An LLM itself can't use wc. Coding agents like Claude Code or Cursor will call out to command line tools for this kind of problem when the LLM detects it.
Well, maybe not wc directly, but they have access to sandboxed Python environments. It must be trivial for an LLM to write the Python code that calculates this.
I don't understand why Gemini insists that it can count the lines itself, instead of falling back to its Python tool [1].
You don't need an explicit rule, you just need to be smarter than than the average mid-curve tries-too-hard-to-feel-right hn poster and realize when you're repeating a calling convention too much.
The gamification is what made it work for me. I had 2 months to learn some Turkish before a trip and once I realized it was a game I beat everyone else in my cohort every day. When someone would come up on my heels I'd make sure to spend 30-60 extra minutes that day. I still know Turkish better than any other language and I've been immersed in Spanish for 3 years.
This is right by where I grew up and the broadcast tower and turnpike sign were the first two things I noticed too, but the ability to realize it was the East side instead of the West side because the tower platforms are lower is impressive.
It's not trained on "the commons", it's trained on a large number of individual products with their own ownership and licensing. If copyrights are being violated the restitution will go to those owners, not to "everyone".
I think the inline command pallete likely ran into an internal error making it be unable to generate, and then its "come up with a message telling the user we can't do this" generation got StackOverflow'd.
