[HN Gopher] Genie 3: A new frontier for world models
___________________________________________________________________
Genie 3: A new frontier for world models
Author : bradleyg223
Score : 996 points
Date : 2025-08-05 14:08 UTC (8 hours ago)
(HTM) web link (deepmind.google)
(TXT) w3m dump (deepmind.google)
| 93po wrote:
| I wouldn't want to be a hollywood production studio or game
| developer right now.
| tkgally wrote:
| Same here. Though if I were a 17-year-old film fan or gamer
| with an imaginative drive, I would be really excited about the
| powerful creative tools that might become available to me soon.
| Mouvelie wrote:
| I don't know if you had the teenage years I had, but there
| would be A LOT of NSFW content made on that thing.
| mclau157 wrote:
| Hollywood maybe for small scenes, but gamers would quickly
| realize and destroy this level of quality and continuity vs. a
| 3D game engine with defined meshes
| 93po wrote:
| i meant more in 5 years when its significantly better
| ducktective wrote:
| Well, what _would_ you want to be? Frontend dev? Mobile dev?
| Script writer? Logo designer? Junior lawyer?
| 93po wrote:
| housewife
| assword wrote:
| Housewife to an AI CEO might be a good gig, if you can take
| the beatings.
| myaccountonhn wrote:
| 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 to be
| there.
| rane wrote:
| 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.
| hooverd wrote:
| There's already a glut of open world slop!
| vaenaes wrote:
| A common refrain among the least creative people in the world.
| yanis_t wrote:
| > Text rendering. Clear and legible text is often only generated
| when provided in the input world description.
|
| Reminds me of when image AIs weren't able to generate text. It
| wasn't too long until they fixed it.
| reactordev wrote:
| And made hands 10x worse. Now hands are good, text is good,
| image is good, so we'll have to play where's Waldo all over
| again trying to find the flaw. It's going to eventually get to
| a point where it's one of those infinite zoom videos where the
| AI watermark is the size of 1/3rd of a pixel.
|
| What I'd really love to see more of is augmented video. Like,
| the stormtrooper vlogs. Runway has some good stuff but man is
| it all expensive.
| maerF0x0 wrote:
| someone mentioned physics. Which might be an interesting
| conundrum because an important characteristic of games is
| that some part of them is both novel and unrealistic.
| (They're less fun if they're too real)
| reactordev wrote:
| It depends on the genre. Simulation "games" tend to love
| realism of simulation while providing an accelerated time.
| Others like you said, are more fun with plausible physics
| or physics that bend the rules a little bit. Sometimes, a
| game just about funky physics becomes a hit - Goat
| Simulator.
|
| Walking/Running/Steps have already been solved pretty well
| with NN's, but simulation of vehicle engines and vehicle
| physics have not. Not to my knowledge. I suspect iRacing
| would be extremely interested in such a model.
|
| _edit_
|
| I take it back, PINN's are a thing and now I have a new
| rabbit hole...
| TheAceOfHearts wrote:
| I wouldn't say that the text problem has been fully fixed. It
| has certainly gotten a lot better, but even gpt-image-1 still
| fails occasionally when generating text.
| yencabulator wrote:
| Note that the prompt and the generated chalkboard disagree on
| whether there's a dash or not.
| yanis_t wrote:
| And unfortunately not possible to play around for the general
| public.
| cj wrote:
| > World models are also a key stepping stone on the path to
| AGI, since they make it possible to train AI agents in an
| unlimited curriculum of rich simulation environments.
|
| I don't think Humans are the target market for this model, at
| least right now.
|
| Sounds like the use case is creating worlds for AI agents to
| play in.
| hodgehog11 wrote:
| This kind of announcement without an appropriate demo to verify
| their claims is pretty common with DeepMind at this point. They
| barely even discuss their limitations, so as always, this
| should be taken with a grain of salt.
| Miraste wrote:
| Most of the big labs never go into their models' limitations.
| OpenAI does it best, despite their inveterate hype-building.
| Their releases always have a reasonable limitations section,
| usually with text/image/video examples of failures.
| qingcharles wrote:
| Here's a (weaker) competitor that's live:
|
| https://odyssey.world/introducing-interactive-video
| romanovcode wrote:
| Yeah, honestly - what's the point of announcing it then?
|
| I DECLARE BANKRUPTCY vibes here
| zb3 wrote:
| Yet another unavailable model from Google.. if I can't use it, I
| don't care. Tell me about it when it's ready to use.
| Tadpole9181 wrote:
| What a strange take. Do you not care about news coming from the
| James Webb Telescope either, just because you can't play with
| the telescope personally?
|
| It's a whitepaper release to share the STOTA research. This
| doesn't seem like an economically viable model, nor does it
| look polished enough to be practically usable.
| growthwtf wrote:
| I think it's a perfectly valid take coming from some
| intersection of an engineering mindset and FOSS culture. And,
| the comparison you bring up is a bit of a category error.
|
| We know how James Webb works and it's developed by an
| international consortium of researchers. One of our most
| trusted international institutions, and very verifiable.
|
| We do not know how Genie works, it is unverifiable to non-
| Google researchers, and there are not enough technical
| details to move much external teams forward. Worst case, this
| page could be a total fabrication intended to derail
| competition by lying about what Google is _actually_ spending
| their time on.
|
| We really don't know.
|
| I don't say this to defend the other comment and say you're
| wrong, because I empathize with both points. But I do think
| that treating Google with total credulity would be a mistake,
| and the James Webb comparison is a disservice to the JW team.
| zb3 wrote:
| James Webb Telescope is not something that can be - and is
| released. AI models are, and others are announcing them when
| they're available, but DeepMind introduces noise here with
| their "trust us, that works, now go away" approach.
| delusional wrote:
| > James Webb Telescope is not something that can be - and
| is released
|
| I would actually turn that around. The Telescope is
| released. It's flying around up there taking photos. If
| they kept it in some garage while releasing flashy PR pages
| about how groundbreaking it is, then I'd be pretty
| skeptical.
| alganet wrote:
| It's a bitter take, but your comparison with JWST is invalid.
|
| The main product of the telescope is its data, not the
| ability for anyone to play with the instruments.
|
| The main product of the model is the ability for anyone to
| play with it.
|
| Strange rebutal.
| esafak wrote:
| You don't have to be the customer of every product (that
| affects you).
| brotchie wrote:
| 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.
| curwin wrote:
| Same, even worse that the world was generated on the fly--
| nobody even hand-crafted it. That makes it even more
| depressing.
| drstewart wrote:
| ... so like the real world?
| thatfrenchguy wrote:
| I mean, Minecraft worlds are generated on the fly and they've
| unleashed quite a it of creativity in children
| simianparrot wrote:
| 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.
| delusional wrote:
| It's also just wrong. Plenty of things get worse.
| crossbody wrote:
| Not really. E.g. clay tablets, physical books will not be
| meaningfully better.
| suddenlybananas wrote:
| Yes, but they're not going to get any worse.
| crossbody wrote:
| "not getting worse" is a pretty low bar
| simianparrot wrote:
| Which is precisely my point. It's the _lowest_ bar
| possible.
| yencabulator wrote:
| Books are printed on worse paper these days that doesn't
| last as long.
| Workaccount2 wrote:
| While true, it's the speed of improvement that gives the
| statement gravity.
| westoncb wrote:
| The difference is the incentive to improve, and actual
| present rate of improvement, for models like this is far
| higher than it is for jetpacks. (That and certain intrinsic
| features at least suggest the route to improvement is roughly
| "more of the same," vs "needs massive unknown breakthrough".)
| r0fl wrote:
| Trillions of dollars are not being invested in making jet
| packs any better
|
| Your comparison is incorrect
| rkozik1989 wrote:
| You say assuming money is limitless and investor patience
| for returns is endless.
| dragonwriter wrote:
| 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.
| ekianjo wrote:
| > Personal jetpacks are the worst they'll ever be
|
| Have they become better over the past 20 years?
| danvoell wrote:
| My take as well. Feels like something that is going to be
| plugged into my brain when I'm drooling in a nursing home.
| RALaBarge wrote:
| Think of all of the suffering it will prevent
| dlivingston wrote:
| Literally, The Matrix. (I just rewatched the first one for
| the first time in a decade and forgot how damn good of a
| movie it is.)
| MarkusQ wrote:
| > First AI thing that's made me feel a bit of derealization...
|
| > ...and this is the worst the capabilities will ever be.
|
| I guess if this bothers you (and I can see how it might) you
| can take some small comfort in thinking that (due to
| enshitification) this could in fact be the _best_ the
| capabilities will ever be.
| Philpax wrote:
| Once it has been proven to be possible, other companies
| [1][2][3] can and will reproduce it, and will attempt to push
| the frontier. As far as we know, there's no bottleneck that's
| stalling development here.
|
| [1]: https://www.worldlabs.ai/
|
| [2]: https://wayfarerlabs.ai/
|
| [3]: https://runwayml.com/research/introducing-general-world-
| mode...
| dandellion wrote:
| I suggest you go to google/bing/whatever floats your boat and
| search "it will only get better" then filter results earlier
| than 2010. Things that I just found that were going to "only
| get better":
|
| - Google search
|
| - Web browsers
|
| - Web content
|
| - Internet Explorer
|
| - Music
|
| - Flight process at Mosul airport
|
| - Star Wars
| dist-epoch wrote:
| Google search is better. It's just that now you ask the LLM
| what you want to find out.
| zanellato19 wrote:
| Google search is absolutely not better.
| konart wrote:
| Depends on a perspective though.
| iammrpayments wrote:
| I was going to say it was maybe better for advertisers but
| the auction has gone up and the dashboard has much less
| data due to legal restrictions
| Philpax wrote:
| Those are worse due to economic and cultural reasons, not
| technological reasons. The technology itself will only get
| better.
|
| (Also, implying that music has gotten worse is a boomer-ass
| take. It might not be to your liking, but there's more of it
| than ever before, and new sonic frontiers are being
| discovered every day.)
| x187463 wrote:
| None of those have a quantifiable definition of 'better'. The
| current range of AI models have very easily measured metrics.
| internetter wrote:
| Very much disagree. Current AI benchmarks are quite
| arbitrary as evidenced by the ability of a model to be
| fitted to a particular benchmark. Like the closest
| benchmark to objectivity is "does it answer this question
| factually" and benchmarks like that are just as failable
| really because who decides what questions we ask? The same
| struggles happen when we try to measure human intelligence.
| The more complex the algorithm the harder it is to quantify
| because there are so many parameters. I could easily
| contrive some "search engine benchmark", but it wouldn't be
| that useful because it's only adherent to my own subjective
| definition of what it means for a search engine to be good.
| Terretta wrote:
| > _Star Wars_
|
| And then you watched Mandalorian and Andor?
|
| Jokes aside, Google Search _results_ are worse thanks to so
| much web content being just ad scaffolding, but the
| interesting one here is music.
|
| Music is typically imagined to be its best at whatever ages
| one most listened to it, partly trained in and partly thanks
| to meanings/memories/nostalgia attached to it. As a
| consequence, for most _everyone_ , more recent music seems to
| be "getting worse"!
|
| That said, and back to the SEO effect on Google Results, I'd
| argue mass distribution/advertising/marketing has resulted in
| most audio airtime getting objectively* less complex, but if
| one turns off the mass distribution, and looks around, there
| seems to be plenty of just as good -- even building on what
| came before -- music to be found.
|
| * https://www.researchgate.net/publication/387975100_Decoding
| _...
| Dardalus wrote:
| Are you really trying to say that these models aren't going
| to get better from here? You think that the insane progress
| of the last 5 years just stops right here?
| torginus wrote:
| If it helps, if you look at the biology of human vision, you
| find out things like the width of your cone of sharp vision is
| about 2 degrees, or the size of your thumb held out at arms
| length.
|
| Due to this physical limitation, what you 'see' in front of
| you, widely accepted as ground truth reality, cannot possibly
| real, its a hallucination produced by your brain.
|
| Your brain, compared to the sensory richness of reality you
| experience around you, has very limited direct inputs from the
| outside world, it must construct a rich internal model based on
| this.
|
| It's very weird (at least to me), that the boundary between
| reality and assumption (basically educated guessing) is very
| arbitrary, and definitely only exists in our heads.
| remir wrote:
| That's pretty much the basis for the simulation theory. See
| also "My Big TOE" (Theory of Everything) from Tom Campbell.
| swax wrote:
| It's an unsettling feeling as what's more complicated - all the
| atoms and galaxies, trillions of life forms, the unimaginable
| distances of our universe OR a relatively simple world model
| that is our conscious experience and nothing else.
| j_timberlake wrote:
| No it's good, you're ahead of the curve, most people aren't
| there yet.
|
| The next step is to realize that, if life is a cheap
| simulation, not everyone might have... uh... fully simulated
| minds. Player Characters vs NPCs is what gamers would say,
| though it doesn't have to be binary like that, and the term NPC
| has already been ruined by social media rants. (Also, NPC is a
| bad insult because most of the coolest characters in games are
| NPC rivals or bosses or whatnot.)
| NoScopeNinja wrote:
| It sounds cool that Genie 3 can make whole worlds you can
| explore, but I wonder how soon regular people will actually get
| to try it out?
| qingcharles wrote:
| These guys are working on the same thing and have a real demo
| you can play:
|
| https://odyssey.world/introducing-interactive-video
| yoavm wrote:
| Wow, a few years ago, if you've shown me this and Genie 3,
| I'd assume there were at least 10 years of development
| between them. This looks worse than Doom.
| qingcharles wrote:
| The rate of change is insane these days. I remember Sora
| launching and thinking "wow" and within weeks it looked
| like hot garbage.
| modeless wrote:
| 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
|
| > - Physics is still hard and there are obvious failure cases
| when I tried the classical intuitive physics experiments from
| psychology (tower of blocks).
|
| > - Social and multi-agent interactions are tricky to handle.
| 1vs1 combat games do not work
|
| > - Long instruction following and simple combinatorial game
| logic fails (e.g. collect some points / keys etc, go to the door,
| unlock and so on)
|
| > - Action space is limited
|
| > - It is far from being a real game engines and has a long way
| to go but this is a clear glimpse into the future.
|
| Even with these limitations, this is still bonkers. It suggests
| to me that world models may have a bigger part to play in
| robotics and real world AI than I realized. Future robots may
| learn in their dreams...
| kfarr wrote:
| Bitter lesson strikes again!
| nxobject wrote:
| _Especially_ given the goal of a world model using a rasters-
| only frame-by-frame approach. Holy shit.
| ivape wrote:
| _So this just happened from scaling the model_
|
| Unbelievable. How is this not a miracle? So we're just
| stumbling onto breakthroughs?
| silveraxe93 wrote:
| 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.
| ivape wrote:
| 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 ...
| silveraxe93 wrote:
| Lemme start by saying this is objectively amazing. But I
| just really wouldn't call it a breakthrough.
|
| We had one breakthrough a couple of years ago with GPT-3,
| where we found that neural networks / transformers +
| scale does wonders. Everything else has been a smooth
| continuous improvement. Compare today's announcement to
| Genie-2[1] release less than 1 year ago.
|
| The speed is insane, but not surprising if you put in
| context on how fast AI is advancing. Again, nothing
| _new_. Just absurdly fast continuous progress.
|
| [1] -
| https://deepmind.google/discover/blog/genie-2-a-large-
| scale-...
| ducktective wrote:
| Wasn't the model winning gold in IMO result of a
| breakthrough? I doubt an stochastic parrot can solve math
| at IMO level...
| Philpax wrote:
| As far as we know, it was "just" scale on depth (model
| capability) and breadth (multiple agents working at the
| same time).
| bakuninsbart wrote:
| Why wouldn't it? I still have to hear one convincing
| argument how our brain isn't working as a function of
| probable next best actions. When you look at amoebas
| work, and animals that are somewhere between them and us
| in intelligence, and then us, it is a very similar kind
| of progression we see with current LLMs, from almost no
| state of the world, to a pretty solid one.
| pantalaimon wrote:
| Joscha Bach postulates that what we call consciousness
| must be something rather simple, an emergent property
| present in all sufficiently complex biological organisms.
|
| We don't inherit any software, so cognitive function must
| bootstrap itself from it's underlying structure alone.
|
| https://media.ccc.de/v/38c3-self-models-of-loving-grace
| glenstein wrote:
| >We don't inherit any software, so cognitive function
| must bootstrap itself from it's underlying structure
| alone.
|
| Hardware and software, as metaphors applied to biology, I
| think are better understood as a continuum than a binary,
| and if we don't inherit any software (is that true?), we
| at least inherit assembly code.
| pantalaimon wrote:
| > we don't inherit any software (is that true?), we at
| least inherit assembly code
|
| To stay with the metaphor, DNA could be rather understood
| as firmware that runs on the cell. What I mean with
| software is the 'mind' that runs on a collection of
| cells. Things like language, thoughts and ideas.
|
| There is also a second level of software that runs not on
| a single mind alone, but collection of minds, to form
| cliques or a societies. But this is not encoded in genes,
| but in memes.
| glenstein wrote:
| I think we have some notion of a proto-grammar or ability
| to linguistically conceptualize, probably at the level of
| some primordial conceptual units that are more
| fundamental than language, thoughts and ideas in the
| concrete forms we generally understand them to have.
|
| I think it's like Chomsky said, that we don't learn this
| infrastructure for understanding language any more than a
| bird "learns" their feathers. But I might be losing track
| of what you're suggesting is software in the metaphor. I
| think I'm broadly on board with your characterization of
| DNA, the mind and memes generally though.
| airstrike wrote:
| At the most fundamental level, is it even linguistic?
| Would Tarzan speak at all?
| suddenlybananas wrote:
| Children (who aren't alone) will invent languages to
| communicate between each other, see Nicaraguan Sign
| Language.
| quesera wrote:
| The emergent property theory seems logical, but I'm also
| partial to the quantum-tunneling-miasma theory which
| basically posits that there could be something fairly
| complex going on, and we just lack the ability to
| observe/measure it in our current physics. (Although I
| have difficulty coherently separating this theory from
| faith-based beliefs)
| CharlieDigital wrote:
| > We don't inherit any software
|
| I wonder, though. Many animal species just "know" how to
| perform certain complex actions without being taught the
| way humans have to be taught. Building a nest, for
| example.
|
| If you say that this is emergent from the "underlying
| structure alone", doesn't this mean that it would still
| be "inherited" software (though in this case, maybe we
| think of it like punch cards).
| pantalaimon wrote:
| That's interesting indeed - or take spiders building
| nets. So there must be some 'microcode' that does get
| inherited like physical features.
|
| But then you have things like language or societal
| customs that are purely 'software'.
| tim333 wrote:
| We inherit ~2GB of digital data as DNA. Quite how that
| turns into nest building how tos is not yet known but it
| must happen somehow.
| JeremyNT wrote:
| Even as a layman and AI skeptic, _to me_ this entirely
| matches my expectations, and something like this seemed
| like it was basically inevitable as of the first demos of
| video rendering responding to user input (a year ago?
| maybe?).
|
| Not to detract from what has been done here in any way, but
| it all seems entirely consistent with the types of progress
| we have seen.
|
| It's also no surprise to me that it's from Google, who I
| suspect is better situated than any of its AI competitors,
| even if it is sometimes slow to show progress publicly.
| glenstein wrote:
| >It's basically what every major AI lab head is saying from
| the start.
|
| I suppose it depends what you count as "the start". The
| _idea_ of AI as a real research project has been around
| since at least the 1950s. And I 'm not a programmer or
| computer scientist, but I'm a philosophy nerd and I know
| debates about what computers can or can't do started around
| then. One side of the debate was that it awaited new
| conceptual and architectural breakthroughs.
|
| I also think you can look at, say, Ted Talks on the topic,
| with guys like Jeff Hawkins presenting the problem as one
| of searching for conceptual breakthroughs, and I think
| similar ideas of such a search have been at the center of
| Douglas Hofstadter's career.
|
| I think in all those cases, they would have treated "more
| is different" like an absence of nuance, because there was
| supposed to be a puzzle to solve (and in a sense there is,
| and there has been, in terms of vector space and back
| propagation and so on, but it wasn't necessarily clear that
| physics could "pop out" emergently from such a foundation).
| jonas21 wrote:
| When they say "the start", I think they mean the start of
| the LLM era (circa 2017). The story of this era has been
| that scaling to more data and more compute will always
| beat clever algorithms and conceptual breakthroughs (i.e.
| Rich Sutton's Bitter Lesson [1]).
|
| [1]
| http://www.incompleteideas.net/IncIdeas/BitterLesson.html
| spaceman_2020 wrote:
| becoming really, really hard to refute the Simulation Theory
| shreezus wrote:
| There are a lot of "interesting" emergent behaviors that
| happen just a result of scaling.
|
| Kind of like how a single neuron doesn't do much, but connect
| 100 billion of them and well...
| diwank wrote:
| > 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
| neom wrote:
| I'm invested in a startup that is doing something unrelated
| robotics, but they're spending a lot of time in Shenzhen, I
| keep a very close eye on robotics and was talking to their
| CTO about what he is seeing in China, versions of this are
| already being implemented.
| dingnuts wrote:
| what is a robot dream when there is clearly no consciousness?
|
| What's with this insane desire for anthropomorphism? What do
| you even MEAN learn in its dreams? Fine-tuning overnight?
| Just say that!
| gavinray wrote:
| > What's with this insane desire for anthropomorphism?
|
| Devil's advocate: Making the assumption that consciousness
| is uniquely human, and that humans are "special" is just as
| ludicrous.
|
| Whether a computational medium is carbon-based or silicon-
| based seems irrelevant. Call it "carbon-chauvinism".
| bakuninsbart wrote:
| That's not even a devil's advocate, many other animals
| clearly have consciousness, at least if we're not
| solipsistic. There have been many very dangerous
| precedents in medicine where people have been declared
| "brain dead" only to awake and remember.
|
| Since consciousness is closely linked to being a moral
| patient, it is all the more important to err on the side
| of caution when denying qualia to other beings.
| mandolingual wrote:
| "Consciousness" is an overloaded thought killer that
| swerves all conversation into obfuscated semantic
| arguments. One person will be talking about 'internality'
| and self-image (in the testable, mechanical sense that
| you could argue Chain of Thought models already have in a
| petty way) and the other will be grappling with the
| concept of qualia and the ineffable nature of human
| experience.
| olddustytrail wrote:
| Yes, and an object in OOP isn't really a physical object.
| And a string isn't really a thin bit of rope.
|
| No-one cares. It's just terminology.
| Aco- wrote:
| "Do Androids Dream of Electric Sheep?"
| casenmgreen wrote:
| I may be wrong, but this seems to make no sense.
|
| A neural net can produce information outside of its original
| data set, but it is all and directly derived from that
| initial set. There are fundamental information constraints
| here. You cannot use a neural net to itself generate from its
| existing data set wholly new and original full quality
| training data for itself.
|
| You can use a neural net to generate data, and you can train
| a net on that data, but you'll end up with something which is
| no good.
| schmidtleonard wrote:
| We are miles away from the fundamental constraint. We know
| that our current training methodologies are scandalously
| data inefficient compared to human/animal brains.
| Augmenting observations with dreams has long been theorized
| to be (part of) the answer.
| vanviegen wrote:
| > current training methodologies are scandalously data
| inefficient compared to human/animal brains
|
| Are you sure? I've been ingesting boatloads of high
| definition multi-sensory real-time data for quite a few
| decades now, and I hardly remember any of it. Perhaps the
| average quality/diversity of LLM training data has been
| higher, but they sure remember a hell of a lot more of it
| than I ever could.
| neom wrote:
| I might be misunderstanding your comment so sorry if so.
| Robots have sensors and RL is a thing, they can collect
| real world data and then processing and consolidating real
| world experiences during downtime (or in real time),
| running simulations to prepare for scenarios, and updating
| models based on the day's collected data. The way I saw it
| that I thought was impressive was the robot understood the
| scene, but didn't know how the scene would respond to it's
| actions, so it gens videos of the possible scenarios, and
| then picks the best ones and models it's actuation based on
| it's "imagination".
| hnuser123456 wrote:
| It's feasible you could have a personal neural net that
| fine-tunes itself overnight to make less inference mistakes
| in the future.
| exe34 wrote:
| Any idea how humans do it? Where do they get novel
| information from?
| Demplolo wrote:
| I actually think you can.
|
| The LLM has plenty of experts and approaches etc.
|
| Give it tool access let it formulate it's own experiments
| etc.
|
| The only question here is if it becomes a / the singularity
| because of this, gets stuck in some local minimum or
| achieves random perfection and random local minimum
| locations.
| scarmig wrote:
| Humans are dependent on their input data (through lifetime
| learning and, perhaps, information encoded in the brain
| from evolution), and yet they can produce out of
| distribution information. How?
|
| There is an uncountably large number of models that
| perfectly replicate the data they're trained on; some
| generalize out of distribution much better. Something like
| dreaming _might_ be a form of regularization: experimenting
| with simpler structures that perform equally well on
| training data but generalize better (e.g. by discovering
| simple algorithms that reproduce the data equally well as
| pure memorization but require simpler neural circuits than
| the memorizing circuits).
|
| Once you have those better generalizing circuits, you can
| generate data that not only matches the input data in
| quality but potentially exceeds it, if the priors built
| into the learning algorithm match the real world.
| delusional wrote:
| Computers aren't humans.
|
| We have truly reached peak hackernews here.
| stavros wrote:
| Humans produce out-of-distribution data all the time, yet
| if you had a teacher making up facts and teaching them to
| your kids, you would probably complain.
| scarmig wrote:
| Humans also sometimes hallucinate and produce non-
| sequitors.
| suddenlybananas wrote:
| Maybe you do, but people don't "hallucinate". Lying or
| being mistaken is a very different thing.
| tim333 wrote:
| Humans can learn from visualising situations and thinking
| through different scenarios. I don't see why AI / robots
| can't do similar. In fact I think quite a lot of training
| for things like Tesla self driving is done in simulation.
| thecupisblue wrote:
| This is definitely one of the potential issues that might
| happen to embodied agents/robots/bodies trained on the
| "world model". As we are training a model for the real
| world based on a model that simulates the real world, the
| glitches in the world simulator model will be incorporated
| into the training. There will be edge cases due to this
| layered "overtraining", where a robot/agent/body will
| expect Y to happen but X will happen, causing unpredictable
| behaviour.I assume that a generic world agent will be able
| to autocorrect, but this could also lead to dangerous
| issues.
|
| I.e. if the simulation has enough videos of firefighters
| breaking glass where it seems to drop instantaneously and
| in the world sim it always breaks, a firefighter robot
| might get into a problem when confronted with unbreakable
| glass, as it expects it to break as always, leading to a
| loop of trying to shatter the glass instead of performing
| another action.
| casenmgreen wrote:
| 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.
| alphabetting wrote:
| I doubt there was a condition on writing positively. Other
| people who tested have said this won't replace engines.
| https://togelius.blogspot.com/2025/08/genie-3-and-future-
| of-...
| echelon wrote:
| > What I don't think this technology will do is replace
| game engines. I just don't see how you could get the very
| precise and predictable editing you have in a regular game
| engine from anything like the current model. The real
| advantage of game engines is how they allow teams of game
| developers to work together, making small and localized
| changes to a game project.
|
| I've been thinking about this a while and it's obvious to
| me:
|
| Put Minecraft (or something similar) under the hood. You
| just need data structures to encode the world. To enable
| mutation, location, and persistence.
|
| If the model is given additional parameters such as a
| "world mesh", then it can easily persist where things are,
| what color or texture they should be, etc.
|
| That data structure or server can be running independently
| on CPU-bound processes. Genie or whatever "world model" you
| have is just your renderer.
|
| It probably won't happen like this due to monopolistic
| forces, but a nice future might be a future where you could
| hot swap renderers between providers yet still be playing
| the same game as your friends - just with different looks
| and feels. Experiencing the world differently all at the
| same time. (It'll probably be winner take all, sadly, or
| several independent vertical silos.)
|
| If I were Tim Sweeny at Epic Games, I'd immediately drop
| all work on Unreal Engine and start looking into this tech.
| Because this is going to shore them up on both the gaming
| and film fronts.
| K0balt wrote:
| As a renderer, given a POV, lighting conditions, and
| world mesh might be a very, very good system. Sort of a
| tight MCP connection to the world-state.
|
| I think in this context, it could be amazing for game
| creation.
|
| I'd imagine you would provide item descriptions to vibe-
| code objects and behavior scripts, set up some initial
| world state(maps), populated with objects made of objects
| - hierarchically vibe-modeled, make a few renderings to
| give inspirational world-feel and textures, and vibe-tune
| the world until you had the look and feel you want. Then
| once the textures and models and world were finalised, it
| would be used as the rendering context.
|
| I think this is a place that there is enough feedback
| loops and supervision that with decent tools along these
| lines, you could 100x the efficiency of game development.
|
| It would blow up the game industry, but also spawn a
| million independent one or two person studios producing
| some really imaginative niche experiences that could be
| much, much more expansive (like a AAA title) than the
| typical indie-studio product.
| echelon wrote:
| > you could 100x the efficiency of game development.
|
| > It would blow up the game industry, but also spawn a
| million independent one or two person studios producing
| some really imaginative niche experiences that could be
| much, much more expansive (like a AAA title) than the
| typical indie-studio product.
|
| All video games become Minecraft / Roblox / VRChat. You
| don't need AAA studios. People can make and share their
| own games with friends.
|
| Scary realization: YouTube becomes YouGame and Google
| wins the Internet forever.
| keithwhor wrote:
| You've just described what Roblox is already doing.
| echelon wrote:
| Roblox can't beat Google in AI. Roblox has network
| effects with users, but on an old school tech platform
| where users can't magic things into existence.
|
| I've seen Roblox's creative tools, even their GenAI
| tools, but they're bolted on. It's the steam powered
| horse problem.
| phkahler wrote:
| But can we use it to create movies one scene at a time?
| SequoiaHope wrote:
| You don't ask people to speak how you want, you simply only
| invite people who already have a history of speaking how
| you want. This phenomena is explained in detail I. Noam
| Chomsky's work around mass media (eg NY Times doesn't tell
| their editors what to do exactly, but only hire editors who
| already want to say what NY Times wants, or have a certain
| world view). The same can be applied to social media
| reviews. Invite the person who gives glowing reviews all
| the time.
| delusional wrote:
| Do you know where Noam makes that argument? I've been
| trying to figure out where I picked it up years ago. I'd
| like to revisit it to deepen my understanding. It's a
| pretty universal insight.
| kevindamm wrote:
| I think it was in "Manufacturing Consent" by Edward S.
| Herman and Noam Chomsky.
|
| https://en.wikipedia.org/wiki/Manufacturing_Consent#:~:te
| xt=...
|
| https://www.goodreads.com/book/show/12617.Manufacturing_C
| ons...
|
| Though this is often associated with his and Herman's
| "Propaganda Model," Chomsky has also commented that the
| same appears in scholarly literature, despite the overt
| propaganda forces of ownership and advertisement being
| absent:
|
| https://en.wikipedia.org/wiki/Propaganda_model#:~:text=Ch
| oms...
| make3 wrote:
| It wouldn't be surprising if a structured version of this
| with state cached per room for example could be used in a
| game.
|
| & you're basically seeing GPT-3 and saying it will never be
| used in any serious application.. the rate of improvement
| in their model is insane
| echelon wrote:
| Don't put the world state into the model. Use the model
| as a renderer of whatever objects the "engine" throws at
| it.
|
| Use the CPU and RAM for world state, then pass it off to
| the model to render.
|
| Regardless of how this is done, Unreal Engine with all of
| its bells and whistles is toast. That C++ pile of
| engineering won't outdo something this flexible.
| rpcope1 wrote:
| How many watts and how much capital does it take to run
| this model? How many watts and how much capital does it
| take to run unity or unreal? I suspect there's a huge
| discrepancy here, among other things.
| echelon wrote:
| 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 approaching the entire gaming
| industry and they don't even see it coming it's happening so
| fast.
|
| Exciting that building games could become as easy as having
| the idea itself. I'm imagining something like VRChat or
| Roblox or Fortnite, but where new things are simply spoken
| into existence.
|
| It's absolutely terrifying that Google has this much power.
| sureglymop wrote:
| 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?
| echelon wrote:
| I played around with Diamond WM on my 3090 machine. I
| also ran fast SDXL-turbo and LCM models with ControlNets
| paired with a 3D game prototype I threw together. The
| results were very compelling, and I was just one person
| hacking things together.
|
| This is 100% going to happen on-device. It's just a
| matter of time.
| rakete wrote:
| I am convinced as well this will eventually be how we
| render games and simulations.
|
| Maybe just as kind of a DLSS on steroids where the engine
| only renders very simple objects and a world model
| translates these to the actual graphics.
| tim333 wrote:
| I imagine Unreal Engine will start incorporating such
| stuff?
| csomar wrote:
| Also he is ex-Google Mind. Like the worst kind of pick you
| can make when there are dozens of eligible journalists out
| there.
| kkukshtel wrote:
| I similarly am surprised at how fast they are progressing. I
| wrote this piece a few months ago about how I think steering
| world model output is the next realm of AAA gaming:
|
| https://kylekukshtel.com/diffusion-aaa-gamedev-doom-minecraf...
|
| But even when I wrote that I thought things were still a few
| years out. I facetiously said that Rockstar would be nerd-
| sniped on GTA6 by a world model, which sounded crazy a few
| months ago. But seeing the progress already made since GameNGen
| and knowing GTA6 is still a year away... maybe it will actually
| happen.
| throwmeaway222 wrote:
| I'm trying to wrap my head around this since we're still
| seeing text spit out slowly ( I mean slowly as in 1000's of
| tokens a second)
|
| I'm starting to think some of the names behind LLMs/GenAI are
| cover names for aliens and any actual humans involved have
| signed an NDA that comes with millions of dollars and a death
| warrant if disobeyed.
| ewoodrich wrote:
| > Rockstar would be nerd-sniped on GTA6 by a world model
|
| I'm having trouble parsing your meaning here.
|
| GTA isn't really a "drive on the street simulator", is it?
| There is deliberate creative and artistic vision that makes
| the series so enjoyable to play even decades after release,
| despite the graphics quality becoming more dated every year
| by AAA standards.
|
| Are you saying someone would "vibe model" a GTAish clone with
| modern graphics that would overtake the actual GTA6 in
| popularity? That seems extremely unlikely to me.
| everforward wrote:
| Probably depends on how you engage with GTA. "Drive on the
| street simulator" along with arrays of weapons and
| explosions is the majority of my hours in GTA.
|
| I despise the creative and artistic vision of GTA online,
| but I'm clearly in a minority there gauging by how much
| money they've made off it.
| forrestthewoods wrote:
| > this is a clear glimpse into the future.
|
| Not for video games it isn't.
| dlivingston wrote:
| Unless and until state can be stored outside of the model.
|
| I for one would love a video game where you're playing in a
| psychedelic, dream-like fugue.
| throwmeaway222 wrote:
| It's kinda crazy though that a single game session would be
| burning enough natural gas to power 3 cities. Unless that's
| not true
| forrestthewoods wrote:
| It is plausible to run a full simulation the old fashioned
| way and realtime render it with a diffusion model.
|
| It is not currently, or near term, realistic to make a
| video game where a meaningful portion of the simulation is
| part of the model.
|
| There will probably be a few interactive model-first
| experiences. But they'll be popular as short novelties not
| meaningful or long experiences.
|
| A simple question to consider is how would you adjust a set
| of simple tunables in a model-first simulator? For example
| giving the player more health, making enemies deal 2x
| damage, increasing move speed, etc etc. You can not.
| tugn8r wrote:
| But that was always going to be the case?
|
| Reality is not composed of words, syntax, and semantics. A
| human modal is.
|
| Other human modals are sensory only, no language.
|
| So vision learning and energy models that capture the energy to
| achieve a visual, audio, physical robotics behavior are the
| only real goal.
|
| Software is for those who read the manual with their new NES
| game. Where are the words inside us?
|
| Statistical physics of energy to make machine draw the glyphs
| of language not opionated clustering of language that will
| close the keyboard and mouse input loop. We're like replicating
| human work habits. Those are real physical behaviors. Not just
| descriptions in words.
| ojosilva wrote:
| Gaming is certainly a use case, but I think this is primarily
| coming as synthetic data generation for Google's robots
| training in warehouses:
|
| https://www.theguardian.com/technology/2025/aug/05/google-st...
|
| Gemini Robot launch 4 mo ago:
|
| https://news.ycombinator.com/item?id=43344082
| resters wrote:
| consider the hardware DOOM runs on. 720p would only be a true
| test of capability if every bit of possible detail was used.
| Oarch wrote:
| I don't think I've ever seen a presentation that's had me
| question reality multiple times before. My mind is suitably
| blown.
| andhuman wrote:
| Now this could be the killer app VR's been looking for.
| gundmc wrote:
| Interesting! This feels like they're trying to position it as a
| competitor to Nvidia's Omniverse, which is based on the Universal
| Scene Descriptor format as the backbone. I wonder what format
| world objects can be ingested into Genie in - e.g. for the
| manufacturing use cases mentioned.
| dzonga wrote:
| movies are about to become cheap to produce.
|
| good writers will remain scarce though.
|
| maybe we will have personalized movies written entirely through
| A.I
| mclau157 wrote:
| I can see this being incredible for history lessons and history
| school lectures
| MarkusQ wrote:
| 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.)
| scotty79 wrote:
| History is mostly made up. You can be sure mostly about
| general facts. The other 80% are just narratives.
| ecshafer wrote:
| If you read actual history the historians typically go into
| quite a lot of depth on why they think X happened as
| opposed to Y, and what the limitations are on the theories
| and the reasoning. The amount of archaeological and written
| records we have is very important to those facts.
| quesera wrote:
| Also true of the present. :)
| suddenlybananas wrote:
| Not really, since it will hallucinate all sorts of ridiculous
| anachronisms.
| ivape wrote:
| It's going to replace video games.
| mclau157 wrote:
| 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
| okasaki wrote:
| They do both. Nobody played Cyberpunk 2077 for the riveting
| gameplay.
|
| Actually that game felt a lot like these videos, because
| often you would turn around and then look back and the game
| had deleted the NPCs and generated new ones, etc.
| cptroot wrote:
| People played Cyberpunk 2077 because it had oceans of
| engaging story, which _is_ the gameplay.
| klibertp wrote:
| 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.
| lbrito wrote:
| >No most people are testing skills in video games
|
| You must be young. As people get older they (usually) care
| less about that.
| nosignono wrote:
| > Do people play video games to look at pretty scenery?
|
| Yes.
|
| > No most people are testing skills in video games
|
| That's not mutually exclusive with playing for scenery.
|
| Games, like all art, have different communities that enjoy
| them for different reasons. Some people do not want their
| skills tested at all by a game. Some people want the
| maximum skill testing. Some want to experience novel
| fantasy places, some people want to experience real places.
| Some people want to tell complex weaving narratives, some
| people want to optimize logistics.
|
| A game like Flower is absolutely a game about looking at
| pretty scenery and not one about testing skill.
| SirMaster wrote:
| I doubt it. The only video games I play are competitive games
| like DotA 2, Counter Strike 2, Call of Duty, Rainbow 6 Siege,
| etc. I don't really see how this completes or replaced that
| at all.
| ecshafer wrote:
| Why? Sure a virtual walk around the Pantheon in all its glory
| would be _nice_. But would that really improve history lessons?
| It doesn 't help students understand why things happened, and
| what the consequences were and how they have impacted the rest
| of history of the modern world.
| Philpax wrote:
| Inhabiting a foreign cultural context can provide information
| that factual lessons may struggle to convey to the same
| degree. Of course, there's a limit to this - especially with
| regards to historical accuracy - but you are much more likely
| to understand why specific historical decisions were made if
| you are "in the room" where they happened, so to speak.
| motoxpro wrote:
| Engagement is one of the core pieces education and one of the
| hardest things to solve. If you remember back to being a kid,
| reading white papers is not really a thing. Interesting (e.g.
| engaging) teachers and field trips (which not all schools
| have access to) are tools that help kids learn.
|
| At the limit, if you could stay engaged you would be an
| expert in pretty much anything.
|
| "It doesn't help students understand why things happened, and
| what the consequences were and how they have impacted the
| rest of history of the modern world." I would say the
| opposite, let's recreate each step in that historical journey
| so you can see exactly what the concequenses were, exactly
| why they happened and when.
| Workaccount2 wrote:
| I wonder how hard it would be to get VR output?
|
| That's an insane product right there just waiting to happen. Too
| bad Google sleeps so hard on the tech they create.
| SeanaldMcDnld wrote:
| Consistent output and spatial coherence across each eye, maybe
| a couple years? But meeting head tracking accuracy and latency
| requirements, I'd bet decades. There's no way any of this tech
| reduces end to end latency to acceptable levels, without a
| massive change in hardware. We'll probably see someone use
| reprojection techniques in a year or so and claim they've done
| it. But true generated pixels straight to the headset based on
| head tracking, is so so far away.
| kridsdale3 wrote:
| Agree. So I'll make a wild bet of "20 years". And hope for
| the best.
| nosignono wrote:
| You don't have to do it in real time, per se. I imagine a
| world in which the renderer and the world generation are
| decoupled. For example, you could descriptively articulate
| what you wanted to achieve and have it generate a world,
| quietly do some structure from motion (or just generate the
| models and textures), and those those as assets in a game
| engine for the actual moment to moment rendering.
|
| You'd have some "please wait in this lobby space while we
| generate the universe" moments, but those are easy to hide
| with clever design.
| pawelduda wrote:
| It's hard to get an acceptable VR output for today's rendering
| engines still. In the examples provided, the movement seems to
| be slow and somewhat linear, which doesn't translate to head
| movements in VR. VR needs 2 consistent videos with much higher
| resolutions and low latency is a must. The feedback would still
| be very dependent on people's tolerance to all imperfections -
| some would be amazed, others would puke. That's why VR still
| isn't in the spotlight after all the years (I personally find
| it great).
| kridsdale3 wrote:
| I think VR will come at the same time they make multiplayer.
| There needs to be differentiation between the world-state and
| the viewport. Right now, I suspect they're the same.
|
| But once you can get N cameras looking at the same world-state,
| you can make them N players, or a player with 2 eyes.
| fnands wrote:
| Damn, I'm getting Black Mirror vibes from this. Maybe because I
| watched the Eulogy episode last night.
|
| Really great work though, impressive to see.
| ollin wrote:
| This is very encouraging progress, and probably what Demis was
| teasing [1] last month. A few speculations on technical details
| based on staring at the released clips:
|
| 1. You can see fine textures "jump" every 4 frames - which means
| they're most likely using a 4x-temporal-downscaling VAE with at
| least 4-frame interaction latency (unless the VAE is also
| control-conditional). Unfortunately I didn't see any real-time
| footage to confirm the latency (at one point they intercut screen
| recordings with "fingers on keyboard" b-roll? hmm).
|
| 2. There's some 16x16 spatial blocking during fast motion which
| could mean 16x16 spatial downscaling in the VAE. Combined with 1,
| this would mean 24x1280x720/(4x16x16) = 21,600 tokens per second,
| or around 1.3 million tokens per minute.
|
| 3. The first frame of each clip looks a bit sharper and less
| videogamey than later stationary frames, which suggests this is
| could be a combination of text-to-image + image-to-world system
| (where the t2i system is trained on general data but the i2w
| system is finetuned on game data with labeled controls).
| Noticeable in e.g. the dirt/textures in [2]. I still noticed some
| trend towards more contrast/saturation over time, but it's not as
| bad as in other autoregressive video models I've seen.
|
| [1] https://x.com/demishassabis/status/1940248521111961988
|
| [2]
| https://deepmind.google/api/blob/website/media/genie_environ...
| ollin wrote:
| Regarding latency, I found a live video of gameplay here [1]
| and it looks like closer to 1.1s keypress-to-photon latency (33
| frames @ 30fps) based on when the onscreen keys start lighting
| up vs when the camera starts moving. This writeup [2] from
| someone who tried the Genie 3 research preview mentions that
| "while there is some control lag, I was told that this is due
| to the infrastructure used to serve the model rather than the
| model itself" so a lot of this latency may be added by their
| client/server streaming setup.
|
| [1] https://x.com/holynski_/status/1952756737800651144
|
| [2] https://togelius.blogspot.com/2025/08/genie-3-and-future-
| of-...
| rotexo wrote:
| You know that thing in anxiety dreams where you feel very
| uncoordinated and your attempts to manipulate your
| surroundings result in unpredictable consequences? Like you
| try to slam on the brake pedal but your car doesn't slow
| down, or you're trying to get a leash on your dog to lead it
| out of a dangerous situation and you keep failing to hook it
| on the collar? Maybe that's extra latency because your brain
| is trying to render the environment at the same time as it is
| acting.
| svdr wrote:
| Your brain does not need to render any environments, just
| the experience of being in them.
| crossbody wrote:
| I am much more convinced now that the Simulation Argument is
| correct
| sercanov wrote:
| yeah the whole explosion around AI made me lean more to
| simulation theory. it's literally happening in front of our
| eyes and we're a baby civilization
| Fraterkes wrote:
| I'm seeing a lot of variations on this in this thread, but we
| have been able to render photoreal things, and do intricate
| physical simulations, for a long time. This is mostly
| impressive because it is a real-time way to generate and render
| big, intricate worlds.
|
| But if you believe reality is a simulation, why would these
| "efficient" world-generation methods convince you of anything?
| The tech our reality would have to be running on is still
| inconceivable science fiction.
| ivape wrote:
| _but we have been able to render photoreal things, and do
| intricate physical simulations, for a long time._
|
| Not like this we haven't. This is convincing because I can
| have any of you close your eyes and imagine a world where
| pink rabbits hand out parking tickets. We're a neurolink away
| from going from thought > to prompt > to fantasy.
| crossbody wrote:
| Agree with ivape.
|
| To add: our reality does not have to be rendered in it's
| entirety, we'll just have very convincing and unscripted
| first-person view simulations. Only what you look at is
| getting rendered (e.g. tiny structures only get rendered
| when you use microscope).
| Fraterkes wrote:
| I guess I should have clarified: when you talk about
| reality being a simulation, do you mean that we
| collectively live in a simulated universe, or that you
| personally are playing a very realistic vr game?
| alec_irl wrote:
| What is the purpose of this? It seems designed to muddy the
| waters of reality vs. falsehood and put creatives in film/tv out
| of jobs. Real Jurassic Park moment here
| Centigonal wrote:
| They mention some possible applications in the video. Training
| environments for robotics (use sample data to simulate the
| surface of mars or the inside of a nuclear reactor),
| educational worlds for students (like the old Encarta virtual
| tours), and disaster preparedness simulations (e.g. training
| firefighters on an endless variety of burning homes).
|
| Obviously, none of these are super viable given the low
| accuracy and steerability of world models out today, but
| positive applications for this kind of tech do exist.
|
| Also (I'm speculating now instead of restating the video), I
| think pretty soon someone will hook up a real time version of
| this to a voice model, and we will get some kind of interactive
| voice + keyboard (or VR) lucid dream experience.
| sercanov wrote:
| like how? is this mainly realtime inference?
| idencap wrote:
| what a time to be alive
| hnthrow90348765 wrote:
| Think of the pornographic possibilities
|
| /s
| Mouvelie wrote:
| Why even be sarcastic about it ? There is no human invention
| that has not exploded thanks (or because of) pornographic
| possibilities. HD-DVD vs Blueray, Internet...I'd even argue
| that XR is not as big as it could be because it is really
| clamped down to deviant usage !
| lackoftactics wrote:
| 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.
| Uehreka wrote:
| 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 be
| released to the public isn't very interesting to me.
| whywhywhywhy wrote:
| > 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.
| rowanG077 wrote:
| 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.
| xlbuttplug2 wrote:
| What would scare me is if this becomes economically viable enough
| to release to the public, rather than staying an unlimited budget
| type of demo.
| nkotov wrote:
| I wonder how far are we from being able to use this at home as a
| form of entertainment.
| timeattack wrote:
| Advances in generative AI are making me progressively more and
| more depressive.
|
| Creativity is taken from us at exponential rate. And I don't buy
| argument from people who are saying they are excited to live in
| this age. I can get that if that technology stopped at current
| state and remained to be just tools for our creative endeavours,
| but it doesn't seem to be an endgame here. Instead it aims to be
| a complete replacement.
|
| Granted, you can say "you still can play musical
| instruments/paint pictures/etc for yourself", but I don't think
| there was ever a period of time where creative works were just
| created for sake of itself rather for sharing it with others at
| masse.
|
| So what is final state here for us? Return to menial not-yet-
| automated work? And when this would be eventually automated,
| what's left? Plug our brains to personalized autogenerated worlds
| that are tailored to trigger related neuronal circuitry for
| producing ever increasing dopamine levels and finally burn our
| brains out (which is arguably already happening with tiktok-style
| leasure)? And how you are supposed to pay for that, if all work
| is automated? How economics of that is supposed to work?
|
| Looks like a pretty decent explanation of Fermi paradox. No-one
| would know how technology works, there are no easily available
| resources left to make use of simpler tech and planet is littered
| to the point of no return.
|
| How to even find the value in living given all of that?
| delfinom wrote:
| All I know is I am investing into suicide booth startups
| taberiand wrote:
| So that the robots have a leisure activity, or so that humans
| get a quick escape in the face of runaway climate change?
| wahnfrieden wrote:
| Automation only leads to more labor if we allow that employer
| relation to dictate so. Automation affords leisure time (for
| everything besides labor that life has to offer, including
| optional labor-like pursuits) but it's currently unevenly
| distributed who gets to benefit from that
| worldsayshi wrote:
| We keep coming back to the conclusion that we need to turn
| the economy on its head.
|
| With business as usual capital is power and capital is
| increasingly getting centralized.
| fgafford wrote:
| You need to read Brave New World. Already have all that
| figured out.
|
| Work is fundamental part of society and will never be
| eliminated, regardless of its utility/usefulness. The
| cast/class system determines the type of work. The amount
| (time) of work is set as it was discovered additional leisure
| and to reduce it does not improve individuals happiness.
| wahnfrieden wrote:
| Try reading Dawn of Everything
| snickerdoodle12 wrote:
| I see two ways this is going to go:
|
| 1. Universal Basic Income as we're on the way to a post-
| scarcity society. Unlikely to actually happen due to greed.
|
| 2. We take inspiration from the french revolution and then
| return to a simpler time.
| dist-epoch wrote:
| In the french revolution the army and the people had similar
| kind of weapons. And there was no total surveillance to round
| up the leaders.
| snickerdoodle12 wrote:
| Yes, it'd be difficult. I have some faith that once things
| escalate far enough the people wielding the weapons are
| unwilling to murder their countrymen en masse.
|
| Luigi Mangione has shown that all it takes is one person in
| the right time and place to remove some evil from the
| world.
| HeatrayEnjoyer wrote:
| It needs to happen, at minimum, before drones can
| reliably maintain themselves and kill dissidents in the
| street. At that point even if the human police and
| soldiers become disloyal it'll be too late; a society of
| two types of people, the one guy with access to issue
| prompts, and everyone else.
| holoduke wrote:
| If bio engineering takes off for real we will integrate our
| consciousness in our artificial digital ecosystem.
| maerF0x0 wrote:
| > Unlikely to actually happen due to greed.
|
| Greed makes no sense in a truly post scarcity society. There
| is no scarcity from which to take in a zero sum way from
| another.
|
| Status is the real issue. Humans use status to select
| sexually, and the display is both competitive and
| comparative. It doesnt matter absolutely how many pants you
| have, only that you have more and better than your
| competition.
|
| I actually think this thing is baked into our DNA and until
| sex itself is saturated (if there is such a thing), or DNA is
| altered, we will continue to have a however subtle form of
| competition undergirding all interactions.
| tim333 wrote:
| I think UBI is likely to happen because of greed - people
| like free stuff and will vote for it is it's real. The
| trouble with the pitch:
|
| >Vote for me and we'll hand free money to everyone and the
| robots will do the work
|
| at the moment is the robots doing the work don't exist.
| Things will change when they do.
| dist-epoch wrote:
| > Looks like a pretty decent explanation of Fermi paradox.
|
| It's not. We will be replaced, but the AI will carry on.
| dingnuts wrote:
| this is a religious opinion at this state of technological
| development lol
|
| a lot of these comments border on cult thinking. it's a
| fucking text to 3D image model, not R Daneel Olivaw, calm
| down
| myrmidon wrote:
| Do you _honestly_ believe that human minds won 't be
| overtaken within the century?
|
| I'll concede that it might take even longer to get _full_
| artificial human capabilities (robust, selfrepairing,
| selfreplicating, adaptable), but the writing is on the
| wall.
|
| Even in the very best case that I see (non-malicious AI
| with a soft practical ceiling not too far beyond human
| capabilities) poses giant challenges for our whole society,
| just in ressource allocation alone (because people, as
| workers, become practically worthless, undermining our
| whole system completely).
| hooverd wrote:
| Eh, might as well kill yourself now then.
| skybrian wrote:
| We already live in a world where a vast library of songs by
| musicians who play much better than you are readily available
| on YouTube and Spotify. This seems like more of the same?
| podgietaru wrote:
| I like living in a world where I know that people who have
| spent actually time on nurturing a talent get rewarded for
| doing so, even if that talent is not something I will ever be
| good at.
|
| I don't want to live in a world where these things are
| generated cheaply and easily for the profit of a very select
| few group of people.
|
| I know the world doesn't work like I described in the top
| paragraph. But it's a lot closer to it than the bottom.
| wolttam wrote:
| It's hard to see how there will be room for profit as this
| all advances
|
| There will be two classes of media:
|
| - Generated, consumed en-masse by uncreative, uninspired
| individuals looking for cheap thrill
|
| - Human created, consumed by discerning individuals seeking
| out real human talent and expression. Valuing it based
| merely on the knowledge that a biological brain produced
| (or helped produce) it.
|
| I tend to suspect that the latter will grow in value, not
| diminish, as time progresses
| skeezyboy wrote:
| https://en.wikipedia.org/wiki/Pause_Giant_AI_Experiments:
| _An...
|
| people said the world could literally end if we train
| anything bigger than chatgpt4... I would take these
| projections with a handful of salt
| pizzathyme wrote:
| This is an incredible artifact.
| skybrian wrote:
| It seems to me that you're describing Hollywood?
| Admittedly, there are big budget productions, but
| Hollywood is all about fakery, it's cheap for the
| consumer, and there's a lot of audience-pleasing dreck.
|
| There's no bright line between computer and human-created
| video - computer tools are used everywhere.
| bko wrote:
| > I like living in a world where I know that people who
| have spent actually time on nurturing a talent get rewarded
| for doing so, even if that talent is not something I will
| ever be good at.
|
| Rewarded how? 99.99% of people who do things like sports or
| artistic like writing never get "rewarded for doing so", at
| least in the way I imagine you mean the phrase. The reward
| is usually the experience itself. When someone picks up a
| ball or an instrument, they don't do so for some material
| reward.
|
| Why should anyone be rewarded materially for something like
| this? Why are you so hung up on the <0.001% that can
| actually make some money now having to enjoy the activity
| more as a hobby than a profession.
| podgietaru wrote:
| 99.99% of people, really? You think there isn't a huge
| swath of the economy that are made up of professional
| writers, artists, musicians, graphic designers, and all
| the other creative professionals that the producers of
| these models aim to replicate the skills of?
|
| Why am I so "hung up" on the livelihood of these people?
|
| Doing art is a Hobby is a good in and of itself. I did
| not say otherwise. But when I see a movie, when I listen
| to a song, I want to appreciate the integrity and talent
| of the people that wrote them. I want them to get paid
| for that enjoyment. I don't think that's bizarre.
| holoduke wrote:
| You can still makes movies , music etc. But now with
| better tools. Just accept the new reality and try to play
| this new level. The old won't come back. Its a waste of
| time to complain and feel frustrated. There are plenty of
| opportunities to express your creativity.
| fantasizr wrote:
| I could see that theater and live music (especially
| performed on acoustic instruments) become hyper popular
| because it'll be the only talent worth paying to see when
| everything else is 'cheaply' made.
| pessimizer wrote:
| > I like living in a world where I know that people who
| have spent actually time on nurturing a talent get rewarded
| for doing so, even if that talent is not something I will
| ever be good at.
|
| That world has only existed for the last hundred or so
| years, and the talent is usually brutally exploited by
| people whose main talent is parasitism. Only a tiny
| percentage of people who sell creative works can make a
| living out of it; the living to be made is in buying their
| works at a premium, bundling them, and reselling them,
| while offloading almost all of the risk to the creative as
| an "advance."
|
| Then you're left in a situation where both the buyer of art
| and the creator of art are desperate to pander to the
| largest audience possible because everybody is leveraged.
| It's a dogshit world that creates dogshit art.
| Saline9515 wrote:
| It still requires work, dedication and produces authenticity.
| A world where AI can produce music instantly commoditizes it.
| skybrian wrote:
| Music is already a commodity. You can just buy some
| anonymous background music to play in your restaurant. No
| effort required.
| Saline9515 wrote:
| Yes but I don't want to hear some anonymous background
| music.
|
| A better example would be Spotify replacing artist-made
| music recommandations with low-quality alternatives, to
| reduce what it pays to artists. Everyone except Spotify
| loses in this scenario.
| rohit89 wrote:
| In the future, everyone will have their own ai agents
| capable of generating music to their own tastes. They
| won't be using spotify.
|
| The future with AI is not going to be our current world
| with some parts replaced by AI. It will be a whole new
| way of life.
| roywiggins wrote:
| My prediction is that personal generation is going to be
| niche forever, for purely social reasons. The demand for
| fandoms and fan communities seems to be essentially
| unlimited. Big artists have big fandoms, tiny ones have
| tiny fandoms, but none of that works with personalized
| generations.
| HeatrayEnjoyer wrote:
| Communities around fictional universes are already
| fractured and shrinking in member size because of the
| sheer number of algorithmically targeted universes
| available.
|
| Water cooler talk about what happened this week in
| M.A.S.H. or Friends is extinct.
|
| Worse, in the long run even community may be synthesized.
| If a friend is meat or if they're silicon (or even carbon
| fiber!), does it matter if you can't tell the difference?
| It might to pre-modern boomers like me and you.
| whamlastxmas wrote:
| I mean you can just listen to human made music if that's an
| important part of the experience for you. I doubt humans
| are going to stop anytime soon
| danelski wrote:
| But availability of _new_ works shall change once the
| floor of how popular you need to be to survive off of art
| will change and it will, since not everyone will care.
| Taylor Swift will be fine either way, but it 's not about
| her.
| Saline9515 wrote:
| If you flood the space with AI-made music costing a few
| cents to create, human artists will have a much harder
| time to survive professionally.
| svantana wrote:
| You're quite the pessimist. I think the arts would do well to
| look at sports as a glimpse of their future. Machines are
| faster and stronger than people, but that hasn't had any impact
| on sports at all. Nobody's tuning in to the robot olympics.
| rishabhparikh wrote:
| Agreed that no one wants to watch shotput when the ball is
| launched out of a cannon, but people might be interested when
| the robots competing are anthropomorphs.
|
| For example, robot boxing:
| https://www.youtube.com/watch?v=rdkwjs_g83w
| AstroBen wrote:
| Who did the visual effects of the last movie you watched?
|
| Most commercial artists are very much unknown, in the
| background. This is a different situation from sport
| likium wrote:
| A better analogy would be musicians. Recorded music is around
| but some musicians still make a living, mostly off live
| concerts and merch.
|
| But it might also go the way of pottery, glass-making and
| weaving. They're still around but extremely niche.
| Etheryte wrote:
| > I don't think there was ever a period of time where creative
| works were just created for sake of itself rather for sharing
| it with others at masse.
|
| Numerous famous writers, painters, artists, etc counter this
| idea, Kafka being a notable example, whose significant works
| only came to light after his passing and against his will. This
| doesn't take away from the rest of your discussion point, but
| art always has and always will also exist solely for its own
| sake.
| zyruh wrote:
| I agree. While I love AI, advancements must be responsible. We
| are made to be social beings and giving more and more of lives
| over to AI takes us away from the fundamental need to draw
| creativity, inspiration, and connection from other people.
| Thoughts?
| quantumHazer wrote:
| Machine learning as it is needs human data and input to
| progress further.
|
| Synthetic data can be useful until a certain point, but you
| can't expect to have a better model on synthetic data alone
| indefinitely.
|
| The moat of GDM here is YouTube. That have a bazillion of
| gameplay and whatever videos. But here it is.
|
| The downside I can see is that most people will stop to publish
| content online for free since this companies have absolutely no
| respect whatsoever for the humans that created the data they
| use.
| dawnerd wrote:
| Charging for content means nothing. Meta was pirating media
| and training against that and I suspect everyone else is too
| but hasn't been caught yet.
| dbspin wrote:
| I've never understood this argument... The real world is an
| unbounded training set that its cheap to observe with readily
| available sensors that have existed for almost a century.
| yomismoaqui wrote:
| The question is, why are you doing art?
|
| - Because you enjoy it
|
| - Because you get pats in the back from people you share it
| with
|
| - Because you want to earn money from it
|
| The 1st one will continue to be true in this dystopian AI art
| future, the other not so much.
|
| And sincerely I find that kind of human art, the one that comes
| from a pure inner force, the more interesting one.
|
| EDIT: list formatting
| sunsunsunsun wrote:
| You seem to forget that most artists enjoy it but due to the
| structure of our society are forced to either give it up for
| most of their waking life to earn money or attempt to market
| their art to the masses to make money. This AI stuff only
| makes it harder for artists to make any kind of living off of
| their work.
| MetaWhirledPeas wrote:
| While there are plenty of cases where good artists make
| most of their money from the art, there are plenty of other
| cases where good artists have a 'real job' on the side.
| jjrh wrote:
| Ideally AI makes it so you don't have to work and can
| pursue whatever interests.
| assword wrote:
| > The 1st one will continue to be true in this dystopian AI
| art future, the other not so much.
|
| No it won't, you'll be too busy trying to survive off of what
| pittance is left for you to have any time to waste on leisure
| activities.
| flyinglizard wrote:
| I share your feelings. Also couple that with a populist and
| cynical political climate that can't create effective
| regulations even if it wanted, and that by its very appetite
| for scale AI thrives at the hands of the few that can feed it
| and you get something quite bleak.
|
| My only hope is that we could have created 100k nukes of
| monstrous yields but collectively decided not to. We instead
| created 10k smaller ones. We could have destroyed ourselves
| long ago but managed to avoid it.
| roboboffin wrote:
| 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 need infinite computation.
| rowanG077 wrote:
| 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.
| roboboffin wrote:
| 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.
| seanw444 wrote:
| It doesn't need to generate _everything_. It only needs to be
| marginally better or more efficient than a human for it to
| start generating _everything humans need when needed_.
|
| Edit: left the page open for a while before responding, and
| the other person responded with basically the same thing
| within that time.
| roboboffin wrote:
| If human need drives the creative process, then there will
| always be a human in the loop. Instead, each human becomes
| the "random seed" that initialises the process based on
| their own unique make-up. This is only different from how
| things work now, in that humans are also creating the
| artefact.
|
| Similar to how synths meant we no longer need to play an
| instruments by plucking strings, it hasn't affected the
| higher level creativity of creating music, only expanded
| it.
| pixelesque wrote:
| What's interesting to me along these lines is I assume most of
| the companies funding the research are targeting the "creative"
| media in terms of image generation, music generation, avatars,
| speach, etc.
|
| I can understand it's very interesting from a researcher's
| point-of-view (I'm a software dev who's worked adjacent to some
| ML researchers doing pipeline stuff to integrate models into
| software), but at the same time: Where are the robots to do
| menial work like clean toilets, kitchens, homes, etc?
|
| I assume the funding isn't there? Or maybe it's much less
| exciting to research diffusion networks for image generation
| that working out algorithms for the best way to clean toilets
| :)
| dingnuts wrote:
| robotics is difficult and since transformers are just next
| word predictors they can't actually help us design those
| robots :)
|
| also the billionaires have help so they don't give a shit if
| the menial stuff is automated or not. throw in a little
| misogyny by and large too; I saw a LinkedIn Lunatic in the
| wild (some C-level) saying laundry is already automated
| because laundry machines exist
|
| fucking.. tell me you don't ever do the laundry without
| telling me. That guy's poor wife.
| einarfd wrote:
| There are companies out there working on those problems as
| well. How the funding climate for them are. I don't know. But
| the market for smart robots, should be gigantic. So there
| must be some. Keep in mind that what is easy, and hard for a
| human, which is the result of billions of years of evolution.
| Isn't necessary the same things that are hard or easy for our
| technologies.
| cherry_tree wrote:
| There was a recent talk about using vision language models to
| train robots to do household tasks:
| https://youtu.be/a8-QsBHoH94
|
| I wonder how advanced world models like genie 3 would change
| the approach if it all.
| lentil_soup wrote:
| Or replacing CEOs, investors, bankers? I would have thought
| those would be easier to replace than creating robots to
| clean or replacing artists, or even developers. Maybe I am
| wrong?
| SirHumphrey wrote:
| All these jobs are more who you know not what you know. The
| social network of these people is often an integral part of
| the work, so they are in a sense much safer than
| programmers, accountants and artists.
| myahio wrote:
| What specific form of creative media is this supposed to
| replace though? I feel like its just going to create a brand
| new, exciting category of entertainment. I personally fail to
| see any bad precedent within this announcement.
| skeezyboy wrote:
| a reminder, most of the world do manual labour in exchange for
| money. an LLM cant help with that and never will
| rowanG077 wrote:
| There is huge progress in robotics. Which includes fruits
| from the LLM hype. A lot of manual labor will be able to be
| done by humanoid robots.
| Wissenschafter wrote:
| "Granted, you can say "you still can play musical
| instruments/paint pictures/etc for yourself", but I don't think
| there was ever a period of time where creative works were just
| created for sake of itself rather for sharing it with others at
| masse."
|
| I sit and play guitar by myself all the time, I play for nobody
| but myself, and I enjoy it a lot. Your argument is absurd.
| furyofantares wrote:
| > but I don't think there was ever a period of time where
| creative works were just created for sake of itself rather for
| sharing it with others at masse
|
| Kids do it all the time.
|
| > So what is final state here for us?
|
| Something I haven't seen discussed too much is taste - human
| tastes change based on what has come before. What we will care
| about tomorrow is not what we care about today.
|
| It seems plausible to me that generative AI could get higher
| and higher quality without really touching how human tastes
| changes. That would leave a lot of room for human creativity
| IMO - we have shared experience in a changing world that seems
| very hard to capture with data.
| mbowcut2 wrote:
| It's not a new problem (for individuals), though perhaps at an
| unprecedented scale (so, maybe a new problem for civilization).
| I'm sure there were black smiths that felt they had lost their
| meaning when they were replaced by industrial manufacturing.
| Kiro wrote:
| I don't understand your argument at all. I've made hundreds of
| songs in my life that I haven't shared with anyone and so have
| all other musicians I know. The act of creating is separate
| from finding or having an audience. In fact, I would say that
| the complete opposite of what you say is true.
|
| And even so, music production has been a constant evolution of
| replacing prior technologies and making it easier to get into.
| It used to be gatekept by expensive hardware.
| p4coder wrote:
| Today physical world is largely mechanized, we rarely walk, run
| lift heavy things for survival. So we grow fat and weak unless
| we exercise. Tomorrow vast majority of us will never think,
| create, investigate for earning a living. So we will get dumb
| and dumber over time. A small minority of us will keep
| polishing their intellect but will never be smarter than
| machines just like the best athletes of today can't outrun
| machines.
| pizzathyme wrote:
| This is surprisingly a great analogy because millions of
| people still run every week for their own benefit (physical
| and mental health, social connection, etc).
|
| I wonder if mental exercises will move to the same category?
| Not necessarily a way to earn money, but something everybody
| does as a way of flourishing as a human.
| psbp wrote:
| The process of thinking and exploring ideas is inherently
| enriching.
|
| Nothing can take away your ability to have incredible
| experiences, except if the robots kill us all.
| thinkingtoilet wrote:
| I don't know... There are plenty of otherwise capable
| adults who just get home from work and watch TV. They
| either never, or extremely rarely, indulge in hobbies, go
| see a concert, or even go out to meet others. Not that TV
| can't be art and challenge us but lets be honest, 99% of
| it is not that.
| psbp wrote:
| I have been this person. I can say that it's not a time
| of my life I look back on fondly.
| dartharva wrote:
| I look at it as the pendulum swinging back.
|
| For too long has humanity been collectively submerged into this
| hyper-consumption of the arts. We, our parents and our
| grandparents have been getting bombarded by some or the other
| form of artificial dopamine sweets - from videos to reels to
| xeets to "news" to ads to tunes to mainstream media - every
| second of the day, every single day. The kind of media
| consumption we have every day is something our forefathers
| would have been overwhelmed by within an hour. It is not
| natural.
|
| This complete cheapening of the arts is finally giving us a
| chance to shed off this load for good.
| michalf6 wrote:
| Nick Land kind of took this line of reasoning to its ultimate
| conclusion, I recommend giving his ideas a read even if they
| sound repulsive.
|
| "Nothing human makes it out of the near-future."
| pizzathyme wrote:
| I've tried and failed to find a good starting point for his
| ideas. Do you recommend any?
| michalf6 wrote:
| This is pretty decent, at least the first half:
| https://www.youtube.com/watch?v=lrOVKHg_PJQ
| lbrito wrote:
| >And how you are supposed to pay for that, if all work is
| automated? How economics of that is supposed to work?
|
| With UBI, probably. With a central government formed by our
| robot overlords. But why even pay us at that point?
| curious_cat_163 wrote:
| > So what is final state here for us? Return to menial not-yet-
| automated work? And when this would be eventually automated,
| what's left? Plug our brains to personalized autogenerated
| worlds that are tailored to trigger related neuronal circuitry
| for producing ever increasing dopamine levels and finally burn
| our brains out (which is arguably already happening with
| tiktok-style leasure)? And how you are supposed to pay for
| that, if all work is automated? How economics of that is
| supposed to work?
|
| Wow. What a picture! Here's an optimistic take, fwiw: Whenever
| we have had a paradigm shift in our ability to process
| information, we have grappled with it by shifting to higher-
| level tasks.
|
| We tend to "invent" new work as we grapple with the technology.
| The job of a UX designer did not exist in 1970s (at least not
| as a separate category employing 1000s of people; now I want to
| be careful this is HN, so there might be someone on here who
| was doing that in the 70s!).
|
| And there is capitalism -- if everyone has access to the best-
| in-class model, then no one has true edge in a competition.
| That is not a state that capitalism likes. The economics _will_
| ultimately kick in. We just need this recent S-curve to settle
| for a bit.
| rohit89 wrote:
| > So what is final state here for us?
|
| I think we have a long way to go yet. Humanity is still in the
| early stages of its tech tree with so many unknown and unsolved
| problems. If ASI does happen and solves literally everything,
| we will be in a position that is completely alien to what we
| have right now.
|
| > How to even find the value in living given all of that?
|
| I feel like a lot of AI angst comes from people who place their
| self-worth and value on external validation. There is value in
| simply existing and doing what you want to do even if nobody
| else wants it.
| tekacs wrote:
| We can dream bigger: when music, images, video and 3d assets
| are far easier then treat them as primitives.
|
| We can use these to create entire virtual worlds, games,
| software that incorporates these, and to incorporate creativity
| and media into infinitely more situations in real life.
|
| We can create massive installations that are not a single image
| but an endless video with endless music, and then our hand
| turns to stabilizing and styling and aestheticizing those
| exactly in line with our (the artist's) preferences.
|
| Romanticizing the idea that picking at a guitar is somehow
| 'more creative' than using a DAW to create incredibly complex
| and layered and beautiful music is the same thing that's
| happening here, even if the primitives seem 'scarier' and
| 'bigger'.
|
| Plus, there are many situations in life that would be made
| infinitely more human by the introduction of our collective
| work in designing our aesthetic and putting it into the world,
| and encoding it into models. Installations and physical spaces
| can absolutely be more beautiful if we can produce more, taking
| the aesthetic(s) that we've built so far and making them
| dynamic to spaces.
|
| Also for learning: as a young person learning to draw and sing
| and play music and so many other things, I would have
| tremendously appreciated the ability to generate and follow
| subtle, personalized generation - to take a photo of a scene in
| front of me and have the AI first sketch it loosely so that I
| can copy it, then escalate and escalate until I can do
| something bigger.
| stillpointlab wrote:
| > I don't buy argument from people who are saying they are
| excited to live in this age
|
| What argument is required for excitement? Excitement is a
| feeling not a rational act. It comes from optimism and
| imagination. There is no argument for optimism. There is often
| little reason in imagination.
|
| > How to even find the value in living given all of that?
|
| You might have heard of the Bhagavad Gita, a 2000+ year old
| spiritual text. It details a conversation between a warrior
| prince and a manifestation of God. The warrior prince is facing
| a very difficult battle and he is having doubts justifying any
| action in the face of the decisions he has to make. He is
| begging this manifestation of God to give him good reasons to
| act, good reasons not just to throw his weapons down, give away
| all his possessions and sit in a cave somewhere.
|
| There are no definite answers in the text, just meditations on
| the question. Why should we act when the result is ultimately
| pointless, we will all die, people will forget you, situations
| will be resolved with or without you, etc.
|
| This isn't some new question that LLMs are forcing us to
| confront. LLMs are just providing us a new reason to ask the
| same age-old questions we have been facing for as long as
| writing has existed.
| HocusLocus wrote:
| Genie 3 not only groks the Bhagavad Gita, it can generate
| "Blue & Elephant People: The Movie".
| vessenes wrote:
| Don't be mad bro. Seriously. Every single person working on a
| film has creative input, not just someone hand painting a
| backdrop. You have an immense number of tools available to be
| creative with now. This is a great thing!
| pessimizer wrote:
| > I don't think there was ever a period of time where creative
| works were just created for sake of itself rather for sharing
| it with others at masse.
|
| You don't think there was ever a time without a mass media
| culture? Plenty of people have furniture older than mass media
| culture. Even 20 years ago people could manage to be creative
| for a tiny audience of what were possibly other people doing
| creative things. It's only the zoomers who have never lived in
| a world where you never thought to consider how you could sell
| the song you were writing in your bedroom to the Chinese
| market.
|
| It used to be that music didn't come on piano rolls, records,
| tapes, CDs or files. It used to be that your daughter would
| play music on the piano in the living room for the entire
| family. Even if it was music that wouldn't really sell, and
| wasn't perfectly played, people somehow managed to enjoy it. It
| was not a situation that AI could destroy. If anything, AI
| could assist.
| stronglikedan wrote:
| > How to even find the value in living given all of that?
|
| If your value in living is in any way affected by AI, ever,
| then, well, let's just say I would never choose that for
| myself. Good luck.
| rikroots wrote:
| > Granted, you can say "you still can play musical
| instruments/paint pictures/etc for yourself", but I don't think
| there was ever a period of time where creative works were just
| created for sake of itself rather for sharing it with others at
| masse.
|
| There's a whole host of "art" that has been created by people -
| sometimes for themselves, sometimes for a select few friends -
| which had little purpose beyond that creation[1]. Some people
| create art because they simply _have_ to create art - for
| pleasure, for therapy, for whatever[2]. For many, the act of
| creation was far more important than the act of
| distribution[3].
|
| For me, my obsession is constructing worlds, maps, societies
| and languages that will almost certainly die with me. And
| that's fine. When I feel the compulsion, I'll work on my
| constructions for a while, until the compulsion passes - just
| as I have done (on and off) for the past 50 years. If the world
| really needs to know about me, then it can learn more than it
| probably wants to know through my poetry.
|
| [1] - Emily Dickinson is an obvious example:
| https://en.wikipedia.org/wiki/Emily_Dickinson
|
| [2] - Coral Castle, Florida:
| https://en.wikipedia.org/wiki/Coral_Castle
|
| [3] - Federico Garcia Lorca almost certainly didn't write his
| Sonetos del amor oscuro for publication - he just needed to
| write them:
| https://es.wikisource.org/wiki/Sonetos_del_amor_oscuro
| neom wrote:
| In my opinion, what humans need, crave, chase, is novelty. Just
| look at how phobic we are of boredom. I believe creativity is
| part of the chasing of novelty, or the allaying of boredom. I
| studied film making in my 20s when the shift to digital
| happened, and I was the first cohort through the first digital
| film program in my country. When new ways to create become
| available, the people who struggle are often the ones who are
| unable to adapt their mindset to the new creative mediums and
| don't think "what is new to be done here". Many people when I
| graduated thought I was totally nuts of not owning or using an
| analogue camera, so many reasons, oh you can't trust the CF
| cards, oh the HDR will never get there, oh the shutter is too
| slow. This is just a version of that imo. I think AI and
| robotics are going all the way to the end, I'm trying to adjust
| my old man brain to the new world the best I can, feel blessed
| to have been part of a version of this before.
| tomrod wrote:
| Branding and differentiation.
|
| People still value Amish furniture or woodworking despite Ikea
| existing. I love that if I want a cheap chair made of cardboard
| and glue that I can find something to satisfy that need; but I
| still buy nice furniture when I can.
|
| AI creations are analogous. I've seen some cool AI stuff, but
| it definitely doesn't replace the real "organic" art one finds.
| HeatrayEnjoyer wrote:
| What if it's not cardboard and glue but woodworking of ultra-
| master quality?
|
| These fears aren't realized if AI never achieves superhuman
| performance, but what if they do?
| mindwok wrote:
| Man, same here. I was initially a massive AI evangelist up
| until about a year ago, now I just feel sad for some reason -
| and I don't want to feel sad, I'm a technologist at heart and
| I've been thrilled by every advance since I was born. I feel
| like some sad old boomer yelling at clouds and I'm not even 30
| yet.
|
| My only hope is this: I think the depression is telling us
| something real, we are collectively mourning what we see as the
| loss of our humanity and our meaning. We are resilient
| creatures though, and hopefully just like the ozone layer, junk
| food, and even the increasing rejections of social media and
| screen time, we will navigate it and reclaim what's important
| to us. It might take some pain first though.
| lubujackson wrote:
| Be comforted by the fact that no matter how good the AI gets,
| people crave human connection. Just like AI can generate music
| there is an uncanny valley effect where you quickly deduce
| there's no true humanity behind any of it, and ultimately
| undervalue it. At best you can have something like Minecraft or
| Dwarf Fortress where the generated worlds CAN be inspiring to a
| degree, but that is because the rules around generation are
| incredibly intricate and, ultimately, human.
|
| Yes, AI can make music that sounds decent and lyrics that rhyme
| and can even be clever. But listen to a couple songs and your
| brain quickly spots the patterns. Maybe AI gets there some day,
| but the uncanny valley seems to be quite a chasm - and anything
| that approaches the other side seems to do so by piling lots of
| human intention along the way.
| imiric wrote:
| I can relate. It's exhausting.
|
| The main challenge over the next decade as all our media
| channels are flooded with generated media will become curation.
| We desperately need ways to filter human-created content from
| generated content. Not just for the sake of preserving art, but
| for avoiding societal collapse from disinformation, which is a
| much more direct and closer threat. Hell, we've been living
| with the consequences of mass disinformation for the past
| decade, but automated and much more believable campaigns
| flooding our communication platforms will drastically lower the
| signal-to-noise ratio. We're currently unable to even imagine
| the consequences of that, and are far from being prepared for
| it.
|
| This tech needs strict regulation on a global scale. Anyone
| against this is either personally invested in it, or is
| ignorant of its dangers.
| rolfus wrote:
| I'm one of those excited people! We haven't lost anything with
| this new technology, only gained.
|
| The way I see it, most people aren't creative. And the people
| who are creatives are mostly creating for the love of it. Most
| books that are published are read exclusively by the friends
| and family of the author. Most musicians, most stand-up
| comedians, most artist get to show off their works for small
| groups of people and make no money doing so. But they do it
| anyway. I draw terrible portraits, make little inventions and
| sometimes I build something for the home, knowing full well
| that I do these things for my own enjoyment and whatever ego
| boost I get from showing these things off to people I know.
|
| I'm doing a marathon later and I've been working my ass off for
| the prospect of crossing the finishing line as number four
| thousand and something, and I'll do it again next year.
| j_timberlake wrote:
| I don't know how on Earth people can think like this. Most
| people can find "value" in a slice of pizza. It doesn't even
| have to be a good pizza.
|
| Or kittens and puppies. Do you think there won't be kittens and
| puppies?
|
| And that's putting aside all the obvious space-exploration
| stuff that will probably be more interesting than anything the
| previous 100 billion humans ever saw.
| tim333 wrote:
| >So what is final state here for us?
|
| The merge. (https://blog.samaltman.com/the-merge)
|
| I'm quite enthusiastic. I've always thought mortality sucks.
| HardCodedBias wrote:
| "Creativity is taken from us at exponential rate"
|
| Nothing is being taken away.
| seydor wrote:
| Would progress in these be faster if they created 3d meshes and
| animations instead of full frame videos?
| zbrw wrote:
| I believe that the corpus of video data to train on with video
| far exceeds that of 3D data. It's also much cheaper to produce
| video data. So I'd expect that this is probably the quickest
| way forward from a current world state perspective.
|
| Additionally, video seems like a pretty forward output shape to
| me - 2D image with a time component. If we were talking 3D
| assets and animations I wouldn't even know where to start with
| modeling that as input data for training. That seems really
| hard to model as a fixed input size problem to me.
|
| If there was comparable 3D data available for training, I'd
| guess that we'd see different issues with different approaches.
|
| A couple of examples that I could think of quickly: Using these
| to build games, might be easier if we could interact with the
| underlying "assets". Getting photorealistic results with
| intricate detail (e.g. hair, vegetation) might be easier with
| video based solutions.
| nosignono wrote:
| If the fidelity of the video is high enough, you could use
| SFM to build point clouds from the generated video frames and
| essentially do photogrammatry on the assets from a genie
| video.
| teamonkey wrote:
| I always wonder why they're not chasing more pragmatic and
| lower-hanging fruit first.
|
| There's absolutely no reason that a game needs to be generated
| frame-by-frame like this. It seems like a deeply unserious
| approach to making games.
|
| (My feeling is that it must be easier to train this way.)
| seydor wrote:
| well actually image output is fixed and there s lots of
| training data. Neural networks can learn anything in their
| latent space so there is no need to impose 3D rendering
| constraints, and it s not evident that it's less efficient
| (for the model).
|
| 3D model rendering would be useful however for interfacing
| with robots.
| teamonkey wrote:
| You often view 3D games on a 2D screen. That doesn't mean
| that a game is natively 2D and the 3D world is an
| inconvenient step that can be bypassed. Actually the
| opposite, the 2D representation on screen is just a
| projection.
|
| In VR, for example, the same 3D scene will be rendered
| twice, once for each eye, from two viewpoints 10-15cm
| apart.
|
| If you don't have an internal 3D representation of the
| world, the AI would need to generate _exactly_ the same
| scene from a very slightly different perspective for each
| eye, without any discrepancies or artefacts.
|
| And that's not even discussing physics, collisions or any
| form of consistent world logic that happens off-screen. Or
| multiplayer!
| kouteiheika wrote:
| > To that end, we're exploring how we can make Genie 3 available
| to additional testers in the future.
|
| No need to explore; I can tell you how. Release the weights to
| the general public so that everyone can play with it and non-
| Google researchers can build their work upon it.
|
| Of course this isn't going to happen because "safety". Even
| telling us how many parameters this model has is "unsafe".
| Dlanv wrote:
| Modern AI wouldn't exist without Google's contributions. Yet
| they're a for-profit company. I'm ok with them keeping some
| things closed source every now and then.
| Davidzheng wrote:
| This is one of the most insane feats of AI I have ever seen to be
| honest.
| obayesshelton wrote:
| Strap on a headset and we are one step closer to being in a
| simulation.
| artificialprint wrote:
| Jokes on u, I'm already in a simulation
| sirolimus wrote:
| Not open source, not worth it. Next.
| jl6 wrote:
| Have they explained anywhere what hardware resources it takes to
| run this in 720p at 24fps with minutes-long context?
| addisonj wrote:
| Really impressive... but wow this is light on details.
|
| While I don't fully align with the sentiment of other commenters
| that this is meaningless unless you can go hands on... it is
| crazy to think of how different this announcement is than a few
| years ago when this would be accompanied by an actual paper that
| shared the research.
|
| Instead... we get this thing that has a few aspects of a paper -
| authors, demos, a bibtex citation(!) - but none of the actual
| research shared.
|
| I was discussing with a friend that my biggest concern with AI
| right now is not that it isn't capable of doing things... but
| that we switched from research/academic mode to full value
| extraction _so fast_ that we are way out over our skis in terms
| of what is being promised, which, in the realm of exciting new
| field of academic research is pretty low-stakes all things
| considered... to being terrifying when we bet policy and
| economics on it.
|
| To be clear, I am not against commercialization, but the
| dissonance of this product announcement made to look like
| research written in this way at the same time that one of the
| preeminent mathematicians writing about how our shift in funding
| of real academic research is having real, serious impact is...
| uh... not confidence inspiring for the long term.
| demirbey05 wrote:
| This is bad use of AI, we spend our compute to make science
| faster. I am pretty confident computational cost of this will be
| maybe 100x of chatgpt query. I don't want to think even
| environmental effects.
| dev0p wrote:
| That's completely bonkers. We are making machines dream of
| explorable, editable, interactable worlds.
|
| I wonder how much it costs to run something like this.
| netdur wrote:
| Mark Zuckberd must very very upset looking at this, I expect him
| to throw another billion dollars at google engineers
| idiotsecant wrote:
| A Mind needs a few things: The ability to synthesize sensor data
| about the outside world into a form that can be compressed into
| important features, the ability to choose which of those features
| to pay attention to, the ability to model the physical world
| around it, find reasonable solutions to problems, and simulate
| its actions before taking them, The ability to understand and
| simulate the actions of _other_ Minds, the ability to compress
| events into important features and store them in memory, the
| ability to _retrieve_ those memories and appropriate times and in
| appropriate clarity, etc.
|
| I feel like as time goes on more and more of these important
| features are showing up as disconnected proofs of concept. I
| think eventually we'll have all the pieces and someone will just
| need to hook them together.
|
| I am more and more convinced that AGI is just going to eventually
| _happen_ and we 'll barely notice because we'll get there inch by
| inch, with more and more amazing things every day.
| superjan wrote:
| There are very few people visible in the demo's. I suppose that
| is harder?
| badmonster wrote:
| a massive leap forward for real-time world modeling
| Bjorkbat wrote:
| Genuinely technically impressive, but I have a weird issue with
| calling these world simulator models. To me, they're video game
| simulator models.
|
| I've only ever seen demos of these models where things happen
| from a first-person or 3rd-person perspective, often in the sort
| of context where you are controlling some sort of playable
| avatar. I've never seen a demo where they prompted a model to
| simulate a forest ecology and it simulated the complex interplay
| of life.
|
| Hence, it feels like a video game simulator, or put another way,
| a simulator of a simulator of a world model.
| Bjorkbat wrote:
| Also, to drive my point further home, in one of the demos they
| were operating a jetski during a festival. If the jetski bumps
| into a small Chinese lantern, it will move the lantern.
| Impressive. However, when the jetski bumped into some sort of
| floating structure the structure itself was completely
| unaffected while the jetski simply stopped moving.
|
| This is a pretty clear example of video game physics at work.
| In the real world, both the jetski and floating structure would
| be much more affected by a collision, but in the context of
| video game physics such an interaction makes sense.
|
| So yeah, it's a video game simulator, not a world simulator.
| rohit89 wrote:
| The goal is to eventually be able to model physics and all
| the various interactions accurately.
| Bjorkbat wrote:
| Sure, but if you're trying to get there by training a model
| on video games then you're likely going to wind up
| inadvertently creating a video game simulator rather than a
| physics simulator.
|
| I don't doubt they're trying to create a world simulator
| model, I just think they're inadvertently creating a video
| game simulator model.
| rohit89 wrote:
| Are they training only on video game data though? I would
| be surprised when its so easy to generate proper training
| data for this.
|
| It is interesting to think about. This kind of training
| and model will only capture macro effects. You cannot use
| this to simulate what happens in a biological cell or
| tweak a gravity parameter and see how plants grow etc.
| For a true world model, you'd need to train models that
| can simulate at microscopic scales as well and then have
| it all integrated into a bigger model or something.
|
| As an aside, I would love to see something like this for
| the human body. My belief is that we will only be able to
| truly solve human health if we have a way of simulating
| the human body.
| kridsdale3 wrote:
| In the "first person standing in a room" demo, it's cool to
| see 100% optical (trained from recorded footage from cameras)
| graphics, including non-rectilinear distortion of parallel
| lines as you'd get from a wide-angle lens and not a high-FOV
| game engine. But still the motion of the human protagonist
| and the camera angle were 100% trained on how characters and
| controllers work in video games.
| lubujackson wrote:
| It doesn't feel incredibly far off from demoscene scripts that
| generate mountain ranges in 10k bytes or something. It is
| wildly impressive but may also be wildly limited in how it
| accomplishes it and not extensible in a way we would like.
| phgn wrote:
| So we cannot use this yet?
|
| While watching the video I was just imagining the $ increasing by
| the second. But then it's not available at all yet :(
| ACAVJW4H wrote:
| Wondering What happens when we peer through a microscope or
| telescope?
| koakuma-chan wrote:
| Damn, this reminds me of those Chinese FMV games on Steam.
| _hark wrote:
| 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.
| jimmySixDOF wrote:
| 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.
| mhitza wrote:
| Just imagine if the developers of Star Citizen had access to this
| technology, how much more they could have squeezed from
| unsuspecting backers.
| red_hare wrote:
| Can you imagine explaining to someone from the 1800s that we've
| created a fully generative virtual world experience and the demo
| was "painting a wall blue"
| mattjreid wrote:
| They would be impressed by the paint roller - it wasn't
| invented until the 1940s.
| SirHumphrey wrote:
| Reading works of early computer scientists (mathematicians?)
| like Ada Lovelace or Alan Turing it seems to me that they would
| be a lot less surprised than some current observers. The idea
| of artificial mind comes up a lot and they weren't witness to
| 30 years of slow and uninspiring NLP developments.
| sys32768 wrote:
| I'm imagining how these worlds combined with AI NPCs could help
| people learn real-world skills, or overcome serious anxiety
| disorders, etc.
| forrestthewoods wrote:
| They're very clever to only turn 90 degrees. I'd like to see a
| couple of 1080s with a little bit of 120 degree zig zagging along
| the way please.
| internetter wrote:
| I feel like this tech is a dead end. If it could instead generate
| 3d models which are then rendered, that would be immensely
| useful. Eliminates memory and playtime constraints, allows it to
| be embedded in applications like games. But this? Where do we go
| from here? Even if we eliminate all graphical issues and get
| latency from 1s to 0, what purpose does it serve?
| calebh wrote:
| I think the most likely path forward for
| commercialization/widespread use is to use AI as a post-
| processing filter for low poly games. Imagine if you could take
| low quality/low poly assets, run it through a game engine to
| add some basic lighting, then pass this through AI to get a
| photo-realistic image. This solves the most egregious cases of
| world inconsistency and still allows for creative human fine-
| tuning. The trick will be getting the post-processor to run at
| a reasonable frame rate.
| internetter wrote:
| Don't we already have upscalers which are frequently used in
| games for this purpose? Maybe they could go further and get
| better but I'd expect a model specifically designed to
| improve the quality of an existing image to be better/more
| efficient at doing so than an image generation model
| retrofitted to this purpose.
| ralusek wrote:
| It's interesting, because I was always a bit confused and annoyed
| by the Giant's Drink/Mind Game that Ender plays in Ender's Game.
| It just always felt so different to how games I knew played, it
| felt odd that he would "discover" things that the developers
| hadn't intended, because I always just thought "wait, someone had
| to build that into the game just in case he happened to do that
| one specific thing?" Or if it was implied that they didn't do
| that, then my thought was "that's not how this works, how is it
| coming up with new/emergent stories?"
|
| This feels almost exactly like that, especially the
| weird/dreamlike quality to it.
| arjie wrote:
| This is beautiful. An incredible device that could expand
| people's view of history and science. We could create such
| immersive experiences with this.
|
| I know that everyone always worries about trapping people in a
| simulation of reality etc. etc. but this would have blown my mind
| as a child. Even _Riven_ was unbelievable to me. I spent hours in
| _Terragen_.
| guybedo wrote:
| a lot to unpack here, i've added a detailed summary here:
|
| https://extraakt.com/extraakts/google-s-genie-3-capabilities...
| jp1016 wrote:
| This looks incredibly promising not just for AI research but for
| practical use cases in game development. Being able to generate
| dynamic, navigable 3D environments from text prompts could save
| studios hundreds of hours of manual asset design and prototyping.
| It could also be a game-changer for indie devs who don't have big
| teams.
|
| Another interesting angle is retrofitting existing 2D content
| (like videos, images, or even map data) into interactive 3D
| experiences. Imagine integrating something like this into Google
| Maps suddenly street view becomes a fully explorable 3D
| simulation generated from just text or limited visual data.
| creata wrote:
| It just generates video, though, doesn't it? How are you going
| to get usable assets out of that?
| CharlieDigital wrote:
| Why wouldn't one be able to train an AI model to extract 3D
| models/assets out of an image/still from video?
| cranium wrote:
| I find the model very impressive, but how could it be used in the
| wild? They mention robots (maybe to test them cheaply in
| completely different environments?), but I don't see the use in
| games except during development to generate ideas/assets.
| muskmusk wrote:
| Jesus.
|
| This is starting to feel pretty **ing exponential.
| SpaceManNabs wrote:
| So are foundational models real finally now?
|
| Are they just multimodal for everything?
|
| Are foundational time series models included in this category?
| nektro wrote:
| google pushing new levels of evil with this one
| bluehat974 wrote:
| It's feel like Ready Player One on Vision Pro will arrive soon
| yahoozoo wrote:
| What format do these world models output? Since it's interactive,
| it's not just a video...does DeepMind have some kind of
| proprietary runtime or what?
| creata wrote:
| > Since it's interactive, it's not just a video
|
| I think it just outputs image frames...
| yahoozoo wrote:
| Ah, yea. You're right. After reading a bit more, it's just
| "responding" to the prompts/navigation with real-time
| generation. Pretty cool.
| guybedo wrote:
| it's simulations all the way down
| whatever1 wrote:
| This is scary. I don't have a benchmark to propose but in don't
| think my brain can imagine things with greater fidelity than
| this. I can probably write down the physics better but I think
| these systems have reached parity with at least my imagination
| model
| unboxingelf wrote:
| The Simulation Theory presents the following trilemma, one of
| which must be true:
|
| 1. Almost all human-level civilizations go extinct before
| reaching a technologically mature "posthuman" stage capable of
| running high-fidelity ancestor simulations.
|
| 2. Almost no posthuman civilizations are interested in running
| simulations of their evolutionary history or beings like their
| ancestors.
|
| 3. We are almost certainly living in a computer simulation.
| lotyrin wrote:
| If you take the idea of it needing to be a constructed
| simulation you get the dream argument. If you add that one
| can't verify anyone else having subjective experience you get
| Boltzmann brain. If you add the idea that maybe the ancestor
| simulations are designed to teach us virtuous behavior through
| repeated visits to simulation worlds you get the karmic cycle,
| and Boltzmann brain + karmic cycle is roughly the egg theory.
|
| I think some/all of these things can roughly true at the same
| time. Imagine an infinite space full of chaotic noise that
| arises a solitary Boltzmann brain, top level universe and top
| level intelligence. This brain, seeking purpose and company in
| the void, dreams of itself in various situations (lower level
| universes) and some of those universes' societies seek to
| improve themselves through deliberate construction of karmic
| cycle ancestor simulation. A hierarchy of self-similar
| universes.
|
| It was incredibly comforting to me to think that perhaps the
| reason my fellow human beings are so poor at empathy,
| inclusion, justice, is that this is a karmic kindergarten where
| we're intended to be learning these skills (and the
| consequences for failing to perform them) and so of course
| we're bad at it, it's why we're here.
| crazygringo wrote:
| But there are lots of critiques of that supposed trilemma.
|
| Why would beings in simulations be conscious?
|
| Or maybe running simulations is really expensive and so it's
| done sometimes (more than "almost none") but only sometimes
| (nowhere near "we are almost certainly").
|
| Or simulations are common but limited? You don't need to
| simulate a universe if all you want to do is simulate a city.
|
| The "trilemma" is an extreme example of black-and-white
| thinking. In the real world, things cost resources and so there
| are tradeoffs -- so middle grounds are the rule, not extremes.
| lotyrin wrote:
| Kinda wish the ski scenario had "yeti" as an event you could
| trigger.
| mason_mpls wrote:
| The demo looks like they're being very gentle with the AI, this
| doesn't look like much of an advancement.
| mason_mpls wrote:
| The claims being made in this announcement are not demonstrated
| in the video. A very careful first person walk in an AI video
| isn't very impressive these days...
| qwertox wrote:
| This is revolutionary. I mean, we already could see this coming,
| but now it's here. With limitations, but this is the beginning.
|
| In game engines it's the engineers, the software developers who
| make sure triangles are at the perfect location, mapping to the
| correct pixels, but this here, this is now like a drawing made by
| a computer, frame by frame, with no triangles computed.
| j_timberlake wrote:
| People are thinking "how are video games going to use this?"
|
| That's not the point, video games are worth chump-change compared
| to robotics. Training AIs on real-world robotic arms scaled
| poorly, so they're looking for paths that leverage what AI scales
| well at.
| maerF0x0 wrote:
| I'm still struggling to imagine a world where predicting the next
| pixel wins over over building a deterministic thing that is then
| ran.
|
| Eg: Using AI to generate textures, wire models, motion sequences
| which themselves sum up to something that local graphics card can
| then render into a scene.
|
| I'm very much not an expert in this space, but to me it seems if
| you do that, then you can tweak the wire model, the texture, move
| the camera to wherever you want in the scene etc.
| wolttam wrote:
| At some point it will be computationally cheaper to predict the
| next pixel than to classically render the scene, when talking
| about scenes beyond a certain graphical fidelity.
|
| The model can infinitely zoom in to some surface and
| depict(/predict) what would really be there. Trying to do so
| via classical rendering introduces many technical challenges
| Vipitis wrote:
| I wish they would share more about how it works. Maybe a reseach
| paper for once? we didn't even get a technical report.
|
| From my best guess: it's a video generation model like the ones
| we already head. But they condition inputs (movement direction,
| viewangle). Perhaps they aren't relative inputs but absolute and
| there is a bit of state simulation going on? [although some demo
| videos show physics interactions like bumping against objects -
| so that might be unlikely, or maybe it's 2D and the up axis is
| generated??].
|
| It's clearly trained on a game engine as I can see screenspace
| reflection artefacts being learned. They also train on
| photoscans/splats... some non realistic elements look
| significantly lower fidelity too..
|
| some inconsistencies I have noticed in the demo videos:
|
| - wingsuit discollcusions are lower fidelity (maybe initialized
| by high resolution image?)
|
| - garden demo has different "geometry" for each variation, look
| at the 2nd hose only existing in one version (new "geometry" is
| made up when first looked at, not beforehand).
|
| - school demo has half a caroutside the window? and a
| suspiciously repeating pattern (infinite loop patterns are common
| in transformer models that lack parameters, so they can scale
| this even more! also might be greedy sampling for stability)
|
| - museum scene has odd reflection in the amethyst box, like the
| rear mammoth doesn't have reflections on the right most side of
| the box before it's shown through the box. The tusk reflection
| just pops in. This isn't fresnel effect.
| slj wrote:
| Everyone is in agreement, this is impressive stuff. Mind blowing,
| even. But have the good people at Google decided why exactly we
| need to build the torment nexus?
| pedalpete wrote:
| We were working towards this years ago with Doarama/Ayvri, and I
| remember fondly in 2018 an investor literally yelling at me that
| I didn't know what I was talking about and AI would never be able
| to do this. Less than a decade later, here we are.
|
| Our product was a virtual 3d world made up of satellite data.
| Think of a very quick, higher-res version of google earth, but
| the most important bit was that you uploaded a GPS track and it
| re-created the world around that space. The camera was always
| focused on the target, so it wasn't a first person point of view,
| which, for the most part, our brains aren't very good at
| understanding over an extended period of time.
|
| For those curious about the use case, our product was used by
| every paraglider in the world, commercial drone operations,
| transportation infrastructure sales/planning, out-door events
| promotions (specifically bike and ultramarathon races).
|
| Though I suspect we will see a new form of media come from this.
| I don't pretend to suggest exactly what this media will be, but
| mixing this with your photos we can see the potential for an
| infinitely re-framable and zoomable type of photo media.
|
| Creating any "watchable" content will be challenging if the
| camera is not target focused, and it makes it difficult to create
| a storyline if you can't dictate where the viewer is pointed.
| swalsh wrote:
| To be fair, I'm seeing the demo video, and I still don't
| believe it's possible. This is sci-fi tech.
___________________________________________________________________
(page generated 2025-08-05 23:00 UTC)