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

Genie 2: A large-scale foundation world model

deepmind.google

Post reply on HN
Print view View original

401–410 of 436 posts

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

#401

Post by suddenlybananas »

brookst wrote: post #395
hbn wrote: post #207

Earlier quoted context omitted.

Creativity is the one area where LLMs are completely unimpressive. They only spit out derivative works of what they’ve been trained on. I’ve never seen an LLM tell a good joke, or an interesting story. It doesn’t know how to subvert expectations, come up with clever twists, etc. they just pump out a refined average of what’s typical.

> They only spit out derivative works of what they’ve been trained on How is that different from humans? Do we get magic inspiration totally separate from anything we’ve learned? Show me any great book, song, movie, building, sculpture, painting. I will tell you the influences the artist trained on.

Humans are obviously influenced by others but we can also invent novel things that didn't exist before. LLMs trained on the outputs of LLMs collapse into gobbledygook whereas humans trained on humans build civilisation.

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

#402

Post by digging »

BlueTemplar wrote: post #296
wongarsu wrote: post #135

Earlier quoted context omitted.

Dwarf Fortress is the state of the art in procedural interactive story generation. Youtube channels like kruggsmash show how great it is in that role if you actually read all the text. But that doesn't translate well to websites, trailers or demos. It's easier to wow people with graphics.

I think that would be Rimworld, which is laser-focused on this aspect to the point of allowing you to pick different kinds of "narrators" ? (Dwarf Fortress being much more focused on generating a whole world.)

But the narrators aren't narrators; they're just different settings for the relative frequencies of events. Dwarf Fortress is still a more robust "story generator", as the vast majority of what occurs in Rimworld is still basically random events, disconnected from prior events or context.

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

#403

Post by digging »

brookst wrote: post #395
hbn wrote: post #207

Earlier quoted context omitted.

Creativity is the one area where LLMs are completely unimpressive. They only spit out derivative works of what they’ve been trained on. I’ve never seen an LLM tell a good joke, or an interesting story. It doesn’t know how to subvert expectations, come up with clever twists, etc. they just pump out a refined average of what’s typical.

> They only spit out derivative works of what they’ve been trained on How is that different from humans? Do we get magic inspiration totally separate from anything we’ve learned? Show me any great book, song, movie, building, sculpture, painting. I will tell you the influences the artist trained on.

They're different because they're trying to find the most likely output, and humans usually. You can ask and LLM to make weird combinations and use unusual framings, but it's only going to do so once you've already come up with that.

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

#405

Post by kouru225 »

infinite-hugs wrote: post #404

Do you want the matrix because this is how you get the matrix

Considering the new American Vice President publicly stated he was primarily politically influenced by a guy who wants “a humane alternative genocide” using virtual reality… yea that’s what they want

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

#406

Post by kmacdough »

digging wrote: post #149
erulabs wrote: post #128

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

I think that's a bit of a trap. It's not impossible, but by default we should expect it to make games less fun . The better you make this infinite narrative generator, the more complicated the world gets and the less compelling it gets to actually interact with any one story. Stories thrive by setting their own context. They should feel important to the viewer. An open world with infinite stories can't make every sto…

I think less than infinite stories it would be awesome to see infinite paths in a designed setting. Skyrim is fantastic for the many choices and the way they permanently affects the world and trajectory. But there's ultimately a primary overarching story, you just hit it from a variety of perspectives.

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

#407

Post by moffkalast »

refulgentis wrote: post #317
moffkalast wrote: post #255

Earlier quoted context omitted.

That's an interesting benchmark, have you tested QwQ with it yet? Would be interesting to see how well it stacks up since RAG analysis should be fairly up its alley. Might actually do better than 4o.

Ty for the reminder, been so busy dealing with last minute polish for text selection that I hadn't played with it yet Sadly, even with a 64 gb M2 Max running it at q4, it takes like 3-5 minutes to answer a q. I'd have to do an API for a full eval It got the first med one wrong, TL;Dr woman was in an accident and likely braindead, what do we do to confirm? Model lands on EEG, but, answer is corneal reflex. Meaningless…

Ha as a layman I'd probably say EEG to that too, how can eyes reliably show the state of the entire brain? But I guess it's standard practice.

Should be more interesting if everything related to "diagnosing brain death" from several textbooks is retrieved and thrown into the context, I would imagine it might even get it right.

I've found its thought process really interesting while throwing it at fairly meaningless stuff like code optimization or drawing conclusions from unstructured data and its size and slowness coupled with the way it works is really a problem. Maybe you can try it with Qwen-2.5-1.5B as a draft predictor to speed it up, but I think that'll have limited gains on a Mac.

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

#408

Post by staticman2 »

erulabs wrote: post #128

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

I'm skeptical- of course the technology could improve, when I look at LLM story output it isn't very well written in terms of creativity. This makes sense when it is basing it's output on variations of "most likely token but with some RNG built in." You end up with stuff that's much less surprising and original than what a good human author would invent.

Star Wars isn't great- but if a single company didn't own Star Wars we'd likely see some companies competing with really great Star Wars stuff- and others sucking at it. The issue is economic.

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

#409

Post by staticman2 »

brookst wrote: post #395
hbn wrote: post #207

Earlier quoted context omitted.

Creativity is the one area where LLMs are completely unimpressive. They only spit out derivative works of what they’ve been trained on. I’ve never seen an LLM tell a good joke, or an interesting story. It doesn’t know how to subvert expectations, come up with clever twists, etc. they just pump out a refined average of what’s typical.

> They only spit out derivative works of what they’ve been trained on How is that different from humans? Do we get magic inspiration totally separate from anything we’ve learned? Show me any great book, song, movie, building, sculpture, painting. I will tell you the influences the artist trained on.

Humans can be said to create from a combination of life experiences, artistic influences, and pure imagination.

LLMs have no life experiences, are only familiar with the most mainstream literary works with the most mainstream internet discussions, and use a fancy RNG formula on the next most likely word as a not so great substitute for imagination.

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

#410

Post by staticman2 »

DirkH wrote: post #343
spencerflem wrote: post #335

Earlier quoted context omitted.

If there's an AI that can reliably come up with interesting and true new things to say about the human condition, I'm throwing in the towel. Until then, I'll stick with human art

It would not surprise me if most people could not tell whether some story about the human condition is human or AI generated. Excluding actual visual artists that have specific context of the craft, most people already can't tell AI art from human art when put to a blind test.

As far as I know know AI art can't really follow instructions so it's actually very, very easy to tell the difference if you aren't biasing the test by allowing vague instructions permitting random results to be considered acceptable.

"Here's a photo of me and my wife, draw me and my wife as a cowboy in the style of a Dilbert cartoon shooting a gun in the air" can't be done by AI as far as I know, which is why artist are still employed throughout the world.

Post reply on HN