I don't get this "easier said than done" part.

There are really not that many things in this world you can swap as easily as models.

Api surface is stable and minimal, even at the scale that microsoft is serving swapping is trivial compared to other things they're doing daily.

There is enough of open research results to boost their phi or whatever model and be done with this toxic to humanity, closed, for profit company.

Swapping LLM models isn't hard, but if you build a production app or business process around it, how much time/effort is the testing to have confidence?

Which is easier when maintaining an LLM business process, swapping in the latest model or just leaving some old model alone and deferring upgrades?

Swapping is easy for ad hoc queries or version 1 but I think there's a big mess waiting to be handled.