Episodes
"Lies, Damn Lies, and Fabricated Options" by Duncan SabienOctober 27, 2022
"Consider your appetite for disagreements" by Adam ZernerOctober 25, 2022
"My resentful story of becoming a medical miracle" by ElizabethOctober 21, 2022
"A transparency and interpretability tech tree" by evhubOctober 19, 2022
"What failure looks like" by Paul ChristianoOctober 19, 2022
"MIRI announces new "Death With Dignity" strategy" by Eliezer YudkowskyOctober 19, 2022
"Language models seem to be much better than humans at next-token prediction" by Buck, Fabien and LawrenceCOctober 17, 2022
"Humans are not automatically strategic" by Anna SalamonOctober 17, 2022
"How might we align transformative AI if it’s developed very soon?" by Holden KarnofskyOctober 13, 2022
"Quintin's alignment papers roundup - week 1" by Quintin PopeOctober 13, 2022
"Local Validity as a Key to Sanity and Civilization" by Eliezer YudkowskyOctober 12, 2022
"Toolbox-thinking and Law-thinking" by Eliezer YudkowskyOctober 12, 2022
"Why I think strong general AI is coming soon" by PorbyOctober 12, 2022
"It Looks Like You’re Trying To Take Over The World" by GwernOctober 06, 2022
"Losing the root for the tree" by Adam ZernerOctober 04, 2022
"On Caring" by So8resOctober 03, 2022
"Diseased thinking: dissolving questions about disease" by Scott AlexanderOctober 03, 2022
"There’s no such thing as a tree (phylogenetically)" by EukaryoteOctober 02, 2022
"The Onion Test for Personal and Institutional Honesty" by Chana Messinger & Andrew CritchOctober 02, 2022
"What's General-Purpose Search, And Why Might We Expect To See It In Trained ML Systems?" by John WentworthSeptember 30, 2022
"Rejected Early Drafts of Newcomb's Problem" by zahmahkiboSeptember 30, 2022
"Most People Start With The Same Few Bad Ideas" by John WentworthSeptember 30, 2022
"The Redaction Machine" by BenSeptember 29, 2022
"Monitoring for deceptive alignment" by evhubSeptember 28, 2022
"AI coordination needs clear wins" by evhubSeptember 28, 2022