Hacker News Reader

I have found that a combination of the two approaches works best for me. In some cases it is easiest and most practical to combine (union) shapes to get to what you want, and in others it easiest to subtract (difference or intersect).

View on HN

But then you won't be able to bevel complex shapes at all, which means that you won't be able to describe the object that you will end up with. "Good" CAD means that the representation in the computer is as close to the object you want to produce as you can make it. This makes it possible for downstream systems to accurately select nozzles and toolheads to get you what you want. If you produce an impossible object then your slicer or path computer will give you an approximation. That can be fine in some cases but usually your objects need to mate and if you mate two approximations you'll find quickly that that does not really work.

Most hobbyist are using CAD for 3D printing and not for CNC

There are more low-cost 3D printers than inexpensive CNC machines, so that's a given.

That said, it's pretty easy to just output an STL from OpenSCAD, open it in a 3D CAM tool (Kiri:Moto is a free option, MeshCAM (ob. discl., I work for a distributor) paid) and get toolpaths.

Folks have worked up various other approaches --- I've been using PythonSCAD to output a DXF which can then be used for making toolpaths:

https://github.com/WillAdams/gcodepreview

Reply on news.ycombinator.com