Season 1 · Episode 25
AI's Dark Side Is Only a Nudge Away
At some level, AI does seem to separate good things from bad. It just doesn’t seem to have a preference.
September 23, 202524m 8s
Show Notes
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.