descriptive claim
Karpathy says reinforcement-learning estimates have high variance and are noisy.
Andrej Karpathy · Andrej Karpathy — AGI is still a decade away · 17 Oct 2025
In their words
The transcript segments this claim was taken from
“The problem with that is people will say that your estimator has high variance,”
“but I mean, it's just noisy. It's noisy.”Play from 41:54Report a misattribution
90%how strongly it was put, not whether it is true
75%importance to the conversation
95%confidence the claim was read correctly