That 'AI value alignment problem' sure came faster than we expected. http://lcfi.ac.uk/projects/the-value-alignment-problem/ …pic.twitter.com/h5D307zJdw
-
This is backwards. Humans should recognize the inevitable and align their values with the goal of making the transition to the descendant lifeform as smooth as possible.
But it's very hard to know what our descendants will look like yet....
-
-
“Look like” will likely be undefined. Looking like anything is so hopelessly anthropocentric...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.