OT, but I thought it was neat how all the splash images were just casually generated by dall-e and the author didn't feel the need to mention it because it's just normal now
(Not /s, I genuinely think it's cool things are like this now)
I didn't notice that but thanks, it made me chuckle. Perhaps the author really wanted you to take note of the beautiful blue 8bit style graphics they had drawn?
I would say that the part you quoted suggests it's not generated on the spot.
However,the sentence in the huge font right before the one you quoted could be reasonably interpreted to suggest it's generated on the spot. And as you mention it just looks like a gallery of images that was already generated.
It's still cool, but I'm a bit irked at the misleading framing. Gwern's website showed us amazing text generation from GPT-3, that had all been generated beforehand. We didn't have to be tricked into thinking it was generated on the spot to appreciate it, so I don't see why that's needed here.
I like how, out of the 20 examples, 10 of them essentially copied the HTML snippet in the 'Coder' section of the 2012 image. Most of them even left the "jedi" div intact.
On the other hand, only 6 of the examples copied the yellow-blue-pink splotch motif from the 'Designer' section.
(These don't have any meaning in the bigger scheme of things; they're just statistics that amused me.)
>Btw transparency for this now-viral thread: I didn’t just paste prompts into dall-e, I played with style (eg. cyberpunk, oil, etc) to keep it interesting and diverse
>If I had to quantify, I’d say I’d generate 2 or 3 batches (tweaking prompt) before choosing my fav two pics, each batch outputs 20 images (two tabs 10 per), so prob technically cherry picked 2 out of 60. That said usually other 58 weren’t really broken, just boring / bit less fun
But that doesn't detract the artistic merit of the submission.
Agreed, looked at in that light I'd suggest that it actually adds to the artistic expression. I was one of a few, apparently, that the site loaded for (sans images) and it was a tiny thrill to see it load. So, it felt like watching a performance of sorts, for me at least.
For some reason I find the test image that was used to be quite fascinating on its own. Were I given that image in isolation and told "write a program to generate this" I wouldn't have any idea where to start. After consulting the source code I now realize how it was created, and if anything that makes it even neater, that such a simple approach generates such an interesting-looking image.
Maybe. But aside from that little artifact, it is really nice and it fits a description well. And probably it only took the author few moments to get it generated.
The initial image presented is pretty deceptive considering the author doesn't explain until the very end that all the characters, health bars, etc., were all added by them, and the only "generated" part of the image is the tiles, which they manually sampled and arranged in to a level.
That made my day. I'm kind of worried though that the examples are hand-picked, and by default it doesn't look so nice. I would love, though, to know the algorithm behind this.
(Not /s, I genuinely think it's cool things are like this now)
reply