[rirze]

This.

Every 6 months, I reevaluate how well LLMs can model from scratch or can modify existing files.

It's very superficial (atleast the last time I tried it). I'm guessing if/when LLMs crack visual reasoning, they might be able to do it.

[eMPee584]

Well visual reasoning is one approach, another is a coding-like approach like this cadquery-based solution https://articraft3d.github.io/ which was also posted here a couple of days ago.. https://news.ycombinator.com/item?id=48153064 Curious what you (and others) think, they also are collecting a pool of examples including prompt, reasoning log and token cost, quite interesting imho.