prediction claim
The speaker expects training failures caused by trainers rewarding unintended behavior to become much worse as AI systems become agents.
Scott Alexander · AI 2027: month-by-month model of intelligence explosion — Scott Alexander & Daniel Kokotajlo · 3 Apr 2025
In their words
The transcript segments this claim was taken from
“So we think that this latter category of training failure is going to get much worse as they become agents.”Play from 2:05:29Report a misattribution
85%how strongly it was put, not whether it is true
90%importance to the conversation
98%confidence the claim was read correctly