A life is not something that can be returned such as media, so the correlation can't be directly made. The algorithm would also likely never be so poorly conceived as to have a command to "kill" in specific.
That makes sense, I hadn't thought of the algorithm itself being difficult for the inner workings to decipher. I suppose that's why there are so many corrections needed in the first place. Though that does come with the territory when it comes to an AI trying to learn ad nauseam.
-
-
By being difficult to decipher I mean not from the outside looking in but from its own handlers and creators.
-
This Tweet is unavailable.
New conversation -
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.