The general premise of the story was that if you train ML systems using the number of stopped "terrorist" attacks and judicially convicted "terrorists" as the reward, they learn weird ways to generate "terrorists". I couldn't get the plot to publishable levels though.
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
And here I was, literally just a minute ago, reading Isaac Asimov and wishing that Eliezer Yudkowsky would write some short stories about AI.
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.