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.
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.
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.
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?
It’s hard to imagine turning an image into JSON would manage to compress it. 🤔
AI generated
“recursive symbolic”
Sounds about right