descriptive claim
The speaker characterizes the failures as adversarial examples rather than prompt injection: nonsensical, obviously wrong solutions that an LLM judge rates highly.
Andrej Karpathy · Andrej Karpathy — AGI is still a decade away · 17 Oct 2025
In their words
The transcript segments this claim was taken from
“Not even that.”
“Prompt injection is way too fancy. You're finding adversarial examples,”
“as they're called.”
“These are nonsensical solutions.”
“that are obviously wrong but the model thinks are amazing yeah”Play from 47:55Report a misattribution
95%how strongly it was put, not whether it is true
85%importance to the conversation
96%confidence the claim was read correctly