prediction claim
In-context learning may run a small gradient-descent loop internally within neural-network layers.
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 I do think it's possible that in context learning actually runs a small gradient descent loop internally in the layers of the neural network.”15:25Report a misattribution
0.55how strongly it was put, not whether it is true
0.85importance to the conversation
0.98confidence the claim was read correctly