Andrej Karpathy (@karpathy) “One of my favorite results in 2022 was that it's not enough to just think step b” — TopicDigg
Andrej Karpathy
@karpathy
I like training large deep neural nets.
加入 April 2009
1.1K 正在关注 3M 粉丝
One of my favorite results in 2022 was that it's not enough to just think step by step. You must also make sure to get the right answer :D
(actually a nice insight into a psychology of a GPT; it pays to condition on a high reward)
显示更多
