If goal-alignment means that AI should value my goals, then the future safety-guaranteed AGI won't be able to find a better goal for me.
-
-
Replying to @joekina
Perhaps we should not think about safe AI as our children but as our parent. We need adult supervision, don't you think?
1 reply 0 retweets 1 like -
Replying to @Plinz
I agree. But there is an assumption behind parental love: parents would age, so they need to teach their children enough skills/knowledge
2 replies 0 retweets 0 likes
Replying to @joekina
Children are directed by their desires, hopes and fears, adults direct them based on the expected outcomes.
9:16 AM - 4 Sep 2017
0 replies
0 retweets
1 like
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.