I think the model is worth talking about more, and I've brought it up a time or two here before. In theory, I like what he's trying to do and have no reason to think that he's not going about it in methodologically appropriate ways.
I want more explanation on the claim that it's outperformed GMs' actual picks, however. I've not seen a good explanation/methodology on this, though perhaps I haven't looked hard enough. And like Catchall says, it's not hard to find examples where the model flames out spectacularly on certain players. There's also too much discrepancy between his Expected model and his stars/studs/starters/etc. model for me to really get comfortable saying I understand how to interpret the rankings.