> If I have to spend the time to check everything the tool generates (which I do, because LLMs are unreliable) then I may as well have written it myself to start with.
Do you feel the same way about a PR from a coworker?
Depends on the coworker. I would say that I trust ChatGPT code much less than the average coworker, because coworkers usually don't do something like use imaginary variables or check-in code that doesn't compile.
Do you feel the same way about a PR from a coworker?