What kind of a challenge is solving AI alignment?

From Stampy's Wiki

Is it hard like 'building a secure OS that works on the first try'? Hard like 'the engineering/logistics/implementation portion of the Manhattan Project'? Both? Some other option? Etc.

Canonical Question Info
(edits welcome)
Asked by: Rob Bensinger
OriginWhere was this question originally asked
LessWrong
Date: 2022/03/03


Discussion