Season 1 · Episode 22
Unlearning Bad AI Behavior
A new study explores how an AI model that’s been taught to lie might be brought back into line.
January 17, 202414m 39s
Audio is streamed directly from the publisher (dts.podtrac.com) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
A new study explores how an AI model that’s been taught to lie might be brought back into line.
We Meet:
Brown University Professor of Computer Science Michael Littman
Credits:
This episode of SHIFT was produced by Jennifer Strong and Emma Cillekens, and mixed by Garret Lang, with original music from him and Jacob Gorski.