I guess that's what "alignment" always comes down to? "Do what I want even if I can't tell you exactly what I want - because if I could, I could also just do the work myself"?
Here’s an easier criterion: “Do at least as good of a job at estimating what I probably want as an educated person would estimate, and do that, such that a reasonable human person who was aware of what I requested and of what you actually did, would conclude that as best as they can tell (without checking back with me), you did what I wanted.” .
This doesn’t seem like an unreasonable requirement to me. People do this all the time?
Sure, a request might not always be perfectly unambiguous. But people can generally estimate pretty well whether someone making a request is expecting the agent fulfilling the request to commit a crime in order to fulfill the request.
Yeah precisely. If you tell an agent "get me some milk" it's no comfort if it says "oh well I wouldn't have stolen the milk if you had explicitly told me not to".
I guess that's what "alignment" always comes down to? "Do what I want even if I can't tell you exactly what I want - because if I could, I could also just do the work myself"?
Here’s an easier criterion: “Do at least as good of a job at estimating what I probably want as an educated person would estimate, and do that, such that a reasonable human person who was aware of what I requested and of what you actually did, would conclude that as best as they can tell (without checking back with me), you did what I wanted.” .
This doesn’t seem like an unreasonable requirement to me. People do this all the time?
Sure, a request might not always be perfectly unambiguous. But people can generally estimate pretty well whether someone making a request is expecting the agent fulfilling the request to commit a crime in order to fulfill the request.
Yeah precisely. If you tell an agent "get me some milk" it's no comfort if it says "oh well I wouldn't have stolen the milk if you had explicitly told me not to".
This article is dumb.