descriptive claim
The speaker says micrograd supports forward and backward computation for arbitrary neural networks, but does so inefficiently.
Andrej Karpathy · Andrej Karpathy — AGI is still a decade away · 17 Oct 2025
In their words
The transcript segments this claim was taken from
“And it can do forward and backward arbitrary neural networks,”
“but not efficiently.”Play from 2:17:36Report a misattribution
95%how strongly it was put, not whether it is true
75%importance to the conversation
99%confidence the claim was read correctly