Comment by zerosizedweasle

4 days ago

Given Ilya's podcast this is an interesting title.

I didn't get the reference. Please elaborate.

  • Karpathy colorfully described RL as "sucking supervision bits through a straw".

  • he said RL sucks because it narrowly optimizes to solve a certain set of problems in certain sets of conditions.

    he compared it to students who win at math competition but cant do anything practical .