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

341–350 of 512 posts

Re: Genie 3: A new frontier for world models

#341

Post by scarmig »

stavros wrote: post #332
scarmig wrote: post #317

Earlier quoted context omitted.

Humans are dependent on their input data (through lifetime learning and, perhaps, information encoded in the brain from evolution), and yet they can produce out of distribution information. How? There is an uncountably large number of models that perfectly replicate the data they're trained on; some generalize out of distribution much better. Something like dreaming might be a form of regularization: experimenting wi…

Humans produce out-of-distribution data all the time, yet if you had a teacher making up facts and teaching them to your kids, you would probably complain.

Humans also sometimes hallucinate and produce non-sequitors.

Re: Genie 3: A new frontier for world models

#342

Post by lubujackson »

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…

Be comforted by the fact that no matter how good the AI gets, people crave human connection. Just like AI can generate music there is an uncanny valley effect where you quickly deduce there's no true humanity behind any of it, and ultimately undervalue it. At best you can have something like Minecraft or Dwarf Fortress where the generated worlds CAN be inspiring to a degree, but that is because the rules around generation are incredibly intricate and, ultimately, human.

Yes, AI can make music that sounds decent and lyrics that rhyme and can even be clever. But listen to a couple songs and your brain quickly spots the patterns. Maybe AI gets there some day, but the uncanny valley seems to be quite a chasm - and anything that approaches the other side seems to do so by piling lots of human intention along the way.

Re: Genie 3: A new frontier for world models

#343

Post by rakete »

echelon wrote: post #214
sureglymop wrote: post #202

Earlier quoted context omitted.

How so? It's not really by itself being creative yet, no? It sure seems like a game changer but who knows if one can even use this at scale?

I played around with Diamond WM on my 3090 machine. I also ran fast SDXL-turbo and LCM models with ControlNets paired with a 3D game prototype I threw together. The results were very compelling, and I was just one person hacking things together. This is 100% going to happen on-device. It's just a matter of time.

I am convinced as well this will eventually be how we render games and simulations.

Maybe just as kind of a DLSS on steroids where the engine only renders very simple objects and a world model translates these to the actual graphics.

Re: Genie 3: A new frontier for world models

#344

Post by lubujackson »

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…

It doesn't feel incredibly far off from demoscene scripts that generate mountain ranges in 10k bytes or something. It is wildly impressive but may also be wildly limited in how it accomplishes it and not extensible in a way we would like.

Re: Genie 3: A new frontier for world models

#345

Post by rpcope1 »

echelon wrote: post #297
make3 wrote: post #277

Earlier quoted context omitted.

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

Don't put the world state into the model. Use the model as a renderer of whatever objects the "engine" throws at it. Use the CPU and RAM for world state, then pass it off to the model to render. Regardless of how this is done, Unreal Engine with all of its bells and whistles is toast. That C++ pile of engineering won't outdo something this flexible.

How many watts and how much capital does it take to run this model? How many watts and how much capital does it take to run unity or unreal? I suspect there's a huge discrepancy here, among other things.

Re: Genie 3: A new frontier for world models

#347

Post by suddenlybananas »

scarmig wrote: post #341
stavros wrote: post #332

Earlier quoted context omitted.

Humans produce out-of-distribution data all the time, yet if you had a teacher making up facts and teaching them to your kids, you would probably complain.

Humans also sometimes hallucinate and produce non-sequitors.

Maybe you do, but people don't "hallucinate". Lying or being mistaken is a very different thing.

Re: Genie 3: A new frontier for world models

#348

Post by imiric »

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…

I can relate. It's exhausting.

The main challenge over the next decade as all our media channels are flooded with generated media will become curation. We desperately need ways to filter human-created content from generated content. Not just for the sake of preserving art, but for avoiding societal collapse from disinformation, which is a much more direct and closer threat. Hell, we've been living with the consequences of mass disinformation for the past decade, but automated and much more believable campaigns flooding our communication platforms will drastically lower the signal-to-noise ratio. We're currently unable to even imagine the consequences of that, and are far from being prepared for it.

This tech needs strict regulation on a global scale. Anyone against this is either personally invested in it, or is ignorant of its dangers.

Re: Genie 3: A new frontier for world models

#349

Post by suddenlybananas »

airstrike wrote: post #253
glenstein wrote: post #184

Earlier quoted context omitted.

I think we have some notion of a proto-grammar or ability to linguistically conceptualize, probably at the level of some primordial conceptual units that are more fundamental than language, thoughts and ideas in the concrete forms we generally understand them to have. I think it's like Chomsky said, that we don't learn this infrastructure for understanding language any more than a bird "learns" their feathers. But I…

At the most fundamental level, is it even linguistic? Would Tarzan speak at all?

Children (who aren't alone) will invent languages to communicate between each other, see Nicaraguan Sign Language.

Re: Genie 3: A new frontier for world models

#350

Post by pantalaimon »

CharlieDigital wrote: post #320
pantalaimon wrote: post #87

Earlier quoted context omitted.

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

> We don't inherit any software I wonder, though. Many animal species just "know" how to perform certain complex actions without being taught the way humans have to be taught. Building a nest, for example. If you say that this is emergent from the "underlying structure alone", doesn't this mean that it would still be "inherited" software (though in this case, maybe we think of it like punch cards).

That's interesting indeed - or take spiders building nets. So there must be some 'microcode' that does get inherited like physical features.

But then you have things like language or societal customs that are purely 'software'.

Post reply on HN