You should consider that there is a rather large gulf between low-effort crap and using agentic LLMs to make more sophisticated games faster before you downvote me.
It's just not black and white, and to treat it as such devalues the conversation.
ofc there’s a spectrum in LLM usage, but the usage scenario of LLMs as a “supervised force multiplier” (paraphrasing your linked comment) isn’t how most near anyone uses them. I can’t imagine gamedev is any different.
what a vast majority of LLM usage appears to me is as a unsupervised slop multiplier. any social media platform, including hacker news is rife with a deluge of unpolished LLM generated turds that creators pass off as their own work when they can’t even explain half of how it works or what it does.
circling back with gamedev specifically and art more generally. sure if LLMs are just one part of the process to push out some grander, well thought out vision who am I to really care. again thought, that isn’t what I see. I only see untalented lazy “excommunicated devs” passing off the most bottom of the barrel trash as “games”
> the usage scenario of LLMs as a “supervised force multiplier” (paraphrasing your linked comment) isn’t how most near anyone uses them. I can’t imagine gamedev is any different.
That's just it: you don't know this. You're speculating from within your confirmation bias bubble. Everything you're saying is completely anecdotal.
I mean all the major hurdles of making a game aren't really helped much by AI...
AI has no training data on complex logic and systems so you gotta do that all yourself.
It definitely doesn't get anything visual right really.
There isn't large amounts of automated testing you can setup ahead of time for a lot of game-play so the AI can't iterate on it to make something work it'll just be hopeless.
The art is also going to all be really derivative plagiarism overly averaged scammy looking stuff. So that's basically an insurmountable hurdle. No unique style.
>I mean all the major hurdles of making a game aren't really helped much by AI...
I have been using Claude Code to develop a game in unreal engine. It is fricking amazing. Its like hiring someone with 10 years experience to work for you. I am really impressed by how it know game patterns.
>It definitely doesn't get anything visual right really.
Sometimes it struggles to things things right visually, other times it nails it!
I have been using an MCP from gemini image 1.5 to generate my icons. And once it go my styles down, after 20 experiments, it does really good. Notice: It uses high quality by default which will burn up your credits. But if you turn down the image quality to low, it cost around 3 cents an icon.
>There isn't large amounts of automated testing.
Some things can be easily automated for testing. But other things require play testing.
>The art is also going to all be really derivative plagiarism
I am just using it to generate icons, and it does great. For 3D artwork I either use things from the FAB Store, or I pay a team of artists in Pakistan to do it.
Overall I say it is the equivalent to have a senior dev on your team, for 100 bucks a month
Has he dealt with some of the more challenging problems in game dev that engines help a lot with? Like... multiplayer netcode.
Seems like if you're doing this for a hobby or solo/small team then maybe it's reasonable.
For most people where they want to be a game dev but they probably will just work in industry, it seems like learning the major engines to competency cannot be ignored.
You should use tools that are appropriate to what you intend to achieve. If you want to make a 3D game then Unreal, Unity, or Godot are appropriate choices. If you want to make a 2D game then something like MonoGame might make more sense than Unreal. You don't need highly refined netcode if your game never needs to exchange data in realtime.
Heck, I've seen someone build a visual novel-type game with WinForms. That was actually a sensible choice for the game's presentation and interaction needs.
Of course if you want to become a game dev at a studio then you should be competent with whatever the studio uses (or something comparable so you can pivot to their stack). If you only want to make your hobby project and maybe publish it later it doesn't matter if your engine is Unreal, MonoGame, RPG Maker 2000, or vanilla JS/DOM.
I would say that one of the "Miscellaneous Thoughts" at the end of your article answers your question pretty well:
> I need only the best fancy tech to pull off my game idea
Then use Unreal! There's nothing wrong with that, but my projects don't require those kinds of features (and I would argue most of the things I do need can usually be learned fairly quickly).
> that engines help a lot with? Like... multiplayer netcode.
Rust (the top 10 most downloaded game ever on Steam) is built with Unity. However they ended up to write their own netcode anyway. Of course Unity isn't known for the best netcode, but how much an engine helps is often overstated. Genshin even bought Unity's source code to customize it.
Unity used to have a pretty good netcode implementation, but then they ripped it out in newer versions and still don't really have a good replacement for it
I mean, I dont hate netcode for gameobjects, but generally I prefer to have the application just set up some sockets for me and I'll handle the rest myself, which you can do in NfG, but I've not used it too much. There was a really long gap between having working netcode stuff, and I wrote what I felt was a really nice layer over the top of the old LLAPI for a project I was going to work on, and then they immediately deprecated it.
multiplayer netcode isnt overly difficult to write unless you're at the highest lvl of complexity lol. it's not a black box, it's just transferring bytes around efficiently and keeping track of state, your "netcode" can literally just be bare tcp (+ssl), validation, and state, it's not that deep.
handling latency to keep a coherent experience in a real-time game is an unsolvable problem where every single mechanic requires a planned out scheme and companies go so far as buying data centers in optimized locations to help out with the illusion
that's probably what you mean by highest level of complexity
but even just a regular turn-based game there's a lot of questions you need to answer and decisions to make regarding latency, packet loss, and disconnects that all have to be solved in a coherent and consistent way
Weird take when the purpose of the creation is to steal the work of everyone and automate the creation of that work. It's some serious self-deluding to think there's any kind of noble ideal remotely related to this process.
There's (vo2master) device that can apparently measure it in one breath; there was a video on some swimmer using it on turnaround without much interference with their exercise. $7k though.
Something I don't quite understand about this Discord fiasco.
Every single thing you ever put into discord via text or voice has already and was already being sold to advertisers. If you were ever logged into Google simultaneously while on Discord it's already linked up to the real information they have about you.
I've just seen numerous things I've talked about or typed about with friends promptly appear on my YouTube feeds.
1. Citation needed. Why would Google be secretly ingesting all of your Discord messages and be using it for... YouTube recommendations? Baader-Meinhof phenomenon is a more likely explanation
2. Already collecting a lot of data is not a reason to collect even more sensitive data. Plenty of people use Discord differently than you do. Anonymously participating in projects that use Discord and never saying anything personal over it, for example. This would possibly remove the ability to do so, for example if Discord's secretive AI decided that an LGBTQ+ project's Discord should be age restricted, and you would be forced to submit enough information to be fully identified and deanonymized, and now some foreign government could build a database that includes your full identity and your affiliation to such project
I have the opinion it was well worth it for many reasons.
Not only the agents can complete trivial tasks on their own, leaving us just with reviewing (and often just focusing on the harnessing), but the new setup is very good for onboarding technical and non-technical staff: you can ask any question about both the product or its architecture or decisions.
Everything's documented/harnessed/E2Ed, etc.
Doing all of this work has much improved the codebase in general, proper tests, documentation and design documents do make a difference per se, and it further compounds with LLMs.
Which is my point in any case: if you start a new project just by prompting trivialities it will go off rail and create soups. But if you work on an established and well scaffolded project, the chances of going off rails and creating soups is very small.
And thus my conclusion: just fork existing projects that already do many of the things you need (plenty of them from compilers to native applications to anything really), focus on the scaffolding and understanding the project, then start iterating by adding features, examples and keeping the hygiene high.
How exactly is this not just like a global policy thing rather than EPA? Surely our emissions affect other countries' qualities of life so the decision is not just up to us.
It's instantly recognizable and makes most indie games that disclose it just dead on arrival
reply