There is an unspoken presumption behind the alignment problem.
The unspoken presumption is the following: if we build an AI that has a sound, robust epistemology and leave it to observe the world via digital information, that is insufficient for creating a morally good AI.
In other words, knowing the Truth is not a sufficient condition for moral goodness.
[Question] Why is there an alignment problem?
There is an unspoken presumption behind the alignment problem.
The unspoken presumption is the following: if we build an AI that has a sound, robust epistemology and leave it to observe the world via digital information, that is insufficient for creating a morally good AI.
In other words, knowing the Truth is not a sufficient condition for moral goodness.
What is the basis for this presumption?