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

201–210 of 512 posts

Re: Genie 3: A new frontier for world models

#201

Post by rane »

myaccountonhn wrote: post #141
93po wrote: post #2

I wouldn't want to be a hollywood production studio or game developer right now.

I actually think indie game dev is quite safe from AI (well its already insanely competitive). It might change the field, or shrink the market but I think AI has a chance at replacing workers where the only metric that matters is $$$ and productivity. I just don't see myself consuming, for example, an AI generated autobiography or any AI generated book. As long as enough people feel that way the market will continue…

Is it though? Won't AI make the barrier of entry to indie game dev even lower, as assets and code will be able to be created effortlessly.

Re: Genie 3: A new frontier for world models

#202

Post by sureglymop »

echelon wrote: post #176
casenmgreen wrote: post #150

Earlier quoted context omitted.

The guy who tried was invite by Google to try it. He seems to me too enthusiastic, such that I feel Google asked him in particular because they trusted him to write very positively.

I don't know. I wasn't there and I'm excited. I think this puts Epic Games, Nintendo, and the whole lot into a very tough spot if this tech takes off. I don't see how Unreal Engine, with its voluminous and labyrinthine tomes of impenetrable legacy C++ code, survives this. Unreal Engine is a mess, gamers are unhappy about it, and it's a PITA to develop with. I certainly hate working with it. Innovator's Dilemma fast a…

How so? It's not really by itself being creative yet, no? It sure seems like a game changer but who knows if one can even use this at scale?

Re: Genie 3: A new frontier for world models

#203

Post by klibertp »

mclau157 wrote: post #67
ivape wrote: post #60

Earlier quoted context omitted.

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

There's an entire genre of games (immersive sims) that focus on experiencing the world with little to sometimes no skill required on the part of the player. The genre is diverse and incorporates elements of more gameplay-focused genres. It's also pretty popular.

I think some people want to play, and some want to experience, in different proportions. Tetris is the emanation of pure gameplay, but then you have to remember "Colossal Cave Adventure" is even older than Tetris. So there's a long history of both approaches, and for one of them, these models could be helpful.

Not that it matters. Until the models land in the hands of indie developers for long enough for them to prove their usefulness, no large developer will be willing to take on the risks involved in shipping things that have the slightest possibility of generating "wrong" content. So, the AI in games is still a long way off, I think.

Re: Genie 3: A new frontier for world models

#205

Post by _hark »

Very cool! I've done research on reinforcement/imitation learning in world models. A great intro to these ideas is here: https://worldmodels.github.io/

I'm most excited for when these methods will make a meaningful difference in robotics. RL is still not quite there for long-horizon, sparse reward tasks in non-zero-sum environments, even with a perfect simulator; e.g. an assistant which books travel for you. Pay attention to when virtual agents start to really work well as a leading signal for this. Virtual agents are strictly easier than physical ones.

Compounding on that, mismatches between the simulated dynamics and real dynamics make the problem harder (sim2real problem). Although with domain randomization and online corrections (control loop, search) this is less of an issue these days.

Multi-scale effects are also tricky: the characteristic temporal length scale for many actions in robotics can be quite different from the temporal scale of the task (e.g. manipulating ingredients to cook a meal). Locomotion was solved first because it's periodic imo.

Check out PufferAI if you're scale-pilled for RL: just do RL bigger, better, get the basics right. Check out Physical Intelligence for the same in robotics, with a more imitation/offline RL feel.

Re: Genie 3: A new frontier for world models

#206

Post by whywhywhywhy »

Uehreka wrote: post #111
lackoftactics wrote: post #63

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.

A lot of the negativity around this post is about the fact that there’s no demo and no open weights, which is Correct Negativity. Like don’t get me wrong, it would be cool for something like this to exist, but I’ve generally learned not to trust AI companies’ descriptions of their models until someone (or I) can actually get their hands on it and see if it’s usable at all. A description of a model that isn’t going to…

> but I’ve generally learned not to trust AI companies’ descriptions of their models

Sora was described very similar to this as a "world simulator" but ultimately it never materialized.

This one is a bit more hopeful from the videos though.

Re: Genie 3: A new frontier for world models

#207

Post by lbrito »

mclau157 wrote: post #67
ivape wrote: post #60

Earlier quoted context omitted.

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

>No most people are testing skills in video games

You must be young. As people get older they (usually) care less about that.

Re: Genie 3: A new frontier for world models

#208

Post by jimmySixDOF »

What gets me is the egocentric perspective it has naturally produced from its training data, where you have the perception of a 3D 6 degrees of freedom world space around you. Once it's running at 90 frames per second and working in a meshed geometry space, this will intersect with augmented virtual XR headsets, and the metaverse will become an interaction arena for working with artificial intelligence using our physical action, our gaze, our location, and a million other points of background noise telemetry, all of which will be integrated into what we now today call context and the response will be adjusting in a useful, meaningful way what we see painted into our environment. Imagine the world as a tangible user interface.

Re: Genie 3: A new frontier for world models

#209

Post by roboboffin »

rowanG077 wrote: post #196
roboboffin wrote: post #128

Earlier quoted context omitted.

In theory, creativity is an infinite space. As technology advances it allows humans to explore more and more complex things; take the advancement of music as an example, synths, loops etc. If humans are not stretched to their limits, and are still able to be creative, then the tools will help us find our way through this infinite space. AI will never be able to generate everything for us, because that means it will n…

AI will not be able to generate everything for us. Just the things that are able to be explored by humans and hopefully a tad bit more. AI is already more creative than humans by a lot of measures.

Depends what you mean by creativity. In some ways, AI is not creative at all, everything is generated by mapping text to visuals using diffusion modelling via a shared latent space. It has no agency or creative thought of its own.

Humans have demonstrated time and again, even things beyond our experience can be explored by us; quantum mechanics for example. Humans find a way to map very complex subjects to our own experience using analogy. Maybe AI can help us go further by allowing us to do this on even more complex ideas.

Post reply on HN