It sounds like they don't really use it. Their about page says:

  We’re collecting data to find out if humans' pattern- 
 recognition and puzzle-solving abilities make them more 
  efficient than existing computer programs at pattern- 
 folding tasks. If this turns out to be true, we can then 
  teach human strategies to computers and fold proteins 
  faster than ever!

Indicating that at some point they may use it, though judging from recent trends in reinforcement learning, they probably won't.