As I said before, World models will become simulation engines of AAA games where there is no need to release the actual game artifact and even if the game exists as a binary artifact, it will never be released and will be available on their hosted cloud back-end, then simulated and streamed back to you.
So, Stadia + World Models = New generation of DRM for games.
I am sure the are other typical Google fumbles that would have meant they were not the victor; but I am sure an equivalent service would be mainstream today if AI had not dramatically changed the economics.
[also Google bought DeepMind in 2014; 'way beforehand' is and odd way to look at it]
I disagree, dropping below 60 FPS will be noticed and turn players away, you are not getting that with good input handling even today, it has nothing to do with GPUs and everything to do with networking
> beforehand...
is about the craze, the ChatGPT moment and beyond, when GPUs demand went exponential, not when various types of Ai algorithms were available
sure... despite all the other people who used it and are saying otherwise, and the fact that google totally fumbled in the Ai race as well as built custom silicon for Ai...
... history is helpful ... google didn't - and still doesn't - understand gamers, same for all the other Ai hucksters, gamers are among the most anti-Ai
Stadia was pretty good, be it OnLive was similar quality in like 2010. It even had the best version of Cyberpunk 2077 when that launched. But the model was free version of the service for a limited resolution AND you have to buy games there OR a subscription based option and you still have to buy games there.
That made no sense and wasn't a viable business model.
Game industry is still struggling to find a way to incorporate regular LLMs without suffering catastrophic edge cases. A long way to go before these can do more than fancy tech demo, I think.
Why? Why would a non-deterministic engine be better for a game when it can be instead structured and made deterministic and then more effectively distributed to consumer hardware?
> We'll be riding the huge wave of indie titles that are incoming.
The problem will be separating the wheat (people with good stories and concepts enabled by Ai) from the chaff (people with no taste slopping out trash with Ai)
And nobody will play that trash, and the world won't change.
Also, lmao, they're already trying to nickel and dime you and sell you microtransactions that took 5 minutes to make for 10 bucks. If you think they're going to pay the costs for running a world model for every single person, lol.
I don't know if I'm missing the point, but Genie 4 almost looks worse than Genie 3 in terms of player control? It doesn't even seem to respond to inputs, it just looks like they took some AI generated videos and put the key widgets on top.
another POV is, what even are these experiences? whom are they for? it would take Google 10 minutes to hire all the best game developers for Android, and cost them like $2m, which is peanuts, and give them fancy Google Research titles. but instead, they're trying to get 100 google PMs, who don't give their kids screentime and who don't play any games the objective of making a product for Bart Simpsons. like these people don't realize that being good parents disqualifies them from making immersive first person shooter, "narrative" experiences.
> what even are these experiences? whom are they for?
One possible use for these is to facilitate lab -> this -> real world for robot models. Basically better than lab / algorithmically designed environments and cheaper / easier to train on than real life. Something that "looks" like real life and can scale, to apply RL for robotics to.
The more parsimonious explanation is that 100 PMs are even less qualified to make surgical robots, but at least they can download a video game and play it for 5 minutes. There's a great scene in You Can See Everything where Billy Evans is watching bio presentations on 1.5x speed, which obviously, makes him look like a huge moron - "knowing enough" bio is very bearish.
Anyway, let's take your theory to its logical conclusion: the product development between real and simulated soft tissue behavior is much bigger than Exponential Time being a hypothesis and being proven. There isn't some effective acceleraltruist path here. Dario Amodei was a biotech dropout. The thing you are betting on which Google is not doing anyway, maybe they will destroy the descriptive single cell sequencing paper mill, but they're not going to be able to simulate the fat inside a BMI 30 abuela undergoing a gallbladder removal.
Why hire crew or actors when you could have them be fully AI? Why film a commercial with fluffed, oil dusted, well-lit hamburgers when you could fully render something? Why actually have a vehicle capable of off-roading when you could just AI-render what it looks like off-roading (or vertically taking off, for eg)?
It's a dystopian business use case that I hope will get obliterated in the near future as the generations that believe in this stuff and are fascinated by it age out of the population.
They're not proof-reading the blog posts either. The second sentence:
> Genie 4 is natively multimodal, enabling audio-like music, ambient noises, and interactive dialogue to be simultaneously generated with the world.
(Emphasis mine). Like, yeah, I'd sure hope the music is similar to audio.
I wonder if this was a de-LLMese pass gone wrong, and the original was "enabling audio -- like music, ambient noises, and interactive dialogue -- to be simultaneously generated with the world.
The volume of content on YouTube is enormous, I’m kind of surprised they offer auto captions at all given that they have little to no competition in the space.
Ok but like, surely the Deepmind team could sneeze and get flawless captions for this video. Why rely on the default YouTube captions instead of just attaching correct ones? It seems silly.
So world models capture inherent complexity of physical reality to help teach AI about hidden laws which probably helps train both LLMs and multimodal models used for autonomous vehicles and robots? And AMD acquiring World Labs is a move to outdo Nvidia’s work in this space. And Google probably sees this as a gateway to a new platform of autonomous vehicles and humanoids that they could rent out as a CSP? Competing with Nvidia, Tesla and complementing Waymo. Am I getting that right?
Surprised that "do you really think we're going to make it?" scene made the cut of the first video, her expression and tone is totally out of sync with the scene and demonstrates the problem with almost every AI gen video I've come across when it comes to capturing humanity.
The painting->interactive scene looks astonishing though
In the clip with a marble bust dropped on a watermelon, at this point https://imgur.com/a/IHLnkUs the bust should've toppled over, if the physics were properly modeled.
That's the thing about machine learning over time, and the big hole in the whole world model idea. Time and time again we make simulations and train models and we think that loop will work. It never does.
And why not? Because the first model that can actually learn to handle the simulation not only can do the simulation internally too, but it can do it better than out simulation.
It's where (ex-)"AI luminaries" go to die. It's a way to make glacial, slow progress in the correct direction while never actually getting anywhere.
So we get to a point and people keep making complicated simulations of one kind or another ... and then someone (some model) who's never used the simulation, and doesn't need it for model training gets by far the highest score on every benchmark and everyone agrees the simulation was kind of beside the point.
A big chunk of the right side of castle disappeared, including catapult, when camera turned back while flying on dragon. See 1:25 to 1:29. I was not expecting this to happen in a "world model".
That entire clip looks like it's straight out of a complete bargain-bin videogame. The weird smoothness of the ride, the pivot in mid air, the wings apparently don't have collision with the poles they fly past.
Definitely wouldn't have been one of my picks to show off my fancy new model.
Oh yeah, don't get me wrong "bargain-bin videogame" is a wild step up from "accidental amorphous horrors that defy description". It just jumped out to me as looking unusually bad compared to the other samples they provided. The stained glass deer, for example, was awesome.
Gotta love the kraken destroying the city in the background of the Hong Kong lovers motorcycle scene despite nothing in the prompt about monsters. Filmmakers are still safe.
It's hard for me to understand Google's redefinition of "world models" (basically: a txt2videogame modality for LLMs) as anything other than an attempt to bury Yann Lecun's definition of "world models", which includes an implicit bear case against LLMs and thus Google's stock price.
Looks cool, but it's very hard to get me excited about yet another proprietary model for which absolutely zero technical details are released (not even the number of parameters), which is safetymaxxed to the limit, and whose usage quota will (most likely) be so limited that it'll be effectively useless for anyone who doesn't work at Google or doesn't have infinite money.
I mean this doesn't seem very insane? Basic info about the model, the ability to actually use it. Google in particular is awful about getting access to their models from the UX side: I don't even bother trying them out unless it's via openrouter.
Yeah, I want that too, including the weights and training material. But I am still exited by what one could potentially do with it, by looking at the prompts and generated videos, even if it is cherry picked.
Most cutting edge technologies through history have been 1) somewhat opaque and 2) narrow/exclusive in their deployment. Historically speaking, that's virtually synonymous with "cutting edge technology".
Whining that I, a random Internet user with limited budget, usecases that the researchers don't care about, and no connection to the researchers, don't get technical details (??) or access (??) on day one is just profoundly goofy shit.
Obviously being able to use these things right away would be more exciting. But to be unable to get excited by advancements we can't immediately use is... quite entitled.
We should distill everything else we can into open weights.
These are exciting for robotics and industrial perhaps, but they have no consumer use case until the lid is blown off and consumers can do whatever they want with them.
So much societal progress is behind held up because the leading labs want to keep a stranglehold on the tech. Imagine if every PhD or hacker had access to the raw weights.
The general history of new technologies is that they're available for a narrow set of circumstances and then they proliferate. Can't believe that needs to be said on "hackernews"
You're damn right if you think quota for this model will be reached after two seconds. It's for the investors (and friends and xooglers) to make real use of this, not for you pleb.
What is this for? I cannot understand these models. They are very much polluting the internet with nonsense and use capacity that people and businesses need for actual work.
If these are the cause of why I have to pay 2-4x I used to for a computer, then Google should go fuck themselves.
Google aren't the only ones with this tech. You can try out a 24/7 rolling set of video feeds for yourself at https://fal.live
An LLM generates four alternative prompts for what could happen next and there's a real time vote running for each option. It's trippy, like watching someone's dream.
Podcasting is going through the thousand cheap ads with the obnoxiously inserted interstitial ads. What they have accomplished is me unsubscribing to the worst offending podcast and beginning the journey of ad blocking on podcast with the help of whisper and LLMs. Also now I hate Shopify with the heat of a 1000 burning suns due to their obnoxious ads and the insane rate they get played.
So yea that one expensive ad would probably have a positive impact compared to a tidal wave of slop. Quality > Quantity after all.
The authors could still design their prompts to steer players towards predefined developments and situations. Anyway, the possibilities of something like this are infinite, the only constraint will be the cost of the compute.
Humans interact with their environment by subconsciously simulating it and predicting what will happen in the next few moments. This ability gives us the capacity to work more efficiently and reliably in any environment. These world models will serve a similar purpose to the AI and robotic systems of tomorrow. This is a foundational piece.
Not sure if you're joking, but the only such evidence I could think of would be something like finding some way to influence the hardware of our simulation and seeing a glitch in our world
How does that argument work? I've seen more than a few advances, yet I don't see how any of it provides evidence that we are simulations. This might be one of those things that comes down to the definition of "simulation" I guess.
No it doesn't, not even close. You are looking at a video represented as pixels changing on a flat screen. None of it actually exists. You exist, the computer or phone in front of you is composed of mass and energy, and absolutely none of it is algorithmic. World models, as complex as they are, are still just pushing numbers around on paper.
Even if we can show that it is technically possible to model a universe like ours to the degree that our current perception of reality suggests exists, there are three other big factors that would need to be weighed:
Is it feasible? What Dyson sphere level of power would be needed to maintain such a simulation? Is that level of energy available to whomever is running the simulation?
Is there a positive ROI? What does this advanced civilization get out of running such an expensive simulation?
Is it moral? The simulation involves sentient creatures who are capable of deeply contemplating their own existence, capable of feeling rapturous pleasure and indescribable pain and loss, and ostensibly capable of making moral choices that range from heroic to depraved. Doesn't there come a point where the beings in a simulation are so close to the beings in "base reality" that the same moral principles apply? If you press a button that kicks off a simulation where humans can torture and murder each other, behaving essentially identically to humans in "base reality," aren't you in some sense facilitating those deaths?
You run it to see if your military tactics will defeat the enemy and then you keep running it until you find a strategy that guarantees victory. Who cares if some sim lives are churned through the simulation, our lives are at stake!
Reductionist but I feel like that’s how it would go.
> What Dyson sphere level of power would be needed to maintain such a simulation
Why would you assume energy is relevant to whoever turned on our simulation? If I created a simulation where the only source of energy was cotton candy, my creations might ask "but where would our creator even get enough cotton candy to run a simulation like this", not realize that it's absurd to think that the creator of a simulation has any of the same constraints that exist inside the simulation.
Who is asking for this? Do advertisers really want this? I feel dread about many of the AI products being sold. They're mostly tools to help funnel money from the users to the bosses.
In the man walking through the dressing room scene, the camera starts behind the man. And you can see that the left half of his body is wearing a grey suit... but the right half is wearing a grey dress. :O
And their most impactful application will be training smaller models for military drones to detect, target and kill humans. sigh...
Every time I'm about to be excited about AI the cynic in me slaps me back to reality. I imagine the endless possibilities of AI for disabled people, then realize that it's going to leave millions of people disabled instead.
So, Stadia + World Models = New generation of DRM for games.
Ai generated games suck even more, no skill; no taste, there is no TLC put into them
Then there is the economics of it, cost prohibitive to (re)generate a scene and ship that over internet pipes
https://www.denofgeek.com/games/why-google-stadia-failed-shu...
> beforehand...
is about the craze, the ChatGPT moment and beyond, when GPUs demand went exponential, not when various types of Ai algorithms were available
... history is helpful ... google didn't - and still doesn't - understand gamers, same for all the other Ai hucksters, gamers are among the most anti-Ai
https://www.youtube.com/watch?v=c1Fv1uKTd-w
The latency was no good even on fast internet for even slow games. It is and was pointless.
That made no sense and wasn't a viable business model.
There are so many options for games now that just sticking with the biggest AAA companies seems like a waste.
October? Yeah, just release the "Spiderman saves Halloween" prompt.
This is a wet dream for big studios.
We'll be riding the huge wave of indie titles that are incoming.
The problem will be separating the wheat (people with good stories and concepts enabled by Ai) from the chaff (people with no taste slopping out trash with Ai)
I mean - reviewers!
been checking out the archives lately, nothing recent excites me
Also, lmao, they're already trying to nickel and dime you and sell you microtransactions that took 5 minutes to make for 10 bucks. If you think they're going to pay the costs for running a world model for every single person, lol.
Do you have even the slightest idea of the level of expectation that even the most casual gamer has?
This isn’t achieving much beyond prototyping. They’re burning so much money for no reason.
One possible use for these is to facilitate lab -> this -> real world for robot models. Basically better than lab / algorithmically designed environments and cheaper / easier to train on than real life. Something that "looks" like real life and can scale, to apply RL for robotics to.
Anyway, let's take your theory to its logical conclusion: the product development between real and simulated soft tissue behavior is much bigger than Exponential Time being a hypothesis and being proven. There isn't some effective acceleraltruist path here. Dario Amodei was a biotech dropout. The thing you are betting on which Google is not doing anyway, maybe they will destroy the descriptive single cell sequencing paper mill, but they're not going to be able to simulate the fat inside a BMI 30 abuela undergoing a gallbladder removal.
It's a dystopian business use case that I hope will get obliterated in the near future as the generations that believe in this stuff and are fascinated by it age out of the population.
> Genie form [sic] can simulate scenarios
It's kind of amazing: the juxtaposition of such advanced generative AI and such terrible speech-to-text coming from the same parent company.
> Genie 4 is natively multimodal, enabling audio-like music, ambient noises, and interactive dialogue to be simultaneously generated with the world.
(Emphasis mine). Like, yeah, I'd sure hope the music is similar to audio.
I wonder if this was a de-LLMese pass gone wrong, and the original was "enabling audio -- like music, ambient noises, and interactive dialogue -- to be simultaneously generated with the world.
It's why if you search a practical task you will often see results link to specific parts of a video.
Real nice prompting there, Google. It also still looks like a video game rendering.
The painting->interactive scene looks astonishing though
And why not? Because the first model that can actually learn to handle the simulation not only can do the simulation internally too, but it can do it better than out simulation.
It's where (ex-)"AI luminaries" go to die. It's a way to make glacial, slow progress in the correct direction while never actually getting anywhere.
So we get to a point and people keep making complicated simulations of one kind or another ... and then someone (some model) who's never used the simulation, and doesn't need it for model training gets by far the highest score on every benchmark and everyone agrees the simulation was kind of beside the point.
Question I have is when will they be able to render something more then 30 seconds.
And how much will it cost? There has to be a HUGE amount of computing power behind this. As a video game developer I live in fear and anticipation.
Definitely wouldn't have been one of my picks to show off my fancy new model.
Would be fun to muck around with world models. Are there any that I can try for under £200 p/m without being part of a special project?
I suspect you're reading the base prompt, but the video also demonstrates adding further prompts to change what is happening as the scene progresses.
sure, it's still a cool accomplishment but i can understand being a little bit frustrated / not as excited for such an announcement.
Whining that I, a random Internet user with limited budget, usecases that the researchers don't care about, and no connection to the researchers, don't get technical details (??) or access (??) on day one is just profoundly goofy shit.
Obviously being able to use these things right away would be more exciting. But to be unable to get excited by advancements we can't immediately use is... quite entitled.
The history of ML used to be collaborative up to 5 years ago.
Only open weights matter.
We should distill everything else we can into open weights.
These are exciting for robotics and industrial perhaps, but they have no consumer use case until the lid is blown off and consumers can do whatever they want with them.
So much societal progress is behind held up because the leading labs want to keep a stranglehold on the tech. Imagine if every PhD or hacker had access to the raw weights.
I feel refusal'd just *looking* at this page.
If these are the cause of why I have to pay 2-4x I used to for a computer, then Google should go fuck themselves.
An LLM generates four alternative prompts for what could happen next and there's a real time vote running for each option. It's trippy, like watching someone's dream.
The only place I see this applicable is for visual artists prototyping
So yea that one expensive ad would probably have a positive impact compared to a tidal wave of slop. Quality > Quantity after all.
Video games are interesting because of very specific constraints the developers impose on the player.
Is it feasible? What Dyson sphere level of power would be needed to maintain such a simulation? Is that level of energy available to whomever is running the simulation?
Is there a positive ROI? What does this advanced civilization get out of running such an expensive simulation?
Is it moral? The simulation involves sentient creatures who are capable of deeply contemplating their own existence, capable of feeling rapturous pleasure and indescribable pain and loss, and ostensibly capable of making moral choices that range from heroic to depraved. Doesn't there come a point where the beings in a simulation are so close to the beings in "base reality" that the same moral principles apply? If you press a button that kicks off a simulation where humans can torture and murder each other, behaving essentially identically to humans in "base reality," aren't you in some sense facilitating those deaths?
Reductionist but I feel like that’s how it would go.
Why would you assume energy is relevant to whoever turned on our simulation? If I created a simulation where the only source of energy was cotton candy, my creations might ask "but where would our creator even get enough cotton candy to run a simulation like this", not realize that it's absurd to think that the creator of a simulation has any of the same constraints that exist inside the simulation.
What on Earth is audio-like music? Do they mean music-like audio?
Every time I'm about to be excited about AI the cynic in me slaps me back to reality. I imagine the endless possibilities of AI for disabled people, then realize that it's going to leave millions of people disabled instead.
> movies are going to become video games and video games are going to become something unimaginably better
Sometimes I really wanna skip 10 years into the future and see where all this eventually leads.
[1]: https://x.com/sama/status/1776083954786836979