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

SANA-WM, a 2.6B open-source world model for 1-minute 720p video

nvlabs.github.io

Post reply on HN
Print view View original

51–60 of 162 posts

Re: SANA-WM, a 2.6B open-source world model for 1-minute 720p video

#51

Post by pigpop »

mccoyb wrote: post #16

I struggle with these world models from the perspective of video games (so this post is a particular perspective). I'm not a game developer myself, but some of my favorite games carry a deep sense of intentionality. For instance, there is typically not a single item misplaced in a FromSoftware game (or, for instance, Lies of P -- more recently). Almost every object is placed intentionally. Games which lack this inten…

Even though I doubt the main purpose of these models is to produce video games, I have the opposite view from you in that I am excited to see these put to work as components of procedural generation in video games. I don't think that is going to negatively impact story driven games that you seem to enjoy any more than the market for open world and simulation games currently does. They are separate concerns and use distinct techniques.

Where you look for an intentionally evoked experience authored by a game designer, I am looking for an unexplored world unfolding before me filled with emergent and unique phenomena that perhaps no one and not even the game designer has seen before.

Re: SANA-WM, a 2.6B open-source world model for 1-minute 720p video

#52

Post by orbital-decay »

mccoyb wrote: post #16

I struggle with these world models from the perspective of video games (so this post is a particular perspective). I'm not a game developer myself, but some of my favorite games carry a deep sense of intentionality. For instance, there is typically not a single item misplaced in a FromSoftware game (or, for instance, Lies of P -- more recently). Almost every object is placed intentionally. Games which lack this inten…

> some of my favorite games carry a deep sense of intentionality. For instance, there is typically not a single item misplaced in a FromSoftware game (or, for instance, Lies of P -- more recently). Almost every object is placed intentionally.

That's a pretty specific and one-sided example. There are tons of good games that don't rely on elaborate item placement (e.g. many Bethesda games are great because most items are useless decorations, they broke that rule in recent games, giving the purpose to clutter, and it made them a lot worse). There are tons of good games not relying on this intentionality at all, they're either literally random cool ideas thrown at the wall, or even procedurally generated.

Re: SANA-WM, a 2.6B open-source world model for 1-minute 720p video

#54

Post by jdironman »

mccoyb wrote: post #16

I struggle with these world models from the perspective of video games (so this post is a particular perspective). I'm not a game developer myself, but some of my favorite games carry a deep sense of intentionality. For instance, there is typically not a single item misplaced in a FromSoftware game (or, for instance, Lies of P -- more recently). Almost every object is placed intentionally. Games which lack this inten…

I'm of a strong believer that AI just isn't (may never will be?) a strong judge and executor of "quality". Quality is a loaded term though. Are there any objectively good game designs? Even if there is, maybe only one game of 10 that use the same 'blue print' every reach critical mass (popularity).

Re: SANA-WM, a 2.6B open-source world model for 1-minute 720p video

#55

Post by hackinthebochs »

AshleyGrant wrote: post #35
Leonard_of_Q wrote: post #27

Earlier quoted context omitted.

Games. Build campaigns in hours instead of months. Make it possible for users to create their own campaigns, move the action to different game worlds - 'gimme Mario Kart in the ${favourite_game} world', etc.

Yeah, but is this really that great? Are these models going to remember the town you wandered through on your session yesterday and want to return to? Imagine playing Read Dead Redemption 2 and you attempt to ride your horse from Saint Denis to Valentine and Valentine no longer exists, or is a completely different town located half a mile off from where it was originally. I just don't see how this would work...

It's not hard to imagine a system that combines deterministic state tracking with diffusion generated scenes.

Re: SANA-WM, a 2.6B open-source world model for 1-minute 720p video

#56

Post by fc417fc802 »

danielbln wrote: post #32
robot_jesus wrote: post #24

Earlier quoted context omitted.

By and large I agree, but it doesn’t need to be either/or. Many of the most popular games in the past decade are procedurally generated and have nothing “intentionally” placed (apart from tuning/tweaking the balance of the seeding algorithms).

Which game would that be apart from Minecraft?

Dwarf fortress, no man's sky, elite dangerous, ...

The combination of "many", "most popular", and "nothing" is overstating it by a wide margin but for example the majority of the vegetation in games as far back as oblivion was procedurally placed.

Re: SANA-WM, a 2.6B open-source world model for 1-minute 720p video

#57

Post by mccoyb »

orbital-decay wrote: post #52
mccoyb wrote: post #16

I struggle with these world models from the perspective of video games (so this post is a particular perspective). I'm not a game developer myself, but some of my favorite games carry a deep sense of intentionality. For instance, there is typically not a single item misplaced in a FromSoftware game (or, for instance, Lies of P -- more recently). Almost every object is placed intentionally. Games which lack this inten…

> some of my favorite games carry a deep sense of intentionality. For instance, there is typically not a single item misplaced in a FromSoftware game (or, for instance, Lies of P -- more recently). Almost every object is placed intentionally. That's a pretty specific and one-sided example. There are tons of good games that don't rely on elaborate item placement (e.g. many Bethesda games are great because most items a…

That’s a fair critique of my comments! The space of fun games is large and diverse.

Re: SANA-WM, a 2.6B open-source world model for 1-minute 720p video

#58

Post by duskdozer »

mccoyb wrote: post #16

I struggle with these world models from the perspective of video games (so this post is a particular perspective). I'm not a game developer myself, but some of my favorite games carry a deep sense of intentionality. For instance, there is typically not a single item misplaced in a FromSoftware game (or, for instance, Lies of P -- more recently). Almost every object is placed intentionally. Games which lack this inten…

>We are able to create less satisfying, less humane experiences faster?

Yes, exactly. Inundate the world with superficially plausible yet hollow content, including any desired themes. People who aren't very discerning won't complain; the others will be outmatched and find that 99/100 pieces are all noise and they will need to spend increasing amounts of time trying to find the 1, if they can.

I think there are some good parallels with Amazon: the broken sorting and manipulated unit pricing, coupled with the avalanche of cheap clones pushes users to give up and just buy one of the top listed products (a featured listing/Amazon-clone). If you do a web search for various products and go to images, Amazon product links often take up 50-90% of the results.

Re: SANA-WM, a 2.6B open-source world model for 1-minute 720p video

#59

Post by ctoth »

unfitted2545 wrote: post #39
mccoyb wrote: post #16

I struggle with these world models from the perspective of video games (so this post is a particular perspective). I'm not a game developer myself, but some of my favorite games carry a deep sense of intentionality. For instance, there is typically not a single item misplaced in a FromSoftware game (or, for instance, Lies of P -- more recently). Almost every object is placed intentionally. Games which lack this inten…

If we use world models to train AI systems, are we not essentially forcing something to live so it can gather data for us? Yes, we haven't gone that far with creating consciousness yet, but there is gonna be a lot of money around neural computing devices for consumers in the coming decades, so that will speed up knowing what sense data you need for consciousness.

> are we not essentially forcing something to live so it can gather data for us?

Wait until you learn about what we do to chickens.

Post reply on HN