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

391–400 of 512 posts

Re: Genie 3: A new frontier for world models

#391

Post by jonas21 »

glenstein wrote: post #126
silveraxe93 wrote: post #62

Earlier quoted context omitted.

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…

When they say "the start", I think they mean the start of the current LLM era (circa 2017). The main story of this time has been a rejection of the idea that major conceptual breakthroughs and complex architectures are needed to achieve intelligence. Instead, it's better to focus on simple, general-purpose methods that can scale to massive amounts of data and compute (i.e. the Bitter Lesson [1]).

[1] http://www.incompleteideas.net/IncIdeas/BitterLesson.html

Re: Genie 3: A new frontier for world models

#393

Post by brap »

wolttam wrote: post #388
maerF0x0 wrote: post #376

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, m…

At some point it will be computationally cheaper to predict the next pixel than to classically render the scene, when talking about scenes beyond a certain graphical fidelity. The model can infinitely zoom in to some surface and depict(/predict) what would really be there. Trying to do so via classical rendering introduces many technical challenges

I imagine a future where the “high level” stuff in the environment is pre defined by a human (with or without assistance from AI), and then AI sort of fills in the blanks on the fly.

So for example, a game designer might tell the AI the floor is made of mud, but won’t tell the AI what it looks like if the player decides to dig a 10 ft hole in the mud, or how difficult it is to dig, or what the mud sounds like when thrown out of the hole, or what a certain NPC might say when thrown down the hole, etc.

Re: Genie 3: A new frontier for world models

#395

Post by DiggyJohnson »

dingnuts wrote: post #319
DiggyJohnson wrote: post #227

Earlier quoted context omitted.

https://news.ycombinator.com/newsguidelines.html

lol I thought this was going to be the receipts but no, I guess asking for evidence is against the rules! y'all are in a religion

I genuinely have no idea where you’re coming from on this. You’re assuming way too much about everyone you disagree with

Re: Genie 3: A new frontier for world models

#396

Post by sitkack »

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

How do you claim to know this?

Re: Genie 3: A new frontier for world models

#397

Post by SequoiaHope »

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…

Yeah this is going to be excellent for robotics because it’s good enough to clear the reality gap (visually - physics would be another story).

Re: Genie 3: A new frontier for world models

#398

Post by teamonkey »

CharlieDigital wrote: post #334
creata wrote: post #308

Earlier quoted context omitted.

It just generates video, though, doesn't it? How are you going to get usable assets out of that?

Why wouldn't one be able to train an AI model to extract 3D models/assets out of an image/still from video?

That would be more useful and there are some services that attempt to do that, though I don’t know of any that do it well enough that a human isn’t needed to clean up the mess.

Genie 3 isn’t that though. I don’t think it’s actually intended to be used for games at all.

Re: Genie 3: A new frontier for world models

#399

Post by IAmGraydon »

pantalaimon wrote: post #350
CharlieDigital wrote: post #320

Earlier quoted context omitted.

> 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'.

I’ve always said that animals have short term and long term memory via the hippocampus, and then there’s supragenerational memory stored in DNA - behaviors that are learned over many generations and passed down via genetics.

Re: Genie 3: A new frontier for world models

#400

Post by sitkack »

delusional wrote: post #326
SequoiaHope wrote: post #275

Earlier quoted context omitted.

You don’t ask people to speak how you want, you simply only invite people who already have a history of speaking how you want. This phenomena is explained in detail I. Noam Chomsky’s work around mass media (eg NY Times doesn’t tell their editors what to do exactly, but only hire editors who already want to say what NY Times wants, or have a certain world view). The same can be applied to social media reviews. Invite…

Do you know where Noam makes that argument? I've been trying to figure out where I picked it up years ago. I'd like to revisit it to deepen my understanding. It's a pretty universal insight.

Look for discussion with British journalist Andrew Marr during a BBC interview in 1996.

The lead in to the quote starts at https://youtu.be/GjENnyQupow?t=662

"I don't say you're self-censoring - I'm sure you believe everything you're saying; but what I'm saying is, if you believed something different, you wouldn't be sitting where you're sitting." -- Noam Chomksy to Andrew Marr

Post reply on HN