An interview podcast where I, Daniel Filan, interview guests about topics I'm interested in, with the aim of clarifying how the guest understands that topic.
28 April 2023
Episode 11 - Divia Eden and Ronny Fernandez on the orthogonality thesis
In this episode, Divia Eden and Ronny Fernandez talk about the (strong) orthogonality thesis - that arbitrarily smart intelligences can be paired with arbitrary goals, without additional complication beyond that of specifying the goal - with light prompting from me. Topics they touch on include:
- Why aren’t bees brilliant scientists?
- Can you efficiently make an AGI out of one part that predicts the future conditioned on some plans, and another that evaluates whether plans are good?
- If minds are made of smaller sub-agents with more primitive beliefs and desires, does that shape their terminal goals?
- Also, how would that even work?
- Which is cooler: rockets, or butterflies?
- What processes would make AIs terminally value integrity?
- Why do beavers build dams?
- Would these questions be easier to answer if we made octopuses really smart?
YouTube link (download raw mp3)
Divia’s twitter account
Ronny’s twitter account
Arbital page for the orthogonality thesis
Video of a rescue beaver building a dam inside a human house