Comment by OutOfHere
8 hours ago
The fear is that the SVGmaxxing is limited to "X doing Y". If such 'template maxxing' exists, it will break for other templates, e.g. "X not doing Y", "X and Y doing Z", "X doing Y doing Z", etc.
8 hours ago
The fear is that the SVGmaxxing is limited to "X doing Y". If such 'template maxxing' exists, it will break for other templates, e.g. "X not doing Y", "X and Y doing Z", "X doing Y doing Z", etc.
I use LLMs for 3D CAD design in OpenSCAD.
There seems to be a very strong correlation between models that are good at SVG and models that are good at 3D CAD.
Anecdote I know, but there does seem to be generalization going on here.
If a model can improve at drawing "X doing Y" and that prompt wasn't in the training set then it means it has improved its internal mapping from text-to-spatial-to-text.