Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Genie 2: A large-scale foundation world model

deepmind.google

Post reply on HN
Print view View original

301–310 of 436 posts

Re: Genie 2: A large-scale foundation world model

#301

Post by serf »

lifeformed wrote: post #299

Neat tech but people might mistake this as being useful for game development, where it'll be less helpful than useless. Games are about interactions, and this actively works against it. You don't want the model to infer mechanics, the designer needs deep control over every aspect of it. People mentioned using this for prototyping a game, but that's completely meaningless. What would it even mean to use this to protot…

>It doesn't help you figure out anything mechanically or visually.

people sell entire franchises off of a few pre-rendered generic-fantasy still images -- I would have to disagree with the premise that this is useless as a visual concept tool.

I agree with your notions about integration into an existing game.

Re: Genie 2: A large-scale foundation world model

#302

Post by bionhoward »

onlyrealcuzzo wrote: post #230
wongarsu wrote: post #213

Earlier quoted context omitted.

Oasis (the Minecraft world model) can serve about 5 players on 8 H100 in real-time at 20fps in 360p. This is a much more capable model with two orders of magnitude more context. They pretty much say it can't be played real-time, which I read as they generate less than 15fps@240p on 8 GPUs. Probably why they talk so much about using it for AI training and evaluation rather than human use. There is a distilled version…

> Probably why they talk so much about using it for AI training and evaluation rather than human use. What would they do / how would they use this output to make a better AI?

Embodied cognition is a core theory for AGI; this would enable a vast array of bodies, environments, and situations, that high level of diversity can empower AI adaptability.

For a straightforward example, this could help Waymo rehearse driving in various cities and weather / traffic settings

Re: Genie 2: A large-scale foundation world model

#303

Post by rjrdi38dbbdb »

krainboltgreene wrote: post #178
93po wrote: post #157

Earlier quoted context omitted.

if you do basic chatgpt prompts in late 2024 asking for dynamic story telling, sure, you'll get what you said. it's super dismissive to think that wont get better over time, or that even with the tools today, that you can't get dynamic and interesting stories out of it if you provide it with the proper framework

> it's super dismissive to think that wont get better over time When did we start thinking this way? That things HAVE to get better and in fact to think otherwise is very negative? Is HN under a massive hot hand fallacy delusion?

How could creativity in AI not get better?

Sure, progress will likely not be linear or without challenges, but we already have the human brain as proof that it is possible.

Re: Genie 2: A large-scale foundation world model

#304

Post by moralestapia »

Sateeshm wrote: post #274
moralestapia wrote: post #22

Not even a month ago HN was discussing Ben Affleck's take on actors and AI, somehow taking a side with him and arguing how the tech "it's just not there, etc...". I'll keep my stance, give it two years and very realistic movies, with plot and everything, will be generated on demand.

I'll take that bet

Email on profile!

I'll match any 5-figure amount you propose. I also know an escrow service we can trust.

Re: Genie 2: A large-scale foundation world model

#305

Post by beeflet »

achierius wrote: post #291
wongarsu wrote: post #160

Earlier quoted context omitted.

We already knew it's possible from AI minecraft ( https://oasis.decart.ai ). This is just a more impressive version of that, trained on a wider range of games and with more context frames (Oasis has about a second of context, this one a minute). Even the architecture seems to be about the same. Had they released this two months earlier it would have been incredibly impressive. Now it's still cool and inspiring, but n…

This is far beyond Oasis. Oasis had approximately 0 continuity, and the generated world was a blurry mess. This on the other hand actually approaches usability.

I don't know what the pipeline looks for these, but I assume that's due to the costs associated with training and running. Oasis had a context of only a couple of frames, while this genie model apparently runs for a couple of minutes. I guess they have a couple tricks up their sleeve to optimize this though.

Re: Genie 2: A large-scale foundation world model

#306

Post by galleywest200 »

smusamashah wrote: post #183
freedryk wrote: post #127

Forget video games. This is a huge step forward for AGI and Robotics. There's a lot of evidence from Neurobiology that we must be running something like this in our brains--things like optical illusions, the editing out of our visual blind spot, the relatively low bandwidth measured in neural signals from our senses to our brain, hallucinations, our ability to visualize 3d shapes, to dream. This is the start of addin…

This looks like my dream worlds already but more colorful and a bit more detailed. But the way it hallucinates and becomes inconsistent going back and forth the same place is same as dreams.

I get mild LSD flashbacks to my time in college when I look at the weird blending of edges that AI video does.

Re: Genie 2: A large-scale foundation world model

#310

Post by hustwindmaple1 »

summerlight wrote: post #165
vessenes wrote: post #4

This is.. super impressive. I'd like to know how large this model is. I note that the first thing they have it do is talk to agents who can control the world gen; geez - even robots get to play video games while we work. That said; I cannot find any: - architecture explanation - code - technical details - API access information Feels very DeepMind / 2015, and that's a bummer. I think the point of the "we have no moat…

While this is impressive, yet still looks like a very early prototype. The overall nuance seems that it doesn't try to be a standalone product but a part of broader R&D projects toward general agents... I doubt if they even have any productionized modeling pipelines for this project yet and pretty sure that we won't have an open access anytime soon.

GDM is a research lab. They are not set up for production. There are other teams in Alphabet doing productionization stuff.
Post reply on HN