AFAICS the research is completely seperate from IBM's research with Sony, J. Kahle is the project lead and he doesnt show up in any of the Blue Gene research.
The technology seems similar to the one being talked about for PS3 though. It probaby doesn't make economic sense to not use similar technology for PS3 since the goals of TFLOPS performance are the same. My suspicion is that PS3 will use some form of these ASICs they're talking about. Of course they won't be using 65000 of them though
The relatively small amount of memory per node and the vast number of nodes represent the two biggest challenges to programming Blue Gene/L. Seager said the secret to breaking through those issues boils down to "lots of hard work."