Genie 3: A new frontier for world models • Hacker News Board

Re: Genie 3: A new frontier for world models

#371

Post by thecupisblue » Tue, Aug 05, 2025, 9:39 PM UTC

casenmgreen wrote: post #162

diwank wrote: post #70

Earlier 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…

This is definitely one of the potential issues that might happen to embodied agents/robots/bodies trained on the "world model". As we are training a model for the real world based on a model that simulates the real world, the glitches in the world simulator model will be incorporated into the training. There will be edge cases due to this layered "overtraining", where a robot/agent/body will expect Y to happen but X will happen, causing unpredictable behaviour.I assume that a generic world agent will be able to autocorrect, but this could also lead to dangerous issues.

I.e. if the simulation has enough videos of firefighters breaking glass where it seems to drop instantaneously and in the world sim it always breaks, a firefighter robot might get into a problem when confronted with unbreakable glass, as it expects it to break as always, leading to a loop of trying to shatter the glass instead of performing another action.

Re: Genie 3: A new frontier for world models

#372

Post by ojosilva » Tue, Aug 05, 2025, 9:46 PM UTC

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…

Gaming is certainly a use case, but I think this is primarily coming as synthetic data generation for Google's robots training in warehouses:

https://www.theguardian.com/technology/2025/aug/05/google-st...

Gemini Robot launch 4 mo ago:

https://news.ycombinator.com/item?id=43344082

Re: Genie 3: A new frontier for world models

#373

Post by tim333 » Tue, Aug 05, 2025, 9:46 PM UTC

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).

We inherit ~2GB of digital data as DNA. Quite how that turns into nest building how tos is not yet known but it must happen somehow.

Re: Genie 3: A new frontier for world models

#374

Post by vanviegen » Tue, Aug 05, 2025, 9:46 PM UTC

schmidtleonard wrote: post #182

casenmgreen wrote: post #162

Earlier quoted context omitted.

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…

We are miles away from the fundamental constraint. We know that our current training methodologies are scandalously data inefficient compared to human/animal brains. Augmenting observations with dreams has long been theorized to be (part of) the answer.

> current training methodologies are scandalously data inefficient compared to human/animal brains

Are you sure? I've been ingesting boatloads of high definition multi-sensory real-time data for quite a few decades now, and I hardly remember any of it. Perhaps the average quality/diversity of LLM training data has been higher, but they sure remember a hell of a lot more of it than I ever could.

Re: Genie 3: A new frontier for world models

#375

Post by forrestthewoods » Tue, Aug 05, 2025, 9:48 PM UTC

dlivingston wrote: post #329

forrestthewoods wrote: post #238

Earlier quoted context omitted.

> this is a clear glimpse into the future. Not for video games it isn’t.

Unless and until state can be stored outside of the model. I for one would love a video game where you're playing in a psychedelic, dream-like fugue.

It is plausible to run a full simulation the old fashioned way and realtime render it with a diffusion model.

It is not currently, or near term, realistic to make a video game where a meaningful portion of the simulation is part of the model.

There will probably be a few interactive model-first experiences. But they’ll be popular as short novelties not meaningful or long experiences.

A simple question to consider is how would you adjust a set of simple tunables in a model-first simulator? For example giving the player more health, making enemies deal 2x damage, increasing move speed, etc etc. You can not.

Re: Genie 3: A new frontier for world models

#376

Post by maerF0x0 » Tue, Aug 05, 2025, 9:50 PM UTC

I'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, move the camera to wherever you want in the scene etc.

Re: Genie 3: A new frontier for world models

#377

Post by tim333 » Tue, Aug 05, 2025, 9:52 PM UTC

echelon wrote: post #176

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 don't know. I wasn't there and I'm excited. I think this puts Epic Games, Nintendo, and the whole lot into a very tough spot if this tech takes off. I don't see how Unreal Engine, with its voluminous and labyrinthine tomes of impenetrable legacy C++ code, survives this. Unreal Engine is a mess, gamers are unhappy about it, and it's a PITA to develop with. I certainly hate working with it. Innovator's Dilemma fast a…

I imagine Unreal Engine will start incorporating such stuff?

Re: Genie 3: A new frontier for world models

#378

Post by maerF0x0 » Tue, Aug 05, 2025, 9:52 PM UTC

reactordev wrote: post #7

yanis_t wrote: post #3

> Text rendering. Clear and legible text is often only generated when provided in the input world description. Reminds me of when image AIs weren't able to generate text. It wasn't too long until they fixed it.

And made hands 10x worse. Now hands are good, text is good, image is good, so we’ll have to play where’s Waldo all over again trying to find the flaw. It’s going to eventually get to a point where it’s one of those infinite zoom videos where the AI watermark is the size of 1/3rd of a pixel. What I’d really love to see more of is augmented video. Like, the stormtrooper vlogs. Runway has some good stuff but man is it a…

someone mentioned physics. Which might be an interesting conundrum because an important characteristic of games is that some part of them is both novel and unrealistic. (They're less fun if they're too real)

Re: Genie 3: A new frontier for world models

#379

Post by maerF0x0 » Tue, Aug 05, 2025, 9:56 PM UTC

snickerdoodle12 wrote: post #89

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 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 thing is baked into our DNA and until sex itself is saturated (if there is such a thing), or DNA is altered, we will continue to have a however subtle form of competition undergirding all interactions.

Re: Genie 3: A new frontier for world models

#380

Post by tim333 » Tue, Aug 05, 2025, 9:56 PM UTC

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…

>So what is final state here for us?

The merge. (https://blog.samaltman.com/the-merge)

I'm quite enthusiastic. I've always thought mortality sucks.