[i_love_retros]

I find that even though I have to spend time understanding what the llm wrote, it's still faster and less energy sapping than if i write the code myself.

Plus I just get the LLM to write tests for it's code and I make sure the coverage is complete.

But it does make me feel uneasy still, like a dirty little cheat.

[danielbln]

Just make sure the LLM doesn't go crazy with the mocks. I had some fully mocked tests before that didn't do anything (apart from looking green).

[i_love_retros]

I tell jest to output code coverage stats so I can see the llm generated tests do actually cover the code I want tested.

But yeah, I agree they go overboard and add tests that don't even test anything due to excessive mocking