I can't believe it's been 24 hours and nobody mentioned the word "holodeck" :)
Genie 3: A new frontier for world models
481–490 of 512 posts
Re: Genie 3: A new frontier for world models
#482Earlier quoted context omitted.
I see two ways this is going to go: 1. Universal Basic Income as we're on the way to a post-scarcity society. Unlikely to actually happen due to greed. 2. We take inspiration from the french revolution and then return to a simpler time.
> Unlikely to actually happen due to greed. Greed makes no sense in a truly post scarcity society. There is no scarcity from which to take in a zero sum way from another. Status is the real issue. Humans use status to select sexually, and the display is both competitive and comparative. It doesnt matter absolutely how many pants you have, only that you have more and better than your competition. I actually think this…
That's only if greed is applied exclusively to real wealth. The reality is that greed is also applied to second, third, and even fourth order signs[1].
There is no end to semiotics, and therefore no end to greed. In this case, scarcity is artificial; created only via socially imposed monopoly. If we truly want a post-scarcity society, then we must abolish copyright.
[1] - https://en.wikipedia.org/wiki/Simulacra_and_Simulation
Re: Genie 3: A new frontier for world models
#483Earlier quoted context omitted.
> Future robots may learn in their dreams... So prescient. I definitely think this will be a thing in the near future ~12-18 months time horizon
I may be wrong, but this seems to make no sense. A neural net can produce information outside of its original data set, but it is all and directly derived from that initial set. There are fundamental information constraints here. You cannot use a neural net to itself generate from its existing data set wholly new and original full quality training data for itself. You can use a neural net to generate data, and you ca…
AlphaGo would seem to be a conceptually simple counter example.
Re: Genie 3: A new frontier for world models
#484Earlier quoted context omitted.
I'll try! Let's consider a tree blowing in the wind: To classically render this in any realistic fashion, it quickly gets complex. Between the physics simulation (rather involved) and the number of triangles (trees have many branches and leaves), you're going to be doing a lot of math . I'll emphasize "realistic" - sure, we can real-time render trees in 2025 that look.. ok. However, take more than a second to glance…
Don't you think a sufficiently advanced model will end up emulating what normal 3D engines already do mathematically? At least for the rendering part, I don't see you can "compress" the meaning behind light interaction without ending up with a somewhat latent representation of the rendering equation
in this case I assume it would be taken from motion / pixels of actual trees blowing in the wind. Which does serve up the challenge of like how does dust blow on a hypothetical gameworld alien planet?
Re: Genie 3: A new frontier for world models
#485It's feel like Ready Player One on Vision Pro will arrive soon
Hopefully they'll skip this[0] part: "...once we can rollback some of Halliday's ad restrictions, we estimate we can sell up to 80% of an individual's visual field before inducing seizures!"
Re: Genie 3: A new frontier for world models
#486Earlier quoted context omitted.
I'll try! Let's consider a tree blowing in the wind: To classically render this in any realistic fashion, it quickly gets complex. Between the physics simulation (rather involved) and the number of triangles (trees have many branches and leaves), you're going to be doing a lot of math . I'll emphasize "realistic" - sure, we can real-time render trees in 2025 that look.. ok. However, take more than a second to glance…
Don't you think a sufficiently advanced model will end up emulating what normal 3D engines already do mathematically? At least for the rendering part, I don't see you can "compress" the meaning behind light interaction without ending up with a somewhat latent representation of the rendering equation
If I am not mistaken, we are already past that. The pixel, or token, gets probability-predicted in real time. The complete, shaded pixel, as you will, gets computed ‘at once’ instead of layers of simulation. That’s the LLM’s core mechanism.
If the mechanism allows for predicting how the next pixel will look like, which includes the lighting equation, then there is no need anymore for a light simulation.
Would also like to know how Genie works. Maybe some parts get indeed already simulated in a hybrid approach.
Re: Genie 3: A new frontier for world models
#487Earlier quoted context omitted.
Well, maybe. But there are overwhelmingly large numbers of people who want to be in a fandom , and that means being fans of some shared thing. Maybe that shared thing will be AI generated, but it won't be a world of solipsists.
I think what the person you’re responding to meant was that you can generate a fandom for the content that was generated for you. So, you can get the feeling of being in a fandom despite there being no actual other humans that know what you’re talking about.
Sure, and people might enjoy that, but I'm saying that as much as people want to have fans, people also want to be fans, and that's not compatible with everyone consuming algoslop generated for them personally. Nobody is going to walk around with a T-shirt for an algoband that has an audience of just themselves. Maybe a virtual band gets famous in the same way Hatsune Miku is famous. But that's not personalized generation, that's just an old fashioned band with different tech.
A world without fandom is one without sports. That seems deeply unlikely to me! Anyone can generate personal podcasts with NotebookLM, which people enjoyed for a bit but doesn't seem to have made any impact on actual podcasts at all.
Re: Genie 3: A new frontier for world models
#488Re: Genie 3: A new frontier for world models
#489I'm still struggling to imagine a world where predicting the next pixel wins over over building a deterministic thing that is then ran. Eg: Using AI to generate textures, wire models, motion sequences which themselves sum up to something that local graphics card can then render into a scene. I'm very much not an expert in this space, but to me it seems if you do that, then you can tweak the wire model, the texture, m…
At some point it will be computationally cheaper to predict the next pixel than to classically render the scene, when talking about scenes beyond a certain graphical fidelity. The model can infinitely zoom in to some surface and depict(/predict) what would really be there. Trying to do so via classical rendering introduces many technical challenges
I work in game physics in the AAA industry, and I have studied and experimented with ML on my own. I'm sceptical that that's going to happen.
Imagine you want to build a model that renders a scene with the same style and quality of rasterisation. The fastest way to project a point on the screen is to apply a matrix multiplication. If the model needs to keep the same level of spatial consistency as the resterizer, it has to reproject points in space somehow.
But a model is made of a huge number of matrix multiplications interspersed by non-linear activations. Because of these non-linearities, it can't map a single matrix multiplication to its underlying multiplications. It has to recover the linearity by approximating the transformation with many more operations.
Now, I know that transformers can exploit superposition when processing a lot of data. I also know neural networks could come up with all sorts of heuristics and approximations based on distance or other criteria. However, I've read multiple papers showing that large models have a large number of useless parameters (the last one showed that their model could be reduced to just 4% of the original parameters, but the process they used requires re-training the model from scratch many times in a deterministic way, so it's not practical for large models).
This doesn't mean we might not end up using them anyway for real-time rendering. We could accept the trade-off and give up some coherence for more flexibility. Or, given enough computational power, a larger model could be coherent enough for the human eye, while its much larger cost will be justified by its flexibility. In a way like analogous systems are much faster than digital ones, but we use digital ones anyway because they can be reprogrammed.
With frame prediction and upscaling, we have this trade-off already.
Re: Genie 3: A new frontier for world models
#490Earlier quoted context omitted.
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…
Do you know where Noam makes that argument? I've been trying to figure out where I picked it up years ago. I'd like to revisit it to deepen my understanding. It's a pretty universal insight.
Ooh yes I do!