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

131–140 of 512 posts

Re: Genie 3: A new frontier for world models

#131

Post by ollin »

ollin wrote: post #38

This is very encouraging progress, and probably what Demis was teasing [1] last month. A few speculations on technical details based on staring at the released clips: 1. You can see fine textures "jump" every 4 frames - which means they're most likely using a 4x-temporal-downscaling VAE with at least 4-frame interaction latency (unless the VAE is also control-conditional). Unfortunately I didn't see any real-time foo…

Regarding latency, I found a live video of gameplay here [1] and it looks like closer to 1.1s keypress-to-photon latency (33 frames @ 30fps) based on when the onscreen keys start lighting up vs when the camera starts moving. This writeup [2] from someone who tried the Genie 3 research preview mentions that "while there is some control lag, I was told that this is due to the infrastructure used to serve the model rather than the model itself" so a lot of this latency may be added by their client/server streaming setup.

[1] https://x.com/holynski_/status/1952756737800651144

[2] https://togelius.blogspot.com/2025/08/genie-3-and-future-of-...

Re: Genie 3: A new frontier for world models

#132

Post by pixelesque »

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…

What's interesting to me along these lines is I assume most of the companies funding the research are targeting the "creative" media in terms of image generation, music generation, avatars, speach, etc.

I can understand it's very interesting from a researcher's point-of-view (I'm a software dev who's worked adjacent to some ML researchers doing pipeline stuff to integrate models into software), but at the same time: Where are the robots to do menial work like clean toilets, kitchens, homes, etc?

I assume the funding isn't there? Or maybe it's much less exciting to research diffusion networks for image generation that working out algorithms for the best way to clean toilets :)

Re: Genie 3: A new frontier for world models

#133

Post by skybrian »

Saline9515 wrote: post #119
skybrian wrote: post #95

Earlier quoted context omitted.

We already live in a world where a vast library of songs by musicians who play much better than you are readily available on YouTube and Spotify. This seems like more of the same?

It still requires work, dedication and produces authenticity. A world where AI can produce music instantly commoditizes it.

Music is already a commodity. You can just buy some anonymous background music to play in your restaurant. No effort required.

Re: Genie 3: A new frontier for world models

#134

Post by glenstein »

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

>We don't inherit any software, so cognitive function must bootstrap itself from it's underlying structure alone.

Hardware and software, as metaphors applied to biology, I think are better understood as a continuum than a binary, and if we don't inherit any software (is that true?), we at least inherit assembly code.

Re: Genie 3: A new frontier for world models

#136

Post by Fraterkes »

ivape wrote: post #73
Fraterkes wrote: post #54

Earlier quoted context omitted.

I’m seeing a lot of variations on this in this thread, but we have been able to render photoreal things, and do intricate physical simulations, for a long time. This is mostly impressive because it is a real-time way to generate and render big, intricate worlds. But if you believe reality is a simulation, why would these “efficient” world-generation methods convince you of anything? The tech our reality would have to…

but we have been able to render photoreal things, and do intricate physical simulations, for a long time. Not like this we haven't. This is convincing because I can have any of you close your eyes and imagine a world where pink rabbits hand out parking tickets. We're a neurolink away from going from thought > to prompt > to fantasy.

I guess I should have clarified: when you talk about reality being a simulation, do you mean that we collectively live in a simulated universe, or that you personally are playing a very realistic vr game?

Re: Genie 3: A new frontier for world models

#137

Post by myahio »

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…

What specific form of creative media is this supposed to replace though? I feel like its just going to create a brand new, exciting category of entertainment. I personally fail to see any bad precedent within this announcement.

Re: Genie 3: A new frontier for world models

#138

Post by fgafford »

wahnfrieden wrote: post #85
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…

Automation only leads to more labor if we allow that employer relation to dictate so. Automation affords leisure time (for everything besides labor that life has to offer, including optional labor-like pursuits) but it’s currently unevenly distributed who gets to benefit from that

You need to read Brave New World. Already have all that figured out.

Work is fundamental part of society and will never be eliminated, regardless of its utility/usefulness. The cast/class system determines the type of work. The amount (time) of work is set as it was discovered additional leisure and to reduce it does not improve individuals happiness.

Re: Genie 3: A new frontier for world models

#139

Post by rishabhparikh »

svantana wrote: post #109
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…

You're quite the pessimist. I think the arts would do well to look at sports as a glimpse of their future. Machines are faster and stronger than people, but that hasn't had any impact on sports at all. Nobody's tuning in to the robot olympics.

Agreed that no one wants to watch shotput when the ball is launched out of a cannon, but people might be interested when the robots competing are anthropomorphs.

For example, robot boxing: https://www.youtube.com/watch?v=rdkwjs_g83w

Re: Genie 3: A new frontier for world models

#140

Post by whamlastxmas »

Saline9515 wrote: post #119
skybrian wrote: post #95

Earlier quoted context omitted.

We already live in a world where a vast library of songs by musicians who play much better than you are readily available on YouTube and Spotify. This seems like more of the same?

It still requires work, dedication and produces authenticity. A world where AI can produce music instantly commoditizes it.

I mean you can just listen to human made music if that’s an important part of the experience for you. I doubt humans are going to stop anytime soon
Post reply on HN