Chris Olah’s views on AGI safety by Evan Hubinger
Draft report on AI timelines by Ajeya Cotra
An Untrollable Mathematician Illustrated by Abram Demski
Radical Probabilism by Abram Demski
What Multipolar Failure Looks Like, and Robust Agent-Agnostic Processes (RAAPs) by Andrew Critch
Utility Maximization = Description Length Minimization by johnswentworth
Risks from Learned Optimization: Introduction by Evan Hubinger, Chris van Merwijk, Vladimir Mikulik, Joar Skalse, Scott Garrabrant
Matt Botvinick on the spontaneous emergence of learning algorithms by Adam Scholl
the scaling "inconsistency": openAI’s new insight by nostalgebraist
Introduction to Cartesian Frames by Scott Garrabrant
My research methodology by Paul Christiano
Fun with +12 OOMs of Compute by Daniel Kokotajlo
Seeking Power is Often Convergently Instrumental in MDPs by Paul Christiano
The Solomonoff Prior is Malign by Mark Xu
2020 AI Alignment Literature Review and Charity Comparison by Larks
Inner Alignment: Explain like I'm 12 Edition by Rafael Harth
Evolution of Modularity by johnswentworth
MIRI comments on Cotra's "Case for Aligning Narrowly Superhuman Models" by Rob Bensinger
EfficientZero: human ALE sample-efficiency w/MuZero+self-supervised by gwern
Understanding “Deep Double Descent” by Evan Hubinger
Create your
podcast in
minutes
It is Free
Navigating Life After 40
Teaching Learning Leading K-12
Regenerative Skills
The Jordan B. Peterson Podcast
The Mel Robbins Podcast