This is probably terrible code by anybody's standards but maybe someone wants to take a look: https://github.com/svenstaro/infinerator
Annihilate the Sun and you won't get enough energy to drive a simple counter through thirty 8-bit grayscale pixels.
First, article tried to assess information capacity in Shannon style, completely disregarding what signal is (a) two-dimensional and (b) highly redundant, that is, ignoring the traits of being an image.
Second, article taken too much liberties while mixing photorealistic and pixel-art images. The latter is really an art, since there is no formally defined ("machine") transform between these two types. And last but not least these types have significantly different information density profiles.
No DSP curiosity here.
The article is saying that neural networks are cool, because part of what they do is finding which images actually contain meaningful visual information.
It errs in the same way we often see objects in clouds or constellations.
Use the whole space [32x32x3 bytes = 3072 bytes] to encode a Busy Beaver.
...except that we also do it by math. It is just so fast and optimized, that we refer to it as instinct.
