Hacker News new | ask | show | jobs
by TNWin 211 days ago
I didn't get the reference. Please elaborate.
2 comments
egl2020 211 days ago
Karpathy colorfully described RL as "sucking supervision bits through a straw".
link
apwell23 211 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 .

link