Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Genie 3: A new frontier for world models

deepmind.google

Post reply on HN
Print view View original

271–280 of 512 posts

Re: Genie 3: A new frontier for world models

#271

Post by tekacs »

timeattack wrote: post #75

Advances in generative AI are making me progressively more and more depressive. Creativity is taken from us at exponential rate. And I don't buy argument from people who are saying they are excited to live in this age. I can get that if that technology stopped at current state and remained to be just tools for our creative endeavours, but it doesn't seem to be an endgame here. Instead it aims to be a complete replace…

We can dream bigger: when music, images, video and 3d assets are far easier then treat them as primitives.

We can use these to create entire virtual worlds, games, software that incorporates these, and to incorporate creativity and media into infinitely more situations in real life.

We can create massive installations that are not a single image but an endless video with endless music, and then our hand turns to stabilizing and styling and aestheticizing those exactly in line with our (the artist's) preferences.

Romanticizing the idea that picking at a guitar is somehow 'more creative' than using a DAW to create incredibly complex and layered and beautiful music is the same thing that's happening here, even if the primitives seem 'scarier' and 'bigger'.

Plus, there are many situations in life that would be made infinitely more human by the introduction of our collective work in designing our aesthetic and putting it into the world, and encoding it into models. Installations and physical spaces can absolutely be more beautiful if we can produce more, taking the aesthetic(s) that we've built so far and making them dynamic to spaces.

Also for learning: as a young person learning to draw and sing and play music and so many other things, I would have tremendously appreciated the ability to generate and follow subtle, personalized generation - to take a photo of a scene in front of me and have the AI first sketch it loosely so that I can copy it, then escalate and escalate until I can do something bigger.

Re: Genie 3: A new frontier for world models

#272

Post by kridsdale3 »

Bjorkbat wrote: post #186
Bjorkbat wrote: post #166

Genuinely technically impressive, but I have a weird issue with calling these world simulator models. To me, they're video game simulator models. I've only ever seen demos of these models where things happen from a first-person or 3rd-person perspective, often in the sort of context where you are controlling some sort of playable avatar. I've never seen a demo where they prompted a model to simulate a forest ecology…

Also, to drive my point further home, in one of the demos they were operating a jetski during a festival. If the jetski bumps into a small Chinese lantern, it will move the lantern. Impressive. However, when the jetski bumped into some sort of floating structure the structure itself was completely unaffected while the jetski simply stopped moving. This is a pretty clear example of video game physics at work. In the r…

In the "first person standing in a room" demo, it's cool to see 100% optical (trained from recorded footage from cameras) graphics, including non-rectilinear distortion of parallel lines as you'd get from a wide-angle lens and not a high-FOV game engine. But still the motion of the human protagonist and the camera angle were 100% trained on how characters and controllers work in video games.

Re: Genie 3: A new frontier for world models

#273

Post by rohit89 »

Bjorkbat wrote: post #251
rohit89 wrote: post #247

Earlier quoted context omitted.

The goal is to eventually be able to model physics and all the various interactions accurately.

Sure, but if you're trying to get there by training a model on video games then you're likely going to wind up inadvertently creating a video game simulator rather than a physics simulator. I don't doubt they're trying to create a world simulator model, I just think they're inadvertently creating a video game simulator model.

Are they training only on video game data though? I would be surprised when its so easy to generate proper training data for this.

It is interesting to think about. This kind of training and model will only capture macro effects. You cannot use this to simulate what happens in a biological cell or tweak a gravity parameter and see how plants grow etc. For a true world model, you'd need to train models that can simulate at microscopic scales as well and then have it all integrated into a bigger model or something.

As an aside, I would love to see something like this for the human body. My belief is that we will only be able to truly solve human health if we have a way of simulating the human body.

Re: Genie 3: A new frontier for world models

#274

Post by quesera »

pantalaimon wrote: post #87
ivape wrote: post #65

Earlier quoted context omitted.

It's akin to us sending a rocket to space and immediately discovering a wormhole. Sure, there's a lot of science about what's out there, but to discover all this in our first few trips to orbit ...

Joscha Bach postulates that what we call consciousness must be something rather simple, an emergent property present in all sufficiently complex biological organisms. We don't inherit any software, so cognitive function must bootstrap itself from it's underlying structure alone. https://media.ccc.de/v/38c3-self-models-of-loving-grace

The emergent property theory seems logical, but I'm also partial to the quantum-tunneling-miasma theory which basically posits that there could be something fairly complex going on, and we just lack the ability to observe/measure it in our current physics. (Although I have difficulty coherently separating this theory from faith-based beliefs)

Re: Genie 3: A new frontier for world models

#275

Post by SequoiaHope »

alphabetting wrote: post #175
casenmgreen wrote: post #150

Earlier quoted context omitted.

The guy who tried was invite by Google to try it. He seems to me too enthusiastic, such that I feel Google asked him in particular because they trusted him to write very positively.

I doubt there was a condition on writing positively. Other people who tested have said this won't replace engines. https://togelius.blogspot.com/2025/08/genie-3-and-future-of-...

You don’t ask people to speak how you want, you simply only invite people who already have a history of speaking how you want. This phenomena is explained in detail I. Noam Chomsky’s work around mass media (eg NY Times doesn’t tell their editors what to do exactly, but only hire editors who already want to say what NY Times wants, or have a certain world view). The same can be applied to social media reviews. Invite the person who gives glowing reviews all the time.

Re: Genie 3: A new frontier for world models

#276

Post by kridsdale3 »

Workaccount2 wrote: post #27

I wonder how hard it would be to get VR output? That's an insane product right there just waiting to happen. Too bad Google sleeps so hard on the tech they create.

I think VR will come at the same time they make multiplayer. There needs to be differentiation between the world-state and the viewport. Right now, I suspect they're the same.

But once you can get N cameras looking at the same world-state, you can make them N players, or a player with 2 eyes.

Re: Genie 3: A new frontier for world models

#277

Post by make3 »

alphabetting wrote: post #175
casenmgreen wrote: post #150

Earlier quoted context omitted.

The guy who tried was invite by Google to try it. He seems to me too enthusiastic, such that I feel Google asked him in particular because they trusted him to write very positively.

I doubt there was a condition on writing positively. Other people who tested have said this won't replace engines. https://togelius.blogspot.com/2025/08/genie-3-and-future-of-...

It wouldn't be surprising if a structured version of this with state cached per room for example could be used in a game.

& you're basically seeing GPT-3 and saying it will never be used in any serious application.. the rate of improvement in their model is insane

Re: Genie 3: A new frontier for world models

#278

Post by kridsdale3 »

SeanaldMcDnld wrote: post #154
Workaccount2 wrote: post #27

I wonder how hard it would be to get VR output? That's an insane product right there just waiting to happen. Too bad Google sleeps so hard on the tech they create.

Consistent output and spatial coherence across each eye, maybe a couple years? But meeting head tracking accuracy and latency requirements, I’d bet decades. There’s no way any of this tech reduces end to end latency to acceptable levels, without a massive change in hardware. We’ll probably see someone use reprojection techniques in a year or so and claim they’ve done it. But true generated pixels straight to the head…

Agree. So I'll make a wild bet of "20 years". And hope for the best.

Re: Genie 3: A new frontier for world models

#279

Post by thinkingtoilet »

psbp wrote: post #246
pizzathyme wrote: post #180

Earlier quoted context omitted.

This is surprisingly a great analogy because millions of people still run every week for their own benefit (physical and mental health, social connection, etc). I wonder if mental exercises will move to the same category? Not necessarily a way to earn money, but something everybody does as a way of flourishing as a human.

The process of thinking and exploring ideas is inherently enriching. Nothing can take away your ability to have incredible experiences, except if the robots kill us all.

I don't know... There are plenty of otherwise capable adults who just get home from work and watch TV. They either never, or extremely rarely, indulge in hobbies, go see a concert, or even go out to meet others. Not that TV can't be art and challenge us but lets be honest, 99% of it is not that.

Re: Genie 3: A new frontier for world models

#280

Post by calebh »

internetter wrote: post #258

I feel like this tech is a dead end. If it could instead generate 3d models which are then rendered, that would be immensely useful. Eliminates memory and playtime constraints, allows it to be embedded in applications like games. But this? Where do we go from here? Even if we eliminate all graphical issues and get latency from 1s to 0, what purpose does it serve?

I think the most likely path forward for commercialization/widespread use is to use AI as a post-processing filter for low poly games. Imagine if you could take low quality/low poly assets, run it through a game engine to add some basic lighting, then pass this through AI to get a photo-realistic image. This solves the most egregious cases of world inconsistency and still allows for creative human fine-tuning. The trick will be getting the post-processor to run at a reasonable frame rate.
Post reply on HN