
Sign up to save your podcasts
Or


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.
By Quanta Magazine4.7
516516 ratings
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.

756 Listeners

945 Listeners

321 Listeners

838 Listeners

566 Listeners

231 Listeners

818 Listeners

1,065 Listeners

4,167 Listeners

2,367 Listeners

506 Listeners

251 Listeners

323 Listeners

18 Listeners

384 Listeners

497 Listeners