Not true. Most prompt techniques that work on current modern LLM models will work on different or future models, although it will require a QA pass for any regressions.
But not doing it is an opportunity cost. You don’t built skills, tooling and experience, and you don’t get feedback on what works and where you should go.
It’s like computers in the 1990s: there’s always a better one 6 months away, so if you wait for it to stabilise, then you don’t do anything for a decade. Just enjoy the ride, bearing in mind that things change very fast and some things will be obsolete next year.
I think that a whole lot of what I do in prompt engineering is what's necessary to fully specify the output that I want.
A newer model may be less finicky, so I have a higher chance of getting it to work on the first try (and it's more reliable afterwards), but it's hard for me to imagine it needing a whole lot less prompt.
I don’t think RAG is going away, at least not because of this. But I expect new techniques to become available fairly regularly.