For several of these examples the details change if something goes out of frame and returns. A second castle is added in the dragon one. The people walking away from the camera change in the train platform one. The Hong Kong moped rider doesn't have a helmet and then he has one.

It's very good at maintaining consistency for things that stay in frame, but I don't know that this points to it developing a strong "world simulation" like they claim.

Reading the comments almost everyone seems not impressed at all and points at obvious errors in the samples. Meanwhile it's been just roughly over 3 years since we've seen an AI generated abomination of Will Smith "eating" (or whatever you want to call that act) spaghetti. Yes, AI gets things wrong. You could say the same about LLMs still making obvious errors here and there. To me, personally, this seems super impressive and it's clearly another leap forward. Not perfect, yes. But an improvement.

> Genie 4 has advanced audio capabilities

> Prompt asks for saxophone

Looks inside:

> Sound of a clarinet

Maybe Genie 5 will get it.

It looks like they had a hard time with the magic wand, peacock-to-cat example. Despite using a very long prompt that repeatedly stresses that the video should look photorealistic and NOT like a video game, the output video looks like a video game. The model is clearly capable of generating photorealistic humans and animals, so I wonder why it struggled to do so with that particular prompt.

Reminds me of a post[1] by Sam Altman in 2024:

> 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

Surprising how Tencent's HY-World 2.0 open weights world model didn't get as much attention:

https://github.com/Tencent-Hunyuan/HY-World-2.0

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".

Cool demos, but does anybody else find it troubling that companies keep claiming this tech can train robots? It’s so obviously not representative of the real world.

> Genie 4 is natively multimodal, enabling audio-like music, ambient noises, and interactive dialogue

What on Earth is audio-like music? Do they mean music-like audio?

I think its a useful exercise to try and name a cultural artifact (picture, video, game, music, book, etc) that was improved, or made substantially possible, by this technology. Ideally something that has moved you or provoked a lasting response.

Conversely, try to think of examples where Generative AI has betrayed a lack of creativity or care from the creator, and thus left a sour or ambivalent or impression.

I find the former impossibly hard, and the latter depressingly easy. Do others feel the same?

This is going to transform how we create games, movie content, and interact with virtual worlds, as well as those born from our imagination. You have control, like a simulator where you can close your eyes and immerse yourself in artificial worlds that feel incredibly real. It’s crazy how fast things are changing.

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.

If AR Headsets are supported by Genie 4, it would be mind blowing. But latency would be a bottleneck to get there.

Alert me when these "world models" can make a video of a skateboarding line that fools a skateboarder.

And no, this didn't: https://www.youtube.com/watch?v=V2K_OLiZ_RM

Real time AV testing would be one of the better use case before AVs are released on the roads.

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.

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.

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

That stained glass landscape video is pretty cool. I wonder if it would be possible to implement that effect in a real-time game engine.

What if we're all in Genie 10 right now?

Not that I have zero trust in anything AI related that Google demos, but the first video example on the right, the model completely ignores inputs towards the end.

With Anthropic going public, I expect a lot of model releases from the competition signalling to the market. "We are still around, please leave some money for us too"

If the checker clip is meant to be used to develop a robot to play checkers, then the physics is not remotely good enough. When the robot takes the first piece, the piece looks like it's moving up from the board, then suddenly doesn't. The last move also isn't valid checkers, unless I'm missing something -- the robot offers its piece to be eaten and the human doesn't take it.

guys they are building digital cages so they can rob you blind while you are in your nice digital world, sorry we will ignore this stuff into oblivion

A few years from now, Lydia in Skyrim will have a fully consistent personality with dynamic dialogue and full contextual memories of all our adventures together in Skyrim.

A visual makeover is great but what happens when millions of people fall in love with virtual characters who seem to deserve that love?

The prompts build impressive clips.

I am more interested in how to make consistent "participants" and "environment" with multiple clips so they look like one longer clip.

Will that require same dev/coding harness and spec-kit-like engineering flow?

Like create a spec on how a movie will look like, feed contexts, create tasks so that multiple clips look congruent?

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.

The models need to watch more Gallagher… cuz that watermelon smash was like a 2/10.

Can't wait for the hyper-realistic customer service bots and deepfake propaganda videos.

I don't know. With each new release of these models, they compare side-by-side how they are better than the previous ones, but at the same time I feel less impressed by each new release. Somehow they manage to be a seemingly big step forward but at the same time I feel I have seen so much AI that I just look at the common failure modes and they are all still there.

It's easy for them to show demos of abstract things because they don't necessarily have to follow real-world rules, but anything modeled after real world falls short of expectations.

I would like to see how it breaks, don't spend all your focus on how nice it looks with specially curated shots. At least give a few examples of what happens when it breaks from running too long. They mention that it can fail under "Understanding current limitations" but don't show any examples. Especially since they mention the cases of safety and responsible use, it seems quite relevant to help prepare people by showing them some examples of how it can break and so you an learn to spot it.

Again, very impressive from a technical point. But language is so flawed to do anything creative. It just turns out all looking the same and kind of boring

In the first comparison of Genie 3 to Genie 4 it seems that:

- in Genie 4 the character's suit stopped making sense in the back where it now has a weird fold?

- the controls don't control the character even anymore as now its controlling some kid-height character in first person instead?

- Everything looks like Unreal Engine.

This does not look good.

> Google AI Ultra exclusive

> AI Ultra (and thus Genie) are not available for Workspace companies

Who is this for?

I highly suspect that Genie is being made primarily for internal use, and access is more to gather feedback/training data and a bit of PR.

Q: Is there a easy way for average people to recognize these live super-deep fakes?

I know I could run the content through a fingerprint detector. However, I'm a professional software engineer...not a normal user.

What's the ethical impact of this technology??

What is the point of this vs cheap robotic arm simulations?

The only place I see this applicable is for visual artists prototyping

The future of movies will be promising.

[1]: https://www.minid.net/2026/8/2/the-actor-was-the-expensive-p...

We’ve come a long way from simulating a Unix file system in a GPT-3 prompt haven’t we?

Amazing!

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.

> "A REAL, ultra-photorealistic, high-end 35mm cinematic first-person perspective..."

Real nice prompting there, Google. It also still looks like a video game rendering.

>coming soon to Google AI Ultra subscribers in Project Genie

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 guess they used Genie 4 to make a video about people using Genie 4 in different contexts. This may have some implications.

>audio-like music

My favorite kind of music.

A nit, but given that this is from a major corporation, and LLMs are supposed to be em-dash-happy, it's surprising (disappointing?) that the announcement uses:

> audio-like music

That's a hyphen. What's "audio-like music" -- music that is almost sound but not quite? Music made from raw audio? :-)

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

The playable element is cool PR but the news is that endless synthetic training data for embodied AI models is basically here or close.

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.

Neuralink integration and I'm out of here.

it blows my mind that people actually want this. I couldn't be less interested in it.

I read a book, watch a movie, and play a game, to get the point of view and creative decisions by the people who make them. I don't want shadowy projections of my own mind and whims creating the experience. I can conceptually understand why some people may _think_ they want a "genie" that just grants every wish, but my suspicion is that much like other slop deluging us, they will quickly see that just getting whatever you want doesn't make interesting or good

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.

Showing off an anglo-bias with the Japanese train station in the 1980s, with a man speaking english.

Can someone ELI5 how this "Leads to AGI"? I can kind of understand some sort of "theory of mind" going on here, but how would having a complex world model enable, say, an AGI that could file my taxes for me?

Infinite Tsukuyomi is coming soon…

It looks sooo boring and generic that it's hard for me to imagine anyone thought https://www.youtube.com/watch?v=sFfPkUJd_Jk is a good showcase.

what good in the world could possibly come from this being available? did anyone working on this ever think about that?

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?

all the things you've dreamt of - your vivid dreams - now you can replay them.

for all the a.i misery with hardware prices i.e ram.

such a wonderful world we live in now.

again only available in trusted research preview.

If only there was some way we could create some sort of arrangement of 3D models and place a virtual camera within the arrangement. We could introduce some physics simulation and make the position of the virtual camera move and render what it sees to the user.

If such a system were possible, it seems like it would be far better at consistency and realism, since it could be fine tuned and hand crafted to best represent the desired world. It could be used to make interactive experiences, games, perhaps even feature films!

Alas.

Honestly MiniMax H3 looks better than this at most of the things I've been able to generate locally. These look super AAA game like - movement is uncanny and feels like it was trained on GTA3 or something like that - is this just me?

Wow, wow! What a treat! Such a fascinating time to be alive. Talk about fast feedback loops! This is pretty quick loops for trying out ideas!

I'm very impressed!

The third video is proof that v4 can, ekhm, walk slower?

WERE NOT IN A SIMULATION! YAY!

This should not exist.

Why do we need this? No thank you. We don't need flying cars and more vendor lock in. We need to serve the current google within constraints. That should be driving direction. Being a better ecosystem member. Another fascist product from google.

Good moving toward open world:)

I am again so disappointed with the discourse about AI in these threads. It rarely if ever focuses on anything remotely technical. People just trot out their agenda and their opinions (much like what I am doing now). We are building civilization level tools and the most technical analysis I see is that the blog post announcing it was written by an LLM (it wasn't) or that an ogre riding a unicorn into the clouds of Venus was missing a claw (wth?).

Yah, meta is discouraged here but why are we as a community putting up with this level of meta disruption? I guess I'm supposed to adapt to the new community but there's nothing there there.

I will stick with the more technical posts here and avoid anything to do with a new AI model and the complete and shocking thoughtlessness of the commenters (most of them).

[edit: grammar and spelling]

Who wants this

Is anyone actually making any games with these tools? Like, can I play one on Steam or something?

Why are they plowing money into this garbage? I don't understand it. I guess it is because Google is lagging behind in the AI race but the roi of this bs must be close to zero. Clowns.

Looks cool....

So if those genie 4 characters have all individual chain of thought reasoning and persistent retrospection / recollection, how do these human characters know they are not living in a simulation made by biological humans? Not sure you understand what i'm getting at. Some ethical questions do arise.

Failure modes?

Show them or I'll assume this is pure marketing.

The implications for what we now call video games are crazy.

im realy excited for this

If it’s not open weights, no one should care.

It doesn’t matter how impressive your demo is if it takes a literal data center to run.

Actual innovation can’t be seen at the let’s just throw money at it level. But, it can be seen at the that’s cool. I can run it on my laptop level.

What the fuck are the little wasd/arrow keys supposed to mean? They have no relationship to the movement of the character or the camera. It's just flashing buttons.

Why can't Google just announce something and release at the same day, not always this stupid wait list stuff.

Prompt: make a press release that isn't a slideshow on this company's own browser and hardware platform.

Who'd be down to write a science fiction novel where creating fake images is a crime and not a product?

Hmm, wonder if Databricks trademarked their Genie AI product.

So does this export 3d assets or an Unreal/godot/unity project so it can be turne dinto a game or is it limited to their runtime?

"Building world models responsibly"

... I'm suddenly reminded of Iain M Banks' "Surface Detail".

Impressive slop. But slop nonetheless.

supper cool

But to what end? How does this help humanity? How does this help us encounter truth and beauty? Whether you look at this from a utilitarian angle or from a transcendental one, it is a collosal waste of time, energy, and money.

“audio-like music”

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.

i am starting to get model fatigue..

this is the gta6 I am was hoping for

Not really impressive at all at this point. That dragon clip was pretty awful. If you told me this page was from 2024 I’d believe you.

pretty cool !

why does this need to exist?

From the auto-generated captions on the YouTube video on this page.

> 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.

[flagged]

[flagged]

[flagged]

Looks like we are inching closer to on the fly open world game creation soon. While the updates excite me as a senior data scientist but as a human they all just look scary. Just me?

[dead]

[flagged]

[dead]

[dead]

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.

Y tho?

Every increment of advance in this field is an increment of evidence that we are simulations.

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.