The Bleak Future of NAND Flash Memory [pdf]

And a post by someone countering the conclusions: http://pcper.com/reviews/Editorial/NAND-Flash-Memory-Future-...

His main problem is with their assumption of a constant die-count for future projections. Honestly, I'm not enough of a hardware person to evaluate the methods and claims well, but I'm glad I was exposed to this so it's on my radar. (Oh, and the bottom comment on pcper is wrong: this paper was subjected to peer review as a part of the USENIX FAST conference.)