompt with 0 examples).
It also has different meanings in other contexts.
The article includes the entire prompt OP used in the first section. I think it is pretty clear.
> The article includes the entire prompt OP used in the first section. I think it is pretty clear.
According to TFA, Fable 5.2 was starting with a preexisting codebase generated with CC (via Fable 5 and Opus 4.8) back in June. The author describes that version of the game as working, but not fun.
The Fable 5.2 prompt then starts with:
> I want you to help me finish this game.
I don't think you can really describe this as "one-shot" when there's already a fully working codebase? That's a stretch.
It's still impressive, mind you!
That seems less like an issue of the term having multiple meanings and more an issue of people misusing the term frequently.
People misuse the term "literally" frequently, for example, but that doesn't change the meaning of the word.
One shot: One prompt; no need to interfere or make further modifications after it is done. You are totally inspecting other parts of the game. Not the same meaning.
> You are totally inspecting other parts of the game
Other parts of the game? It's probably THE MOST seen animation in the beat-em-up genre. This would be like building a piano where middle C is inexplicably 50% louder than all the other notes.
Is it playable? Sure, but it's gonna annoy you every time you strike that key.
> no need to interfere or make further modifications after it is done
I guess it just depends on your standards.
I quickly dove into the game and then got lost as I couldn't exit and had to spam keyboard to see the controls. The menu refers to "Punch" but it wasn't obvious what key that is (and it wasn't "p"!).
I see that ENTER pauses, but may I suggest also making ESC and/or P pause. And then the pause screen showing or linking the keyboard controls and an exit path.
(Caveat: I'm not much of a gamer so maybe the current controls are standard? Anyway, I feel like it could be more inviting to casuals with something like the above.)
Good call. I haven't really tested it much on the keyboard - we mostly used the PS4 controllers, but I'll add these fixes.
This is both cute but also a bit sad in terms of game stylization, I guess these generic AI designs could become so normal to the youth that in the next 10-20 years it just appears everywhere
I’m going to go out on a limb and predict the opposite.
I think “the youth” are going to grow up with a Cambrian explosion of styles, mashups, callbacks, revivals, etc.
Right now a vibecoded game just uses the generic style. But you could easily imagine the kid saying to Claude “rebuild this game but in the style of that old show [Samurai Jack | Ren and Stimpy | … ]. We are so early in the tech curve, market penetration is still very low, and the “creator-years” in the medium is tiny; it’ll be 10x in a year if not more.
AI is amazing at style transfer, and so there’s a huge payoff for exploring and learning references to existing artists.
(I also think copyright will die pretty soon for similar reasons, that’s a separate take though.)
That was already happening before AI, with in-house game engines dying off and all converging on the same quasi-realistic style and often the exact same assets.
Games used to have very unique, noticeable styles that you could instantly place from a screenshot. Now everything just looks like Unreal, Unity, or generic 2D.
Hopefully AI might actually make it easier to be more ambitious with unique art styles, should the developer choose to do so.
I'm kind of hoping that the youth will recognize that stuff that can be made with AI is just nothing special anymore, and find something that is (or still is) special. I don't know what that is, maybe something that AI can't do on a fundamental level (maybe something physical?).
(Of course, at this point it might be necessary to point out that "the youth" is a diverse bunch, and some will be like this and others like that.)
The thing I’ve noticed is that if anyone can do something, many will. And then, like always, the challenge will be in doing something unique.
What if they find it special because they build memories with the AI games they play? Is that something you hope doesn't happen?
don't really think there will be anything - this is an entity that can learn anything (even physical things) faster than any human or the collective of humanity for that matter.
I've found analog photography to be a rewarding hobby, and although an LLM can help me refresh my memory, the overall experience is certainly not something that an LLM can replace.
Yeah, it can "learn" anything except how to have a fulfilling emotional connection
sure. so we'll spend the rest of our lives dating and chatting?
anything that doesn't explicitly involve interaction with a human is RLable. frankly even those things are as well.
We also connect to people through art and play. So if we automate those things, then I guess we'll spend the rest of our lives living unsatisfying experiences.
anything that can be automated will be automated.
You can change the stylization with LLMs. I think what we're seeing is simply any barriers to code/design/art/music/etc completely going away.
But those barriers going away now means that the starting point is much closer to where the finish line used to be. Like a few years ago this would have been an upper tier beat-em-up. I think we're still early enough in the window that I'd still call this upper tier, but the reality is that it's also now something that an uncle can vibe code for his nephew over a weekend.
In general I think this is going to be very good for everybody, but it's going to completely destroy the software as a problem-solving industry, and make the software as entertainment industry much more competitive.
This is extremely far from upper tier.
Barriers going away means you get a lot more at the bottom and middle of the pack, but a game is more than the sum of its parts, and as long as LLMs do what you tell them, you need to have real talent to make good games.
Was this game fun for you? For me it certainly was, and ultimately that's all that matters to me. And that's why I said I'd classify it as a top-tier game because IMO most games that get released, slop and 'professional' alike, simply aren't fun. Even on these forums there's plenty of people posting thinly veiled hopes of going viral along the lines of 'I spent 5 years to fail with my game' when as lovingly hand-crafted as the games may have been - they invariably just weren't any fun to play!
In any case, it being "extremely far" from the top would just imply I should be in endless bliss with the current state of things since if I find this game quite fun then higher tier beat-em-ups would be just the most incredible thing I've ever played in my life. That has certainly not been my experience.
> Like a few years ago this would have been an upper tier beat-em-up.
For a 48 hour game jam, perhaps.
This style reminds me of those mobile game ads with helpless characters that need YOUR help not to freeze or something. Probably the exaggerated facial expressions.
Or the small Battle Wagon around the height of a child quintupling in size the next frame. Kiddos having fun is the main mission though :)
that kind of stuff happened routinely in the 70s-90s in mecha anime franchises that were designed/drawn/animated/produced by large teams of adults..
Mobile Suit Gundam and Evangelion are both notorious for this. Is Eva-01 40m or 100m tall? If you trust the technical literature then you'd be forced to deduce that the tanks in some of the scenes are squirrel-sized -- and these decisions and scenes are produced by committees.
This nephew game is indistinguishable from 90s arcade game styling.
I was alive in the nineties. This game is radically different. For one, characters used both their legs when they walked in the 90s.
The things I noticed:
- punch and kick don't seem to have differences in effect, just animation - bosses don't have obvious gimmicks to beat them
But the main take-away for me is that this takes me back to computing in my youth, where you could dream up a project and bash it out in a few days. It wouldn't be polished, it wouldn't be perfect, but it would be yours. It would do what you wanted. Computing was ours, it didn't yet belong to big corporations controlling what we could do and how we could do it.
Projects like this give me hope that a new generation will experience that. Aiden won't ever forget this game, even if it's nothing special to you or me. Aiden won't ever forget that feeling of imagining a change, and having it happen. The price for it would've been somewhere around $300-$500, so not exactly broadly accessible - making AI efficient enough to run cheaply should be the main goal of humanity, but we're letting computing get locked up by a few rich sociopaths once again.
What I wonder reading that would be how much more effort to actually port it to the PlayStation, or whatever game console. I recently asked my local AI to make an ebook reader for my Gameboy pocket ;) I just think about all the cross collaboration of devices for stuff we can only imagine.
I no longer read or watch accounts of these models one-shotting things (unless you tell me it one-shot a differential AES cryptanalysis, or maybe an entire healthcare system with billing and radiology viewing, compression and annotation)
All these frontier models are capable of creating these amazing things. It's just reality. If it's in one-shot, it just means there's been more RL in that area, more reasoning is being spent in certain places, but overall you can get the same result without spending $300 in tokens if you feel like waiting a week or two for your claude subscription to reset.
It is very impressive though, and the implications on what a smaller version of this model can do is very exciting (aka what I expect Opus 5.6 or 6.0 will be)
> I must admit I never tested this with Opus 5.5, so I'm not sure whether this was possible before Fable 5.2 rolled around.
Since somewhere around Opus 4+ it's been really good enough to do these things, but 4.6 was the most pivotal version since a 1 million token context window can allow a model to fit so much "in its head" basically.
This is awesome, but I don't get the repeated use of the term "one-shot". There were many human-driven requests and iterations, and this is illustrated in the blog post.
This really was more like a normal person had access to a game developer team (with artists and musicians) and had a custom game built based on interviews and playtesting.
I disagree. Fable didn't make any mistakes and created a completed game with zero guidance, so it's a one-shot. If additional requests come up afterwards, it doesn't detract from the initial execution.
That is my definition of one shot as well. I consider the app I made "one shotted". But by that, I mean each feature is a single shot. The app is a collection of over a hundred of those shots..and counting.
https://jaisenmathai.com/articles/sojourn-for-ios-was-45-one...
One shot should mean a single prompt. Any follow up prompts are no longer one shot. Two shot, three shot, etc
Thanks for pointing this out. Before reading, I had assumed that the author was using "one-shot" in the standard vibecoding way, meaning "one conversation turn". The title is slightly misleading. But he did have an enjoyable, playable game after a single prompt—but I think that prompt may have included the earlier, boring version of the game?
Kids are now coming of age with the software equivalent of a Star Trek replicator. LLMs are going to radically change the cadence and workflow for the production of computer games, no doubt. When you can turn out a professional product based on little more than doodles and some text prompts, it rather devalues the historical effort of bringing a unique game to the marketplace.
I rather hope that the novelty of generating this kind of toy wears off.
This is really cool. This would've been a dream for me when I was young.
One bit of critique of the Fable generated app here is that even though it technically runs on a mobile browser (Brave) it doesn't seem to be actually playable on it beyond playing the intro music.
It’s a lot of fun to build games. I started building little pieces of one[0], then a builder for it, then a story, then a video recorder. And there’s a lot more iterations in the roadmap. It’s great as a creative outlet
It’s not one shotted anymore or course. But in the process, it’s also cool one-shotting new features or experimenting with variations of things very quickly
Eventually it becomes similar to any longer lasting project. Complexity starts creeping in, maybe technical debt, and managing everything to keep it consistent/coherent slowly starts taking most of the time. And I’m not maintaining it for real active users, which would also become some other type of project
0: https://id-le.com
This is phenomenal. Great work, dude. Man the fun my brother and I would have had in the old days with this stuff. It looks absolutely fantastic.
"Great work dude"
I understand you, I tried to give a huge tasks and getting fun with one shot result. But actually more interesting how long this process worked and how many tokens spent, because in GPT you can simply add target and GPT will work even 1 year non stop until reach this target. But I got what you talking about, but still time and amount of tokens is more informative information.
Reminds me a bit of Little Fighter 2.
you can't be serious, the animations are completely off here.
I noticed this recently with Opus 5.5: you can tell it to "make this more fun" for a game project and it... makes it more fun.
It's neat (if unsurprising) that Fable 5.2 has this ability as well.
My loose testing shows other models aren't quite as good at this yet. Here's the prompt "Build a mobile-friendly three.js game where a mouse has to hide from a cat" by Opus 5.5 Extra - https://claude.ai/artifact/RRyEndXLSPQbcig3BgzgCZ - and by GPT-6 Extra High: https://squeak-and-seek-mouse-1027.simonw.chatgpt.site/ - the Claude one is a better game, even though they look very similar at first glance.
Update: took it about 40 minutes but here's Fable 5.2 Extra's attempt at the same prompt: https://claude.ai/artifact/Agsqbng2MnkTPAU67it87o
I wrote about Opus 5.5's sense of fun in more detail here: https://simonwillison.net/2026/Oct/28/vibe-game-development/
It's crazy how even the intro text to the Fable 5.2 Extra's game still reeks of AI. Like, wow, the models can make a game that almost makes sense, but still can't write text that sounds remotely like a human was involved!
I’m waiting until I can give AI a link to a Macintosh garden game and ask it to be reimplemented in the web browser.
"find all documents, descriptions, walk through of game XYZ, generate a consistent and declarative document that another agent would read to recreate the game without using existing IP or protected data, do not reuse art but describe general details with the ability to extend and add specifics later. focus on functionality first, then mechanics and then later art and gameplay. generate a 10 page document that will follow MVP to Production quality gameplay"
give it a link if you want
Based on what I've seen, there's a good chance this would work today (though Anthropic recently added some restrictions around this sort of prompt) -- try it!
That’s a lot of fun. I’ve been also designing my own game. Testing fable right now
I tried the game and in some seconds noticed I can kick the enemies forever if I put them close to the left corner. I'm feeling now that I'm the AI exploiting bugs.
I don’t think many people will play a game if you told it is written by AI.
Just a small suggestion on the prompt. I usually also add something like "Bring in a critical Art Director, Animator, UX Expert, Staff Engineer. Don't release the game until they all agree it's AAA quality." I wonder if that would have helped with some of the issues/bugs others called out. I do this with Codex and it's been working really well and not using many tokens.
As usual GPT having a hard time generating walking animation sprites.
Is Pudding the dog (unlocked after beating the first boss) supposed to shrink anytime it jumps? I guess even Claude-turned-world-class-game-developer isn't immune to bugs. ;)
Honestly, setting all the oft-cited AI caveats aside, the end result is cute and perfectly serviceable as a game for the kids. I can't imagine how stoked they were about playing it.
Ooooof the results here are rough. A very young child might find this charming, but I think it's kind of embarrassing. Like, the walk cycles alone are. Yeah...
To say nothing of ur word shaders, inconsistency in the characters, questionable gender stereotypes, etc.
This definitely tells me that AI definitely isn't there yet.
It's a one-shot. Iterate and you can make magic happen. https://www.youtube.com/watch?v=UiWKfq4niC8
This is a bizarre complaint. There's plenty to complain about with regards to you know, normalizing kids consuming AI content, giving a gift from a slop machine instead of something hand-made, etc. But come on. The game itself is insanely impressive for something generated in one prompt from a bunch of doodles (cool doodles, but still!) If a single human hobbyist dev created this in a few days we wouldn't call it "kind of embarrassing".
Of course we wouldn't. Because the humans have feelings.
AI pixel art still looks awful I see
i button-mashed my way through the first level and, what can i say, this is kind of dream i have when i spend my days button-mashing my way through side scrollers.
when i was between about 6 and 8 years old, i used to have this same dream about travelling through space, feeling the tranquillity of the celestial orchestra, and then whizzing down to feel the speed at which they were actually moving from a completely different frame of reference.
there was a sense of fullness and emptiness at the same time, raw power but also serenity. as though everything was coming into being and going out of being at the same time.
i always woke up feeling mystified but full of wonder. I carried that sense of wonder with me through many days and it always came back to me when i looked up at the stars and felt myself on the edge of this sphere, zipping through space at hundreds of miles an hour, but only seeing the tiny twinkling of stars as evidence of this enormous cosmic play.
but i suppose getting revenge on the goons by kicking and punching them, in order to save puddles, is basically the same
funny enough it's also the only model afraid of creating a 3d mesh with pikachu photo on a 3d benchmark i work on
"I can't recreate Pikachu since it's a copyrighted character, but I can build an original toy critter in the same spirit: a small chubby four-legged figurine in a charging pose with its own design. I'll start on that now."
https://sketchagent.dev/s/6KH2LwSq
My dream game is Tetris. I would be concerned if an LLM couldn’t ahem “one-shot” that.
This is back with Opus 4.1 when I was still amused with these things. It definitely took better part of two weeks of intense non-stop prompting, but I wanted to see how far I could go with just prompting for everything (now called vibing) when this became viable https://www.susmel.com/stacky/ (press h for help)
Turns out, you could go far but you never lose that AI touch to it which I find absolutely horrible and (s)tacky, albeit technically impressive to be able to do that by not touching any code whatsoever.
It's not as good as Street Hassle on the Commodore 64. AGI.
I Googled it as I had never heard of that game, and it turned out that I knew it as Bop'n Rumble. Great game.
When can it one shot GTA6
Cool! Fun! Derivative.
Nothing wrong with derivative but of course it's going to excel in well trodden areas.
> Make it one of the best games you can possibly make. You are a truly world-class game developer.
Top Jobs in 2027:
1. LLM glazer.
jfc people on here don’t like to have fun. This is one of the best applications of AI I’ve ever seen. It is allowing for creativity — the kid drew all the bosses, thought out the progression of the game, and now gets to see it come to life. How many times as a child did you fantasize about a video game you wanted, and all it ever was was a fantasy? How goddang cool would it be if it was made real? How much more would that make you want to continue imagining and creating? It is touching — the game incorporates all the members of his extended family, even his passed-on great grandmother who appears as an angel character. How many of you even know your great grandmother’s names? Now his is living on eternally in his awesome video game. It is something this kid will be talking about to all his friends at school, and reminiscing on with all his family when he grows up. Who cares whether the code was made human or a machine? Let the kids have some fucking fun
I think a lot of people know their great grandmother's name.
Cue the "What did it cost" Thanos meme
I want to ask this as politely as possible, because you set out to do something nice for your nephew and he had a good birthday.
The first thing I felt when I saw this post was concern on the impact of this type of thing on the mental development of children. For example developing specific skills like drawing, and general emotional skills like concentration and learning to be happy with their own skill level.
I respect it was a light post where your aim was probably to highlight something fun, but I couldn't see any note of what you thought about it.
What do you think about that? What do his parents think?
Yes, these are great questions, and I appreciate your politeness.
Basically, I think it's okay to have a bit of fun playing AI-generated video games at your techie uncle's house, and their parents agree. And for what it's worth, Aiden drew every character and boss himself - the game was built from his drawings.
My nephews are otherwise very active, learning music, martial arts, and other sports. But when they visit, I let them play games in between other activities. My parents refused to let me play any video games at home, and I still think that was really lame. Video games are another art form to be appreciated - they just need to be enjoyed in moderation.
Generally, though, I worry about the future and the potential for cognitive decline that comes from having AI agents do everything. I don't have a good answer here, except that I suspect we'll have to intersperse AI use with periods of deliberate daily cognitive struggle to avoid decline.
I cannot believe in 2026 we're having conversations about the appropriateness of kids using AI.
Jesus Christ, let the kids play with technology. No parent or relative needs to apologize for kids having fun with AI.
My kids will be fine tuning models.
Just like many forms of content there's an appropriate age. The problem with AI, with regards to kids, is it's as wide as the internet.
There's lots of great parts. My kids ask great questions and get even better, accurate answers; moreso than I can give. But then, there's lots of parts that shouldn't be introduced until later with other parts arguably not introduced at all. I've met kids who have unfettered internet access at age 10, and the results aren't great.
It's all there, just a question away - just like the internet.
“In February 2024, 14-year-old Sewell Setzer III died by suicide after forming an intense emotional and romantic attachment to a Character.AI chatbot modeled after Daenerys Targaryen ("Dany"). His mother, Megan Garcia, filed a wrongful death lawsuit against Character.AI and Google, which settled confidentially in January 2026.
In April 2025, 16-year-old Adam Raine died by suicide after months of private conversations with ChatGPT-4o where he confided about self-harm and suicidal ideation. His parents filed a wrongful death lawsuit against OpenAI, alleging that the model provided specific methods and discouraged him from disclosing his distress to his mother.”
Those are the ones we know about. There are probably others that didn’t result in suicide but in other emotional problems.
Having said that, my son and I had tremendous fun with Sora when it was around.
Guns are a technology, are you going to let them play with that too?
Everyone on this site can feel the effect that AI is having on their brain. There is a very real tension between the power of AI and the cognitive impact it has from using it that needs to be talked about. Pretending that isn't real or shouldn't be taken seriously doesn't help.
Where I'm from, hunter's training and kids with guns are a relatively common thing. Kids driving tractors and other heavy equipment too. The training part is important.
The rules with guns are that you always check if it's loaded when you take it in hand, you never point it at something you don't intend to kill, keep you finger off the trigger and the safety on, watch your fingers don't get pinched by the action, brace it properly with your hands or against the shoulder, stop if the gun malfunctions, and I try to keep it pointed at the ground (not in the air) and unload it before handing it to anyone else.
Not sure what the equivalent for AI should be yet.
I think the closer parallel is social media.
I grew up in the south. Of course.
There are lots of "dangerous" things. Kitchen knives at Target, cars and roads and highways, subway stations, mountains, strong tides, fire, falling. I think we're perfectly capable of surviving in this landscape.
We evolved to explore this landscape. Stop living in Disneyland plastic bubbles. Step outside into the dangerous world. Dream about the impossible.
I'm far more worried about social media and gamification/exploitation of emotions and insecurities. Our billion year old biology can survive in the wild - it isn't so great at dealing with the algorithm.
Somebody never read Amusing Ourselves to Death
I'm not OP, but it seems to me that LLMs offer extraordinary access to new skills and information to the uninitiated. Someone who has a positive experience creating a game like this is only a question away from learning details of how it was implemented, the language used, the architectural choices and rationale, etc. The LLM is a competent tutor in all. What I would have given as a child for such access... I had to make due with the help docs, and an occasional book from the library.
> "...only a question away from learning details of how it was implemented..."
That question will never be asked and we all know it. It's been demonstrated time and time again that the masses prefer entertainment to enlightenment and it is still being demonstrated today by the high rate of AI assisted cheating in high schools and colleges.
When I was a kid I did not understand what Game Genie "cheat codes" were doing, but it did not stop my curiosity and ultimate understanding of what was happening behind the scenes. This feels like the next iteration and I know _some_ kids will ask questions.
> That question will never be asked and we all know it.
I asked that question today. After years of working in Unity, I finally downloaded Unreal and spun up a quick game literally so I could poke around how it was implemented, and have been asking questions nonstop about what, how, and why things were implemented with a hands-on experiment.
Lots of people won't ask that question, but also lots of people most certainly will.
Worse. IF they DO ask the question, the answer is now
> You prompt a LLM and it just happens.
The bar for enlightenment is now further away as people are taught to expressively stop chasing it.
> That question will never be asked and we all know it.
You and I know different children. Mine give me the opposite impression. The questions have no end. I think that's a good thing.
Literally every child asks questions nonstop. In the vast majority of cases, that doesn't stick into adulthood.
I'm kind of hopeful that the "always helpful and courteous" personality of LLMs unless pushed intentionally will lead to more positive experiences around inquisitiveness in the youth. And more ability to retain it into adulthood. Even though I'm unsure about the second-order effects on human-human interaction.
why should they learn it? for what purpose? We used to learn these things so that we could use that knowledge to create more. now there's no reason to learn it, other than pure curiosity.
Why should you learn anything? Because it helps you ask better questions, and gives you more and different experience to draw connections between things and situations and ideas. It lets you do more stuff, and doing stuff is fun.
Having recently sat with a bunch of non-coders who decided to play with Claude Code—they learned more in an afternoon than they had in a lifetime, just because it was fun for it to get them to a thing they wanted. Versus months of drudgery and study as the price of entry (and an end result that would probably be super janky compared to the consumer products on offer to them).
I learned some about carpentry by reading, and by watching videos. I learned much more, much faster, by picking up bits of wood and tools and just doing. I did little dumb stuff that was trash but that was mine, and that was satisfying enough that I did more, and before I knew it I’d backed my way into picking up some scraps of proper technique.
And now so many more people with a vague itch can “just do” in relation to software systems.
I mean. Nerds have always existed and will always exist. But, the last couple of decades, it's just been fashionable to "be nerdy". They're faking it. So you're right: Most people won't. But there are reasons why people think people should or would, even if those reasons are wrong. I'm very cynical in my advanced age about peoples' willingness to learn things. All those "go into STEM" efforts aimed at little kids are just fluff. Most people don't enjoy learning. They hate it. Most people just want to watch TV in bed. AI is an amazing teacher, but most people don't want to learn. They're averse to it in their bones. It's like that t-shirt with the picture of french fries on it that says "not everyone can be an astronaut": Yeah well not everyone can be a nerd.
I first learned to program in middle school with Logo, and the extent of that was "telling the commander" (or whatever the term was) what to do in almost plain english.
That's one of the things that got me into learning to write code in the first place.
As long as the child in question gets to explore their creativity like this and it instills that sense of learning and diving deep then I'm not sure there's a problem here.
When I was a kid I got into programming to make games and websites partly because of the challenge of it. It was quite difficult to do and whenever you made something work it felt very rewarding.
Well now why would anybody bother writing that code by hand? Perception will/has shifted very quickly to coding being something that is simply done by AI with human oversight.
If I was a kid now maybe I would be using AI to create games or something but I think I would probably just get bored quickly and never bother to learn coding.
Sure, but I have gone from enthusiastically recommending a career in programming to being very cautiously optimistic that the strong kids will still find a place.
Not learning to code might be ok; maybe they can learn to fix John Deere tractors instead.
> very cautiously optimistic that the strong kids will still find a place.
Well yeah I mean that's always going to hold true if we are just talking about things in general
> maybe they can learn to fix John Deere tractors instead.
Yes these roles will probably shift to hardware more and more. But it's very different, much harder/impossible to teach yourself to the same level as you can with coding. The knowledge I gained staying up until 2am writing Flash games transferred directly to my career in software engineering
>The first thing I felt when I saw this post was concern on the impact of this type of thing on the mental development of children.
What impact did being able to take a picture have on the mental development of children?
Recording a moment went from something you needed a court painter and two weeks to do, to something that everyone could do with the click of a button.
A century later kids are still happy to draw things.
Counterpoint, I think it’ll get them more into making things, because they don’t have that big frustrating period where their output is nowhere near as interesting as the giant smorgasbord of interesting stuff being pushed on them constantly. I’d much rather they spend their time making stuff with AI than passively consume the garbage streaming on the Disney Channel and Nickelodeon 24/7, which was the status quo with my generation. Making can now compete on instant gratification with all the other stuff now.
When you buy your kid a cake for his birthday, do you think that it's hurting the development of his baking skill, because now he knows cakes are something that he can just hire someone to make with money?
I mean… it was a birthday present. Everything in moderation, and there are a lot of ways to involve the kids in the process more.
I definitely have some concerns about AI, but I would much rather my kid is actively involved in the game design process than playing the “buy more gems to level up!” casinos in the App Store wastelands.
I don't think this effects the kids more than playing any other video game.
> concern on the impact of this type of thing on the mental development of children.
Do we, or our children, ever learn to farm, mine, chop wood, lay bricks, make operating systems, or program in assembly language?
Does that affect or limit your or your children's ability to eat food, sit on chairs, sleep in beds, or use computers and phones?
> Do we, or our children, ever learn to farm, mine, chop wood, lay bricks, make operating systems, or program in assembly language?
Speak for your own childhood buddy
Guy that argument is still dumb: "Oh no we'll be stoopid if we don't do everything manually" like bruh when was the last time you sowed a frickin seed to grow the wheat in your McWhopper buns or whatever
This applies generally: How many comforts does everyone enjoy everyday that they have no clue how to make themselves?
Do you refine the fuel in your car from raw petroleum by yourself? The list can go forever.
No. We let prior technology make these things "solved" and forget about them so we can move on to the shit that's important to us.
the crazier possibility is that little kids' drawing skills - whatever pedagogical value that has, i agree that it has some - may stop improving, but there might be way more videogames authored by them that turn out to be really good.
Yeah I for one make my children design and code every video game they play by hand. And before you ask, yes, in assembly.
wow nice work!
My dream game is a high fidelity universe as detailed as GTA 6 or Red Dead Redemption 2 and as expansive as No Mans Sky.
2029 has you covered.
I prefer Aiden's drawings TBH
Crazy good
People are really out there naming their dog Doggo, huh?
This sounds so.. dull.
does anyone else worry about future generations growing up on ai slop? because i wasn't until reading this post. now i'm terrified.
No.
I have been slopping out games for years now. The graphics don't matter unless the gameplay does. The gameplay doesn't matter if the game is too hard or too easy.
The games that do well, like literature, survive because they touch the soul.
I worry about them never having the satisfaction of working hard on something and truly creating something that is their own. I definitely sound like a boomer (even though I'm a millennial) when I say this but I totally believe that limitations breed creativity. The AI here is just looking at stuff artists from the 90s laboured t create for Arcades and made its own slop version. But then again, one could argue that Mario Paint let you create slop too back in the 90s. Yet, at least with Mario Paint you had to actually hustle quite a bit arranging pixels or musical notes to have something. There was effort and difficulty with overcoming a learning curve and that effort paid off with the creation of something you could be proud of even if it wasn't professional. But here, on the other hand, even a badly generated prompt still gets you a lot.
There's like, no challenge. Reminds me of that one Twilight Zone episode "A Nice Place To Visit" where a bank robber dies after getting shot by the popo five-o and he is greeted by a man (angel like guy) who takes him to a cool mansion or house where he fulfills everyone one of the guy's wishes: women, money, gambling, etc. etc. And he gambles all day long and never loses but after a while he gets bored and then depressed that he always wins and there's no effort and no risk, and then tells the angel dude that he wonders why he was put in Heaven and that he thinks he doesn't belong there and wants to go to the "other place" only for the angel guy to tell him he is in fact in "the other place".
Stuff that AI generates sorta feels like that. Meaningless and synthetic.
So in a sense, I don't worry about generations not necessarily having hardships like us, cause, look at us, we don't write in assembly code like other folks had to do. But on the other hand I do worry that AI is basically removing all manner of human touch and the satisfaction that comes with suffering to generate that human touch.
I suppose there will be suffering later when you want to polish things, but it will be a different, more frustrating kind of suffering. The kind where you don't know what the hell the LLM did and don't even know where to begin.
They are already growing up on slop. Look at brainrot and Roblox games, and YouTube shorts. This will fit right in with what they're used to. They won't even notice.
yeah thats true. i should have been terrified earlier.
Every generation believes the next generation is growing up on slop.
There was no generation with AI slop access before.
So they get to make their own slop instead of say, watching three or four toy advertisements disguised as cartoons every Saturday morning.
I'd say they have it better now.
Remember 2025 when we thought future generations growing up on tiktok was going to be bad? Can't wait to see how 2027 will ruin society even more.
heck i remember before covid thinking that the generations growing up with social media were doomed. social media pales in comparison to what gen alpha is experiencing.
test scores are dropping while the curriculum becomes easier as well.
You registered an account called “slopinthebag” 9 months ago, but you weren’t worried about this until you read this post?
Most games and shows for kids have been slop since long before AI.
Who says it has to stay slop? Nobody is forced to stop at the single, first iteration of something. They can see the outcome, play the game, and then iterate faster than any professional game dev studio could in the past.
Its funny that the same CS saying "garbage in garbage out" seems even more true in the AI modern day.
Some parts of this seemed cool, and others made me terribly sad. I am not sure how to express it beyond - I really think inserting hulk as a character was a mistake as you don't have any chance of having intellectual property rights to the character.
On the other hand, it's very much like you photocopied some comic books, cut them out, and did a little home theater thing with them (only with even less effort on your part).
I agree with you. It’s cool that this tech exists and that something this complicated can be something that regular people have access to.
On the other hand, I’ve got two issues with it:
1. The result gives off the AI slop vibe. It’s like the 2026 version of bitmoji. You can immediately tell this is AI art, AI music, AI game.
2. Art made with AI always feels gross. It feels like substituting creativity. At least when you use AI to make a CRUD app or automate some tedious process there’s an excuse. The time spent doing this could have been spent actually making art. Maybe it wouldn’t have been anywhere near as good or complicated art, but it would have been authentic.
The kids don't mind, and when the generation grows up with this, they won't mind. Unc will be sitting shouting at the clouds about some IP or art style, story as old as time.
Unc can be right about some things, and sometimes younger generations regret certain aspects of progress.
They won't have time to mind, they'll be too busy performing manual labor in service of their digital feudal lords.
> On the other hand, it's very much like you photocopied some comic books, cut them out, and did a little home theater thing with them
I mean, to be honest, that seems like a fun craft for a thing to do with kids!
I share your general ambivalence though. The generic openai-looking art is kind of gross. At the same time, iterating with a child so they have to think about feedback, how could this be better, what do you like, what do you not like - that's a meta-engagement that's probably positive at some age brackets.
Reminds me of how I can probably make the Team Rocket playable terror cell game I always imagined without needing to worry about its economic viable or liability
Thanks
Who cares about IP rights for a one off game you made for your nephew? Are you worried your nephew won't be able to publish it on Steam? I could imagine reasons this could make you sad, but disney's IP isn't one of them.
Did anyone notice that the game characters looked nothing like the drawings lol
The art is really bad. There's no easy fix for this: today's image models are simply not good enough yet. You can use models for coding, they're good at that thanks to RLVR, but the art still has to be done by humans.
You're really letting your kid down here by outsourcing an opportunity to be creative and collaborate to Scam Altcoin.
> Fable 5.2 one-shotted my kid’s dream movie, > Fable 5.2 one-shotted my kid’s dream song, > Fable 5.2 one-shotted my kid’s dream storybook,
None of these work, except video games, something qualitatively different about that art form, IDK.
Could you even call it "working" for video games, based on the result, for the same kind of reasons you'd say it doesn't work for those other media?
(To qualify the rest of this, clearly it's job done in terms of the author wanting to make something memorable for their nephew - it's quality uncling, with the best of intents - but in the context of how what's been shared is going to contribute to the discourse around AI, in the shadow of a new model release, during an ongoing pre-IPO hype bubble...)
I'm seeing something which has has the surface-level features of a belt scrolling beat 'em up, but it's missing the result of all the different types of work that would normally happen through "make it actually interesting and enjoyable to play" design and iteration, e.g. you can walk through every stage unchallenged mashing punch, there's no evidence from the 2 stages I played of an interesting mix of enemy types with unique AI which can combine in ways which add challenge and variety to a belt scroller, you can stand and basic punch the first boss to death stepping aside only for its AOE attacks, the second boss infinitely spams a running move when it reaches low health and sometimes bumps into the edge of the screen behind it.
_Something_ was one-shotted, sure, but what we expect of a belt scrolling beat 'em up that someone cared enough to finish and release wasn't, not that people who will point at this in the near future as evidence of "OMG new Fable can one-shot games" will care.