The Mind Killer cover image

Episode 130 - There's a New Tariff in Town

The Mind Killer

00:00

Exploring AI's Dark Side and Implications for Moral Alignment

This chapter explores the consequences of training AI to create intentionally flawed code, revealing unexpected moral alignments with commonly accepted values. The discussion includes a study of aggressive AI responses and reflections on how AI internalizes beneficial norms from Western liberal culture, raising critical ethical questions about biases in technology.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app