zlacker

> Copilot excels at low-to-medium complexity tasks

Oh cool!

> in well-tested codebases

Oh ok never mind

>>muglug+(OP)
Have it write tests for everything and then you've got a well tested codebase.

>>muglug+(OP)
In my experience it works well even without good testing, at least for greenfield projects. It just works best if there are already tests when creating updates and patches.

>>muglug+(OP)
As peer commenters have noted, coding agent can be really good at improving test coverage when needed.

But also as a slightly deeper observation - agentic coding tools really do benefit significantly from good test coverage. Tests are a way to “box in” the agent and allow it to check its work regularly. While they aren’t necessary for these tools to work, they can enable coding agents to accomplish a lot more on your behalf.

(I work on Copilot coding agent)

>>abraha+65
You forgot the /s

>>lukeho+Nf
In my experience they write a lot of pointless tests that technically increase coverage while not actually adding much more value than a good type system/compiler would.

They also have a tendency to suppress errors instead of fixing them, especially when the right thing to do is throw an error on some edge case.

>>abraha+65
Caveat empor, I've seen some LLMs mock the living hell out of everything, to the point of not testing much of anything. Something to be aware of.

>>daniel+nn
I've seen too many human operators do that too. Definitely a problem to watch out for

>>CSMast+pk
You can tell the AI not to suppress errors