Fable 5.2 one-shotted my nephew's dream game
notesbylex.com
notesbylex.com
The world has changed and we can never go back.
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-...
We’re entering into a new era of mankind. With good and bad consequences.
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.
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 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
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.
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.
Couldn't you have been downgraded to 4.8, since direct reproduction of existing games classifies as unsafe?
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
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.
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.
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...
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.
People misuse the term "literally" frequently, for example, but that doesn't change the meaning of the word.
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.
Though, now they will never stop asking for more and more. OOP may have opened Pandora's box. :)
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.
...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...
Perhaps other sites beckon.
> about 320M tokens read from cache, 19M written to cache, 1M output
320 * $0.2 + 19 * $10 + 1 * $40 = $294
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.)
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.
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.
(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.)
anything that doesn't explicitly involve interaction with a human is RLable. frankly even those things are as well.
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.
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.)
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.
https://jaisenmathai.com/articles/sojourn-for-ios-was-45-one...
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.
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
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/
give it a link if you want
"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."
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.
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
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.
Nothing wrong with derivative but of course it's going to excel in well trodden areas.
Top Jobs in 2027:
1. LLM glazer.
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.
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?
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.
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.
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.
You and I know different children. Mine give me the opposite impression. The questions have no end. I think that's a good thing.
> 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.
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.
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.
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.
Not learning to code might be ok; maybe they can learn to fix John Deere tractors instead.
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
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.
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.
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.
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.
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.
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.
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.
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?
Speak for your own childhood buddy
test scores are dropping while the curriculum becomes easier as well.
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'd say they have it better now.
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.
Its funny that the same CS saying "garbage in garbage out" seems even more true in the AI modern day.
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).
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.
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.
Thanks
None of these work, except video games, something qualitatively different about that art form, IDK.
(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.