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

451–460 of 512 posts

Re: Genie 3: A new frontier for world models

#451

Post by scoot »

sandspar wrote: post #431
mattjreid wrote: post #229

Earlier quoted context omitted.

They would be impressed by the paint roller - it wasn't invented until the 1940s.

There's an old documentary where a film crew transported some of those "uncontacted tribe" guys to central London. Rather than being in awe of jet engines or networked internet, the tribesmen guys spent most of their time admiring house construction. "You're telling me there's METAL inside these walls?" I guess we tend to appreciate what we can understand.

I'm pretty sure this has been debunked as an online myth, and no such documentary exists. If you can show otherwise, I'd love to watch it

Re: Genie 3: A new frontier for world models

#452

Post by hhjinks »

ewoodrich wrote: post #322
kkukshtel wrote: post #221

Earlier quoted context omitted.

I similarly am surprised at how fast they are progressing. I wrote this piece a few months ago about how I think steering world model output is the next realm of AAA gaming: https://kylekukshtel.com/diffusion-aaa-gamedev-doom-minecraf... But even when I wrote that I thought things were still a few years out. I facetiously said that Rockstar would be nerd-sniped on GTA6 by a world model, which sounded crazy a few mont…

> Rockstar would be nerd-sniped on GTA6 by a world model I'm having trouble parsing your meaning here. GTA isn't really a "drive on the street simulator", is it? There is deliberate creative and artistic vision that makes the series so enjoyable to play even decades after release, despite the graphics quality becoming more dated every year by AAA standards. Are you saying someone would "vibe model" a GTAish clone wit…

GTA VI's story mode won't be surpassed by a world model, but the fucking around and blowing things up part conceivably could, and that's how people are spending their time in GTA. I don't see a world model providing the framing needed to contextualize the mayhem, thereby making it fun, anytime soon myself, but down the line? Maybe.

Re: Genie 3: A new frontier for world models

#453

Post by kennyadam »

forrestthewoods wrote: post #237

They’re very clever to only turn 90 degrees. I’d like to see a couple of 1080s with a little bit of 120 degree zig zagging along the way please.

The festival of light jetski and the helicopter over cliffs both turn 180+, I think there are one or two more too.

Re: Genie 3: A new frontier for world models

#454

Post by mewpmewp2 »

hhjinks wrote: post #452
ewoodrich wrote: post #322

Earlier quoted context omitted.

> Rockstar would be nerd-sniped on GTA6 by a world model I'm having trouble parsing your meaning here. GTA isn't really a "drive on the street simulator", is it? There is deliberate creative and artistic vision that makes the series so enjoyable to play even decades after release, despite the graphics quality becoming more dated every year by AAA standards. Are you saying someone would "vibe model" a GTAish clone wit…

GTA VI's story mode won't be surpassed by a world model, but the fucking around and blowing things up part conceivably could, and that's how people are spending their time in GTA. I don't see a world model providing the framing needed to contextualize the mayhem, thereby making it fun, anytime soon myself, but down the line? Maybe.

I would envision someone creative working together with Gen AI being able to do something awesome, rather than just saying "make me a GTA clone".

But someone creative having a vision in their head and then just guiding AI to flesh out the assets, details, etc.

Re: Genie 3: A new frontier for world models

#456

Post by 3abiton »

Vipitis wrote: post #381

I wish they would share more about how it works. Maybe a reseach paper for once? we didn't even get a technical report. From my best guess: it's a video generation model like the ones we already head. But they condition inputs (movement direction, viewangle). Perhaps they aren't relative inputs but absolute and there is a bit of state simulation going on? [although some demo videos show physics interactions like bump…

I feel after the 2017 transformer paper, and its impact on current state of AI, and google stocks, it seems Google is much more hesistant to keep things under their wings for now. Sadly, so.

Re: Genie 3: A new frontier for world models

#457

Post by astrange »

dingnuts wrote: post #143
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

what is a robot dream when there is clearly no consciousness? What's with this insane desire for anthropomorphism? What do you even MEAN learn in its dreams? Fine-tuning overnight? Just say that!

AI has traditionally been driven by "metaphor-driven development" where people assume the brain has system X, program something they give the same name, and then assume because they've given it that name it must work because it works in the brain.

This is generally a bad idea, but a few of the results like "neural networks" did work out… eventually.

"World model" is another example of a metaphor like this. They've assumed that humans have world models (most likely not true), and that if they program something and call it a "world model" it will work the same way (definitely not true) and will be beneficial (possibly true).

(The above critique comes from Phil Agre and David Chapman.)

Re: Genie 3: A new frontier for world models

#458

Post by horhay »

Miraste wrote: post #23
hodgehog11 wrote: post #6

Earlier quoted context omitted.

This kind of announcement without an appropriate demo to verify their claims is pretty common with DeepMind at this point. They barely even discuss their limitations, so as always, this should be taken with a grain of salt.

Most of the big labs never go into their models' limitations. OpenAI does it best, despite their inveterate hype-building. Their releases always have a reasonable limitations section, usually with text/image/video examples of failures.

Google does a good job with that too usually. Which makes their last two announcements (IMO success and Genie 3) being a bit light on details is somewhat surprising.

Re: Genie 3: A new frontier for world models

#460

Post by roenxi »

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…

It is possible - for example, getting a blob of physics data, fitting a curve then projecting the curve to theorise what would happen in new unseen situations. The information constraints don't limit the ability to generate new data in a specific domain from a small sample; indeed it might be possible to fully comprehend the domain if there is an underlying process it can infer. It is impossible to come up with wildly unrelated domains though.
Post reply on HN