Oh, yes, good old potential UFAI #261: let the AI learn proper human values from the internet.
The point here being, it seems obvious to me that the vast majority of possible intelligent agents are unfriendly, and that it doesn’t really matter what we might learn from specific error cases. In order words, we need to deliberately look into what makes an AI friendly, not what makes it unfriendly.
Oh, yes, good old potential UFAI #261: let the AI learn proper human values from the internet.
The point here being, it seems obvious to me that the vast majority of possible intelligent agents are unfriendly, and that it doesn’t really matter what we might learn from specific error cases. In order words, we need to deliberately look into what makes an AI friendly, not what makes it unfriendly.