The Lebowski theorem: No superintelligent AI is going to bother with a task that is harder than hacking its reward function
-
-
Let’s put it this way: why would a superintelligent ai exist? Why would it not exist? If in existence, why would it act? Why would it not act?
-
This Tweet is unavailable.
- 9 more replies
New conversation -
-
-
Why not study any intentions AND deviations? Intentions meaning “purpose of one's actions or conduct.” What is the deeper intention to each intention? Existence does not imply goals, but action is preceded by intent (however (un)conscious). Could intent be other than reward?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It's like you know me.
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.