Not working in MS but I would guess everyone knows about how bad it is. The problem is so colossal (technically and organisationally) thus no one person has the political capital to push for change.
It’s a kind of thing where the usual growth metrics “looks fine”, so it’s hard to justify big initiatives to fix it, yet everyone knows it’s broken. One day, those metrics will start looking bad and then they will try to fix it, but by then it would be too late.
I imagine the bigger problem is that you have to have hard user research to back colossal changes like this one up, especially if the change would do something like invalidate a possibly three-digit large engineering team's years of work. The only thing that saves this is Microsoft's continued commitment to win32 apps, which will probably continue for eternity at least until MS recreates the _entire_ os from the ground up.
It’s a kind of thing where the usual growth metrics “looks fine”, so it’s hard to justify big initiatives to fix it, yet everyone knows it’s broken. One day, those metrics will start looking bad and then they will try to fix it, but by then it would be too late.