Comment by ksaun
11 days ago
I was an experienced game designer and producer (mostly RTS and narrative RPG). Some years ago, my career was derailed by major health developments. Since then, I haven't been able to work as I once did. I didn't expect I'd be able to meaningfully contribute to a game again.
Earlier this year, a colleague encouraged me to experiment with Claude Code. So now I have a little game project. :) Being unfamiliar with genAI, I chose something modest so that I'd more likely be able to push it to a fairly polished state.
Tentatively called Vestiges, it's a single player 2D roguelite strategy game with meta progression, some narrative, and a card minigame (the latter inspired by work I did on Star Wars: Knights of the Old Republic II). It's set in the near future. You are using software (the game) to navigate a person's digitized mind, reading their memories.
I hope to have a playable demo within the next month or so.
I certainly would love to see the demo.
Star Wars nut here.
For all the bad rap that AI gets in game development, stories like this should be heard more. I occasionally get tendinitis and I can't code for the entire day like when I was young. I get some relief dictating to the AI when I need to rest my hands. I can imagine it's a much bigger help for someone who is struggling with worse.
I've always wanted to make a game but never chased that down as I took a different career path. I seen unreal is coming out with an mcp type thing which got me thinking about looking into trying. I liked the old Thief games and would like to make something along those lines but with a different flavor. Sounds like a fun game. Keep us Posted :)
I'd like to hear more about your experience using AI for game development.
I've had a strangely asymmetric experience where frontier models are failing apparently basic tasks like making changes to a Pong clone without breaking it, while the same models are successfully designing and implementing multiplayer servers with rollback netcode!
I think it has to do with what they can and cannot verify (i.e. they can't actually play pong to see if they broke it), but I'm not sure.
(Also happy to hear anyone else's experiences on this matter!)
Overall, I've been very pleased, though I have seen inconsistency like you mention.
First, some background: At the start, I used Sonnet, but after a couple weeks, I'd switched to mostly Opus. I've used Fable when available. For any significant new feature or work, I use /brainstorming (superpowers plug-in). For Vestiges, I haven't written any design documentation per se. I'll start off a /brainstorming with a hefty prompt, maybe 5-15 lines. Throughout the brainstorming steps, I'll think of additional ideas/details about the feature, etc. I'll just add the change/addition to my answer to whatever question it had asked and it seems to handle that fine.
Sometimes I catch things in the subsequent design review process and it handles new guidance well there, too. Typically, I've left some details underspecified and Claude fills in the gaps -- often quite well, but I have to pay attention. The details that it decides later in the process (the implementation steps) are often solid, but when they're not, it's easy to iteratively fix later. Most of the time when Claude asks for clarity on a detail, its recommended option is what I wanted.
It's been rare for Claude to do something that just didn't work (but it has happened occasionally). I have found that it's not good at imagining the player's perspective; it doesn't consider the player's cognitive load for UX considerations, for example. That seems to be consistent with your observation about what they can and cannot verify. A recent instance was when I added a tutorial (which was much more scripted than regular gameplay, providing a more specific experience); I ultimately had to get very directly involved to get to the quality I wanted.
Vestiges doesn't have any gameplay involving timing like Pong does. I could imagine that sort of gameplay being harder for it to get right.
(I hope that covers some of what you were seeking!)
>Vestiges doesn't have any gameplay involving timing like Pong does. I could imagine that sort of gameplay being harder for it to get right.
Thanks. Yeah I think that's the main thing. They can look at pictures (although I've had some amusing results with that, too...), so theoretically they could play a game frame by frame if they run it very slowly. That would just very slow (like 10 minutes per 1 second of gameplay) and very expensive.
But basically, they can't "see video" yet, so they're blind in that domain. They can only see static images, not movement.
I expect this to be solved eventually, either with some new architecture (Google is doing a lot of interesting work in this space), or -- and this is kinda funny -- just running them really fast. The labs are experimenting with specialized hardware (e.g. Cerebras) lately, which can do inference at thousands of tokens per second, and several of them have plans to offer it in the next few weeks.
In other words, I think we're going to get around the "time-blindness" issue, in the short term, by just... running them really fast. (Then it would only take 1 minute per second of gameplay, instead of 10...)
Unfortunately, specialized inference hardware massively increases the per-token costs, as well as the tokens per second, so... it's not going to be a practical option for a little while!
--
Re: Superpowers: Thanks for the tip, that sounds very cool.
1 reply →
I've been having a bunch of fun working on a couple games on a new platform - everything (platform and games) developed with AI.
quackwave.com
Hasn't really been stress tested yet (this is the first time I'm mentioning it publicly), but it's been fun playing with friends & family and iterating.
Party game platform, think "jackbox but no host screen" - just need a web browser open on phone/tablet/PC.
Your comment matches my experience: it has to do what can and cannot be verified. As an example, it was much easier to have AI write a large e2e test using Playwright (then add test cases and expand) than to assume it'll correctly fix bugs without guidelines like this. Also, the human loop is still important in things like screenshot verification - but the frontier models are getting even better here so I'm not sure for how much longer this will be true. The ratio of test code to production code is a bit over 2:1 right now.
I have an amusing update to report, I've checked one of the major new features that was added a few days ago. It turns out it was implemented backwards, and in a way which defeats the entire purpose.
Nevertheless, several thousand lines of test code were added, and all tests pass!
I found this particularly amusing because, I've been obsessed with correctness and verification lately, thinking about rewriting the game in Rust, and adding formal verification to the game.
What I realized here is that, this wouldn't have helped at all. The AI would have just written the wrong code in Rust, and then written a mathematical proof that the wrong code is correct...
1 reply →
This an inspirational comment, thanks for posting it! I love that more and more people are being enabled (or re-enabled in your case) as software developers thanks to ai.
Big fan of SW:KOTOR series. Would love to test Vestiges when ready.
You should consider creating the game on Steam, so you can start building your audience.
Thanks! I've been hesitant about Steam because of the strong anti-genAI sentiments there. (And the initial fee to set-up a game's page.) You are right, though, and I probably should just push past my reservations.
(When I began this effort, I was just enjoying feeling productive again and didn't have any real plan to release. But I've been pleased enough with how it's been coming along that I've started seriously thinking about it.)
The anti-AI crowd on Steam only really seems to care about it being used for art, from what I've seen in reviews.
3 replies →
Where can I subscribe for updates?
Glad to hear. I could say I'm in a similar position actually, but my setbacks have been more psychological.
I am also interested in trying this game out! And I'm really glad to hear how agentic coding got you back in the game (literally)!
I would like to play this demo when it comes out.
That’s just pure pazaak! Would totally like to see this game
Yes, the minigame is like Pazaak. I've prototyped two more radical variants that might also make the cut.
I'd be interested in the demo!!
I'd love to try it out too.
[dead]