Would author be able to do it otherwise? Is particular tool choice making result worse?

Bit identical/pixel-faithful reproductions are easy to verify…

"LLMs are amazing, I'm so much more productive now"

"oh yeah? Show me what you made, you can't, nobody can, it's all just AI psychosis"

"I made a pixel perfect Office document viewer"

"well... I wish you hadn't"

I'm fine with that, even as someone who hates AI.

Would this project exist otherwise? i doubt it

which means it probably gets all the halucinated assets correctly and any real world documents wrong.

Still, looks pretty; if it actually has proper testing, could close the gap. Code not being the hard part is a major impediment to good software coming out of these things.