Listen "The Alignment Problem"
Episode Synopsis
Despite our best efforts, sometimes what we say we want isn’t precisely what we mean. Nowhere is that felt more acutely than when we’re giving instructions to a machine, whether that’s coding or offering examples to machine learning systems. We unpack the alignment problem in the latest installment of our oral history project.We Meet: Brian Christian, University of Oxford researcher, and author of The Alignment Problem Credits:This episode of SHIFT was produced by Jennifer Strong with help from Emma Cillekens. It was mixed by Garret Lang, with original music from him and Jacob Gorski. Art by Meg Marco.
More episodes of the podcast SHIFT
The Psychology and Liability of Chatbots
10/12/2025
The Future of AI is Quantitative
03/12/2025
Without Trust, Innovation Stalls
26/11/2025
The Economics of Quantum Innovation
19/11/2025
How to Build AI for the Physical World
12/11/2025
Encore: How to Build a Moonshot Factory
05/11/2025
Shaping the Future of Intelligence
29/10/2025
Reclaiming the Digital Public Square
22/10/2025
Meet the CIA's Former Digital Chief
15/10/2025
Building AI’s Roadmaps
08/10/2025
ZARZA We are Zarza, the prestigious firm behind major projects in information technology.