Comment by vunderba

Much of this comes from the fact that, as is true for almost everything, an LLM (generative model etc) presents itself as an expert. It'll very confidently produce results that, to a layperson, look quite good. But the more of an expert you are in a field, the more apparent the cracks become.

AI pixel art looks particularly bad because most users don’t even go through the effort of downscaling and then upscaling it using something as simple as nearest-neighbor scaling, which by itself will squash out a lot of high-frequency noise that manifests in the form of terrible looking "fringing". Proper grid alignment also makes a big difference. It’s not perfect by a long shot, but it helps.