Yeah a small amount of manually-written code still makes sense, when it's faster to write it than to tell LLM to write it.
In particular comments. I'm not a fan of the comment style LLM tends to write, so I often just write them manually.
And also coming up with the right architecture is also often manual job. Design how to implement things, and let LLM implement it.
The most common use for a shovel seems to be "this is as close as I dare get to the wire we know is around here - scrape the dirt away until you find it and then I'll dig the rest out."