descriptive claim
In the described training setup, instructions not to lie or cheat are given for only one-tenth or one-one-hundredth as much time as the other training.
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
“And then you're going to be doing this alternative training where afterwards for one-tenth or one-one-hundredth of the time, like, yeah, don't lie,”
“don't cheat.”Play from 2:05:54Report a misattribution
85%how strongly it was put, not whether it is true
70%importance to the conversation
94%confidence the claim was read correctly