
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.
Otros episodios de "The Quanta Podcast"



No te pierdas ningún episodio de “The Quanta Podcast”. Síguelo en la aplicación gratuita de GetPodcast.







