It's often much faster than rds. And in the long long term there will be tools for computing on feather files that don't require loading it into memory. (In the short term I'll add ways to pull in slices of the full dataset)
Either way, the idea of mixed Python/R pipelines with feather file intermediates input/outputs is pretty sweet. Learn in scikit, save to feather, plot in ggplot2... using Make to tie the pieces together?