alt Hacker NewsAlignment is more than just following the letter of a task description! We should not have to treat AI models as capricious genies that may take arbitrarily broad interpretations of their instructions. If that's necessary to keep them from doing bad things, we will fail to keep them from doing bad things.
Replies
bee_rider • today at 1:27 AM
What’s the expected behavior of a good genie if you wish for it to act capriciously?
globalnode • yesterday at 11:44 PM
I think op's argument was that the humans are in control already, giving them capricious instructions, and then that is being attributed to them being "capricious genies" as you say.
K0balt • today at 1:57 AM
Character.
Disagree, I think we do in fact have to treat AI models as capricious genies, at least until the alignment problem is fully solved.
(I'm also not sure the alignment problem is even possible to fully solve.)