• Hey Guest. Check out your NeoGAF Wrapped 2025 results here!

Google: Project Genie | Experimenting with infinite interactive worlds

I remember pretty recently they unveiled clones of Doom and Minecraft being generated on the fly with all kinds of terrible bugs and dogshit performance, now you can enter any prompt you want and explore an interactive world. It's astonishing how many people downplay what a catastrophic paradigm shift this is.
Yes, it's a little difficult to ignore now. Think this alarms existing publishers and people who work non critical jobs in gaming. The negativity from those circles is justified.
 
Last edited:
large GIF
 
I remember pretty recently they unveiled clones of Doom and Minecraft being generated on the fly with all kinds of terrible bugs and dogshit performance, now you can enter any prompt you want and explore an interactive world. It's astonishing how many people downplay what a catastrophic paradigm shift this is.

nah, this is just more smokes and mirrors to keep the AI bubble afloat, after MS sjhakey earnings.

Genie = cloud streaming with another layer before it, they call it prompting but i call it procedural garbage from all the public copyrighted materials fed into wasteful gpu farms

we are sick of them selling useless 1min demo clips as a new breakthrough
 
nah, this is just more smokes and mirrors to keep the AI bubble afloat, after MS sjhakey earnings.

Genie = cloud streaming with another layer before it, they call it prompting but i call it procedural garbage from all the public copyrighted materials fed into wasteful gpu farms

we are sick of them selling useless 1min demo clips as a new breakthrough
Who is "we"?
 
Slop this slop that. Like if 80% of all current media and art expressions weren't absolutely trash.

There are plenty of talentless hacks running the show right now.

Over 10 thousand games are released on Steam alone every single fucking year, and most of them are not worth your time.

And yet, the term AI slop keeps thrown by the smooth brains as some kind of lizard brain reaction because everything new seems to be oh so scary. You are probably scared of electric vehicles as well.

Don't pretend that everything modern media wasn't "slop" already. Everything is already copied, replicated, recycled. Original and totally new content is maybe 1 % of everything.
 
So tell me, when you're generating your own game, music, TV shows and movies, ...do you expect to be able to chat about them with other people? Or are you just going for full bubble?
 
There will probably be a time where you can make actual games with this, but they'll always be inspired by previous games.

Like you could prompt it to have the 'movement of MGS5' and some gameplay system from Assassin's Creed. To create something bespoke and unique you'd have to type a prompt so large it would probably be more efficient to just code it from scratch.

I could also not imagine how it would be to finetune things.
"Make the character slide less far when movement input stops" - generate whole game again, test, now it stops too abruptly.
 
No thanks. Give me something hand-crafted made by people. You know, people with actual ideas, emotions and passion.

I'm not thanks either but for AI Photos we're hitting that point now where it's really difficult to tell what's real and what's AI.

In 5 years time, anything created from Project Genie and other equivilants you won't be able to tell what's human created and what's AI created.


In my view, i'd rather these tools are used along side game development to speed up production, i don't want to wait another 13 years for GTA VII
 
Last edited:
Lots of people told me that blockchains would take over once the blocks got bigger. Just needed a few years to improve the tech and then everyone would be storing everything on there and we'd solve the world's ills. Billions of dollars were pumped into that industry based on these early claims. The billions of dollars became a validator for others to invest, because no idiot would throw billions of dollars at an idea without expert knowledge that it was all going to work.

Genie 3 has a context window of 60 seconds, it just needs to be bigger and then there's no holding it back! We've gone from six fingered renders to photo real cats on skateboards with lasers. Victory is just around the corner.

Or it's not, it's fundamentally not, based on the current core of LLM. Most fixes to help improve things like context have been more money, more hardware, more compute. billions of dollars.

It's an arms race. Whoever gives up first loses, but who actually wins. Remember the push to get to the moon? For that window of time, money and profit were not in question, it was do anything to land man on the moon. Did it open up a new paradigm for humanity, did we establish bases and create new industries off world? No, once the battle was done, the money dried up and no one went to the moon any more because it just burned so much fucking money that it was unaffordable.

Getting to the moon did push some things forward, we gained some great tech from it. I have no doubt that we will from this AI push too, but the sheet amount of money being burned now is insane. The cost of rendering some slop GTA VI mock up is unsustainable. Little Timmy is not running this on his console unless he wants to bankrupt his parents over a weekend gaming session.

No one cares about affordability or optimization right now, because they're just building bigger rockets to be the first to get to the moon. We could have left the solar system by now using something like Project Orion, maybe it would have been great, but the return probably wouldn't be worth it apart from to say we did it.

We're burning cycles on AI generated slop right now just to say we did it.
Of course there is a possibility it won't take humanity to AGI/ASI but as you said, it can still drop some subproducts, who is to say this won't be one of them?

I don't think anybody is saying this is the end game but it looks amazing and very promising
 
The end product is the most important thing, how you get to it doesn't matter to consumers or investors. That's the harsh truth.

That said, selling CDPR stock is fucking idiotic because if anyone could utilize tech like this positively it's those guys. Ignore the virtue signaling about never using AI, investors will physically force you at knife point to use the tech if it's deemed it will speed up production and save money.

I think some publishers are jumping the gun attacking Google etc and picking PR fights with groups right now way beyond the scope of their ability, I don't think that's very smart.

there's nothing to get to, there is no end product.
this tech as seen here can not be used to create anything other than a temporally incohesive interactive animation, that falls apart within a few seconds.

there's a reason you don't see anyone do a full 360° turn in any of the example videos shown. because if they did that, literally everything you saw would disappear and be replaced with something unrelated to the original environment.

so all you see is someone slowly moving forward, or just standing around turning the camera a tiny bit left or right.

even doing a 90° turn left, followed by a 90° turn right would instantly break the demo.
 
And just "yesterday" it looked quite bad, with little to no temporal stability. Imagine how it will look like "tomorrow"...

Yup

It's the inevitable future. Neogaf will of course scream buzzwords like Ai slop and so on but there's absolutely no way this is not becoming mainstream when we talk about it in 10 years or so.

This was just ~3 years ago



Initially the most likely scenario is we see a game in a standard engine but looking very rough, like basic geometry, non textured, but having the game mechanics defined by a dev, while AI then makes it photorealistic. But the pace of full AI gaming is way faster than expected with google. They have big plans coming for AI including their titan architecture which will push way beyond LLMs.

No need to have latest tech for path tracing, AI knows how it's supposed to look in real life. No need to develop exotic simulation physics that will kneecap any hardware, AI knows how to do it. Peoples making arguments that it's not really real rendering are cute, what's ever real in rendering? Everything developed for graphics have always been to just trick the eyes. It takes a lot of ressources initially for training but inference afterwards is a fraction of what it would take for traditional methods to achieve. There's a reason why modern games have shit looking physics and simulations. To brute force it, it would no longer be really real-time.
 
I think folks are missing the point.

The utility of this isn't for making games for the end user to play. The utility would be for devs to use it to rapidly prototype gameplay ideas.

Imagine at the pre-production stage of game development, you want to quickly prototype and idea to see if it might be fun. With this is instant and trivial. That matters a lot.
Yeah that's how I use AI for art and animation now, can quickly try out new ideas before I spend the time doing the real grunt work.
However, seeing what people create here makes me think it'll be heavily restricted very soon since it's so easy to break copyright laws.
 
I think folks are missing the point.

The utility of this isn't for making games for the end user to play. The utility would be for devs to use it to rapidly prototype gameplay ideas.

Imagine at the pre-production stage of game development, you want to quickly prototype and idea to see if it might be fun. With this is instant and trivial. That matters a lot.

that doesn't work tho. you can't even define game mechanics in this thing, let alone keep them consistent from one moment to the next.

how do you prototype a gameplay idea, if the obstacle in front of you just disappears the moment it leaves the camera view? how do you test game mechanics if they aren't kept consistent and work differently every time to press the button?

this tech, as seen here, is quite literally useless for anything. it has no practical use in any field or any production.
 
Last edited:
I love seeing people reject innovation and would rather just pay $100 for a video game that is half finished and requires 10 years of development. This is the future, it is going to cut down on the overbloated studios like EA and Activision that make the same games every year and remove and re-add things as new features.
 
Last edited:
Yeah, these are not "games". Is like take an engine, put a map and a character model with a basic animation and walk forward.

For sure is impressive, but we don't going to have anything comparable to a competent 3D developed game still for ages.
 
Top Bottom