It’s literally just a JSON map of per pixel words used to “encode” the color.
The worst part of AI generated content is that people won’t give new ideas, art, etc. the benefit of the doubt and will just assume it’s slop.
Reading OP and thinking about their misinformed understanding of what they are doing, I came upon an idea I propose to all of you: the almighty Babylonian Compression Algorythm.
As long as we have all combinations of (say, 256x256px) images in the database, we can cut down image size to just a reference to a file in said database.
It produces a bit-by-bit copy of any image without any compression, so it puts OOP’s project to shame. Little, almost non-existent problem is having access to said database, bloated with every existing but also not-yet-existing image. But since OOP’s solution depends on proprietary ChatGPT on someone else’s server, we are on par there.
Funny enough that actually wouldn’t be more efficient of a compression algorithm, the size of the file reference would be at best exactly the same size as the image that is being referenced, just because any fewer bits would lead to duplicate reference locations.
Funny thing is that it would probably be more efficient as OOP’s approach, since it stores a word in a JSON map for each pixel.
De-duplicate the internet. You have your orders.
Like a library of Babel of images.
Here’s my “symbolic image compressor”:
American Gothic is a painting of two people standing in front of a farmhouse. One has a pitchfork.
Are you impressed? I used symbols to compress the image down to under a kilobyte. And I didn’t need an AI.
Wow, that’s super impressive. The compression is so efficient that it’s like I can see the original image in my head. Truly, we are living in the future.
Also infuriating is when the OP gets told by a mod to stop posting AI slop comments and OP responds:
I’m explaining the project in as detailed and clear a manner as possible - using the LLM to do it. The same one that helped me build it. Shut it down then man, why warn me?
Lol. It’s funny to see vibecoders stumble
That’s not a vibe coder. That’s just an idiot.
Same difference imho
It’s a vibethinker
So the superset that includes vibe coders?
That’s the Uberset that includes everyone.
I think you do need to write code to implement compression algorithms.
Oh! That’s way worse.
Hopefully he’s in high school or something and it’s an immaturity thing.
Otherwise, no doubt all of the skilled people on his team want him gone.
It’s hard to imagine turning an image into JSON would manage to compress it. 🤔
AI generated
“recursive symbolic”
Sounds about right
deleted by creator
Is that like converting raster images to SVG? Either it emebeds the actual image as data, or it “vectorizes” every fucking pixel. Filesize will show you which.
