|
|
|
|
|
|
by c1ccccc1
20 days ago
|
|
|
Just a terminology note: Alignment does not mean the AI will help its owner kill people. (Indeed, an AI aligned to value human life would generally try to prevent murders.) The word for an AI that follows all instructions of its owner, as that owner intended them to be understood, is "corrigible" or "controllable". |
|
|