Rendered at 16:46:51 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
criemen 1 days ago [-]
A German magazine (c't) ran a Asteroids programming contest in 2008 - create a client with access to the emulator output of the game that provides keyboard inputs to control the game.
The highest scoring submission that won the contest had a high score of around 137k.
Last week, I had GPT-6 Astra, Sol and Luna implement and hill-climb on this task, as I wanted to see how big the difference in smartness is. Luna implemented something, but never exceeded ca. 20k points, with a large variance.
Sol got something in the area of the humans implementation.
Astra, which finished fastest, had a highscore of around 1.7Mm when the game seemed to fairly reliably crash. On the way, it disassembled parts of the ROM to extract information about the game.
I didn't do a ton work to document and measure the specifics, but it was very impressive.
looperhacks 1 days ago [-]
If I remember correctly, back then all "good" entries in the contest solved the game by syncing with the RNG and could basically predict where and how new asteroids would spawn. The difference between entries was planning ahead movement and residence against control issues due to the contest setup (like inputs getting delayed). I wonder how Astra managed so much better, I thought the problem was already solved
criemen 1 days ago [-]
Thanks! I went back, and had a look at both the contest rules and the highest scoring submission again.
Turns out I benchmarked against infinite games, whereas the contest measured a 5min time limit. So, Astra solved a different problem.
Comparing strategies, though, Astra does something pretty different from the highest scoring submission. It doesn't predict the RNG, instead it reacts to the visuals on-screen, planning ahead by estimating velocity of all objects on screen.
Unlike the winning solution, it actively flies the ship, whereas the winning solution basically only rotates and teleports.
So Astra behaves more like a regular "perfect" player would, rather than one that breaks the PRNG.
suddenlybananas 23 hours ago [-]
It is a bit frustrating that you reported it as being so much better than human made solutions despite not checking even the most basic conditions.
criemen 23 hours ago [-]
My apologies, and it's too late to edit the parent now.
To be fair, though, I mainly ran this experiment to distinguish models, not to see if they were better than humans or not, so for that purpose it didn't really matter if the basic conditions were the same or not.
NitpickLawyer 23 hours ago [-]
> On the way, it disassembled parts of the ROM
You should check the logs, there's probably a bunch of retro gaming forums that got hacked behind the scenes :D
Kuyawa 1 days ago [-]
I am going to try to build the original Prince of Persia using Swift as it is the best language for building a macOS game. Being a classic 2D cinematic platformer, Apple's native frameworks provide exactly what I need without the overhead of a massive cross-platform engine, and I love simplicity
So here goes my weekend, flag this and get a life
andsoitis 1 days ago [-]
Share it when you're done! Even if it isn't complete complete.
Kuyawa 20 hours ago [-]
Already started and will be ready soon, check back in an hour
2 hours later and $2 in tokens, Prince of Persia in Swift 6 for MacOS is ready (MacMini M1 and Tahoe 26.6.2 is my setup)
Not fully tested by me (AI tested it fully on every milestone, ~340 tests) but for sure tonight I'll do it from beginning to end
Let me know what you think, feedback is always welcome
And btw, cmd+1..5 can change the resolution to a bigger canvas, I prefer it at cmd+5 almost full screen. Haven't tested retina display as I use a TV as monitor and resolution is not optimal
Enjoy!
* I love DeepSeek
* All rights belong to their owners
* Interesting docs to read: readme, architecture and prompt
* There is an app in build folder, that's the game
* Don't trust code downloaded from the internet, ask your AI model of choice to review it for malicious code. I trust DeepSeek, but you shouldn't trust me
Kuyawa 18 hours ago [-]
Adding respawn and saving last level so restart takes you there and not to the beginning
I forgot where the sword is, can't pass the first guard, hmm
tehlike 21 hours ago [-]
Instead of fixing a broken version, maybe each model should have started from scratch
jablongo 19 hours ago [-]
yea for a real comparison between models this would have been better, but I have a feeling he just wanted to play the best possible version of PoP.
tehlike 16 hours ago [-]
That may still be a new model. Having an existing broken engine might bias the new model in iterative design vs figuring out what's wrong in the first place.
msephton 15 hours ago [-]
I agree this would have been more interesting.
jablongo 19 hours ago [-]
This isn't really comparing the models; he's using successive models to improve his rebuild of Prince of Persia. Either way though, it will be interesting to see which games, if any, resist implementation via LLM. I recently started a Starcraft 2 like real time strategy game with Fable managing many Opus agents and it got to a playable 3d game with 3 races, 40+ units, and 40+ buildings in 3 days.
smokel 1 days ago [-]
The prompts provided are atrocious. It's amazing that the LLMs actually built something useful.
> My first prompt was simple: "in this original code there 6502 assembly code for prince of persia, use the save level files and try to do it in c# console."
Do what in the what now in the console?
gcanyon 1 days ago [-]
"now char coming but movement everything wrong ... prince is not in floor"
I'm assuming a language barrier on the part of the author. I wonder if the models would do better being prompted in the author's main language.
cavemandaveman 1 days ago [-]
Or having another model proofread the prompts and write clearer instructions
opiotrek 12 hours ago [-]
That was my same thought, these are barely coherent sentences in English.
daemonologist 1 days ago [-]
Yeah, I'm thinking the nigh-unreadable AI-speak we get these days makes a lot more sense if this is what they're training on. Or maybe the author has translated the prompts from another language?
InsideOutSanta 1 days ago [-]
It's so confusing how the actual article is in English, but the prompts are just gibberish. But LLMs are pretty good at deciphering gibberish; I often put our CEO's absolutely atrocious E-Mails into ChatGPT and tell it to explain wtf he wants from me.
Also, I feel like the LLMs would have done better if they had started from scratch each time, rather than being burdened by the output from the previous attempt.
aksss 22 hours ago [-]
The prompts were awful and really distracted from an otherwise cool project concept. Also, testing the next model by iterating on the first model’s crappy foundation. Why not start from the original each time?
koala_man 1 days ago [-]
Unsurprisingly it was buggy without the obligatory "Make no mistakes."
rhipitr 1 days ago [-]
Off tangent but the latest prince of Persia game is really fun
pawelduda 1 days ago [-]
I played The Lost Crown and it's top tier, I assume you're talking about The Rogue?
It's one of the best recent metroidvanias. It deserves a lot more attention. I was surprised by how good it was.
dofm 1 days ago [-]
It looks like one of those spam shooty game ads you get between Youtube Shorts.
Prince of Persia is a piece of contemplative, subtle, beautifully, artistically minimal motion puzzle art. God knows what that is.
7734128 24 hours ago [-]
However, it's Ubisoft and therefore tainted.
rothron 18 hours ago [-]
I see a lot of these attempts at getting a model to replicate a classic game. I'm sure this is a use case with some interest, not everyone wants to spin up an emulator, but it strikes me as odd. Rather than English being the new high level language for programming, the LLMs is handed a finished game as a specification and asked to copy it.
That gets you past the problem of the lack of specificity in English, but requires you to already have the thing you want to get made. At least tokens are cheap.
OakNinja 16 hours ago [-]
English has been the high level language for programming since Common Business-Oriented Language - COBOL.
Programming has always been defining the problem you have. Nothing has changed from that perspective. Sometimes that problem is recreating something that already exists :)
gambiting 19 hours ago [-]
The real miracle of AI is that it could work with these prompts at all
"now char coming but movement everything wrong ... prince is not in floor"
I'm a games developer and I have no idea what OP is asking for here.
hapless 23 hours ago [-]
when the author mentioned playing prince of persia on a pc-xt, i assumed this was some kind of ai-generated nonsense
but no
they actually did port the game to the lowest-end hardware available in 1989. you could actually play prince of persia on an 8088 with a cga card!
brandonmenc 23 hours ago [-]
Just about every PC game in 1989 ran on an XT with CGA.
hapless 21 hours ago [-]
The XT came out in 1983, it was a real piece of shit by 1989 standards
Not to mention, the PC was a pretty, uh, "challenging" platform for video games. It amazes me someone managed to port something as graphically sophisticated as PoP to an 8088 with CGA.
InsideOutSanta 9 hours ago [-]
PCs were incredibly expensive at the time, though, and barely useful. Most people didn't buy a new one every two years, despite the fast progress in hardware development. So many people, especially kids, were stuck with "ancient" hardware. I had friends who had an 8088 PC or an Apple II in the late 90s.
brandonmenc 15 hours ago [-]
The XT was significantly more powerful than the Apple II in every way except color depth.
There's a massive discrepancy between the English in this post and barely coherent prompts in it
keeda 17 hours ago [-]
I see your Prince of Persia and raise you seventeen games fully or partially reversed and ported to the web by one very capable guy in a few weeks with frontier and open weight models:
In case you mistake him for an “AI booster”, you should see this guy’s other posts, he is extremely critical of the AI frontier labs and Tech Bros and this whole AI bubble.
But he is also a very experienced game developer, and under his control the latest models have pulled off these crazy feats. What you are reading is the analysis of a domain expert and what it means for the industry.
dofm 1 days ago [-]
Just one thing you could do is not drag Prince of Persia into this.
Please.
jessechili 22 hours ago [-]
[flagged]
Kuyawa 1 days ago [-]
[flagged]
jackblack11 21 hours ago [-]
[flagged]
oynqr 21 hours ago [-]
[flagged]
jackblack11 21 hours ago [-]
This site is full of corporate simps and ai douches for the past 5 years, what do you expect?
The highest scoring submission that won the contest had a high score of around 137k. Last week, I had GPT-6 Astra, Sol and Luna implement and hill-climb on this task, as I wanted to see how big the difference in smartness is. Luna implemented something, but never exceeded ca. 20k points, with a large variance. Sol got something in the area of the humans implementation.
Astra, which finished fastest, had a highscore of around 1.7Mm when the game seemed to fairly reliably crash. On the way, it disassembled parts of the ROM to extract information about the game.
I didn't do a ton work to document and measure the specifics, but it was very impressive.
Comparing strategies, though, Astra does something pretty different from the highest scoring submission. It doesn't predict the RNG, instead it reacts to the visuals on-screen, planning ahead by estimating velocity of all objects on screen. Unlike the winning solution, it actively flies the ship, whereas the winning solution basically only rotates and teleports. So Astra behaves more like a regular "perfect" player would, rather than one that breaks the PRNG.
To be fair, though, I mainly ran this experiment to distinguish models, not to see if they were better than humans or not, so for that purpose it didn't really matter if the basic conditions were the same or not.
You should check the logs, there's probably a bunch of retro gaming forums that got hacked behind the scenes :D
So here goes my weekend, flag this and get a life
https://github.com/kuyawa/prince
2 hours later and $2 in tokens, Prince of Persia in Swift 6 for MacOS is ready (MacMini M1 and Tahoe 26.6.2 is my setup)
Not fully tested by me (AI tested it fully on every milestone, ~340 tests) but for sure tonight I'll do it from beginning to end
Let me know what you think, feedback is always welcome
And btw, cmd+1..5 can change the resolution to a bigger canvas, I prefer it at cmd+5 almost full screen. Haven't tested retina display as I use a TV as monitor and resolution is not optimal
Enjoy!
* I love DeepSeek
* All rights belong to their owners
* Interesting docs to read: readme, architecture and prompt
* There is an app in build folder, that's the game
* Don't trust code downloaded from the internet, ask your AI model of choice to review it for malicious code. I trust DeepSeek, but you shouldn't trust me
I forgot where the sword is, can't pass the first guard, hmm
> My first prompt was simple: "in this original code there 6502 assembly code for prince of persia, use the save level files and try to do it in c# console."
Do what in the what now in the console?
I'm assuming a language barrier on the part of the author. I wonder if the models would do better being prompted in the author's main language.
Also, I feel like the LLMs would have done better if they had started from scratch each time, rather than being burdened by the output from the previous attempt.
That looks really amazing
Prince of Persia is a piece of contemplative, subtle, beautifully, artistically minimal motion puzzle art. God knows what that is.
That gets you past the problem of the lack of specificity in English, but requires you to already have the thing you want to get made. At least tokens are cheap.
Programming has always been defining the problem you have. Nothing has changed from that perspective. Sometimes that problem is recreating something that already exists :)
"now char coming but movement everything wrong ... prince is not in floor"
I'm a games developer and I have no idea what OP is asking for here.
but no
they actually did port the game to the lowest-end hardware available in 1989. you could actually play prince of persia on an 8088 with a cga card!
Not to mention, the PC was a pretty, uh, "challenging" platform for video games. It amazes me someone managed to port something as graphically sophisticated as PoP to an 8088 with CGA.
Don't waste your time.
https://georgzoeller.com/blog/posts/what-reverse-engineering...
He also did this thing where he “spliced” different game concepts and turned WoW into an FPS: https://news.ycombinator.com/item?id=49652089
In case you mistake him for an “AI booster”, you should see this guy’s other posts, he is extremely critical of the AI frontier labs and Tech Bros and this whole AI bubble.
But he is also a very experienced game developer, and under his control the latest models have pulled off these crazy feats. What you are reading is the analysis of a domain expert and what it means for the industry.
Please.