The largest change in VMAX was the move to industry standard controllers (which incidentally EMC used to say was a bad idea and gave the vendors that did it a tough time). This approach has been adopted by most of the legacy "big name" vendors now.
Outside of that, the logical deisgn of vmax (how data is adressed and written) is pretty much similar to its predecessors. The core OS (along with the hypers and metas concept) is laregly unchanged. A lot has been bolted on top of this and wrapped in management tools to bring the whole lot together.
This limits the effectiveness of any new capabilities.
Modern day computing requirements are somewhat different to the mainframe era and as long as the fundametals of the vmax are based on what is now a fairly archaic approach to writing data it will never be able to compete with emerging mid-range technologies and new generation vendors and will become as niche as high-end UNIX systems and mainframes are increasingly becomming.