by FredrikNoren on 5/21/24, 10:05 AM with 297 comments
by Bjorkbat on 5/21/24, 6:43 PM
For example, AI website builders. It's impressive as a tech demo that you can prompt an AI to make a website for you, but otherwise I don't think this is going to be disruptive to the web design industry since it's already pretty easy to make a website using a drag-and-drop builder like Squarespace or Webflow. Granted, it can get complex when you add certain special features on these platforms, but same goes for an AI-generated website. AI doesn't eliminate the complexity, it just hides it. At best it'll get you maybe 80% of where you want to go and you can get to the remaining 20% by hand. At worst, the complexity is so thoroughly hidden that addressing it isn't an option. It simply does not allow you to manually edit the outputs, or makes it unreasonably difficult to do so.
In that same vein, an AI game maker is pretty impressive as a tech demo, but I feel like it isn't a huge improvement over a code-light game maker. You're not eliminating the complexity of making a game, just hiding it.
Nonetheless, it's a pretty interesting tech demo.
by Jasper_ on 5/21/24, 8:41 PM
const tentsFacingNorth = getAllUnitIds()
.filter(unitId => getUnitString(unitId, "unitStrings/tags")?.includes("tent"))
.filter(unitId => Math.abs(getUnitRotation(unitId) % (2 * Math.PI)) < 0.01).length;
I would more traditionally expect a range of 0 to 2pi, but then this code wouldn't work for anything close to 2pi on the other side. And if the range was -pi to pi, why have the modulo use 2pi :)
Additionally, "facing north" probably implies a bigger epsilon than 0.01 radians. That's only half a degree! Even if it was super tight, I would expect maybe 10 degrees slop in either direction, which would be 0.17 radians.
The gameplay programmer way to do this would be to get the facing vector and dot that with the vector for north, and compare the results. Dealing with angles isn't worth it.
Oh, also, I'm guessing getUnitString().includes("tent") would work for anything with substring tent, so no adding tentacles to your game.
by EncomLab on 5/21/24, 12:55 PM
Making a game is not hard - marketing a game is.
by PeterisP on 5/21/24, 10:22 PM
I.e. if an programmer wants to create a game, then getting the artwork in a consistent style is a big problem, and solving that alone (i.e. as a plugin for Unity or Unreal or Godot or whatever) would be both powerful and difficult.
Conversely, if someone without programming skills wants to create a game, then it would be best to focus solely on the AI assistance for gameplay design with a fixed, well-known engine and an integrated well-populated market for content, and assume that they will get the content packs there, leaving that problem out of your scope but making it easy to integrate the AI-generated logic with the pre-made content packs.
by bogwog on 5/21/24, 1:43 PM
by jarjoura on 5/21/24, 4:26 PM
I don’t know, but Unity is already pretty much point and click game building. I spent a few weeks building a card game with it during lockdown, and without a lot of code, I had an ugly, and basic, but totally playable game.
The hardest part to a game is building something fun yes, but it also has to meet some level of quality bar and work on any platform.
by mysterydip on 5/21/24, 12:32 PM
by Ito10 on 5/21/24, 2:10 PM
For example, I am indeed interested, but will anyone really play the game I make with AI?
If I spend the same time watching YouTube and learning Godot or Unity, will it be more likely to make games and even make money, and I can also use Meshy to produce my assets. Unity also has Muse (though it's hard to use).
If the games I make don’t make money, what is your business model?
by FredrikNoren on 5/21/24, 10:05 AM
by iamleppert on 5/21/24, 8:16 PM
Having the ability to programmatically generate new games would be amazing. It would be great to have the game completely generated by AI, and then pipe the screenshots into a video AI tool to create the ads.
Will it support slot based games and gambling card games? My head is just buzzing at the possibilities and the opportunity for profits from this!
by hdlothia on 5/21/24, 5:06 PM
by aredox on 5/21/24, 12:25 PM
Next: a strategy game where you give orders in plain text, instead of hundreds of clicks per minutes
by anotheryou on 5/21/24, 4:06 PM
by kkukshtel on 5/22/24, 3:51 PM
by arvindrajnaidu on 5/21/24, 2:55 PM
It is an iOS app called Burning Idea, it lets you build small apps by talking to it.
by viccis on 5/21/24, 5:22 PM
by ccppurcell on 5/21/24, 8:29 PM
by Pingk on 5/21/24, 2:47 PM
by gieksosz on 5/22/24, 2:48 AM
by cmovq on 5/21/24, 7:05 PM
by parentheses on 5/22/24, 6:11 AM
by acureau on 5/22/24, 1:13 PM
by zengineer on 5/21/24, 1:19 PM
How does it generate 3d models?
Btw there is also https://frvr.ai for more casual games
by arvindrajnaidu on 5/21/24, 3:04 PM
by RecycledEle on 5/24/24, 9:27 PM
by SubiculumCode on 5/21/24, 2:34 PM
by spacecrafter3d on 5/21/24, 12:50 PM
by MCLAU155 on 5/21/24, 1:10 PM
by __loam on 5/21/24, 7:38 PM
by wokwokwok on 5/21/24, 2:29 PM
Most people want to take an existing basic game, and tweek it a bit, incrementally, adding new art, ideas and levels, and removing the stuff they don't like.
They definitely do not want to write code.
They most certainly do not want to debug generated code and I think you've hit the nail on the head with 'generating actual code sucks, is hard and basically doesn't work' with current models.
What I see in the demos looks different though; it looks like you have a configuration driven set of basic game elements and let the AI tweek the structured and easily-to-validate-schema config.
Which I think is fantastic.
"Make this unit bigger", "Add new type of fighter", "Get rid of this unit", "make the terrain here smoother and add a lake"; I feel like this kind of structured tool use is currently possible, if you write a framework of constrained actions (which is what it appears you've done).
So, props to you. This feels like something that is both actually novel and interesting.
...but; I feel there is going to be a difficult path ahead.
The more generic you make the engine, the more different types of games you can make with it; however, in doing so, the tools you have (eg. "modify unit config", "generate 2d sprite for unit", etc.) will have to become more generic; and the more generic they become, the less effective the agents will be at using them.
Our current batch of GPT4-ish models seems like they're relatively well suited for using specific tools with specifically constrained inputs to plan and achieve goals; however, as the tools become generic, the solution space balloons out widely and you start getting random crap instead of actual real solutions to tasks.
Specifically, I'm skeptical about your generic `createOrUpdateRule` and that you can effectively scale it to complex interactive behaviors; it just feels like the agents will never express complex ideas with that kind of coding; it'll only ever be an array of trivial behaviors.
Maybe that's all you need in some cases; but I don't think you can build actual games that way.
So, practically speaking, this might actually only ever really work as like a 'super modding tool' that takes basically a fully working game and lets you mod it in a very specific set of ways; but that would mean creating a 'template game' for various different game types, and different 'modify game' tools for each one. Otherwise, the final product is never going to really be beyond 'unit moves back and forth randomly'.
...but, that would still be really fantastic.
I guess, I hope you don't get lost trying too hard to build a generic Unity clone using AI that is kind of so-so (ie. generates random code that doesn't work and you have to constantly debug), instead of an amazing thing that is slightly less generic, but lets you do amazing things within a specific set of restrictions.
by SrslyJosh on 5/21/24, 5:30 PM
by hatenberg on 5/21/24, 2:33 PM
Just asking? How on earth can an entire ecosystem be so damn tone-deaf and lack self-preservation?