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

61–70 of 512 posts

Re: Genie 3: A new frontier for world models

#61

Post by dragonwriter »

r0fl wrote: post #53
simianparrot wrote: post #28

Earlier quoted context omitted.

The same argument can be used for anything. Personal jetpacks are the worst they’ll ever be. Doesn’t mean they’re any close to being useful.

Trillions of dollars are not being invested in making jet packs any better Your comparison is incorrect

And if trillions of dollars were being invested in that, it would mean lots of investors being disappointed in a few years, not that jet packs were close to being useful.

Not sure if that's what you are trying to say about AI, or not.

Re: Genie 3: A new frontier for world models

#62

Post by silveraxe93 »

ivape wrote: post #58
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…

So this just happened from scaling the model Unbelievable. How is this not a miracle? So we're just stumbling onto breakthroughs?

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.

Re: Genie 3: A new frontier for world models

#63

Post by lackoftactics »

I thought I was not going to see too many negative comments here, yet I was mistaken. I thought if it's not LLM, people would have a more nuanced take and could look at the research with an open mind. The examples on the website are probably cherry-picked, but progress is really nice compared to Genie 2.

It's a nice step towards gains in embodied AI. Good work, DeepMind.

Re: Genie 3: A new frontier for world models

#64

Post by rowanG077 »

I'm not sure this is interesting beyond the wow effect. Unless we can actually get the world out of the AI. The real reason chatgpt and friends actually have customers is that the text interface is actually durable and easily to build upon after generation. It's also super ez to feed text into a fresh cycle. But this, while looking fancy, doesn't seem to be on the path to actually working out. Unless there is a sane export to unreal or something.

Re: Genie 3: A new frontier for world models

#65

Post by ivape »

silveraxe93 wrote: post #62
ivape wrote: post #58

Earlier quoted context omitted.

So this just happened from scaling the model Unbelievable. How is this not a miracle? So we're just stumbling onto breakthroughs?

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 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 ...

Re: Genie 3: A new frontier for world models

#66

Post by RALaBarge »

danvoell wrote: post #31
brotchie wrote: post #9

First AI thing that’s made me feel a bit of derealization… …and this is the worst the capabilities will ever be. Watching the video created a glimmer of doubt that perhaps my current reality is a future version of myself, or some other consciousness, that’s living its life in an AI hallucinated environment.

My take as well. Feels like something that is going to be plugged into my brain when I'm drooling in a nursing home.

Think of all of the suffering it will prevent

Re: Genie 3: A new frontier for world models

#67

Post by mclau157 »

ivape wrote: post #60
mclau157 wrote: post #26

I can see this being incredible for history lessons and history school lectures

It's going to replace video games.

Do people play video games to look at pretty scenery? No most people are testing skills in video games and this will not test skill for a while

Re: Genie 3: A new frontier for world models

#68

Post by scotty79 »

MarkusQ wrote: post #44
mclau157 wrote: post #26

I can see this being incredible for history lessons and history school lectures

Some physicist once said "I endeavor to never write more clearly than I think"; in the same way, history probably shouldn't be presented more vividly than it's understood. (We already have this problem with people remembering incidental details and emotional vibes from historical fiction as if they were established historical fact; VR diffusion delusions would make this much worse.)

History is mostly made up. You can be sure mostly about general facts. The other 80% are just narratives.

Re: Genie 3: A new frontier for world models

#70

Post by diwank »

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…

> 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

Post reply on HN