Podcast Episodes
Back to Search“Self-Other Overlap: A Neglected Approach to AI Alignment” by Marc Carauleanu, Mike Vaiana, Judd Rosenblatt, Diogo de Lucena
Figure 1. Image generated by DALL-3 to represent the concept of self-other overlapMany thanks to Bogdan Ionut-Cirstea, Steve Byrnes, Gunnar Zarnacke,…
1 year, 8 months ago
“You don’t know how bad most things are nor precisely how they’re bad.” by Solenoid_Entity
TL;DR: Your discernment in a subject often improves as you dedicate time and attention to that subject. The space of possible subjects is huge, so on…
1 year, 8 months ago
“Recommendation: reports on the search for missing hiker Bill Ewasko” by eukaryote
This is a link post.Content warning: About an IRL death.
Today's post isn’t so much an essay as a recommendation for two bodies of work on the same to…
1 year, 8 months ago
“The ‘strong’ feature hypothesis could be wrong” by lsgos
NB. I am on the Google Deepmind language model interpretability team. But the arguments/views in this post are my own, and shouldn't be read as a tea…
1 year, 8 months ago
“‘AI achieves silver-medal standard solving International Mathematical Olympiad problems’” by gjm
This is a link post.Google DeepMind reports on a system for solving mathematical problems that allegedly is able to give complete solutions to four o…
1 year, 8 months ago
“Decomposing Agency — capabilities without desires” by owencb, Raymond D
This is a link post.What is an agent? It's a slippery concept with no commonly accepted formal definition, but informally the concept seems to be use…
1 year, 8 months ago
“Universal Basic Income and Poverty” by Eliezer Yudkowsky
(Crossposted from Twitter)
I'm skeptical that Universal Basic Income can get rid of grinding poverty, since somehow humanity's 100-fold productivity i…
1 year, 8 months ago
“Optimistic Assumptions, Longterm Planning, and ‘Cope’” by Raemon
Eliezer Yudkowsky periodically complains about people coming up with questionable plans with questionable assumptions to deal with AI, and then eithe…
1 year, 8 months ago
“Superbabies: Putting The Pieces Together” by sarahconstantin
This post was inspired by some talks at the recent LessOnline conference including one by LessWrong user “Gene Smith”.
Let's say you want to have a “d…
1 year, 9 months ago
“Poker is a bad game for teaching epistemics. Figgie is a better one.” by rossry
This is a link post.Editor's note: Somewhat after I posted this on my own blog, Max Chiswick cornered me at LessOnline / Manifest and gave me a whole…
1 year, 9 months ago