zlacker

>>dheera+(OP)
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.

>>dash2+c4
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.