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

211–220 of 436 posts

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

#211

Post by dekhn »

sa-code wrote: post #143
pmayrgundter wrote: post #129

Earlier quoted context omitted.

I can't wait for Schizophrenic automobiles

There is a fleshed out realisation of this in Cyberpunk 2077. The cab AI is called Delamain > Delamain was a non-sentient AI created by the company Alte Weltordnung. His core was purchased by Delamain Corporation of Night City to drive its fleet of taxicabs in response to a dramatic increase in accidents caused by human drivers and the financial losses from the resulting lawsuits. The AI quickly returned Delamain Cor…

Probably my favorite side quest in the whole game.

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

#212

Post by jsheard »

griomnib wrote: post #191
dmarcos wrote: post #188

Earlier quoted context omitted.

If stories (and AAA games in general) are bland in games is due in large part to how expensive are to produce. Risk tolerance is low. If game assets are cheap to generate you’ll see small teams or even solo developers willing to take more creative risks

Counter point: you’d see a corresponding exponential increase in QA labor, and just like with the web, Steam will be absolutely flooded with slop. So I see the most likely outcome is a lot of dogshit and Steam being forced to make draconian moves to protect the integrity of the store.

QAing a game built on a framework where fundamental mechanics are non-deterministic and context-sensitive sounds like a special kind of hell. Not to mention that once you find a bug there's no way to fix it directly, since the source code is an opaque blob of weights, so you just have to RLHF it until it eventually behaves.

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

#213

Post by wongarsu »

niceice wrote: post #190
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…

Any estimates of how much one of these cost to generate and keep a minute of context? Secondly, any estimate of how much the price could fall in 5-10 years?

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 that works in real-time, but they don't show anything from that version (which is a statement in itself).

For reducing the price, ASICs like etched may be the way forwards [1]. The models will get bigger for a time, but there may be a lot of room for models that can exploit purpose-built hardware.

1: https://www.etched.com

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

#214

Post by dmarcos »

rafaelmn wrote: post #198
dmarcos wrote: post #188

Earlier quoted context omitted.

If stories (and AAA games in general) are bland in games is due in large part to how expensive are to produce. Risk tolerance is low. If game assets are cheap to generate you’ll see small teams or even solo developers willing to take more creative risks

Or you'll see a flood of shit that's impossible to filter.

Thanks to high bandwidth Internet, YouTube and smartphones is easier than ever to produce and distribute high quality video. So much good stuff coming from it.

Expect something similar if video games, interactive 3D is cheap to produce.

Filtering is a much easier problem to solve and abundance a preferable scenario.

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

#215

Post by artninja1988 »

warkdarrior wrote: post #96
artninja1988 wrote: post #5

Looking at the list of authors, is this from their open endedness team? I found their position paper on it super convincing https://arxiv.org/abs/2406.02061

Did you link the wrong Arxiv paper? https://arxiv.org/abs/2406.02061 does not look like a position paper nor does it share any authors with this Genie 2 work.

Yes, I meant this paper https://arxiv.org/abs/2406.04268 Should have double checked, sorry and thank you for pointing it out

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

#216

Post by ddtaylor »

erulabs wrote: post #128

It’s interesting to me that we continue to see such pressure on video and world generation, despite the fact that for years now we’ve gotten games and movies that have beautiful worlds filled with lousy, limited, poorly written stories. Star Wars movies have looked phenomenal for a decade, full of bland stories we’ve all heard a thousand times. Are there any game developers working on infinite story games? I don’t ca…

> It’s interesting to me that we continue to see such pressure on video and world generation, despite the fact that for years now we’ve gotten games and movies that have beautiful worlds

Those beautiful worlds took a lot of money to make and the studios are smart enough to realize consumers are apathetic/stupid enough to accept much lower quality assets.

The top end of the AAA market will use this sparingly for the junk you don't spend much time on - stuff the intern was doing before.

The bottom of the market will use this for virtually everything in their movie-to-game pipeline of throwaway games. These are the games designed just to sucker parents and kids out of $60 every month. The games that don't even follow the story of the movie and likely makes the story worse.

Strangely enough this is where the industry makes the vast majority of it's day-to-day walking around cash.

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

#217

Post by dmarcos »

alphabetting wrote: post #195
griomnib wrote: post #191

Earlier quoted context omitted.

Counter point: you’d see a corresponding exponential increase in QA labor, and just like with the web, Steam will be absolutely flooded with slop. So I see the most likely outcome is a lot of dogshit and Steam being forced to make draconian moves to protect the integrity of the store.

Seems like there's already a lot of slop on steam and I really doubt it will be difficult for quality content to be highlighted even if the amount of games increases 1000x or more

Yeah. Video and Youtube is an example. Filtering is not a hard problem. Mega tons of bad stuff doesn’t bother me.

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

#219

Post by ricardobeat »

aithrowawaycomm wrote: post #58

It is jaw-dropping and dismaying how for-profit AI companies use long-standing terms like "world model" and "physics" when they mean "video game model" and "video game physics." Or, as you can plainly see, "models gravity" when they mean "models Red Dead Redemption 2's gravity function, along with its cinematic lighting effects and Rockstar's distinctively weighty animations." Which is to say Google is not modeling g…

Remembering off-screen objects, generating spatially consistent features, modeling physical interactions and lights, understanding what "up the stairs" means, all seem to warrant talking about a world model, because that's exactly what's required to do these things compared to simply hallucinating video sequences.

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

#220

Post by lovich »

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…

I asked this in a similar thread the other day but what is with this pattern as well exemplifies with the below quote

> 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

Post reply on HN