> This seems like it's fixing the symptom rather than the underlying issue?
This is also my experience when you haven't setup a proper system prompt to address this for everything an LLM does. Funniest PRs are the ones that "resolves" test failures by removing/commenting out the test cases, or change the assertions. Googles and Microsofts models seems more likely to do this than OpenAIs and Anthropics models, I wonder if there is some difference in their internal processes that are leaking through here?
The same PR as the quote above continues with 3 more messages before the human seemingly gives up:
> please take a look
> Your new tests aren't being run because the new file wasn't added to the csproj
> Your added tests are failing.
I can't imagine how the people who have to deal with this are feeling. It's like you have a junior developer except they don't even read what you're telling them, and have 0 agency to understand what they're actually doing.
Another PR: https://github.com/dotnet/runtime/pull/115732/files
How are people reviewing that? 90% of the page height is taken up by "Check failure", can hardly see the code/diff at all. And as a cherry on top, the unit test has a comment that say "Test expressions mentioned in the issue". This whole thing would be fucking hilarious if I didn't feel so bad for the humans who are on the other side of this.
Typically, you wouldn't bother manually reviewing something until the automated checks have passed.
Let them finish a pull request before spending time reviewing it. That said, a merge request needs to have an issue written before it's picked up, so that the author does not spend time on a solution before the problem is understood. That's idealism though.