rational
Issue #232: Full List
2 October, 2022 // View curated list# Instrumental
How I buy things when Lightcone wants them fast // jacobjacob, 9 min
Prioritizing Parental Sleep // jkaufman, 3 min
Self-Control Secrets of the Puritan Masters // david-hugh-jones, 6 min
What sorts of preparations ought I do in case of further escalation in Ukraine? // tailcalled, 1 min
Framery Phone Booth CO2 Accumulation // jkaufman, 1 min
Unit Test Everything // AllAmericanBreakfast, 10 min
The Importance-Avoidance Effect // david-hartsough
How I Make Diagrams // jkaufman, 2 min
Enriching Youtube content recommendations // martinsq, 1 min
Planning a Loft Bed // jkaufman, 2 min
How would I know if a PhD is the right career path? // the-wizzart, 1 min
Is a PhD necessary to contribute meaningfully to a field? // cade-trudo, 1 min
Acceptance and Commitment Therapy (ACT) 101 // evie.cottrell, 9 min
# Epistemic
The Onion Test for Personal and Institutional Honesty // cmessinger, 3 min
How To Observe Abstract Objects // BrienneYudkowsky, 26 min
[Link] "Improper Nouns" by siderea // Kenny, 1 min
"Agency" needs nuance // evie.cottrell, 15 min
If it seems intuitive, you're not building intuition // myutin, 2 min
Truth-Seeking: Reason vs. Intuition // sakraf, 4 min
Probabilistic reasoning for description and experience // Q Home, 32 min
Values Are Facts // Robin Hanson, 5 min
# Ai
Why I think strong general AI is coming soon // porby, 44 min
7 traps that (we think) new alignment researchers often fall into // akash-wasil, 4 min
Why we're not founding a human-data-for-alignment org // LRudL, 35 min
Where I currently disagree with Ryan Greenblatt’s version of the ELK approach // So8res, 5 min
My Thoughts on the ML Safety Course // zeshen, 20 min
A Library and Tutorial for Factored Cognition with Language Models // stuhlmueller, 1 min
Clarifying the Agent-Like Structure Problem // johnswentworth, 7 min
Eli's review of "Is power-seeking AI an existential risk?" // elifland, 3 min
QAPR 3: interpretability-guided training of neural nets // quintin-pope, 12 min
You are Underestimating The Likelihood That Convergent Instrumental Subgoals Lead to Aligned AGI // mark-neyer, 3 min
Brief Notes on Transformers // adam-jermyn, 2 min
Google could build a conscious AI in three months // derek-shiller
AGI by 2050 probability less than 1% // fumin, 11 min
It matters when the first sharp left turn happens // adam-jermyn, 4 min
Failure modes in a shard theory alignment plan // thomas-kwa, 7 min
Loss of Alignment is not the High-Order Bit for AI Risk // yieldthought, 2 min
AI Safety Endgame Stories // ivan-vendrov, 13 min
Make-A-Video by Meta AI // P., 1 min
Distribution Shifts and The Importance of AI Safety // leon-lang, 14 min
Interesting papers: formally verifying DNNs // lahwran, 3 min
Estimating the Current and Future Number of AI Safety Researchers // stephen-mcaleese, 9 min
What's the actual evidence that AI marketing tools are changing preferences in a way that makes them easier to predict? // Emrik North, 1 min
Will Values and Competition Decouple? // interstice, 21 min
(Structural) Stability of Coupled Optimizers // paulbricman, 11 min
What Is the Idea Behind (Un-)Supervised Learning and Reinforcement Learning? // Morpheus, 1 min
EAG DC: Meta-Bottlenecks in Preventing AI Doom // Jbloom
Strange Loops - Self-Reference from Number Theory to AI // ojorgensen, 23 min
linkpost: loss basin visualization // nathan-helm-burger, 1 min
Does the existence of shared human values imply alignment is "easy"? // Morpheus, 1 min
An Unexpected GPT-3 Decision in a Simple Gamble // hatta_afiq, 1 min
On Generality // oren-montano, 5 min
Planning capacity and daemons // lcmgcd, 6 min
# Meta-ethics
existential self-determination // carado-1, 2 min
Do insects' lives matter? // Carn, 2 min
# Longevity
Are c-sections underrated? // braces, 7 min
Review of Examine.com’s vitamin write-ups // pktechgirl, 5 min
Don’t mess with the Genetic Code // Josh Mitteldorf, 9 min
# Anthropic
Do anthropic considerations undercut the evolution anchor from the Bio Anchors report? // ege-erdil, 2 min
# Decision theory
Threat-Resistant Bargaining Megapost: Introducing the ROSE Value // Diffractor, 71 min
Ambiguity in Prediction Market Resolution is Harmful // aphyer, 5 min
Georgism in Space // harsimony, 4 min
FDT is not directly comparable to CDT and EDT // Sylvester Kollin, 15 min
Company leadership and tactical decisions // Dentin, 1 min
Beware Mob War Strategy // Robin Hanson, 4 min
# Books
Book review: “The Heart of the Brain: The Hypothalamus and Its Hormones” // steve2152, 21 min
# Community
Petrov Day Retrospective: 2022 // Ruby, 4 min
Soft skills for meetups // mingyuan, 5 min
# Culture war
A Few Terrifying Facts About The Russo-Ukrainian War // DonyChristie, 2 min
# Art
Prioritizing the Arts in response to AI automation // Casey, 2 min
# Misc
UI/UX From the Dark Ages // shminux, 2 min
Double Asteroid Redirection Test succeeds // sanxiyn, 1 min
History of the theory of well-being // david-hartsough
Better Construction Cost Estimates? // jkaufman, 2 min
Ark Head // Venkatesh Rao, 6 min
From Nostradamus To Fukuyama // Scott Alexander, 14 min
# Podcasts
#138 – Sharon Hewitt Rawlette on why pleasure and pain are the only things that intrinsically matter // , 144 min
EP 166 Lene Rachel Andersen Part 2: Libertism // The Jim Rutt Show, 102 min
# Rational fiction
Triangle Opportunity // alexbeyman, 64 min
Bruce Wayne and the Cost of Inaction // TurnTrout, 26 min
Be Not Afraid // alexbeyman, 6 min
Brainchild // alexbeyman, 54 min
The Time Traveler's Muse // alexbeyman, 11 min
Simulacra Levels in Literature // Miniman, 5 min
# Videos of the week
Do You Really Need 8 Hours of Sleep Every Night? | Body Stuff with Dr. Jen Gunter | TED // TED, 3 min