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.
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.
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
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.
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
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".
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.
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
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.
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.
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?
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.
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.
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.
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.
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?
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.
> 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)
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.
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
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.
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.
> 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
Sounds glib, but honestly ... more Ads :/
What on Earth is audio-like music? Do they mean music-like audio?
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.
The only place I see this applicable is for visual artists prototyping
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.
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 painting->interactive scene looks astonishing though
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?
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.
Real nice prompting there, Google. It also still looks like a video game rendering.
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.
> 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.
It's why if you search a practical task you will often see results link to specific parts of a video.
> 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.
So, Stadia + World Models = New generation of DRM for games.
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!
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.
There are so many options for games now that just sticking with the biggest AAA companies seems like a waste.
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
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.
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
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.