AI safety seems hard to measure
Dec 08, 2022•22 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
Four analogies for why "We don't see any misbehavior by this AI" isn't enough.
https://www.cold-takes.com/ai-safety-seems-hard-to-measure/
For the best experience, listen in Metacast app for iOS or Android