jasonswett

The reason it works is because there's a difference between the model knowing something and the agent doing something. Claude will happily write giant untested functions even though it "knows" that short functions are easier to understand and then testing enables safe refactoring etc. The model also "knows" many conflicting "facts", such as the fact that testing is smart and that testing is a waste of time. It can't act on both beliefs at the same time. That's why nudging it toward your own preferred behaviors works.

I HATE this. I call it speculative coding. Claude often calls it "defensive" programming. It's easily my #1 LLM pet peeve. I have yet to figure out a reliable way to make this stop happening.

OP here. I don't know, in my experience Claude took "clean the kitchen before we make dinner" to heart in an astonishingly productive way. I haven't tried many other analogies though.

Thanks, I'm glad you like it!

My experience has been that yes, LLMs already know about TDD, OOP, etc., but they won't necessarily BEHAVE according to what they know unless you tell them. And of course, they "know" a lot of things that conflict with each other.

Good point! Will add a date.

Totally agree, although I'd maybe replace "knowledge" with "knowledge or behavior".

> Just because a piece of duplication costs something doesn’t automatically mean that the de-duplicated version costs less. It doesn’t happen very often, but sometimes a de-duplication unavoidably results in code that’s so generalized that it’s virtually impossible to understand. In these cases the duplicated version may be the lesser of two evils.