Playing Zork with AI-generated imagery [video]
youtube.com
youtube.com
Either way, there's going to be a whole new field to adapt these generative models into games and productivity apps. Its going to require a lot of clever thinking to avoid nonsense output and UX/UI where generative imagery makes sense, but its a field ripe for incredible advancements
Yeah, the abrupt change in the house when you open the window starting around 2:16 or so shows it's got a ways to go there. https://youtu.be/ZpCrBBj6AWE?t=137
they can skip the need to relearn or rehire by asking ChatGPT for more verbose prompts from Zorg’s prompts and the feeding that into Stable Diffusion
and you can always string concatenate for specific composition details you want, and also use the prior image as a base for the next image
That's why I don't believe artists will be replaced, the average Joe can't tell a good from a bad painting, or a good from a bad picture, let alone generate it.
the law (an common sense) implies that as long as you're not reproducing art, you can do this. and latent space doesn't save or reproduce that content at all. It mimics, combines remixes or reinvents it. The same what a human brain is doing after learning how to draw.
humanity wouldn't be where it is now when it's forbidden to learn from inventions.
continuity is a solved problem and so is quality and specifics
As somebody who eagerly bought into Infocom's advertising back in the day, about how the best adventure game graphics were always going to come from my imagination, it's sort of disillusioning how well it worked. E.g., https://i.imgur.com/xxPn3Mh.png is better than what was in my mind's eye at the time, notwithstanding the Escherian chair. I honestly don't know if I want to watch that video.
But a lot of Infocom puzzles did depend on you translating a verbal description into the appropriate object--e.g. U-shaped metal = magnet.
Disclaimer: Sometimes beta tester back in the day. And knew lots of the people involved.
I do wonder what it'd be like to have images accompanying something like Emily Short's Counterfeit Monkey which works brilliantly because it's all wordplay. I get the feeling the answer is "less engaging" and "less intuitive", but at least - procedurally generated or otherwise - they wouldn't look like stock photos.
Well... There have been so many visualizations of Zork over the decades. I still default to the InvisiClues images from the early 80's, which I think are far better than the first graphical attempts of the white house (Zork Zero).
However, this is extremely cool. It's like real-time Myst (yes, I know that exists, but that's a raytraced version of the original, not this). The meta data optimization was unexpected.
The video ended too soon.
These are not that.
Is there any correlation between the intonation and meaning of "OK Boomer" and "OK Google"?
___
* while keeping as close as possible to the literal text
I'm so stealing this. Just sums things up nicely
What is the qualitative difference between this project and someone manually entering the descriptions/states into an image generation AI and presenting that output as a static image file?
Is it the image generation model they're presenting here?
Genuine questions. I'm not trying to be dismissive. What am I missing?
Google hasn't been exceptional since they shuttered Labs. Man I used to be excited when something new popped up in Labs, haha. Now it's just.. lame.
Area 120 doesn't have the same feel, partially because it's branding is something your dad would think is cool, but also because nothing interesting has ever come out of it. Mostly just "this is Google's version of x". Where'd all the innovation go?
(I couldn't really say. I just watch music videos and it's all fans praising the musicians. It's probably different elsewhere.)
Remember what it was like when it was semi-obligatory for newspaper websites to have a comments section on every article?
Fair play if they managed to tidy it up, admittedly I've not checked a YouTube comment section in ages. I'll update my knowledge :)
>Where'd all the innovation go?
who wants to innovate something cool when in a matter of months the GoogOverloards will decide to shutter it. that's not an enticement to spend time developing something.
Idk call it Google Poggers or something (I never said I had the answers, hah)
Like many a big organisation, it's been taken over by the managerial class, which will strangle any efforts at innovation, and prefer keeping things the way they are.
https://www.youtube.com/watch?v=4Z4RKRLaSug
>Josh from the Game Helpin' Squad actually tries to get some work done. Or, rather, he complains about how people didn't appreciate it when he got some work done.
Fear and Loathing in Las Vegas (7/10) Movie CLIP - The High Water Mark (1998) HD
https://www.youtube.com/watch?v=vUgs2O7Okqc
>Strange memories on this nervous night in Las Vegas. Has it been five years? Six? It seems like a lifetime, the kind of peak that never comes again. San Francisco in the middle sixties was a very special time and place to be a part of. But no explanation, no mix of words or music or memories can touch that sense of knowing that you were there and alive in that corner of time in the world. Whatever it meant.
>There was madness in any direction, at any hour. You could strike sparks anywhere. There was a fantastic universal sense that whatever we were doing was right, that we were winning.
>And that, I think, was the handle -- that sense of inevitable victory over the forces of Old and Evil. Not in any mean or military sense; we didn't need that. Our energy would simply prevail. We had all the momentum; we were riding the crest of a high and beautiful wave.
>So now, less than five years later, you can go up on a steep hill in Las Vegas and look West, and with the right kind of eyes you can almost see the high-water mark -- that place where the wave finally broke and rolled back.
Would love to see this implemented generally for other text adventures!
Having "Google Research" on it feels mildly embarrassing.