LLMs can actually be a useful tool for populating out unit tests.
My experience with this is the LLM commenting out the existing logic and just returning true, or putting in a skeleton unit test with a comment that says “we’ll populate the code for this unit test later”.
Tangent5280@lemmy.world 1 day ago
It’s so ridiculous, like an ancient Egyptian slave telling its master that “we will” “take care of it later”
So stupid for an LLM to do