Those two examples are fine applications of ML. The problem is when you're dealing with sequential, timestamped content that SHOULD be displayed in the order it was posted. I think companies should very judiciously apply ML in these cases, and only possibly for 'top stories' or huge events that are occurring. However it appears ML is being applied across the board, using multiple signals and throwing the chronological order of the content out of whack, which is very frustrating.
I agree that the problem exists, but its not just Twitter, and this is an unfortunate side-effect of recommendations in general: even if you do count-based recommendations, you are going to have a bit of echo chamber.