> Companies seem to be persuaded that, like assembly lines of old, A.I. can increase productivity. A recent paper by researchers at Microsoft and three universities found that programmers’ use of an A.I. coding assistant called Copilot, which proposes snippets of code that they can accept or reject, increased a key measure of output more than 25 percent.

> The engineers said that the company had raised output goals and had become less forgiving about deadlines.

There are two issues this article brings to mind:

1. Feels like we are back when lines of code was a measure of productivity.

2. We’ve heard this tune before, and the problem we have now is that you don’t understand what you didn’t write. Software development is in large part about understanding the system from the highest level to its smallest details, and this takes away a key part of how our world works, in favor of a “cattle not pets” view of code.

Now, if you don’t expect your programmers to have an understanding of the system they built, and you treat code as disposable, then you’ll center around a world where folks aren’t trained to learn a system, and I don’t see that as a world that is compatible with increased reliance on A.I.