Being an old school web-based sports sim dev in the era of vibe coded games
18 points
2 days ago
| 1 comment
| zengm.com
| HN
schnitzelstoat
1 hour ago
[-]
Are there any popular/successful vibe-coded games? I suppose perhaps they wouldn't disclose that it was vibe-coded but I'm not aware of a single one.
reply
utopiah
47 minutes ago
[-]
> Are there any popular/successful vibe-coded games?

Fair question... I'd even go as far as broadening the scope :

Are there any popular/successful vibe-coded anything?

And by popular/successful I don't mean bought Github stars from other GenAI/LLMs related project as it's been a demonstrated practice https://awesomeagents.ai/news/github-fake-stars-investigatio... for that specific domain now.

reply
jvanderbot
38 minutes ago
[-]
At some point in the apparently-impending "software is free" era, s/w stops being a product that has to be "popular" and starts being mostly bespoke. One possible future is that your machine does you want because you have a local agent molding it into the right form all the time.

Bit of a stretch, but possible. I've had agents write 100x more code for me _to be productive at things_ than they do for new projects I want to sell/share.

reply
yieldcrv
17 minutes ago
[-]
yes, there are

no, most won’t burn themselves by publicly linking them as vibe coded

there is that ny times article about the peptide guy and lovable showcase by revenue though. I guess next up are even more disqualifiers about the term “successful”, but my outstanding question is who cares? What does convincing you buy, an Anthropic pro subscription at best?

reply
pennaMan
8 minutes ago
[-]
don't ask how the sausage is made
reply
yoz-y
1 hour ago
[-]
Turns out making a game, even with full help of the LLM power is still a massive effort most people won’t go through.

Even simpler but non-trivial programs require a lot of back and forth. So in the end it will be the same kind of motivated people that will be able to produce something good. We’re nowhere near “Claude, build me GTA6”

reply
AndrewOMartin
25 minutes ago
[-]
We might get a powerful enough model to run "Claude, build me GTA6" before GTA6.
reply
tripledry
10 minutes ago
[-]
Highly doubt it.
reply
pennaMan
6 minutes ago
[-]
someday we will have models that can resolve physics to such degree to predict the future with surgical accuracy and when someone says "maybe models will become advanced enough to create a whole other universe from scratch" you will be there saying "highly doubt it"
reply
grebc
1 minute ago
[-]
Someday.
reply
adamzbik
57 minutes ago
[-]
S&box is a good example of how the scene might look in the LLM era. They made games easy to make and publish, and while Garry's Mod always had a hacky, rough vibe to the available game modes (Source engine magic + CSS textures), you'd always feel that the games were made by people.

Fast forward to 2026 and the next generation platform is here, and while there are unique, passion projects available, most of the discover screen is filled with vibe coded xp farming games with AI slop thumbnails. The issue is so big Facepunch had to actively derank and punish games that would do this, because the "marketing" content was so detached from the game (despite everything being AI generated pretty much).

reply
SpaceNoodled
1 hour ago
[-]
If there truly were, I'm sure we wouldn't hear the end of it. However, the state of the art is all hype and no substance, i.e., slop.
reply
rvz
59 minutes ago
[-]
We would have heard about one already by now but it appears that we are still waiting.

Or maybe it is not worth the time and tokens spent to vibe code yet another Minecraft / Roblox clone that makes no money.

reply