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

161–170 of 236 posts

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

#161

Post by sarchertech »

famouswaffles wrote: post #151
sarchertech wrote: post #124

Earlier quoted context omitted.

There must be a huge push end of year. >How many games do you imagine can be released per day even with the help of current Sota LLMs ? Given the number of people who want to make games—if code is the bottleneck, and LLMs can really make you hugely more productive, I’d expect to see an actual explosion. My experience is that neither of those assumptions are true though.

>Given the number of people who want to make games—if code is the bottleneck Game development is not a zero sum game. There can be multiple bottlenecks or difficult hurdles. >and LLMs can really make you hugely more productive, I’d expect to see an actual explosion. Well growth was double the previous year. Maybe you might not call that an explosion, it's still a very noticeable uptick.

It is possible that LLMs boost productivity by 2x-10x and there’s another bottleneck that limited the growth to a few thousand games.

I think it’s much more likely that LLMs don’t actually boost productivity all that much.

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

#162

Post by ryoshu »

georgeecollins wrote: post #145
yonatan8070 wrote: post #69

Earlier quoted context omitted.

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…

We did that on a game I worked on over ten years ago. It was a mobile game and we knew that it was very important to player retention (and interest in multiplayer) to have the first multiplayer interaction be "fun". So we would simulate the first person you played against as though they were another human. Based on play data of other humans. Because you only played them once you didn't think you were playing a bot. W…

Humans prefer humans over bots in multiplayer. Even if you dumb down LLM-powered-bots, there's no sense of accomplishment on beating a bot that can be dialed up-or-down. And the social aspect... maybe some amount of gamers want to talk to bots instead of humans in a pvp match. Curious on the numbers there.

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

#163

Post by GaggiX »

dingnuts wrote: post #122
AIPedant wrote: post #61

Earlier quoted context omitted.

Yeah, I figured this was clickbait but my jaw still dropped a bit when I saw this: I cloned the backend for Truco and gave Claude a long prompt explaining the rules of Escoba and asking it to refactor the code to implement it. How long would it take the human dev to refactor the code themselves? I think it's plausible that it would be longer than 3 days, but maybe not!

As an LLM hater, I have to say, this is exactly the use case I want code generation for. If I need to figure out the problem as I develop, which is the case for new code, the model can kindly get out of my way. But if I have already written a bunch of code and I can explain the problem with the understanding that I've gained from my implementation and have the bot redo the grunt work? fine with me..

>As an LLM hater

I thought this was the start of a joke or something, I guess if you use LLMs you are a "LLM lover" then.

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

#164

Post by ryoshu »

cherryteastain wrote: post #118
pton_xd wrote: post #115

Earlier quoted context omitted.

There are some game systems that lend themselves to unit testing, like say map generation to ensure that the expected landmarks are placed reasonably, or rooms are connected, or whatever. But most game interactions are just not easily "unit testable" since they happen across frames (eg over time). How would you unit test an enemy that spawns, moves towards the player, and attacks? I'm sure you could conjure up any nu…

> How would you unit test an enemy that spawns, moves towards the player, and attacks? You can easily write a 'simulation' version of your event loop and dependency inject that. Once time can be simulated, any deterministic interaction can be unit tested.

A lot of games aren't deterministic within a scope of reasonable test coverage.

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

#165

Post by rustystump »

uncircle wrote: post #128
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…

> 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. I disagree. Sure, it's hard, but it's much harder to come up with novel and fun gameplay ideas. Once you have the fun idea, it's just a matter of splitting the problem in bite-…

I understand the “writers block” but once you do have a vision or idea, it is incredibly hard to bring it into reality. Much like building a product you have to cut and cut and cut due to time/skill/money constraints. I think many people get hung up on “originality” part too much.

Most of the comments lamenting the idea stage come from those who have not pushed past that. Once you do have an idea, a vision, that is when the real work begins. It is also the most difficult. For every completed game no matter how bad, there is a graveyard of thousands of incomplete projects that no one sees. People vastly underestimate the effort it takes to make a complete game.

If you do struggle with, “what kind of game”, go play games. Alot of games. Write about the games. Between the likes and didnt likes, is the kind of game only you can make.

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

#166

Post by rustystump »

jama211 wrote: post #91
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.

People build up too great of expectations when the topic of “creativity” comes in. Nothing is new under the sun.

Also, i press “x” to doubt you can build any game mechanic not because i have no doubt you are a talented engineer but because the domain is really that vast. Multiplayer netcode is a prime example and why I used an idea which had a multiplayer component that was realtime.

Ideas are cheap. Making them real is not. It is why engineers get paid so well.

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

#167

Post by rustystump »

mattbuilds wrote: post #102
rustystump wrote: post #92

Earlier quoted context omitted.

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.

I’m not saying coding is easy, but when it comes to games it is the easy part. Lots of people can code, very few can make something actually fun. Knowing how to code (or how to use an engine/blueprints/visual scripting) is just the start. It’s like making films. Everyone can record some videos on their phone, but it takes much more than that to make something people want to watch.

That analogy is more accurate for LLM vibe coding than real programming which i think proves my point. Not everyone can code. Actually code. Ideas are bountiful compared to the required skill to bring them into reality.

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

#168

Post by chrz »

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…

Depends on the game but absolutely we run thousand iterations of a game, but for balance. Which mechanics keep player engaged you need to get feedback from players

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

#169

Post by greesil »

ryoshu wrote: post #164
cherryteastain wrote: post #118

Earlier quoted context omitted.

> How would you unit test an enemy that spawns, moves towards the player, and attacks? You can easily write a 'simulation' version of your event loop and dependency inject that. Once time can be simulated, any deterministic interaction can be unit tested.

A lot of games aren't deterministic within a scope of reasonable test coverage.

Set the same seed for the test?

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

#170

Post by deadbabe »

sarchertech wrote: post #108
MarceColl wrote: post #98

Earlier quoted context omitted.

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

How many big game jams have you won/placed very highly in though?

Game jams typically require games to adhere to a theme that is only known the day of, and the best entries will make a game specifically around that, not just adapt some pre-existing idea to it.
Post reply on HN