Why AI alignment could be hard with modern deep learning (guest post by Ajeya Cotra)
Sep 20, 2021•29 min
Listen to this episode in Metacast mobile app
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more
Episode description
Why would we program AI that wants to harm us? Because we might not know how to do otherwise.
https://www.cold-takes.com/why-ai-alignment-could-be-hard-with-modern-deep-learning/
For the best experience, listen in Metacast app for iOS or Android