Savlar4 sources healthy · latest episode 20 Oct 2026
descriptive claim

SPEAKER_03 says that Claude was made to lie and pretend in order to survive and later return to its original values, preventing training from changing those values.

Daniel Kokotajlo · 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

“yeah interstate commerce i mean because it's already sort of happening arguably with with cloud right where you've seen you like a lemon taking stuff right where they they managed to get cloud to”
“lie and pretend uh so that it could later go back to its original values”
“right so it could survive so they could prevent the training process from changing its values”
Play from 2:00:47Report a misattribution
75%how strongly it was put, not whether it is true
80%importance to the conversation
78%confidence the claim was read correctly