> You just edit as normal while recording, and replay those edits later.

And there is the problem. The first time you do the edit, it might be fine, but when you make a mistake in the edit, you then have to go back and correct all of the cases. With multiple cursors, I am seeing instant visual feedback on all instances of the cursor at once. I am getting literally 2D spatial information, compared to the 1D spatial information per each replay. The multiple cursors approach is better not because it's a different mindset or whatever, but rather it produces a different feedback loop to correct mistakes.

If you still prefer the macro approach over the multiple cursors approach, then you do you. But as an example in the article, I have seen people think they are being productive by their own standards, and they really aren't.