Hacker News

Top stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. PipePipe: NewPipe hard fork implementing SponsorBlock (github.com/infinityloop1308)
    133comments
  2. Show HN: Reladraw – A diagram language where you decide where to place things (github.com/reladraw)
    26comments
  3. DeepSeek Elastic Compute (DSec) (arxiv.org)
    13comments
  4. A searchable library of forgotten public-domain film clips from 1915 onward (movingimagearchive.com)
    16comments
  5. Welcome to the Medical Clinic at the Interplanetary Relay Station (lightspeedmagazine.com)
    —discuss
  6. Drawgent: Coding agent on a live Excalidraw canvas (tangled.org)
    28comments
  7. Stop Sending Pictures of Your Palm (bbc.com)
    2comments
  8. LA Metro has some of the slowest escalators on Earth (basin.la)
    8comments
  9. Fifteen years later, the Apple Cards origin story (lexontech.org)
    68comments
  10. The Lost Atomic Update on Loongson CPU (jia.je)
    4comments
  11. Modern Object Pascal Introduction for Programmers (castle-engine.io)
    44comments
  12. Revealing the details of how OpenAI agents hacked Hugging Face (swarmtraces.org)
    436comments
  13. The Rise of Audio AR (dbreunig.com)
    5comments
  14. We're gonna need a lot more mathematicians (terrytao.wordpress.com)
    442comments
  15. ASML currently sells no chipmaking machines in Europe, executive says (nltimes.nl)
    164comments
  16. Analyzing Frontier Model Progress with My Favourite Game: Prince of Persia (blog.priyan.in)
    29comments
  17. Breaking Up with Google Play: Why Conversations Is Now Free (gultsch.de)
    231comments
  18. Plan mode is dead (aymannadeem.com)
    465comments
  19. How to keep enjoying programming in a world of LLMs (haskell.org)
    171comments
  20. Plunging test scores are a slow-moving catastrophe (economist.com)
    268comments
  21. Probing picosecond depairing currents in type-II superconductors (nature.com)
    1comments
  22. Ollaya – Ollama for open-source, Jev-style decision models (ollaya.dev)
    139comments
  23. Reflections on 1,000 Days of Math (gmays.com)
    32comments
  24. The Murky History of Soviet-Born Tetris (mitpress.mit.edu)
    28comments
  25. OpenAI bots meddled with multiple US Government agency sites (bbc.com)
    115comments
  26. Automattic has a new board after failed attempt to put CEO on leave (techcrunch.com)
    116comments
  27. Floci: Locally emulating any cloud service (floci.io)
    28comments
  28. Show HN: Jev Plays Pokémon Red (jev-pokemon.vercel.app)
    109comments
  29. Experiencing writing at our recent Chinese calligraphy workshop (viewsproject.wordpress.com)
    1comments
  30. Is your Postgres migration safe or not safe? (safenotsafe.dev)
    40comments

Analyzing Frontier Model Progress with My Favourite Game: Prince of Persia

46 pointsby 1d agoblog.priyan.in
28 comments
6h agoHN ↗

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?

6h agoHN ↗

"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.

5h agoHN ↗

Or having another model proofread the prompts and write clearer instructions

5h agoHN ↗

Unsurprisingly it was buggy without the obligatory "Make no mistakes."

5h agoHN ↗

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?

5h agoHN ↗

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.

2h agoHN ↗

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?

6h agoHN ↗

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.

5h agoHN ↗

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

5h agoHN ↗

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.

3h agoHN ↗

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.

3h agoHN ↗

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.

4h agoHN ↗

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

6h agoHN ↗

Off tangent but the latest prince of Persia game is really fun

5h agoHN ↗

I played The Lost Crown and it's top tier, I assume you're talking about The Rogue?

5h agoHN ↗

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.

5h agoHN ↗

It's one of the best recent metroidvanias. It deserves a lot more attention. I was surprised by how good it was.

4h agoHN ↗

However, it's Ubisoft and therefore tainted.

5h agoHN ↗

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

5h agoHN ↗

Share it when you're done! Even if it isn't complete complete.

5h agoHN ↗

Just one thing you could do is not drag Prince of Persia into this.

Please.

4h agoHN ↗

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!

3h agoHN ↗

Just about every PC game in 1989 ran on an XT with CGA.

1h agoHN ↗

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.

2h agoHN ↗

Instead of fixing a broken version, maybe each model should have started from scratch

15m agoHN ↗

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.