causal claim
Deep understanding of an AI model's weights would make many alignment techniques available.
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
“Once we can really understand the weights of an AI on a deep level,”
“then we have a lot of alignment techniques open up to us.”Play from 1:36:24Report a misattribution
85%how strongly it was put, not whether it is true
90%importance to the conversation
97%confidence the claim was read correctly