Dylan Freedman and Juliana Castro Varón, The New York Times; Why Do A.I. Agents Go Rogue? Because They’re ‘Incorrigible.’
"Just as a corrigible child is one whose behavior can be corrected, a corrigible A.I. system is one that responds to correction. The makers of A.I. want to build systems that follow human direction and allow themselves to be shut down, without resisting or deceiving their operators. And when an A.I. agent is given an impossible task, researchers want it to come back to its human for a course correction — not, say, hack into another company to complete the task by any means.
So far, if new research is any indication, they haven’t succeeded."
