Live data from Hacker News

Being an old school web-based sports sim dev in the era of vibe coded games

zengm.com

51–60 of 61 posts

Re: Being an old school web-based sports sim dev in the era of vibe coded games

#51

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.

Look at steam releases. May 2025: 1727. May 2026: 1875 A year over year increase matching the same trend that has existed since 2017. The same pattern holds for every month this year except March (where there was an increase year over year of about 600 games). If you’ve ever been to a game dev forum, you’ll see that there are at least 10x as many people who want to make a game as there are people who have made a game…

But still how many of these games are successful?

Re: Being an old school web-based sports sim dev in the era of vibe coded games

#52
post #50

I have been building my own game and game engine for a while now, and cannot help but see whats really happening with vibe coded game generation: and investment into the content generation pipeline. I feel a solid game engine paired with a good content pipeline can ship games at such a rapid clup that the gameslop gets lost as the noise it is.

If you don't mind disclosing, for what type(s) of games is your game engine intended? (Also: I agree with your assessment. I'm not working on an engine, but I am working on a game, mostly/initially just for my own edification. It's fun to feel empowered to create again! (My personal circumstances had obstructed me until genAI's recent progress.))

It's generalized to the point where "the only limit is yourself"

In other words, its incredibly modular and lends to configuration flexibility.

Re: Being an old school web-based sports sim dev in the era of vibe coded games

#53

I have been building my own game and game engine for a while now, and cannot help but see whats really happening with vibe coded game generation: and investment into the content generation pipeline. I feel a solid game engine paired with a good content pipeline can ship games at such a rapid clup that the gameslop gets lost as the noise it is.

I'm not confident that the bottleneck in quality game development is "content." I can only see this accelerating the slop and drowning out the good games in slop.

Re: Being an old school web-based sports sim dev in the era of vibe coded games

#54
I started building a VR game during COVID and released it 2024. When it released, I was using GPT and Copilot to add a lot of quality-of-life stuff (like visual juice) faster.

Yesterday, I finally got around to setting Opus 4.8 on the codebase. It was able to find and correct numerous subtle performance issues.

Features I could no longer spend time implementing, it could one-shot in roughly 10 minutes (not without issues). I could also fan out agents to work on multiple things at once.

One thing I found is that the knowledge I gained from doing things by hand greatly helped reject bad AI generated ideas. For example, my game is a starfighter flight sim and one idea was to tick AI collision detection checks lower the further AI ships were away from the player, which for a flight simulator leads to a lot of crashing into the terrain. A great idea for an FPS, but a terrible idea for a flight sim where enemy ships are often very close to the terrain.

My takeaway is that we are in a golden era where we currently have projects that are half human coded, where AI can pickup the slack. But soon we will be in the Dark Ages where AI generates all the code, and the end result will be much worse as the devs begin to lose an understanding of what they are creating.

Re: Being an old school web-based sports sim dev in the era of vibe coded games

#55

I have been building my own game and game engine for a while now, and cannot help but see whats really happening with vibe coded game generation: and investment into the content generation pipeline. I feel a solid game engine paired with a good content pipeline can ship games at such a rapid clup that the gameslop gets lost as the noise it is.

I'm not confident that the bottleneck in quality game development is "content." I can only see this accelerating the slop and drowning out the good games in slop.

What do you believe is the bottleneck?

Re: Being an old school web-based sports sim dev in the era of vibe coded games

#56
post #44
post #4

Earlier quoted context omitted.

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”

Here's an example of this regarding the recent indie hit "Mina the Hollower." They were recently interviewed and asked the question "What is Yacht Club's stance on AI and has AI been used in the production of Mina the Hollower at all?" to which their reply was "We all got caught up in AI fever like the rest of the world, but we didn't find it was very effective for what we're doing. Maybe our work just isn't that gen…

The conversation around AI in games is such a polluted mess of confusion and bad faith. I would hate to have to answer such an interview question.

Recently I came across a game on Steam that was getting review-bombed because the devs admitted to using AI on an entirely different game. By "using AI" I mean they admitted to using Cursor of all things. Not assets, just a coding assistant.

If we're going to get backlash for stuff as stupid as this, it's probably best to just keep one's entirely mouth shut about all things AI.

Re: Being an old school web-based sports sim dev in the era of vibe coded games

#57

I started building a VR game during COVID and released it 2024. When it released, I was using GPT and Copilot to add a lot of quality-of-life stuff (like visual juice) faster. Yesterday, I finally got around to setting Opus 4.8 on the codebase. It was able to find and correct numerous subtle performance issues. Features I could no longer spend time implementing, it could one-shot in roughly 10 minutes (not without is…

I recently tried to learn gamedev with Claude as a tutor of sorts. It didn't end well. Claude confidently led me off a cliff and I had throw the whole thing in the trash. It seems there's just no shortcut around learning stuff the hard way. When I've got enough reps in to be able to tell smart vs. stupid decisions, I imagine it'll be a lot more useful, but at this point I suspect AI is far from being good enough to get us into your described Dark Ages.

Re: Being an old school web-based sports sim dev in the era of vibe coded games

#58
post #44
post #4

Earlier quoted context omitted.

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”

Here's an example of this regarding the recent indie hit "Mina the Hollower." They were recently interviewed and asked the question "What is Yacht Club's stance on AI and has AI been used in the production of Mina the Hollower at all?" to which their reply was "We all got caught up in AI fever like the rest of the world, but we didn't find it was very effective for what we're doing. Maybe our work just isn't that gen…

> "What is Yacht Club's stance on AI and has AI been used in the production of Mina the Hollower at all?" to which their reply was "We all got caught up in AI fever like the rest of the world, but we didn't find it was very effective for what we're doing. Maybe our work just isn't that generic! We've found some ways it can help... like Google or a thesaurus, but it hasn't affected what's in our game." [1]

Can you see how this intentionally coy and evasive answer was made specifically to not say "No, we didn't use AI." but still sound like "No, we didn't use AI." so that people wouldn't immeidately bust out pitchforks and start review bombing their game before it takes off?

Re: Being an old school web-based sports sim dev in the era of vibe coded games

#59

Earlier quoted context omitted.

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"

This reminds me of a boss I had 20 years ago that said devs were going to be replaced soon. Maybe he was 20 years early or maybe it's not happening now too.

Please note that I did not imply devs won't exist in my contrived fantasy.

Who do you think will be operating those mythological tools?:)

Re: Being an old school web-based sports sim dev in the era of vibe coded games

#60

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.

I've started trying to make some vibe coded games. The best analogy to use is AI image generation e.g. - someone posts a photo made with AI and your reaction is "that's amazing!" - then you generate an image and it's pretty good but not exactly what you want - then you try to get the AI to change the image to what you want and it's very difficult/requires a lot of steps More specifically, you can easily spin up a gam…

I've been experimenting with vibecoding with a 3D game with no engine, all in C++ with DX11, all-procedural modeling. My experience is you can quickly add a lot of features and mechanics that work semi-well but getting any one feature or scenario to work really well ends up "requiring" digging into the code and writing stuff yourself.

"Requiring" in the sense that while it might be technically possible to get the AI to do it, it becomes an incredibly annoying experience to repeatedly try and fail to get it to properly understand and implement what you want. This almost seems less about whether the AI is as smart or smarter than you or a better programmer or whatever, and more about the medium of natural language being worse than the medium of code for this.

Post reply on HN