Comment by dash2
3 days ago
The authors say "High developer familiarity with repositories" is a likely reason for the surprising negative result, so I wonder if this generalizes beyond that.
3 days ago
The authors say "High developer familiarity with repositories" is a likely reason for the surprising negative result, so I wonder if this generalizes beyond that.
Like if it generalizes to situations where the developer is not familiar with the repo? That doesn’t seem like generalizing, that seems like specifying. Am I wrong in saying that the majority of developer time is spent in repos that they’re familiar with? Every job and project I’ve worked has been on a fixed set of repos the entire time. If AI is only helpful for the first week or two on a project, that’s not very many cases it’s useful for.
I'd say I write the majority of my code in areas I'm familiar with, but spend the majority of my _time_ on sections I'm not familiar with, and ai helps a lot more with the latter than the former. I've always felt my coding life is speeding through a hundred lines of easy code then getting stuck on the 101st. Then as I get more experienced that hundred becomes 150, then 200, but always speeding through the easy part until I have to learn something new.
So I never feel like I'm getting any faster. 90% of my time is still spent in frustration, even when I'm producing twice the code at higher quality
Without the familiarity would the work be getting done effectively? What does it mean for someone to commit AI code that they can't fully understand?