It's slow between each UI interaction compared to auto-complete type systems. But CC can do much more per step. That's especially true if you use it to write scripts that encapsulate multiple steps of a process. Then it can run the scripts.

Perhaps not coincidentally, that's what efficient (or "lazy", you choose) developers do as well.

Claude Code has been pretty poky for me running under WSL 2 on my Server 2022 box (admittedly, with pretty outdated hardware). It would routinely hang after a lot of use and performance would degrade over time.

Since the last couple of updates I don't seem to have those problems as prominently any more. Plus it seems to have greatly improved its context handling as well -- I've encountered far fewer occurrences where I've had to compact manually.