[jasonm23]

I have to add that working effectively with LLMs is a skill too, mostly in terms of prompting and system level prompts to skip _most_ of the fabrication and nonsense.

They have to be explicitly told often to keep things brief, non-fiction and non-sycophantic.

Then you still need to curate responses, but less so.

[d4rkp4ttern]

Agreed, and being productive with Claude Code and similar cli tools requires being deliberate about creating docs for background info, spec, and implementation plan, and final implementation notes.