#2 is happening a lot more than people think. It’s incredibly hard to quantify tech debt in software and so as a result productivity measurements are pretty inaccurate. Even without AI there is a trend of devs writing a barely working system and then throwing it over the wall to “maintenance programmers”. Said devs are often rated highly by management as being productive compared to the “maintenance devs,” but all they really did was make other people deal with their garbage. I’ve seen these sorts of systems take months to years to be production ready while the original dev is already off to their new gig (and maybe cluelessly bragging on HN about how much better they are than the people cleaning up their mess).

To get an accurate productivity metric you’d have to somehow quantify the debt and “interest” vs some alternative. I don’t think that’s possible to do, so we’re probably just going to keep digging deeper.