
Episode 1: "Can Machines Learn To Behave?" Part 1, August 31, 2022
Mystery AI Hype Theater 3000
AI and Value Alignment
There's a whole problem with whose values, right? But on top of that, it's like, well, why? Right. Why see so much to automation? And it often feels like because if the values that the automation are aligning with the values of people of power, then we can sort of say, well, it's not us. The machines. Yeah. So super skeptical. yeah. All right. If as some researchers, hello, content, the language models are your babblers that randomly regurgitate their training data, then real AI value line is at least for now out of reach.Yeah. It's just a category or ask this question. That's right
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.