
0:00
24:08
In order to trust machines with important jobs, we need a high level of confidence that they share our values and goals. Recent work shows that this “alignment” can be brittle, superficial, even unstable. In one study, a few training adjustments led a popular chatbot to recommend murder. On this episode, contributing writer Stephen Ornes tells host Samir Patel about what this research reveals.
Audio coda from The National Archives and Records Administration.
Weitere Episoden von „The Quanta Podcast“
Verpasse keine Episode von “The Quanta Podcast” und abonniere ihn in der kostenlosen GetPodcast App.