Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

zengm.com

Post reply on HN
Print view View original

21–30 of 61 posts

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

#21

Post by akoboldfrying »

I always enjoy hearing the thoughts of someone who took a slightly different path (indie game development being a favourite), and isn't committed to advancing some thesis -- pressing me to love this or hate that. It feels like it gives my brain a chance to step back from dopamine- or rage-induced habits and just... connect with other people.

I don't know what will happen either. I hope that you and I and other hardworking, basically good people will continue to have a somewhat meaningful, somewhat pleasant existence in the post-AI world, and I think that might be possible, but I just don't know.

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

#22

Post by owebmaster »

pennaMan wrote: post #14
tripledry wrote: post #12

Earlier quoted context omitted.

Highly doubt it.

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.

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

#23

Post by sarchertech »

schnitzelstoat wrote: post #2

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 (it’s probably much higher than 10x).

If games were easy to vibe code, or if AI speed up game dev 10x, I would expect it to almost immediately show up as a flood of games on Steam.

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

#24

Post by whizzter »

kakacik wrote: post #20
adornKey wrote: post #16

Earlier quoted context omitted.

Hm. Nowadays a lot of games look alike. They use some 3D-Engine and most of the work is in the 3D-modelling and writing some interesting scripts. For modelling and scripting I think we're not far away. A lot of games just reused old historical stories or fiction and a lot of stories feel like cheap soap operas. As soon as an AI can separate the good from the bad scrips it'll be mostly done.

Clearly you don't work in game development, this comment put a smile on my face. Although I expected a bit more from hacker news crowd

You overvalue the HN crowd (or undervalue the AI hype-machine) considering you're downvoted and GP is upvoted (Another gamedev here smiling at GP's comment).

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

#25

Post by everyday7732 »

schnitzelstoat wrote: post #2

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.

enclose.horse is somewhat popular and successful, posted here on hacker news a while ago.

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

#26

Post by inigyou »

tripledry wrote: post #12
AndrewOMartin wrote: post #10

Earlier quoted context omitted.

We might get a powerful enough model to run "Claude, build me GTA6" before GTA6.

Highly doubt it.

It's not hard if you just imagine a slop re-skin of any other GTA of similar game.

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

#27

Post by gafferongames »

whizzter wrote: post #24
kakacik wrote: post #20

Earlier quoted context omitted.

Clearly you don't work in game development, this comment put a smile on my face. Although I expected a bit more from hacker news crowd

You overvalue the HN crowd (or undervalue the AI hype-machine) considering you're downvoted and GP is upvoted (Another gamedev here smiling at GP's comment).

Yet another classic unskilled but unaware of it from the hacker news crowd (another professional gamedev here).

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

#28

Post by short_sells_poo »

sarchertech wrote: post #23
schnitzelstoat wrote: post #2

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…

I wonder if there's also another aspect: Games have to be fun for humans and this involves a lot of trial and error with actual humans in the loop.

You can't just spin up a bunch of claude agents to implement a game for you, because implementing a new feature requires that you playtest it with a fairly fine granularity as it's being implemented.

You can save some time implementing various subsystems with llms, but at some point the dev cycle will turn into: tweak things, build, play, rinse and repeat.

I'm sure asset flip and friendslop games will become cheaper to make with ai tooling, but if you want to make a genuinely good game, it will have to involve humans actually playtesting it during development.

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

#29

Post by Cthulhu_ »

sarchertech wrote: post #23
schnitzelstoat wrote: post #2

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…

Thing is, Steam already was flooded with shovelware - I suspect a percentage of new relelases includes plenty of AI usage that was previously made in other ways (e.g. using asset libraries)

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

#30

Post by Cthulhu_ »

adornKey wrote: post #16
tripledry wrote: post #12

Earlier quoted context omitted.

Highly doubt it.

Hm. Nowadays a lot of games look alike. They use some 3D-Engine and most of the work is in the 3D-modelling and writing some interesting scripts. For modelling and scripting I think we're not far away. A lot of games just reused old historical stories or fiction and a lot of stories feel like cheap soap operas. As soon as an AI can separate the good from the bad scrips it'll be mostly done.

I'm sure AI will be used in asset generation but it'll be in deployed similarly as procedural generation of mass assets like trees and npcs.

I don't yet see it used for characters as they quickly become kind of generic / predictable.

Post reply on HN