opinion claim
The speaker thinks AI labs are probably addressing reward-model exploits by adding adversarial examples to the LLM judge's training data and labeling them as incorrect.
Andrej Karpathy · Andrej Karpathy — AGI is still a decade away · 17 Oct 2025
In their words
The transcript segments this claim was taken from
“i think the labs are probably doing all that like okay so the obvious thing is like the the should not get 100 reward okay well take the put in the training set of the lm judge and say this is not 100”
“0% you”Play from 48:20Report a misattribution
70%how strongly it was put, not whether it is true
75%importance to the conversation
94%confidence the claim was read correctly