The October inflection point for vibe game development

hackerbone

its only a few months away when we'll be vibe coding GTA 7 full e2e - make no mistakes kinda vibe

Sphax

I'm not looking forward to playing vibe coded games, but yes I feel like models are good enough today to write small scoped games. I used Sol and GLM 5.3 Flash to produce a prototype of a tower defense game for myself, and it works just fine. I _am_ looking forward however to game developers using AI to debug and optimize their games. Let's squeeze all the performance we can get from existing hardware.

angusturner

To keep some perspective, I encourage people to name one single cultural artifact (picture, video, game, music, book, etc) that was improved, or made substantially possible, by AI. Ideally something that has moved you or provoked a lasting response. Then try to think of examples where Generative AI has betrayed a lack of creativity or care from the creator, and thus left a sour or ambivalent impression. Personally, I can't do the former and the latter is depressingly easy.

simonw

The other relevant trend from the last few weeks has been coding agent game decompilation and remixing. Here's a good piece about that: https://popcar.bearblog.dev/ai-is-mass-decompiling-games-tha...

frabjoused

This is a game where the work was actually put in: https://thesecretsproject.com

david2ndaccount

Counter point: a buddy of mine who doesn’t know how to program has been vibe-coding a video game for the last month. He got very excited early on with what he thought was quick progress, but it’s been a month and he still doesn’t have anything approaching a game or even what he wants.

Silamoth

Wow, we really do live in the worst timeline. At least a lot of gamers are rallying against generative “AI” slop assets, and indie devs are largely against generative “AI” in general. But yikes, this is just unfortunate. I don’t want the games industry to be polluted with slop that has no soul. But also, I want opportunities for people to learn or just exist in game development via smaller projects. There is some market for web games, casual games, and generally small games. These markets can be great for indie devs and beginners. But if we lose that market to the slop machine, real people will lose a lot of these opportunities.

2001zhaozhao

AI has been absolutely great for serious game dev as well. I am now completing dozens of tickets a week on my game engine and building features and architectures I've planned and theorized for years but never had the time to actually build them. Seeing them come to fruition one by one over the last few weeks and months has been incredibly rewarding. For example, I've long wanted to do a specific architectural approach that allows my Minecraft server's players and standalone game players to crossplay with each other. Now it's actually happening! I think the problem in the future will not be making games, it will be standing out because games are becoming easier and easier to make nowadays! There are still many game genres, especially multiplayer, that suffer from not having a big enough playerbase and too much fragmentation can definitely worsen the game experience there.

jakubmazanec

Counterpoint: trying to use Opus 5.5 to generate game design ideas, and it still sucks so much. It is always trying to see steer me into taking definitive decisions, while I'm trying just to explore the design space and compare various ideas against each other. Muddled, incoherent text, and not following my instructions make the process infuriating, and not very useful.

xyzsparetimexyz

> If you are offended by AI-generated art, AI-generated music, AI-generated writing, and AI-generated code, I have bad news for you: vibe coded games combine all of those at once. Yeah this is a major problem. At least do one of these yourself. > And if the game isn’t fun enough, add this: > Make it a LOT more fun I think theres also a certain quality that AI is missing in HOW it creates '''art''' like this. Games are often fun but they're not ABOUT having fun. Same way as how some of the best movies aren't always enjoyable to watch. I don't believe that an AI created soulslike would be any good because it would miss that some stuff is meant to feel frustrating or kinda bs or unfair at first.

arm32

Counter-point: I played the games that Mr. Willison said "didn't suck", and I can confirm that they actually kinda do suck , really bad, and I was really bored, overwhelmed, or a strange mixture of both, throughout the gameplay of them. We need to not glaze it so much. It's cool that a rock put these demos together, but they're not "really fun". Not even close. The UI is pretty thanks to the Claude Design's injected stylesheet doing a lot of heavy lifting. Also, it's been easy to make not "really fun" games since the late 90's with no-code game maker tools. Klik & Play anybody? GameMaker? The only difference is now, thanks to the hard work of Three.js and browser tech contributors—the graphics are better.