Yeah: in a world where I am coding, I can put in the effort to make the software work the way I think... to use an LLM, I largely have to think the way it wants to work / converse.
It's not like you need to limit yourself to Anthropic and Claude Code. I myself developed "rik" a harness that can modify only a single file and hook up blazingly fast models for it to be like wide-context autocompletion.
The malleability is still here, just different.
2) In fact I have never used off-the-shelf coding assistants (Claude Code, etc.) and have only used my own harness; yet to me the issue is that the model itself often likes to think about problems in ways I find frustrating and unhelpful. The issue isn't at the level of how diffs are applied (that's commodity) or how context is managed (I can fix that) but in how problems are described, how abstractions are managed, and the language used to discuss them.