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

Making games in Go: 3 months without LLMs vs. 3 days with LLMs

marianogappa.github.io

Post reply on HN
Print view View original

91–100 of 236 posts

Re: Making games in Go: 3 months without LLMs vs. 3 days with LLMs

#91

Post by jama211 »

rustystump wrote: post #81

I have done a decent amount of hobby game dev including completing several games. The comments here i think show a strong lack of real game dev knowledge. Coding is a hard part of game dev. Coming up with interesting novel mechanics or plays on known genres is rather easy but bringing them to life is hard esp the code. Multiplayer vampire survivors but with giant battletech mech customization. See, very easy. Good lu…

I largely agree with your point, but interestingly I’ve always found the ideas and blue sky thinking game design part the hardest personally. I can code nearly any game mechanic at this point, but struggle with the writing/creativity part of game development. If you find that easy, you should consider yourself rather blessed, it doesn’t come naturally to us all.

Re: Making games in Go: 3 months without LLMs vs. 3 days with LLMs

#92

Post by rustystump »

mattbuilds wrote: post #18
deadbabe wrote: post #2

A developer who can build a game by hand in 24 hours could probably build and publish something very polished and professional on Steam within 3 days using LLMs, which leads to some kind of software Fermi paradox: where are all the games??

I’m sorry but the difficult part of making games isn’t the coding, it is making something that is appealing and enjoyable to play. An LLM isn’t going to help with that at all. How is it going to know if something is fun? That’s the real work. Also the idea that a dev who could making a game in 24 hour would create something professional and polished in 3 days is a joke. The answer to “where are all the games” is simp…

This is almost on the money. Making something fun often requires coding, art, sound etc to bring the fun out. So in fact coding is the difficult part, along with all the other stuff needed for something to be fun. Imo tooling like ue blueprints and visual scripting is in the coding bucket.

Re: Making games in Go: 3 months without LLMs vs. 3 days with LLMs

#93

Post by Ekaros »

deadbabe wrote: post #2

A developer who can build a game by hand in 24 hours could probably build and publish something very polished and professional on Steam within 3 days using LLMs, which leads to some kind of software Fermi paradox: where are all the games??

That misses huge parts of games. Actual content. Could be story, could be levels, could be features, could be item design, could be balance.

All of these take time and many of them are iterative processes where you might not even know if it fits or is right before multiple tries.

Re: Making games in Go: 3 months without LLMs vs. 3 days with LLMs

#94

Post by maloga »

znort_ wrote: post #71
kousthub wrote: post #34

Asking for information - Is Go/wasm doing something here which React/JavaScript cannot?

in this case, no. it's a client game and performance isn't at all critical, so the state and loop could be trivially handled by a regular js function. if at some point a server architecture was desired, it would be trivial to host that function on node. my take: as a backend developer he was fixated with the idea of having a server no matter what (if your only tool is a hammer, everything looks like a nail), and as g…

Nah, whatever bug you're referring to is my fault, haha, don't blame the LLM. But in between game state bugs are very unlikely, haha: https://github.com/marianogappa/escoba-de-15/blob/main/src/A...

I can't imagine state surviving a location reload with nothing on local storage and no server.

Re: Making games in Go: 3 months without LLMs vs. 3 days with LLMs

#95

Post by milesvp »

kaiokendev wrote: post #67
starchild3001 wrote: post #30

What I like about this post is that it highlights something a lot of devs gloss over: the coding part of game development was never really the bottleneck. A solo developer can crank out mechanics pretty quickly, with or without AI. The real grind is in all the invisible layers on top; balancing the loop, tuning difficulty, creating assets that don’t look uncanny, and building enough polish to hold someone’s attention…

> It’s like the rise of Unity in the 2010s: the engine democratized making games, but we didn’t see a proportional explosion of good game, just more attempts. But we did? We've come a long way from the limited XBLA catalog. It didn't happen overnight, but doubtless we wouldn't have the volume of games we have today without Unity, Godot, Gamemaker, Renpy, RPG Maker...

> we didn’t see a proportional explosion of good game, just more attempts.

I'm not sure the 2 of you are disagreeing. We definitely saw an explosion of indie games. In 2010, there were less than 10 indie games released on steam per month. By 2022, there were ~500/mo, and today there's ~750/mo (I expect that the 250/mo jump around 2022 can likely be attributed to LLMs).

What's hard to say is if this increase significantly increased the number of good games. Mostly because "good" is highly subjective, but also, I think something else happens. I've been playing games for the better part of 40 years, and what I noticed, is that in that time, the number of must play games each year has largely gone unchanged, despite the industry being orders of magnitude larger than it was 40 years ago. But that is also tricky, because 2 things happen every year, our standards get higher, and our preferences get more refined.

https://steamdb.info/stats/releases/?tagid=492

Re: Making games in Go: 3 months without LLMs vs. 3 days with LLMs

#97

Post by tialaramex »

yonatan8070 wrote: post #69
zahlman wrote: post #64

Earlier quoted context omitted.

> The interesting question to me is: what happens when AI can not only implement but also playtest -- running thousands of iterations of your loop, surfacing which mechanics keep simulated players engaged? How is AI supposed to simulate a player, and why should it be able to determine what real people would find engaging?

Game companies already collect heaps of data about players, which mechanics they interact with, which mechanics they don't, retention, play time, etc. I don't think it's much of a stretch to take this data over multiple games, versions, and genres, and train a model to take in a set of mechanics, stats, or even video and audio to rate the different aspects of a game prototype. I wouldn't even be surprised if I heard…

Ah yes, the huge game companies, definitely outfits I would associate with producing fun games I haven't seen before and not churning out Existing Franchise N+1 every year with barely perceptible differences and higher prices each iteration.

Re: Making games in Go: 3 months without LLMs vs. 3 days with LLMs

#98

Post by MarceColl »

sarchertech wrote: post #57
Profan wrote: post #16

Earlier quoted context omitted.

The part of this that always confuses me is like nobody's aware gamejams exist, this has been a thing long before the LLM craze and people have been producing decent games on very limited timespans already, but people are forgetting how insanely high the bar is now, LLMs do not even remotely begin to fix the problem of your competition being incredibly stiff. Just look at something like ludum dare and all the top ent…

> are all usually quite polished given the timespan The open secret is that they might not start coding or building assets until the start time, but they have spent a lot of time thinking about the ideas before then (even when the "theme" isn't known before hand people tend to make ideas fit theme with tweaks), which just speaks to the "code is not the bottleneck" thesis.

For one datapoint, I've participated in many gamejams and I've never ever spent any time beforehand thinking about ideas.

Re: Making games in Go: 3 months without LLMs vs. 3 days with LLMs

#99

Post by davepeck »

zerr wrote: post #36
starchild3001 wrote: post #30

What I like about this post is that it highlights something a lot of devs gloss over: the coding part of game development was never really the bottleneck. A solo developer can crank out mechanics pretty quickly, with or without AI. The real grind is in all the invisible layers on top; balancing the loop, tuning difficulty, creating assets that don’t look uncanny, and building enough polish to hold someone’s attention…

My litmus test for generative AI: generate a complete spritesheet for a 2D pixel art action game, e.g. only for the battle tank or main hero movements. No success so far.

Ive never once successfully gotten a usable sprite sheet out of ChatGPT. The concept seems foreign to it and no matter how hard I try to steer it it’ll find a way to do something hopeless (inconsistent frame sizes; incoherent animations; no sense of consistent pixel sizes or what distinguishes (say) 8-bit from 16-bit era sprites; it’ll draw graph paper in the background for some reason; etc etc.). If anyone has a set of magic prompts for this, I’d love to learn about it. But my suspicion is that it’s just fundamentally the wrong tool for the job — you probably need a purpose-built model.

Re: Making games in Go: 3 months without LLMs vs. 3 days with LLMs

#100

Post by maloga »

zerr wrote: post #36
starchild3001 wrote: post #30

What I like about this post is that it highlights something a lot of devs gloss over: the coding part of game development was never really the bottleneck. A solo developer can crank out mechanics pretty quickly, with or without AI. The real grind is in all the invisible layers on top; balancing the loop, tuning difficulty, creating assets that don’t look uncanny, and building enough polish to hold someone’s attention…

My litmus test for generative AI: generate a complete spritesheet for a 2D pixel art action game, e.g. only for the battle tank or main hero movements. No success so far.

Agreed, I got an LLM to build me a Super Mario Bros game with 0 code and it's playable after 2 prompts but I'm stuck with the spritesheet as well.
Post reply on HN