I wanted to get the number of word changes between commits in my blog. I asked for a git-diff-based Nushell pipeline from Gemini.

Gemini proposed this:

git diff --word-diff=plain -- "*.md" | rg -o '\{\+(.*?)\+\}' | str replace -r '\{\+|\+\}' '' | str join " " | str words | length

What I ended up doing:

git diff --word-diff=plain -- "*.md" | rg -o '\{\+(.*?)\+\}' | str replace -a "{+" "" | str replace -a "+}" "" | str replace -a ' ' "\n" | lines | length

I notice LLMs tend to err on the side of complexity. I don’t know if this is due to their training to spit out as many tokens as possible, but using regular expressions when a simple string replacement may suffice is a good sign that they may be adding more complexity than necessary.