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

51–60 of 236 posts

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

#51

Post by Xss3 »

brookst wrote: post #43
zerr wrote: post #38

Earlier quoted context omitted.

Delegating all the fun of making games to LLMs and leaving only the boring part for yourself puts you in the infinite procrastination mode. Watching LLM generating the code doesn't help with producing the dopamine.

Some people think the fun part is the requirements and gameplay, and code is the boring part.

Games dev at my alma mater was split into two courses, bachelor of science (which focused on the technical side) and bachelor of arts which focused on 3d modelling, animation, concept art, etc.

Both groups wanted to make games.

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

#52

Post by hollowturtle »

raincole wrote: post #50
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…

> we didn’t see a proportional explosion of good game We definitely saw an explosion of good indie games by around early half of 2010s. Whether it had anything to do with Unity is another moot point.

even indie games are painstackingly hard to develop, don't make the mistake of associating indie with easy, rather harder i'd say if you go solo or with a few others in a very high risk job

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

#54

Post by nahnahno »

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…

This is not true in my experience. Cranking out code is obviously the bottleneck, unless you have the luxury of working on a very narrow problem. The author describes a multi-modal project that does not afford this luxury.

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

#55

Post by lkramer »

hollowturtle wrote: post #52
raincole wrote: post #50

Earlier quoted context omitted.

> we didn’t see a proportional explosion of good game We definitely saw an explosion of good indie games by around early half of 2010s. Whether it had anything to do with Unity is another moot point.

even indie games are painstackingly hard to develop, don't make the mistake of associating indie with easy, rather harder i'd say if you go solo or with a few others in a very high risk job

I don't think the post you replied to says otherwise, but Unity meant there was now a path with professional grade tools without spending a fortune. It definitely did create a new wave of indie games, some of them amazing.

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

#57

Post by sarchertech »

Profan wrote: post #16
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??

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.

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

#58

Post by hollowturtle »

hollowturtle wrote: post #53

[flagged]

The only reason I can think of is some sort of virtue signaling, like to promote one self. But even then why not spending ~6 months and super polish the game that would make you look like a rockstar? Eventually using ai in the process to learn where it can be useful... otherwise i don't understand

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

#60

Post by petralithic »

fsloth wrote: post #29
virgildotcodes wrote: post #22

Earlier quoted context omitted.

[flagged]

” but it only did so by stochastically parroting hallucinated slop” I’m not sure what the argument here is. That you should only use the most primitive tools available? ”LLMs suck” arguments sound exactly like ”IDE:s suck! True engineers writes everything in notepad.exe”. Or ”debuggers suck! Use only printfs!” People have different ways of cognition and different strategies of problem solving and tool use. The fact y…

They're being sarcastic, they're parodying common objections people have about AI, it's not about the technology at all but about their feeling of obsolescence which impacts their pride.
Post reply on HN