descriptive claim
A paper hard-coded neural-network weights so gradient descent was implemented through attention and other network internals.
Andrej Karpathy · Andrej Karpathy — AGI is still a decade away · 17 Oct 2025
In their words
The transcript segments this claim was taken from
“In fact, I think even the paper was stronger because they actually hard-coded the weights of a neural network to do gradient descent through”
“attention and all the internals of the neural network.”Play from 16:10Report a misattribution
80%how strongly it was put, not whether it is true
75%importance to the conversation
94%confidence the claim was read correctly