Comment by musesum
10 hours ago
I wrote something similar in a Claude Code instructions.md: "minimize cyclomatic complexity" What happened next? It generated an 8 line wrapper function called only once from a different file. So, I told it to inline that logic in the caller. The result? One. Line. Of. Code.
So, I asked it to modify its instructions.md file to not repeat that mistake. The result was the new line "Avoid single-use wrapper functions; inline logic at the call site unless reused"
instructions.md is the new intern.
Maybe a better way to handle "minimize cyclomatic complexity" would be to set an agent in a loop of code metrics, refactor, test and repeat.
Good idea. Am still a bit shy around token budget spend.
I think this is at the moment the practical limitation to using AI for everything (and what the coding agents themselves also optimize for to some degree, or it's the slider they can play with for price vs quality, the "thinking" models being the exact same, but just burning more tokens).
1 reply →
This seems like a perfect use case for a local model. But I've found in practice that the system requirements for agents are much higher than for models that can handle simple refactoring tasks. Once tool use context is factored in, there is very little room for models that perform decently.
2 replies →