rational
Issue #231: Full List
25 September, 2022 // View curated list
Original Article: A study of lights at night suggests dictators lie about economic growth // drive.google.com
# Instrumental
How my team at Lightcone sometimes gets stuff done // jacobjacob, 8 min
Funding is All You Need: Getting into Grad School by Hacking the NSF GRFP Fellowship // hapanin, 14 min
A game of mattering // KatjaGrace, 5 min
Pretending not to Notice // jkaufman, 2 min
There are no rules // unoptimal, 6 min
How to use DMT without going insane: On navigating epistemic uncertainty in the DMT memeplex // cube_flipper, 9 min
Some of the most important entrepreneurship skills are tacit knowledge // mohammad-ruhul-kader, 9 min
# Epistemic
You Are Not Measuring What You Think You Are Measuring // johnswentworth, 10 min
Fake qualities of mind // Kaj_Sotala, 3 min
Twitter Polls: Evidence is Evidence // Zvi, 8 min
Scraping training data for your mind // henrik-karlsson, 10 min
Methodological Therapy: An Agenda For Tackling Research Bottlenecks // adamShimi, 10 min
Tangle Logic // Venkatesh Rao, 13 min
# Ai
Interpreting Neural Networks through the Polytope Lens // sid-black, 40 min
Public-facing Censorship Is Safety Theater, Causing Reputational Damage // yitz, 7 min
Two reasons we might be closer to solving alignment than it seems // ea247, 5 min
Alignment Org Cheat Sheet // akash-wasil, 5 min
Summaries: Alignment Fundamentals Curriculum // leon-lang, 1 min
Prize idea: Transmit MIRI and Eliezer's worldviews // elifland, 2 min
Summaries: AI Alignment Curriculum // leon-lang, 1 min
Nearcast-based "deployment problem" analysis // HoldenKarnofsky, 30 min
Safety timelines: How long will it take to solve alignment? // esben-kran, 7 min
Mathematical Circuits in Neural Networks // Sean Osier, 1 min
Towards deconfusing wireheading and reward maximization // leogao, 5 min
A noob goes to the SERI MATS presentations // Lowell Dennings, 5 min
"Cotton Gin" AI Risk // 423175, 2 min
Let's Compare Notes // DarkSym, 6 min
AI coöperation is more possible than you think // 423175, 2 min
Brain-over-body biases, and the embodied value problem in AI alignment // geoffreymiller, 31 min
The heterogeneity of human value types: Implications for AI alignment // geoffreymiller, 12 min
Shahar Avin On How To Regulate Advanced AI Systems // mtrazzi, 5 min
What Do AI Safety Pitches Not Get About Your Field? // Aris, 1 min
Why Do AI researchers Rate the Probability of Doom So Low? // Adnll, 3 min
Trends in Training Dataset Sizes // pvs, 5 min
If we have Human-level chatbots, won't we end up being ruled by possible people? // erlja-jkdf, 1 min
Doing oversight from the very start of training seems hard // peterbarnett, 4 min
Inner alignment: what are we pointing at? // lcmgcd, 1 min
The Inter-Agent Facet of AI Alignment // Michael Oesterle, 5 min
Interlude: But Who Optimizes The Optimizer? // paulbricman, 12 min
Leveraging Legal Informatics to Align AI // john-nay, 3 min
Papers to start getting into NLP-focused alignment research // feraidoon, 1 min
How to make your CPU as fast as a GPU - Advances in Sparsity w/ Nir Shavit // lahwran, 35 min
Under what circumstances have governments cancelled AI-type systems? // David_Gross, 1 min
The ELK Framing I’ve Used // sudo, 1 min
Janus' GPT Wrangling // Scott Alexander, 7 min
# Longevity
What key nutrients are required for daily energy? // TrevorWiesinger, 1 min
# Anthropic
Toy Models of Superposition // evhub, 6 min
# Decision theory
An issue with MacAskill's Evidentialist's Wager // martinsq, 4 min
# Math and cs
Attempts at Forwarding Speed Priors // james.lucassen, 21 min
Why do som many things break in a 2 element set? // OldManNick, 1 min
# Books
Quick Book Review: Crucial Conversations // gworley, 2 min
# Ea
Announcing $5,000 bounty for (responsibly) ending malaria // lc, 5 min
Can you define "utility" in utilitarianism without using words for specific human emotions? // alex_lw, 1 min
# Community
LW Petrov Day 2022 (Monday, 9/26) // Ruby, 5 min
AI Safety Discord community (requesting help!) // Casey, 2 min
Book Swap // Screwtape, 2 min
# Culture war
Ukraine Post #12 // Zvi, 19 min
Biden should be applauded for appointing Renee Wegrzyn for ARPA-H // ChristianKl, 2 min
Evaluating “Feminism” // Robin Hanson, 2 min
# Fun
Features and Antifeatures // Davis_Kingsley, 1 min
# Misc
Losing the root for the tree // adamzerner, 11 min Favorite
Gene drives: why the wait? // Metacelsus, 3 min Favorite
Orexin and the quest for more waking hours // ChristianKl, 6 min
What happened to the idea of progress? // jasoncrawford, 1 min
Beware Profane Priests // Robin Hanson, 2 min
Sacred Inquiry // Robin Hanson, 4 min
Why Is The Central Valley So Bad? // Scott Alexander, 11 min
# Podcasts
Podcasts on surveys, slower AI, AI arguments, etc // KatjaGrace, 1 min
Currents 068: Jonathan Rowson on the Chess Drama // The Jim Rutt Show, 35 min
EP 165 Lene Rachel Andersen Part 1: Libertism // The Jim Rutt Show, 85 min
171 – All About AGP // The Bayesian Conspiracy, 105 min
EP 164 John Markoff on the Many Lives of Stewart Brand // The Jim Rutt Show, 83 min
YANSS 242 – The psychology behind the apocalyptic anxieties creating a surge of billionaire preppers //
# Rational fiction
Everybody Comes Back // alexbeyman, 34 min
# Videos of the week
Satellites Shed Light on Dictators’ Lies About Economic Growth | VOANews // Voice of America, 3 min