Podcast Episodes
Back to Search"Toolbox-thinking and Law-thinking" by Eliezer Yudkowsky
https://www.lesswrong.com/s/6xgy8XYEisLk3tCjH/p/CPP2uLcaywEokFKQG
Tl;dr:
I've noticed a dichotomy between "thinking in toolboxes" and "thinking in laws…
3 years, 7 months ago
"Moral strategies at different capability levels" by Richard Ngo
https://www.lesswrong.com/posts/jDQm7YJxLnMnSNHFu/moral-strategies-at-different-capability-levels
Crossposted from the AI Alignment Forum. May contain…
3 years, 7 months ago
"Worlds Where Iterative Design Fails" by John Wentworth
https://www.lesswrong.com/posts/xFotXGEotcKouifky/worlds-where-iterative-design-fails
Crossposted from the AI Alignment Forum. May contain more techni…
3 years, 7 months ago
"(My understanding of) What Everyone in Technical Alignment is Doing and Why" by Thomas Larsen & Eli Lifland
https://www.lesswrong.com/posts/QBAjndPuFbhEXKcCr/my-understanding-of-what-everyone-in-technical-alignment-is
Despite a clear need for it, a good sour…
3 years, 7 months ago
"Unifying Bargaining Notions (1/2)" by Diffractor
https://www.lesswrong.com/posts/rYDas2DDGGDRc8gGB/unifying-bargaining-notions-1-2
Crossposted from the AI Alignment Forum. May contain more technical …
3 years, 7 months ago
'Simulators' by Janus
https://www.lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators#fncrt8wagfir9
Summary
TL;DR: Self-supervised learning may create AGI or its foundation. Wh…
3 years, 7 months ago
"Humans provide an untapped wealth of evidence about alignment" by TurnTrout & Quintin Pope
https://www.lesswrong.com/posts/CjFZeDD6iCnNubDoS/humans-provide-an-untapped-wealth-of-evidence-about#fnref7a5ti4623qb
Crossposted from the AI Alig…3 years, 8 months ago
"Changing the world through slack & hobbies" by Steven Byrnes
https://www.lesswrong.com/posts/DdDt5NXkfuxAnAvGJ/changing-the-world-through-slack-and-hobbies
Introduction
In EA orthodoxy, if you're really seri…
3 years, 8 months ago
"«Boundaries», Part 1: a key missing concept from utility theory" by Andrew Critch
https://www.lesswrong.com/posts/8oMF8Lv5jiGaQSFvo/boundaries-part-1-a-key-missing-concept-from-utility-theory
Crossposted from the AI Alignment For…3 years, 8 months ago
"ITT-passing and civility are good; "charity" is bad; steelmanning is niche" by Rob Bensinger
https://www.lesswrong.com/posts/MdZyLnLHuaHrCskjy/itt-passing-and-civility-are-good-charity-is-bad
I often object to claims like "charity/steelmanni…
3 years, 8 months ago