We Put Claude Code in Rollercoaster Tycoon

(labs.ramp.com)

100 points | by iamwil 5 days ago

15 comments

  • pocketarc 6 minutes ago
    I love the interview at the end of the video. The kubectl-inspired CLI, and the feedback for improvements from Claude, as well as the alerts/segmentation feedback.

    You could take those, make the tools better, and repeat the experience, and I'd love to see how much better the run would go.

    I keep thinking about that when it comes to things like this - the Pokemon thing as well. The quality of the tooling around the AI is only going to be come more and more impactful as time goes on. The more you can deterministically figure out on behalf of the AI to provide it with accurate ways of seeing and doing things, the better.

    Ditto for humans, of course, that's the great thing about optimizing for AI. It's really just "if a human was using this, what would they need"? Think about it: The whole thing with the paths not being properly connected, a human would have to sit down and really think about it, draw/sketch the layout to visualize and understand what coordinates to do things in. And if you couldn't do that, you too would probably struggle for a while. But if the tool provided you with enough context to understand that a path wasn't connected properly and why, you'd be fine.

  • hk__2 23 minutes ago
    > The only other notable setback was an accidental use of the word "revert" which Codex took literally, and ran git revert on a file where 1-2 hours of progress had been accumulating.
    • Filligree 2 minutes ago
      Yet another reason to use Jujutsu. And put a `jj status` wrapper in your PS1. ;-)
  • nipponese 16 minutes ago
    > kept the context above the ~60% remaining level where coding models perform at their absolute best

    Maybe this is obvious to Claude users but how do you know your remaining context level? There is UI for this?

  • lukebechtel 45 minutes ago
    > We don't know any C++ at all, and we vibe-coded the entire project over a few weeks. The core pieces of the build are…

    what a world!

    • yoyohello13 25 minutes ago
      Everyone should read that section. It was really interesting reading about their experiences/challenges getting it all working.
    • AndrewKemendo 41 minutes ago
      I would’ve walked for days to a CompUSA and spent my life savings if there was anything remotely equivalent to this when I was learning C on my Macintosh 4400 in 1997

      People don’t appreciate what they have

      • lifetimerubyist 37 minutes ago
        It’s worse. They’re proud they don’t know.
        • risyachka 26 minutes ago
          Its like ordering a project from upwork- someone did it for you, you have no idea what is going on, kinda works though.
  • fnordpiglet 21 minutes ago
    Interesting article but it doesn’t actually discuss how well it performs at playing the game. There is in fact a 1.5 hour YouTube video but it woulda been nice for a bit of an outcome postmortem. It’s like “here’s the methods and set up section of a research paper but for the conclusion you need to watch this movie and make your own judgements!”
    • Sharlin 9 minutes ago
      It does discuss that? Basically it has good grasp of finances and often knows what "should" be done, but it struggles with actually building anything beyond placing toilets and hotdog stalls. To be fair, its map interface is not exactly optimal, and a multimodal model might fare quite a bit better at understanding the 2D map (verticality would likely still be a problem).
    • cyanydeez 16 minutes ago
      I was told the important part of AI is the generation part, not the verification or quality.
  • haunter 8 minutes ago
    This is what I want but for PoE/PoE2 builds. I always get a headache just looking at the passive tree https://poe.ninja/poe2/passive-skill-tree
  • equinumerous 13 minutes ago
    This is a cool idea. I wanted to do something like this by adding a Lua API to OpenRCT2 that allows you to manipulate and inspect the game world. Then, you could either provide an LLM agent the ability to write and run scripts in the game, or program a more classic AI using the Lua API. This AI would probably perform much better than an LLM - but an interesting experiment nonetheless to see how a language model can fare in a task it was not trained to do.
  • neom 12 minutes ago
    Wonder how it would do with Myst.
  • mentos 39 minutes ago
    The opening paragraph I thought was the agent prompt haha

    > The park rating is climbing. Your flagship coaster is printing money. Guests are happy, for now. But you know what's coming: the inevitable cascade of breakdowns, the trash piling up by the exits, the queue times spiraling out of control.

  • khoury 1 hour ago
    Can't wait for someone to let Claude control a runescape character from scratch
  • skybrian 1 hour ago
    Would a way to take screenshots help? It seems to work for browser testing.
    • joshribakoff 1 hour ago
      I’ve been doing game development and it starts to hallucinate more rapidly when it doesn’t understand things like the direction it placing things or which way the camera is oriented

      Gemini models are a little bit better about spatial reasoning, but we’re still not there yet because these models were not designed to do spatial reasoning they were designed to process text

      In my development, I also use the ascii matrix technique.

      • kleene_op 47 minutes ago
        Spatial awareness was also a huge limitation to Claude playing pokemon.

        It really seems to me that the first AI company getting to implement "spatial awareness" vector tokens and integrating them neatly with the other conventional text, image and sound tokens will be reaping huge rewards. Some are already partnering with robot companies, it's only a matter of time before one of those gets there.

        • nszceta 19 minutes ago
          This is also my experience with attempting to use Claude and GLM-4.7 with OpenSCAD. Horrible spatial reasoning abilities.
      • hypercube33 20 minutes ago
        I disagree. With opus I'll screenshot an app and draw all over it like a child with me paint and paste it into the chat - it seems to reasonably understand what I'm asking with my chicken scratch and dimensions.

        As far as 3d I don't have experience however it could be quite awful at that

      • miohtama 48 minutes ago
        They would need a spatial reason or layout specific tool, to translate to English and back
        • falcor84 13 minutes ago
          I wonder if they could integrate a secondary "world model" trained/fine-tuned on Rollercoaster Tycoon to just do the layout reasoning, and have the main agent offload tasks to it.
  • HelloUsername 1 hour ago
    *OpenRCT2
  • nacozarina 5 days ago
    next up: Crusader Kings III
    • Deukhoofd 46 minutes ago
      Crusader Kings is a franchise I really could see LLMs shine. One of the current main criticisms on the game is that there's a lack of events, and that they often don't really feel relevant to your character.

      An LLM could potentially make events far more aimed at your character, and could actually respond to things happening in the world far more than what the game currently does. It could really create some cool emerging gameplay.

    • mcphage 1 hour ago
      > You’re right, I did accidentally slaughter all the residents of Béziers. I won’t do that again. But I think that you’ll find God knows his own.
      • Forgeties79 30 minutes ago
        Paradox future hire right here
  • huflungdung 38 minutes ago
    [dead]
  • azhenley 39 minutes ago
    Edit: HN's auto-resubmit in action, ignore.
    • Bluescreenbuddy 35 minutes ago
      What
      • eterm 32 minutes ago
        So, this link is actually 5 days old, if you hover the "2 hours ago" you'll see the date 5 days ago.

        HN second-chance pool shenanigans.