← Back to context Comment by TNWin 3 days ago I didn't get the reference. Please elaborate. 2 comments TNWin Reply egl2020 3 days ago Karpathy colorfully described RL as "sucking supervision bits through a straw". apwell23 3 days ago 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 .
apwell23 3 days ago 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 .
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 .