Toyesh Singh
@toyesh_7
FAFO | character development ongoing
ID: 1065919041091641345
23-11-2018 10:44:38
2,2K Tweet
69 Takipçi
1,1K Takip Edilen
The most interesting part for me is where Andrej Karpathy describes why LLMs aren't able to learn like humans. As you would expect, he comes up with a wonderfully evocative phrase to describe RL: “sucking supervision bits through a straw.” A single end reward gets broadcast across