logoalt Hacker News

Genie 4

701 points • by acossta • yesterday at 4:06 PM • 424 comments • view on HN

Comments

alphabetting • yesterday at 5:00 PM

The playable element is cool PR but the news is that endless synthetic training data for embodied AI models is basically here or close.

➕ show 1 reply
jackb4040 • yesterday at 4:45 PM

It's hard for me to understand Google's redefinition of "world models" (basically: a txt2videogame modality for LLMs) as anything other than an attempt to bury Yann Lecun's definition of "world models", which includes an implicit bear case against LLMs and thus Google's stock price.

st3fan • yesterday at 10:28 PM

This should not exist.

Sol- • yesterday at 4:40 PM

Neuralink integration and I'm out of here.

ElijahLynn • yesterday at 8:56 PM

Wow, wow! What a treat! Such a fascinating time to be alive. Talk about fast feedback loops! This is pretty quick loops for trying out ideas!

I'm very impressed!

dzonga • yesterday at 7:52 PM

all the things you've dreamt of - your vivid dreams - now you can replay them.

for all the a.i misery with hardware prices i.e ram.

such a wonderful world we live in now.

tumdum_ • yesterday at 6:45 PM

It looks sooo boring and generic that it's hard for me to imagine anyone thought https://www.youtube.com/watch?v=sFfPkUJd_Jk is a good showcase.

mike_hearn • yesterday at 4:49 PM

Google aren't the only ones with this tech. You can try out a 24/7 rolling set of video feeds for yourself at https://fal.live

An LLM generates four alternative prompts for what could happen next and there's a real time vote running for each option. It's trippy, like watching someone's dream.

zardo • yesterday at 4:36 PM

Showing off an anglo-bias with the Japanese train station in the 1980s, with a man speaking english.

reverseblade2 • yesterday at 4:46 PM

Infinite Tsukuyomi is coming soon…

inshard • yesterday at 4:31 PM

So world models capture inherent complexity of physical reality to help teach AI about hidden laws which probably helps train both LLMs and multimodal models used for autonomous vehicles and robots? And AMD acquiring World Labs is a move to outdo Nvidia’s work in this space. And Google probably sees this as a gateway to a new platform of autonomous vehicles and humanoids that they could rent out as a CSP? Competing with Nvidia, Tesla and complementing Waymo. Am I getting that right?

prymitive • yesterday at 4:59 PM

The third video is proof that v4 can, ekhm, walk slower?

sahilrane_ • yesterday at 6:53 PM

Good moving toward open world:)

next_xibalba • yesterday at 9:32 PM

The implications for what we now call video games are crazy.

➕ show 1 reply
twayst0 • yesterday at 9:18 PM

im realy excited for this

ddtaylor • yesterday at 5:00 PM

Is anyone actually making any games with these tools? Like, can I play one on Steam or something?

siva7 • yesterday at 5:49 PM

So if those genie 4 characters have all individual chain of thought reasoning and persistent retrospection / recollection, how do these human characters know they are not living in a simulation made by biological humans? Not sure you understand what i'm getting at. Some ethical questions do arise.

amelius • yesterday at 7:18 PM

Failure modes?

Show them or I'll assume this is pure marketing.

➕ show 1 reply
SV_BubbleTime • yesterday at 7:37 PM

If it’s not open weights, no one should care.

It doesn’t matter how impressive your demo is if it takes a literal data center to run.

Actual innovation can’t be seen at the let’s just throw money at it level. But, it can be seen at the that’s cool. I can run it on my laptop level.

➕ show 1 reply
Thorentis • yesterday at 10:29 PM

But to what end? How does this help humanity? How does this help us encounter truth and beauty? Whether you look at this from a utilitarian angle or from a transcendental one, it is a collosal waste of time, energy, and money.

m3kw9 • yesterday at 6:04 PM

Why can't Google just announce something and release at the same day, not always this stupid wait list stuff.

➕ show 1 reply
jeffbee • yesterday at 5:05 PM

Prompt: make a press release that isn't a slideshow on this company's own browser and hardware platform.

TZubiri • yesterday at 5:02 PM

Who'd be down to write a science fiction novel where creating fake images is a crime and not a product?

➕ show 1 reply
viccis • yesterday at 4:47 PM

Hmm, wonder if Databricks trademarked their Genie AI product.

tempfile • yesterday at 5:41 PM

What the fuck are the little wasd/arrow keys supposed to mean? They have no relationship to the movement of the character or the camera. It's just flashing buttons.

pdntspa • yesterday at 4:28 PM

So does this export 3d assets or an Unreal/godot/unity project so it can be turne dinto a game or is it limited to their runtime?

hackersnooze1 • yesterday at 9:04 PM

“audio-like music”

zhengyi13 • yesterday at 6:00 PM

"Building world models responsibly"

... I'm suddenly reminded of Iain M Banks' "Surface Detail".

suncore • yesterday at 5:57 PM

Impressive slop. But slop nonetheless.

lilingfei7 • yesterday at 9:27 PM

supper cool

_s_a_m_ • yesterday at 6:21 PM

i am starting to get model fatigue..

varispeed • yesterday at 4:47 PM

What is this for? I cannot understand these models. They are very much polluting the internet with nonsense and use capacity that people and businesses need for actual work.

If these are the cause of why I have to pay 2-4x I used to for a computer, then Google should go fuck themselves.

pacman1337 • yesterday at 4:43 PM

this is the gta6 I am was hoping for

godockly • yesterday at 8:29 PM

pretty cool !

apishare_api • today at 12:47 AM

[flagged]

avazhi • yesterday at 6:20 PM

Not really impressive at all at this point. That dragon clip was pretty awful. If you told me this page was from 2024 I’d believe you.

artursapek • yesterday at 5:08 PM

why does this need to exist?

robbie_cox • today at 12:00 AM

[flagged]

Zambyte • yesterday at 4:21 PM

From the auto-generated captions on the YouTube video on this page.

> Genie form [sic] can simulate scenarios

It's kind of amazing: the juxtaposition of such advanced generative AI and such terrible speech-to-text coming from the same parent company.

➕ show 3 replies
soren_ai • yesterday at 9:17 PM

[flagged]

Aeveus • yesterday at 4:31 PM

[dead]

rvz • yesterday at 4:10 PM

As I said before, World models will become simulation engines of AAA games where there is no need to release the actual game artifact and even if the game exists as a binary artifact, it will never be released and will be available on their hosted cloud back-end, then simulated and streamed back to you.

So, Stadia + World Models = New generation of DRM for games.

➕ show 8 replies
233mhz • yesterday at 4:34 PM

Y tho?

delichon • yesterday at 4:51 PM

Every increment of advance in this field is an increment of evidence that we are simulations.

➕ show 4 replies
ajs1998 • yesterday at 4:52 PM

Who is asking for this? Do advertisers really want this? I feel dread about many of the AI products being sold. They're mostly tools to help funnel money from the users to the bosses.