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

121–130 of 512 posts

Re: Genie 3: A new frontier for world models

#121

Post by hooverd »

dist-epoch wrote: post #93
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…

> Looks like a pretty decent explanation of Fermi paradox. It's not. We will be replaced, but the AI will carry on.

Eh, might as well kill yourself now then.

Re: Genie 3: A new frontier for world models

#122

Post by flyinglizard »

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 share your feelings. Also couple that with a populist and cynical political climate that can’t create effective regulations even if it wanted, and that by its very appetite for scale AI thrives at the hands of the few that can feed it and you get something quite bleak.

My only hope is that we could have created 100k nukes of monstrous yields but collectively decided not to. We instead created 10k smaller ones. We could have destroyed ourselves long ago but managed to avoid it.

Re: Genie 3: A new frontier for world models

#123

Post by neom »

diwank wrote: post #70
modeless wrote: post #13

Consistency over multiple minutes and it runs in real time at 720p? I did not expect world models to be this good yet. > Genie 3’s consistency is an emergent capability So this just happened from scaling the model, rather than being a consequence of deliberate architecture changes? Edit: here is some commentary on limitations from someone who tried it: https://x.com/tejasdkulkarni/status/1952737669894574264 > - Physi…

> 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'm invested in a startup that is doing something unrelated robotics, but they're spending a lot of time in Shenzhen, I keep a very close eye on robotics and was talking to their CTO about what he is seeing in China, versions of this are already being implemented.

Re: Genie 3: A new frontier for world models

#124

Post by zbrw »

seydor wrote: post #80

Would progress in these be faster if they created 3d meshes and animations instead of full frame videos?

I believe that the corpus of video data to train on with video far exceeds that of 3D data. It's also much cheaper to produce video data. So I'd expect that this is probably the quickest way forward from a current world state perspective.

Additionally, video seems like a pretty forward output shape to me - 2D image with a time component. If we were talking 3D assets and animations I wouldn't even know where to start with modeling that as input data for training. That seems really hard to model as a fixed input size problem to me.

If there was comparable 3D data available for training, I'd guess that we'd see different issues with different approaches.

A couple of examples that I could think of quickly: Using these to build games, might be easier if we could interact with the underlying "assets". Getting photorealistic results with intricate detail (e.g. hair, vegetation) might be easier with video based solutions.

Re: Genie 3: A new frontier for world models

#125

Post by Philpax »

ecshafer wrote: post #76
mclau157 wrote: post #26

I can see this being incredible for history lessons and history school lectures

Why? Sure a virtual walk around the Pantheon in all its glory would be nice . But would that really improve history lessons? It doesn't help students understand why things happened, and what the consequences were and how they have impacted the rest of history of the modern world.

Inhabiting a foreign cultural context can provide information that factual lessons may struggle to convey to the same degree. Of course, there's a limit to this - especially with regards to historical accuracy - but you are much more likely to understand why specific historical decisions were made if you are "in the room" where they happened, so to speak.

Re: Genie 3: A new frontier for world models

#126

Post by glenstein »

silveraxe93 wrote: post #62
ivape wrote: post #58

Earlier quoted context omitted.

So this just happened from scaling the model Unbelievable. How is this not a miracle? So we're just stumbling onto breakthroughs?

Is it actually unbelievable? It's basically what every major AI lab head is saying from the start. It's the peanut gallery that keeps saying they are lying to get funding.

>It's basically what every major AI lab head is saying from the start.

I suppose it depends what you count as "the start". The idea of AI as a real research project has been around since at least the 1950s. And I'm not a programmer or computer scientist, but I'm a philosophy nerd and I know debates about what computers can or can't do started around then. One side of the debate was that it awaited new conceptual and architectural breakthroughs.

I also think you can look at, say, Ted Talks on the topic, with guys like Jeff Hawkins presenting the problem as one of searching for conceptual breakthroughs, and I think similar ideas of such a search have been at the center of Douglas Hofstadter's career.

I think in all those cases, they would have treated "more is different" like an absence of nuance, because there was supposed to be a puzzle to solve (and in a sense there is, and there has been, in terms of vector space and back propagation and so on, but it wasn't necessarily clear that physics could "pop out" emergently from such a foundation).

Re: Genie 3: A new frontier for world models

#128

Post by roboboffin »

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…

In theory, creativity is an infinite space. As technology advances it allows humans to explore more and more complex things; take the advancement of music as an example, synths, loops etc.

If humans are not stretched to their limits, and are still able to be creative, then the tools will help us find our way through this infinite space.

AI will never be able to generate everything for us, because that means it will need infinite computation.

Re: Genie 3: A new frontier for world models

#130

Post by dawnerd »

quantumHazer wrote: post #118
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…

Machine learning as it is needs human data and input to progress further. Synthetic data can be useful until a certain point, but you can’t expect to have a better model on synthetic data alone indefinitely. The moat of GDM here is YouTube. That have a bazillion of gameplay and whatever videos. But here it is. The downside I can see is that most people will stop to publish content online for free since this companies…

Charging for content means nothing. Meta was pirating media and training against that and I suspect everyone else is too but hasn’t been caught yet.
Post reply on HN