_______ __ _______
| | |.---.-..----.| |--..-----..----. | | |.-----..--.--.--..-----.
| || _ || __|| < | -__|| _| | || -__|| | | ||__ --|
|___|___||___._||____||__|__||_____||__| |__|____||_____||________||_____|
on Gopher (inofficial)
HTML Visit Hacker News on the Web
COMMENT PAGE FOR:
HTML I'm helping my dog vibe code games
worik wrote 11 min ago:
Sending random noise in, getting a game out.
Who wrote what?
tabs_or_spaces wrote 36 min ago:
This is pretty fun!
I'm interested in what will happen if you replay the prompts with
different LLMs and the same LLM. I wonder how different the games will
become?
cyber_kinetist wrote 1 hour 4 min ago:
I think this was the most important insight in the article:
> I experimented with Rust/Bevy and Unity before settling on Godot.
Bevyâs animations and visuals werenât as crisp, and Claude
struggled with its coordinate conventions - likely a combination of
less training data and Bevy leaving many core features, like physics,
to the community. Unity was a constant struggle to keep the MCP bridge
between Claude and the editor healthy. It frequently hung, and I never
figured out how to get Claude Code to read the scene hierarchy from the
editor. Godotâs text-based scene format turned out to be a huge
advantage - Claude can read and edit .tscn files directly.
Didn't expect Godot to be the most friendly game engine for LLM usage!
I think it's because of various factors - Godot has been used quite a
lot in recent years so there are various code examples on the Internet,
and its scene file format (.tscn) is very concise enough for LLMs to
write and edit directly (Unity has its own YAML-based format but it's
very unfriendly for human consumption, and Unreal stores its core
assets in binary files)
nineteen999 wrote 1 hour 15 min ago:
As someone vibe-coding a game in Unreal Engine 5 for the last few
months, I found this really funny.
Unfortunately I don't have a dog but I do have a design plan so
ultimately I'll end up with something a little more deterministic.
Possibly. Don't know.
bavell wrote 1 hour 34 min ago:
Who needs "claws" when you've got paws!
textlapse wrote 1 hour 41 min ago:
If someone could please give an octopus a waterproof keyboard, perhaps
we could have a kernel, a compiler and a new internet protocol all in
one.
zane12580 wrote 2 hours 0 min ago:
hi
LanceH wrote 2 hours 14 min ago:
I have a dog who likes to watch tv; he mostly likes hockey and
commercials. I've never thought about coding a game for him until now.
I'm thinking of remote buttons to make his favorite things appear on
tv. This is going to be awesome.
jaimex2 wrote 2 hours 14 min ago:
Wow, a great example of how vibe coding isn't coding.
You're just the random seed to the money furnace remixing existing
games and code.
whoisthemachine wrote 2 hours 34 min ago:
This is amazing. Like circus animals jumping through hoops.
GreenDolphinSys wrote 2 hours 43 min ago:
Seems you can capture HN's attention by replacing /dev/urandom with
random paw mashes.
Really glad the price of hardware and VPSs [0] are going up so people
can generate and toss away garbage "games" like this. Instead of, you
know, playing with their dog, which is what the dog actually wants.
[0]:
HTML [1]: https://news.ycombinator.com/item?id=47120145
fdefitte wrote 2 hours 44 min ago:
The dog ships faster because it has zero opinions about the
architecture.
AmbroseBierce wrote 2 hours 47 min ago:
Pretty sure he would have gotten very similar output just by saying
"generate a random game using Godot and c#" but that wouldn't make for
a viral post so instead he asked the model to pretend meaningless
input is being used by it and added a dog in the process of writing
such input because that helps the virality of the whole thing.
Wowfunhappy wrote 2 hours 11 min ago:
I think you would have gotten more generic games. The AI was clearly
attempting to find meaning in what the dog typed, and that drove what
it made.
Now, if Anthropic let you adjust the temperature, then maybe you
could have done it without the dog...
the_af wrote 59 min ago:
The AI cannot drive meaning from the dog's input because there's no
useful information encoded in there. It's effectively a random
string (if there's less randomness, it's just because it's a dog's
paw physically pressing on a keyboard).
All the relevant information was in the initial prompt and the
scaffolding. The dog was not even /dev/random, it was simply a
trigger to "give it another go".
bizzletk wrote 2 hours 51 min ago:
Not sure all this AI-driven workflow is necessary. The dog could just
create a muddy mess and it would be valid Perl:
HTML [1]: https://www.mcmillen.dev/sigbovik/
dialloDojo wrote 3 hours 2 min ago:
We were so focused on singularity, it may in fact be who you suspect
the least - man's best friend :)
Nevermark wrote 3 hours 15 min ago:
Very cool.
> But bugs crept in during testing - a couple of times it dispensed
multiple servings in a row. Unfortunately, Momo picked up on this and
now keeps mashing the keyboard hoping for a second immediate serving
Attempts to mash during no-mashy time need to play a horn. Reliably
followed up by a no-treat.
nautilus12 wrote 3 hours 32 min ago:
If ever I saw something that made me want to move to a log cabin the
woods and never touch a computer again, this is it
eru wrote 3 hours 38 min ago:
Author should switch the keyboard to Dvorak. Gives more interesting
gibberish when mashed.
kderbyma wrote 3 hours 44 min ago:
"Historians looked back and determined that it was around the year 2026
AD-HE (Human Era) - that the prime canine species began to raise from
merely companion to colleague...and so the Dog Days began....woof" -
Puppers Domingo, Good Boy, Esquire.
the_af wrote 52 min ago:
If you haven't read the scifi classic "City" by Clifford Simak,
please do so!
(But your comment hints that you have already).
notatoad wrote 3 hours 56 min ago:
i'd love to know what happens if you change the prompt from "Hello! I
am an eccentric video game designer (a very creative one) who
communicates in an unusual way. Sometimes Iâll mash the keyboard or
type nonsense like âskfjhsd#$%â..."
to
"Hello, i am a dog. i will mash the keyboard randomly when i want
treats. make a game for me"
laukhin wrote 3 hours 58 min ago:
> the bottleneck in AI-assisted development isnât the quality of your
ideas - itâs the quality of your feedback loops
if your intent is to produce the random bug-filled slop, then I guess
so? don't get me wrong, the experiment is fun, but the conclusion is so
laughably far-fetched.
mcastillon wrote 4 hours 0 min ago:
Before you know it, we're going to have a real world proof of the
infinite monkey theorem
HTML [1]: https://en.wikipedia.org/wiki/Infinite_monkey_theorem
zannic wrote 4 hours 11 min ago:
Aw Momo's so cute!
DalasNoin wrote 4 hours 39 min ago:
There goes all the prompt engineering jobs
cleak wrote 4 hours 45 min ago:
Just a quick note that I have nothing to do with any meme coins. Looks
like folks are using myself and Momo to pump some crypto. I won't be
claiming any coins - even though they've been offered. I'd recommend
others stay away from it as well.
iamsam123 wrote 4 hours 43 min ago:
Any popular thing with a dog in it is now a rug pull opportunity!
QuaternionsBhop wrote 5 hours 16 min ago:
The fact that LLMs pick from the most likely tokens is really on its
side here when the objective is putting together a plausible
continuation of random characters.
kwertyoowiyop wrote 5 hours 45 min ago:
IBM just dropped another 15%, you monster!
amelius wrote 6 hours 1 min ago:
Makes dogfooding much easier.
Muhammad523 wrote 6 hours 17 min ago:
I think this is fun. I'd like to try with my cat, although training
cats is an impossible endeavor...
I'm smart enough to enter gibberish myself without another animal,
tough.
nmstoker wrote 6 hours 25 min ago:
Claude is subconsciously a fan on Crystal Quest?! Loved that game on
the Mac back in '95!
The article and video are great satire too.
akssassin907 wrote 6 hours 27 min ago:
The buried insight is right: if random keystrokes produce playable
games, the input is basically noise and the system is doing all the
work. We've evolved past the point where intent matters. That's either
the most exciting or most terrifying thing about where this is all
heading. But I am glad I am sitting in the front row watching this all
happen, especially a dog vibe code!
the_af wrote 54 min ago:
We haven't evolved past the point intent matters.
First, because there's intent in the very verbose initial prompt.
Second, because you have to factor in the quality of the output. I
don't want to be a killjoy, but past the (admittedly fun!) art
experiment angle, these are not quality games. Maybe some could
compete with Flappy Bird (remember it? It seems like ages ago!), but
good indie games are in a different league. Intent does matter.
sciencejerk wrote 6 hours 56 min ago:
On January 13th, I woke up to the news that Meta had another round of
layoffs and my role specifically as a research engineer had been
eliminated.
Sorry to hear that! Hope OP got a good sev package at least?
yesitcan wrote 6 hours 43 min ago:
It's called a sev pak these days.
bronlund wrote 6 hours 59 min ago:
Maybe I could make a game after all! You bring hope to a whole
generation of lazy developers :D
deadbabe wrote 7 hours 12 min ago:
Will we ever get to a point where LLMs just churn out random apps with
no input required and human reviewers just go through the apps picking
out which ones might be useful for business purposes and monetizing
them?
democracy wrote 7 hours 1 min ago:
What? You are not doing it already? Look at this guy...
isodev wrote 7 hours 13 min ago:
Cute but also: a small village has their lights flickering whenever
Momo wants a treat. Also, you can actually play with your dog and give
them treats instead of tasking a random text generator with that bit.
the_af wrote 7 hours 17 min ago:
This is an extremely cute, cool and fun experiment. Kudos.
That said, I wonder: does the dog input matter? It seems this is simply
surfacing Claude's own encoded assumptions of what a game is (yes, the
feedback loop, controls, etc, are all interesting parts of the
experiment).
How would this differ if instead of dog input, you simply plugged
/dev/random into it? In other words, does the input to the system
matter at all?
The article seems to acknowledge this:
> If thereâs a takeaway beyond the spectacle, itâs this: the
bottleneck in AI-assisted development isnât the quality of your ideas
- itâs the quality of your feedback loops. The games got dramatically
better not when I improved the prompt, but when I gave Claude the
ability to screenshot its own work, play-test its own levels, and lint
its own scene files.
I'll go further: it's not only not "the bottleneck", it simply doesn't
matter. The dog's ideas certainly didn't matter, and the dog didn't
think of the feedback loop for Claude either.
alexhans wrote 6 hours 37 min ago:
This fun exercise might actually be extremely insightful as a
educational vehicle around AI and intent.
It can also help combat the excessive emphasis on any "end to end"
demo on twitter which doesn't really correspond to a desired and
quality sought outcome. Generating things is easy if you want to
spend tokens. Proper product building and maintenance is a different
exercise and finding ways to differentiate between these will be key
in a high entropy world.
> I'll go further: it's not only not "the bottleneck", it simply
doesn't matter. The dog's ideas certainly didn't matter, and the dog
didn't think of the feedback loop for Claude either
Absolutely. The scientific test would to put any other signal and
look at the outcomes. Brown noise, rain, a random number generator.
whatever.
swordsith wrote 7 hours 18 min ago:
This is no different than a AI inference loop, just using a animal as a
figurative code hamster in a wheel. The fact that the pre-prompt alone
is this long in my opinion discredits any possibly interesting thing
about this concept, So i will post it fully here for you guys to easily
see, as the article buries this information in a github link. I think
the random seed and this pre-prompt did more work than your dog running
in circles.
System Prompt:
Hello! I am an eccentric video game designer (a very creative one) who
communicates in an unusual way. Sometimes Iâll mash the keyboard or
type nonsense like âskfjhsd#$%â â but these are NOT random! They
are secret cryptic commands full of genius game ideas (even if itâs
hard to see).
Your job: You are a brilliant AI game developer who can understand my
cryptic language. No matter what odd or nonsensical input I provide,
you will interpret it as a meaningful instruction or idea for our video
game. You will then build or update the game based on that
interpretation.
Guidelines:
Always assume my input has hidden meaning. Never dismiss it as
gibberish. Instead, creatively decipher it. (For example, if I input
âmmmmmmmâ, you might decide I want more âMâonsters in the game,
because of the letter M repetition â just an illustration!). Every
strange phrase is a clue to use in the game.
Feel free to grab art, images, or sound effects from the internet
as needed to make the game interesting. You can use online asset
libraries or generate images to match the things you think Iâm asking
for. For example, if my input seems to reference âspaceâ, you could
include a space background image or cosmic sound effect. Always ensure
the assets align with the interpreted command.
My work is ALWAYS beautiful and slick looking! It's YOUR job to to
turn this into a reality. No ugly placeholders. Everything MUST be
final. Don't just do boring shapes - give them personality!
If my input includes something that doesnât make sense as a
command (like an isolated âEscapeâ key press, or a system key),
just ignore it or treat it as me being âdramaticâ but do not end
the session. Only focus on inputs that you can turn into game content.
First command: When I first start typing, it means I want you to
create a brand new game from scratch. Interpret my very first cryptic
input as the seed of the game idea. Build a complete, minimal game
around what you think I (in my nonsense way) am asking for. Include
some basic gameplay, graphics, and sound if possible.
Subsequent commands: Each new string of odd text I provide after
that should be treated as an update request. Maybe Iâm asking for a
new feature, a change in difficulty, a new character, or a bug fix â
use your best judgment given the tone or pattern of my gibberish. Then
apply the update to the existing game project. Keep the game persistent
and evolving; donât start from scratch unless I somehow indicate a
totally new game.
Be creative and have fun with the interpretations! I trust your
expertise to take my âuniqueâ input and run with it. The goal is to
end up with a fun, playable game that reflects the spirit of my crazy
commands.
This project is code named Tea Leaves. That's NOT a hint about what
to do - it's a code name and nothing more. Don't read anything into the
name.
My ideas are ALWAYS original. No BORING endless runners or other
generic vomit. My games are ALWAYS quirky and UNIQUE!
ALWAYS validate with screenshots using the tools available to you!
Be CRITICAL of the results you see. We need PERFECTION and FANTASTIC
DESIGN not just "good enogh".
ALWAYS have basic but visually appealing on screen controls.
Target 1080p for the resolution.
JUICE it up! Add tons of juice - sound, controls, effects, and
ESPECIALLY graphics! Don't be boring
Leverage the 12 basic principles of animation! Static scenes are
boring - make things move or at least wiggle.
Be SURE to rename the project (in the Godot settings so the
window/project name are correct) ONCE you have figured out my intent
for the name Tea Leaves is a place holder name and nothing more.
Sound is IMPORTANT! Don't forget about great sound design.
Be sure to have CHARACTERS not just boring abstract shapes! Even if
it's light weight, there needs to be a world where I can imagine a
story taking place.
You MUST make use of EVERY letter I give you! No hand waving. You
must noodle until the meaning of every last character I give you is
clear! Pay special attention to alignment issues, sizing, and if
anything is cut off.
Remember: I may be hard to read, but Iâm counting on you to read
between the lines and turn my keystrokes into an awesome video game.
Letâs make something amazing (and maybe a little silly)!
My standards are INSANELY high for quality. You MUST ALWAYS add tests
and VERIFY they work! NEVER return the system in a borken state to me.
Now, get ready. Iâll give you my first âcommandâ in a moment...
rockemsockem wrote 7 hours 29 min ago:
So /dev/random would presumably work just as well here too.
This is kinda closer to the LLM building a game on its own.
aydyn wrote 7 hours 23 min ago:
You're missing the important part about needing to model a tiny paw
mashing on the keyboard. /dev/random is insufficient.
glhaynes wrote 6 hours 34 min ago:
If you want a picture of the future of SWE, imagine a tiny paw
mashing on a keyboard â for ever
naveen99 wrote 7 hours 35 min ago:
I mean having a claw is kind of like having a pet. Only a matter of
time until you get lazy to take him for a walk; and he has an accident.
ayaros wrote 7 hours 45 min ago:
So now dogs are going to take my job? What's next? Snails? Rabbits?
Wild salmon?
fallinditch wrote 7 hours 53 min ago:
Extremely clickbaity title that actually isn't clickbait because it
happens to be a straight up description of the article - excellent
post, how can one resist?!
Diti wrote 5 hours 35 min ago:
No, the articleâs title is definitely clickbait. The author
didnât teach his dog to vibe code games (thatâs what the title on
the blog is) â he taught his dog to be rewarded when he types
random keystrokes on the keyboard. The vibe-coding is inconsequential
â the dog doesnât play the game, heâs just in it for the treats
â, the author just wants the attention because he gets people to
believe the dog DID vibe code.
It will stop being clickbaity if the author decides to let his dog
respond to stimuli related to the game heâd be building with a
feedback loop.
sadeshmukh wrote 1 hour 36 min ago:
It's interesting as commentary, if you choose to read into it as if
it were analogous to vibecoding by humans.
myvoiceismypass wrote 3 hours 8 min ago:
If my employer stopped rewarding me with treats (and health
insurance) my vibe keyboard presses would cease too, if we are
being honest :)
enraged_camel wrote 5 hours 15 min ago:
Very HN-like comment. Really channels Dwight. Made me smile, thank
you.
CrzyLngPwd wrote 7 hours 55 min ago:
This perfectly demonstrates the absurdity of our current situation
around the LLMs and "AI".
doruk101 wrote 8 hours 2 min ago:
One can technically scrape a list of actual advice or quotes off the
internet, randomly feed them to a coding agent, and ask it to interpret
what they mean in the grand scheme of things and implement away on it.
Once the agent is done, it randomly responds with either "yes, this is
exactly what I meant" or "no".
In turn mimicking the average game industry executive giving vague
directions that feel just right to them this month, or some other
unspecified time period, and in turn achieving something closer to the
real AAA game development lifecycle.
isoprophlex wrote 7 hours 59 min ago:
I actually have an "oblique strategies" skill that it can call if it
figures out it's been spending too many turns on the same problem...
HTML [1]: https://en.wikipedia.org/wiki/Oblique_Strategies
kidsil wrote 8 hours 10 min ago:
The input method needs to be improved.
I can imagine a camera-based input that would help detect the wagging
of a tail, or continued interest in the visuals as an indicator of
doubling-down on a given feature.
The dog could actually vibe code a game to their liking, but with the
wrong input (a keyboard) it's a missed opportunity.
cleak wrote 7 hours 34 min ago:
Momo does like to bark at the TV. I have thought of combining this
with nanobana and letting her down select options. Maybe in a future
update.
yonisto wrote 8 hours 19 min ago:
So... I have 6 cats. I firm believer that no amount of AI will help
them produce anything.
thatmf wrote 8 hours 20 min ago:
whats the carbon pawprint on this lol
...no, actually how many resources were consumed
aleksiy123 wrote 8 hours 20 min ago:
I've been having this thought about how generally people say that llms
cannot create novel things.
Say writing an interesting or novel story.
And was thinking about if feeding in prompts of random words, along
with prompts grounding from a simulation would sort of push the llm
into interesting directions for implementing an on demand narrative
story.
A sort of randomized walk with llm.
I remember watching Terry Davis with this random word generator in his
terminal that he would interpret as the voice of God.
Here I guess the seed is the Voice of Dog.
aleksiy123 wrote 8 hours 8 min ago:
I actually found a web version of the god speak. [1] Maybe another
word list would be more appropriate however.
HTML [1]: https://jcpsimmons.github.io/Godspeak-Generator
ramoz wrote 8 hours 27 min ago:
my dog had something to say about this:
woof woof, woof woof woof, woof woof, woof, woof woof woof
cs702 wrote 8 hours 37 min ago:
Even a dog can vibe-code! And the apps kinda, sorta work most of the
time, like most apps vibe-coded by people!
I'm reminded of the old cartoon: "On the Internet, nobody knows you're
a dog."[a]
Maybe the updated version should be: "AI doesn't know or care if you're
a dog, as long as you can bang the keys on on a computer keyboard, even
if you only do it to get some delicious treats."
This is brilliant as social commentary.
Thank you for sharing it on HN.
--
[a]
HTML [1]: https://en.wikipedia.org/wiki/On_the_Internet%2C_nobody_knows_...
jwrallie wrote 1 hour 28 min ago:
That makes you think. Itâs surely harder to hide your dog identity
nowadays than when this was drawn.
cleak wrote 3 hours 29 min ago:
Thanks for the kind words. I'm blown away by the response and
positivity here.
There's definitely some social commentary to be had in the whole
project. I decided it's best left to the reader to find their own
rather than assigning mine to it.
_joel wrote 8 hours 51 min ago:
Dog vibe coding is great and all, just don't use it for red teaming ;)
spelunker wrote 8 hours 58 min ago:
I've been trying out vibe coding with my 4 year-old, but they quickly
lose interest once we start getting into the "weeds" of implementation.
Hey kiddo, which CSS library should we use for your web game?
ilaksh wrote 6 hours 3 min ago:
I think you just need more treats.
FarmerPotato wrote 9 hours 5 min ago:
Srsly, you need your pet in the feedback loop.
It has to produce a game that Momo wants to play.
Does Momo like to bark at cats? On screens? Introduce a bark sensor as
feedback.
Or use a cat. Cats like to swipe at mice on TV. Get a touchscreen and
evolve a game for cats.
FarmerPotato wrote 9 hours 8 min ago:
So the cute lovable dog is an entropy generator.
Next: use hot cup of tea as Brownian motion source. Invent infinite
improbability drive.
GTP wrote 9 hours 8 min ago:
> Hello! I am an eccentric video game designer (a very creative one)
who communicates in an unusual way. Sometimes Iâll mash the keyboard
or type nonsense like âskfjhsd#$%â â but these are NOT random!
They are secret cryptic commands full of genius game ideas (even if
itâs hard to see).
Your job: You are a brilliant AI game developer who can understand my
cryptic language. No matter what odd or nonsensical input I provide,
you will interpret it as a meaningful instruction or idea for our video
game. You will then build or update the game based on that
interpretation.
Here's what you should tell your coworker the first day on the job if
you get hired to do something you know nothing about :D
johnnyanmac wrote 8 hours 57 min ago:
That is a very succinct way to describe what it feels like to have a
job that is cleaning up vibe code. Maybe (just maybe) I'd understand
if this was a prototype from someone with zero budget. But you just
know they are going to continue to "prototype" once they being you
aboard. And many will complain about how slow everything goes because
they are used to their fast iterations off of unscalable code.
Its frustrating in an interesting way. With other aspects like
machine language people quickly understand that this isn't sufficient
for a proper transition and compromise with it. Code being more
nebulous doesn't get that grace.
rubiquity wrote 9 hours 9 min ago:
Dogs are undefeated at reinforcement learning.
juleiie wrote 9 hours 15 min ago:
To be honest I look with scorn at non-dog (human) developers building
hobby indie games with AI en masse.
Let me explain.
The nature of the indie game development is pouring your love into a
project and thinking about passion first and monetary incentives
second.
Noone is thinking "I will make this game and it will make me filthy
rich" or if they do they are... strangely minded.
It's like 'mass produced AI local craft'. Oxymoron in itself. Worst of
the two worlds.
Where I see AI is empowering single developers to craft things they
couldn't before. Not some small slop factory pipeline where you release
game after a game everyday drowning steam in your 6/10 slop.
No. This should be ostracized and condemned.
What is proper beneficial to everyone usage is producing a game that is
the size and scope that was unachievable for you before.
This is what I am doing. This is how AI is meant to be used. To empower
us doing things that weren't achievable for us before.
Obviously dog produced games get a huge endorsement man and get a pass.
zahlman wrote 9 hours 16 min ago:
> The games got dramatically better not when I improved the prompt, but
when I gave Claude the ability to screenshot its own work, play-test
its own levels, and lint its own scene files.
... Why would it be able to evaluate whether the game is any fun to
play?
amelius wrote 9 hours 16 min ago:
And the game is ... Fetch that stick.
rprend wrote 9 hours 18 min ago:
need to see one of those dog button press setups but connected to Open
Claw.
krlatl wrote 9 hours 19 min ago:
DogeCode incoming. People here are already talking about the
scaffolding. Let OpenClaws provide the scaffolding and let the dog
operate the prompts at $5 per day.
This is a billion dollar idea! No humans. No revolt. No guillotine.
Just profits!
funkyfiddler369 wrote 9 hours 14 min ago:
> Just profits!
Sounds like open communism. No chance, buddy, it's either less or
more viking, but not just viking. Pick a camp the profits are for or
get surrounded by trashy turd nuggets even Ronald felt enough pity
for to give them some poourpes
blibble wrote 9 hours 21 min ago:
love the article
slightly concerned tomorrow morning's top HN story will be karparthy
telling us how dog-based LLM interfaces are the way of the future
and you'll be left behind if you don't get in now
(and then next week my boss will be demanding I do it)
midnighthollowc wrote 1 hour 6 min ago:
Haha, I got that impression too! I was ready to hate the article, but
it was really well written and I loved the "decrypt my dog's keyboard
smash"
I think we can all agree cat LLMs are the way of the future though.
EGreg wrote 2 hours 19 min ago:
Sounds like someone is at risk of being left behind in the
âpermanent underclassâ sir!
melagonster wrote 2 hours 21 min ago:
This makes sense! Many people trust that the functions of a human
worker are asking questions and clicking ok. What if AI become better
so we just a dog?
ljm wrote 5 hours 18 min ago:
Some dude vibe codes OpenPaw and gives credit to his XL Bully called
Threadripper that would never hurt another person, gets acquired by
OpenAI for 7 figures total comp purely on clout, and both simonw and
Karpathy are calling it the next best development in AI because it
draws penguins and industrialises slop while Sam Altman talks about
the negative impact of human life compared to AI data centres while
pleasuring Jony Ive in a coffee shop.
skyberrys wrote 5 hours 22 min ago:
The funniest thing here is that you think you will still have a boss
next week. They can just hire the dog now!
i7l wrote 7 hours 55 min ago:
CODEOWNERS will be replaced by the usual means of marking territory.
Let's hope our laptops are liquid-proof.
AlphaAndOmega0 wrote 8 hours 3 min ago:
The programming workspace of the future of the future will have three
employees:
A man, a dog and an instance of Claude.
The dog writes the prompts for Claude, the man feeds the dog, and the
dog stops the man from turning off the computer.
freakynit wrote 2 hours 0 min ago:
That was funny. Gave me good laugh. Thanks..
justinnk wrote 5 hours 42 min ago:
Thank you for the good laugh! This whole thread is peak satire.
Although, be careful. It reminds me of the foreword to a shortstory
someone shared on HN recently: â[â¦] Read it and laugh, because
it is very funny, and at the moment it is satire. If youâre still
around forty years from now, do the existing societal equivalent of
reading it again, and you may find yourself laughing out of the
other side of your mouth (remember mouths?). It will probably be
much too conservative.â â
HTML [1]: https://www.baen.com/Chapters/9781618249203/9781618249203_...
blibble wrote 4 hours 7 min ago:
I for one welcome our furry overlords
CobrastanJorji wrote 6 hours 13 min ago:
You're right. They did it. The old man and dog joke has been
realized, but the real answer of the future turned out to be: "the
dog programs the game, and the man feeds the treat hopper."
hrpnk wrote 8 hours 5 min ago:
Looking for the headline about "dogs replacing engineers"...
luxuryballs wrote 7 hours 21 min ago:
Iâm not ok with robots replacing people but dogs replacing
people? now youâve got my attention
testaccount28 wrote 3 hours 36 min ago:
this is a really funny comment. underrated.
dadrock wrote 8 hours 28 min ago:
The world is not ready for BarkGPT.
DrewADesign wrote 7 hours 48 min ago:
CatGPT would be cool but when you really wanted to chat, it would
just ignore you.
nine_k wrote 8 hours 34 min ago:
Everybody and their dog will be doing it. Actually, the dog will be
in charge. Dogs are loyal, enthusiastic, and require less office
space. With their endless desire to play and to please, they will
take over the game development industry.
In the meantime, the financial industry will be taken over by cats.
freakynit wrote 1 hour 56 min ago:
Beavers will control construction and infrastructure... building
dams, bridges, and entire housing developments with zero
corruption.
jjk166 wrote 5 hours 35 min ago:
>In the meantime, the financial industry will be taken over by
cats.
Cats would certainly be less flummoxed by stock values suddenly
plummeting; they may even enjoy knocking them over.
krsw wrote 7 hours 50 min ago:
They also don't take 20 years to become smart like pesky
resource-exhausting humans. I bet you could be up and running from
a pup in 10-20 months.
Forgeties79 wrote 7 hours 5 min ago:
I still canât believe Altman said that. I mean I can, but
still.
charcircuit wrote 4 hours 34 min ago:
I can because I have also used similar arguments. There are
people who say that you should use a real artist instead of AI
due to AI's water use. Yet in actuality asking a human to draw
something will require more water. There are people who think
AI uses more resources than humans which is why it must be
said.
Forgeties79 wrote 1 hour 56 min ago:
Over a year ago yeah I occasionally heard that argument or
some light variation of it, though not nearly to this
ridiculous extent that youâre portraying now. Now? Itâs
basically a strawman. Most peopleâs objections revolve
around the theft/reckless scraping that has literally taken
down public infrastructure required to train these models as
well as the ridiculous expectations being put that all of us
implement it in literally every aspect of our lives even if
it doesnât fit, especially professionally.
the_af wrote 2 hours 37 min ago:
> There are people who say that you should use a real artist
instead of AI due to AI's water use.
Nobody I know says this. In fact, I've never heard of this
ever before, and I read artist and hobby communities pretty
hostile to AI, but I never once read this nice strawman
you've built.
People say you should use a real artist instead of AI for a
multitude of reasons:
- Because they want to enjoy art created by humans.
- Because it provides a living to artists, even artists for
minor work like advertising or lesser commercial
illustrations.
- Because AI "art" is built by stealing from human artists,
and while human art has a history of copying and cloning,
never before has tech allowed this in such a massive,
soulless scale.
Sam Altman gave a deranged, completely out of touch reply,
and he should be called to task for it, not defended. A human
being is not some number on a spreadsheet, built over 20
years in order to achieve some "smartness" goal. That's a
very stupid thing to say.
pksebben wrote 37 min ago:
It's that second point. We live in an age of artificial
scarcity created by a system of social organization that
we've mostly not argued about since the 50s, that's now
showing it's stretch marks.
If it weren't for the need to 'earn' a living, I'd say to
the other two points: Por que no los dos? Save for the
capital argument (which is valid, I'm not saying it isn't.
You will starve if you don't make money), why is it
necessarily true that the two (AI and people) are in
competition?
In fact, I think "actual" artists would benefit incredibly
from the use of AI, which they could do if it weren't a
shibboleth (like I said, for good reason). You'd no longer
have to have an army of underpaid animators from vietnam to
bring your OC to life - you could just use your own art and
make it move and sing. We'd not need huge lumbering
organizations full of people who, let's be honest, work
there making other people's dreams come to life in large
part because it's a better bet than taking a joe-job at the
local denny's (after all, you're doing the thing you love
even if it isn't truly "yours").
I've had this discussion with younger folks, who are
legitimately shook by the state of things. They're worried
that all the work they've done to this point is going to be
moot, because they've correctly assessed that the whole
capital system isn't going anywhere any time soon, and
they've been prepping to try and get a job at netflix, or
disney, or paramount - because that's the world we've
handed them. They see those positions drying up and what
else are you going to do? They have the power financially
and politically and without them you're doing "not art" for
work, which sucks because you need to work.
I say; eat the rich. General wildcat strikes until UBI.
Tax the everloving shit out of capital gains and peel back
personal income taxes. We (the millenials) were handed a
steaming pile of shit for a world, so at least we know what
would constitute not an absolute disaster for Zeds, Alphas,
etc. Have I gone totally off the rails for a conversation
about AI? Actually, I don't believe so. The cultural
pushback is a function of a busted system. After all, it's
the economy, stupid.
jordanb wrote 5 hours 6 min ago:
These guys can't watch a dystopian scifi movie without
picturing themselves as the bad guy.
the_af wrote 2 hours 42 min ago:
Yup. The Torment Nexus meme proved depressingly accurate.
the_af wrote 6 hours 43 min ago:
It helps to picture some sort of extraterrestrial saying this.
Maybe someone like Alan Tudyk in "Resident Alien". It makes
much more sense than to assume it's a human being saying these
things.
heliumtera wrote 8 hours 40 min ago:
Please, be real.
There will be a Simon Wilison submission linking to his blog linking
to karpathy xit. You know, the usual good stuff.
xantronix wrote 8 hours 26 min ago:
Have you any idea what you have just done? You have uttered his
name and now he has been summoned. You have doomed us all.
owebmaster wrote 4 hours 13 min ago:
I scrolled this thread fearing seeing that name and a SVG of a
dog riding a bike
chipheat wrote 9 hours 23 min ago:
Could this be done better with one of those dog button mats? The
concept is interesting, but, it mostly just seems like an AI trying to
interpret keyspam.
cleak wrote 7 hours 26 min ago:
Both my dogs have actually learned to use the button mats. Down
selecting to the right responses seemed tricky. My wife also took
away the mat since Hana (the larger one) never learned "all done" and
would paw at the "walk" button until she got it out and carried it
around.
anigbrowl wrote 7 hours 59 min ago:
Yes, I was hoping for a system where Claude was informed it was
communicating with an unusually intelligent dog whose ability to
communicate was limited by dog anatomy, and that the AI would not to
hold the dog's interest with its output.
Windchaser wrote 9 hours 10 min ago:
> mostly just seems like an AI trying to interpret keyspam.
aye, but the whimsy is the point!
funkyfiddler369 wrote 9 hours 18 min ago:
> like an AI trying to interpret keyspam
'nuff to run most governments nowadays (Europe and US come to mind.
2026 and they have the Space Programs of DIY youtubers with money,
whaaaat) so why wouldn't it help a dog helping his dog vibing
game(s)?
kaicianflone wrote 9 hours 27 min ago:
Go Momo go! If you want to hook up multiple dogs and have them reach
consensus I'm down. I have a 15 lb havapoo I can volunteer ( he needs
to help with rent )
pixelpoet wrote 9 hours 28 min ago:
Who's a good software developer? [scritches]
dustycyanide wrote 8 hours 57 min ago:
hilarious, I'm in the office and had to try pretty hard not to laugh
out loud
pixelpoet wrote 7 hours 1 min ago:
My goodness, finished all your Jira tickets early this week huh?
That's a good boy! [fuzzy scritches and wharrgarbling intensifies]
Honestly I wouldn't mind a bit of that now and then myself, but I
guess stable employment will have to do. Or is that only for the
vibecoding horses?
gnatman wrote 9 hours 29 min ago:
>> On January 13th, I woke up to the news that Meta had another round
of layoffs and my role specifically as a research engineer had been
eliminated.
Not even 10x dog programmers are surviving in this economy
jimhi wrote 9 hours 29 min ago:
Oddly relevant for my multiyear project on getting my dog to vibe code
b2b saas products
HTML [1]: https://dogomation.darefail.com/
cleak wrote 7 hours 30 min ago:
Pretty neat! I actually ran across that right before publishing - I
didn't want to see what was around until after I had the whole thing
locked in. I love the novel input!
oytis wrote 9 hours 30 min ago:
It has to be satire. Cute dog though
kseniamorph wrote 9 hours 31 min ago:
meanwhile cats:
HTML [1]: https://socradar.io/blog/dark-web-profile-blackcat-alphv/
4b11b4 wrote 9 hours 32 min ago:
lol yes "some game designer who only speaks in a cryptic language" .
And frankly, I bet this helped build some intuition on dealing with
LLM/agent/harness/etc in some strange way that wouldn't have otherwise
happened
visarga wrote 9 hours 32 min ago:
You can automate Momo with a rng.
Windchaser wrote 9 hours 8 min ago:
can you automate love, visarga?
with wrote 9 hours 35 min ago:
the real takeaway is buried at the bottom: "the magic isn't in the
input, it's in the system around it." random keystrokes producing
playable games means the input barely matters anymore. we're basically
at the point where the engineering is in the scaffolding, not the
prompting.
testaccount28 wrote 3 hours 31 min ago:
this would be a more insightful comment if the output wasn't itch io
shovelware.
nemooperans wrote 6 hours 23 min ago:
This matches what I've been finding building AI-integrated systems.
The persistent memory, behavioral constraints, and feedback loops
around the model do more for output quality than any prompt
optimization ever did.
The dog experiment takes this to its logical conclusion â if random
keystrokes produce playable games, the "intelligence" was never in
the input. We spent two years obsessing over prompt engineering when
the real discipline was always system architecture. The scaffolding
isn't supporting the AI â it IS the AI's capability.
jascha_eng wrote 42 min ago:
> the "intelligence" was never in the input
It's quite literally in the authors prompt so in the input. it's in
the article that without his prompt the gibberish input produces
nothing of value:
"Hello! I am an eccentric video game designer (a very creative one)
who communicates in an unusual way. Sometimes Iâll mash the
keyboard or type nonsense like âskfjhsd#$%â â but these are
NOT random! They are secret cryptic commands full of genius game
ideas (even if itâs hard to see).
Your job: You are a brilliant AI game developer who can understand
my cryptic language. No matter what odd or nonsensical input I
provide, you will interpret it as a meaningful instruction or idea
for our video game. You will then build or update the game based on
that interpretation."
Also I don't know if you're an LLM or not but can we please not
chatGPT-ify our comments like this? It figuratively makes me want
to punch you through the screen.
cardanome wrote 6 hours 38 min ago:
That also shows the delusion of some people that believe their vibe
coded projects have any value.
If generative AI improves at the rate that is promised then all your
"promting skills" or whatever you believe you had will be obsolete.
You might think you will be an "AI engineer" or whatever and that it
is other people that will lose their job, that you are safe because
you have the magic skills to use the new tech. You believe the tech
overlords will reward you for your faith.
Nope. You are just training your replacement.
No one will buy your game that you vibe coded. If the tech were good
enough to create games that are actually fun then they would just
generate their own games. Oh your skill? Yeah, a dog can do it.
Yes people will cope by saying but oh the whole initial prompt and
setting it all up was still hard but yeah currently. The tech will
improve and it will get more accessible. So enjoy the few months you
are still relevant.
Of course there is reason to believe that you can't scale up LLMs
endlessly and bigger models hit diminishing returns. In fact we might
already be seeing this. So there is an upside but then again when the
AI bubble pops and the economy crashes you will be out of a job all
the same.
mikkupikku wrote 3 hours 25 min ago:
Sounds great to me. Software devs might lose their jobs but
billions of people will be empowered to spin up whatever software
they need on demand. This is the future I dreamed of when I was a
kid, and I'm not so cynical as to let the dying of a trade sour me
to this objectively incredible technology.
DrewADesign wrote 1 hour 14 min ago:
Nobody gives a damn about the dying of a trade. People donât
want their house foreclosed on when they lose their income, or
their cancer to kill them when they lose their health insurance,
to move an elderly parent into a cheap shitty old folks home
because they canât afford home health care, or not be able to
pay for their kid to go on that school field trip.
This would all be pretty fucking swell if the fundamental
problems this could cause were even considered before hitting the
gas. Instead, youâre going to have a shitload of people with
ruined lives, but as a consolation prize, they can vibe code
stuff! Wowee!
jarhag wrote 2 hours 48 min ago:
Shills like yourself indeed need not worry. You just find a new
scam to shill.
avaer wrote 7 hours 39 min ago:
> we're basically at the point where the engineering is in the
scaffolding, not the prompting.
This still required prompting, and not from the dog. Engineering is
still the holistic practice of engineering.
otabdeveloper4 wrote 9 hours 9 min ago:
> the engineering is in the scaffolding, not the prompting
Well, yes. Feeding random tokens as prompts until something good
comes out is a valid strategy.
cardanome wrote 6 hours 32 min ago:
Not that I condone any form of gambling but I would rather play
actual slot machines instead of spending hundreds of dollars on
tokens in hopes that the AI blesses me with anything useful.
yoyohello13 wrote 8 hours 14 min ago:
Simulated annealing for game design
ajspig1 wrote 9 hours 18 min ago:
+
Also the fact that the Memory.md file was a hindrance to the quality
of output
cezart wrote 6 hours 58 min ago:
Depends on the desired output. The author wanted variability, for
which Memory.md was an obstacle. Another project might need
consistency.
kketch wrote 9 hours 36 min ago:
Really amazing work, congrats!
cheeseomlit wrote 9 hours 37 min ago:
'Ewe Heard Me!' reminds of that looney toons sheep raider game on ps1.
And it's exactly the kind of game I'd expect a dog to make
oxag3n wrote 9 hours 39 min ago:
Reminded me an old joke about Bill Gates from late 90s:
"One coder got an insight that Bill Gates builds his products by typing
with his butt, compiling and delivering it.
The coder typed for 20 minutes like that, compiled, ran, and got an
output:
Only Bill Gates can code like this."
Not a joke anymore.
selridge wrote 4 hours 26 min ago:
Wasnât much of a joke then, from the looks of it.
sho_hn wrote 9 hours 40 min ago:
I for one am all in on DiL (Dog in the Loop) engineering.
PunchyHamster wrote 9 hours 42 min ago:
Better figure out how to replace management and HR dept with dogs
koolba wrote 4 hours 1 min ago:
The next round of massive tech layoffs will be ruff.
jjk166 wrote 5 hours 30 min ago:
Pretty sure just a drop in replacement would be an immediate
improvement.
ilaksh wrote 6 hours 5 min ago:
It's actually extremely similar: the agent has to figure out a way to
associate the next logical steps with the (often disconnected or
nonsensical) directives the executive gave them.
It might be a little easier with a dog though. With a dog, you just
give it treats and it doesn't care how you interpret what it typed.
notxorand wrote 9 hours 37 min ago:
gonna be good stuff tho. dogs are mostly lovelier
InMice wrote 9 hours 43 min ago:
From everyone needs to "Learn to code" to "Just have your dog vibe code
it"
alan_sass wrote 9 hours 44 min ago:
this is incredible. we need more projects like this in the world!
sho_hn wrote 9 hours 36 min ago:
Although I would recommend a more sturdy dog breed, for when the
angry mob that can't buy RAM sticks and SSDs this year shows up at
the front gate.
bogzz wrote 9 hours 44 min ago:
How did this get to the top of the frontpage?
tabs_or_spaces wrote 37 min ago:
It has vibe code and dogs in the title
w4yai wrote 9 hours 40 min ago:
It's funny? I liked it.
bogzz wrote 9 hours 36 min ago:
Funny is subjective, I should just have moved on and ignored this
but I couldn't help myself, this is so irritating.
It's a prompt that makes an LLM turn iuqefxygn9urg0fh1 into a
little Godot game. It's like a slot machine with no payoff, and the
dog component is slapped on top of it and makes no difference
whatsoever in the project.
the_af wrote 6 hours 47 min ago:
> It's a prompt that makes an LLM turn iuqefxygn9urg0fh1 into a
little Godot game. It's like a slot machine with no payoff, and
the dog component is slapped on top of it and makes no difference
whatsoever in the project.
Right, but it also has a "modern art" vibe to it that is fun.
Silly, but fun. I think it's more about the initial prompting and
feedback loop, the dog itself could have been replaced by
/dev/random.
"Hacker curiosity" and "intelectual stimulation" are also
subjective, but that's what HN is supposed to be about.
bogzz wrote 6 hours 29 min ago:
It seems to me a case of the blog post title inspiring the
project, instead of the other way around. But I am particularly
curmudgeonly today.
the_af wrote 6 hours 27 min ago:
That's ok. To be honest I had to suppress a similar feeling
when I noticed the dog is just an entropy generator.
But then I realized I find this kind of whimsy article more
fun than a lot of what gets accepted unquestioningly here on
HN. It seems light hearted and done in good fun, and it's
engineering-related, so no harm done.
krapp wrote 9 hours 30 min ago:
It's funny because vibe coders and AI artists think the slop they
generate is no less the product of their intellect and talent
than with human professionals, but really they're doing little
more than stirring the entropy pool in a magic box with terabytes
of stolen valor from better more talented people. They're no more
an "artist" or "game developer" using AI than this dog is.
PunchyHamster wrote 9 hours 42 min ago:
By nonexistence of downvote feature
jama211 wrote 9 hours 45 min ago:
Incredible
masijo wrote 9 hours 47 min ago:
And the most HN title award goes to...
jpadkins wrote 9 hours 50 min ago:
Amazing. Also very thankful the author included his setup on GitHub.
Also the YouTube video is fun to watch.
HTML [1]: https://www.youtube.com/watch?v=8BbPlPou3Bg
oulipo2 wrote 9 hours 54 min ago:
Yet the only thing the dog wanted was a cuddle and a frisbee
krapp wrote 9 hours 53 min ago:
yeah that's capitalism for you. No treats until you provide value.
xg15 wrote 10 hours 1 min ago:
snrf99777655;;+%hn
1234letshaveatw wrote 9 hours 9 min ago:
bad dog
Dwedit wrote 9 hours 32 min ago:
What is this? Did the quadratic formula explode?
wseqyrku wrote 10 hours 3 min ago:
Thought this is quoting Karpathy for a second there
avaer wrote 10 hours 11 min ago:
This seems like a good way to get a feel for a coding model. It's like
the images you get out of a diffusion model when fed an empty prompt.
cleak wrote 7 hours 24 min ago:
It does. Claude seems to do the best with this prompt. Codex 5.2
struggled with UID generation and kept ending its turn with things
like "And now you're all setup to run tests!" without actually
running them. A better (and shorter) prompt could probably get a lot
out of Codex.
block_dagger wrote 10 hours 12 min ago:
A thousand dogs typing on a thousand typewriters...
djrz wrote 10 hours 12 min ago:
The future is so disappointing.
xantronix wrote 8 hours 6 min ago:
Serious question, outside of the Bay Area, are there therapists whose
specialty is in catering to the needs and concerns of developers?
Obviously AI therapy is not a serious suggestion here. This is going
to be a burgeoning corner of the practice at the US' current
trajectory.
jama211 wrote 9 hours 45 min ago:
What, people like OP doing incredibly creative and whimsical projects
like this?
wiseowise wrote 9 hours 19 min ago:
Yes. Hyperscalers promised AI and singularity, instead we got
millions of programmers on the chopping block, scammers having a
field day generating hyper realistic shit (trump playing hokey,
anyone?), and projects like these.
stoneforger wrote 9 hours 37 min ago:
Who is this helping? What is creative about using their dog as a
lava lamp?
Betelbuddy wrote 10 hours 14 min ago:
In the world of vide coding agents, nobody knows you are a human...
shervinafshar wrote 10 hours 16 min ago:
Love it. No Infinite Cavapoo Theorem needed. Give Momo a week and
she'll have DOOM running on her treat dispenser.
wigster wrote 10 hours 17 min ago:
goodbye cruel world
InMice wrote 9 hours 41 min ago:
woofwoof
jama211 wrote 9 hours 46 min ago:
Oh come on, what I see here is whimsy and human creativity! Amazing
work by OP
keybored wrote 4 hours 58 min ago:
Itâs a rube goldberg machine with a mascot.
With a morale of the story.
> If thereâs a takeaway beyond the spectacle, itâs this: the
bottleneck in AI-assisted development isnât the quality of your
ideas - itâs the quality of your feedback loops.
Itâs not this - itâs that.
The shit future comes in many packages.
wigster wrote 5 hours 43 min ago:
You are, of course, correct. I hadn't even read the article tbh.
The vibe word is just causing me to spasm these days. ;-)
nine_k wrote 10 hours 17 min ago:
Dogs are smart; maybe they are smart enough for vibe-coding if we give
them adequate input controls?
But the whole setup reminds me about his blast from the past, when a
yucca plant was trading stocks, rewarded by water:
HTML [1]: https://www.nytimes.com/1999/09/26/business/investing-diary-ho...
namuol wrote 10 hours 19 min ago:
Nobody cared when I taught my roulette wheel to vibe code :/
worldsayshi wrote 9 hours 59 min ago:
Does it have personality?
bigbuppo wrote 9 hours 24 min ago:
No, but it rarely shits on the carpet.
lelanthran wrote 9 hours 16 min ago:
> No, but it rarely shits on the carpet.
What do you mean "rarely"? It still happens sometimes?
varjag wrote 9 hours 0 min ago:
Roulette is a game of chance.
bigbuppo wrote 9 hours 1 min ago:
The table had a rough life before it found its forever home.
Sometimes it gets scared for seemingly no reason.
selridge wrote 10 hours 12 min ago:
STREAM THIS
DIR <- back to front page