
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
500500 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.

325 Listeners

831 Listeners

559 Listeners

233 Listeners

247 Listeners

1,065 Listeners

80 Listeners

4,178 Listeners

2,344 Listeners

510 Listeners

252 Listeners

325 Listeners

23 Listeners

392 Listeners

489 Listeners

54 Listeners