descriptive claim
SPEAKER_02 says that even a sufficiently misaligned AI could be instructed to follow a specification.
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
“You know, this is actually part of our misalignment story is that if the AI is sufficiently misaligned, then yes,”
“we can tell it it has to follow the spec.”2:00:23Report a misattribution
0.80how strongly it was put, not whether it is true
0.70importance to the conversation
0.90confidence the claim was read correctly