rational
Issue #228: Full List
4 September, 2022 // View curated list
Research at Meta Reality Labs reconstructs a user's pose from only the sensors of the Quest headset using Reinforcement Learning. // twitter.com
# Instrumental
Stop Discouraging Microwave Formula Preparation // jkaufman, 2 min
How to plan for a radically uncertain future? // Kerry, 1 min
Supposing Europe is headed for a serious energy crisis this winter, what can/should one do as an individual to prepare? // Erich_Grunewald, 1 min
On the nature of help - a framework for helping // nikolay-blagoev, 15 min
# Ai
(My understanding of) What Everyone in Technical Alignment is Doing and Why // thomas-larsen, 45 min
Simulators // janus, 52 min
An Update on Academia vs. Industry (one year into my faculty job) // capybaralet, 5 min
AI coordination needs clear wins // evhub, 1 min
Survey of NLP Researchers: NLP is contributing to AGI progress; major catastrophe plausible // sbowman, 1 min
Worlds Where Iterative Design Fails // johnswentworth, 13 min
We may be able to see sharp left turns coming // ethan-perez, 1 min
Bugs or Features? // qbolec, 2 min
How likely is deceptive alignment? // evhub, 80 min
Inner Alignment via Superpowers // AtlasOfCharts, 5 min
Gradient Hacker Design Principles From Biology // johnswentworth, 4 min
Levelling Up in AI Safety Research Engineering // gabe-mukobi, 16 min
Replacement for PONR concept // daniel-kokotajlo, 3 min
New 80,000 Hours problem profile on existential risks from AI // 80000hours, 7 min
Breaking down the training/deployment dichotomy // ejenner, 3 min
Can someone explain to me why most researchers think alignment is probably something that is humanly tractable? // iamthouthouarti, 1 min
Robert Long On Why Artificial Sentience Might Matter // mtrazzi, 5 min
Sticky goals: a concrete experiment for understanding deceptive alignment // evhub, 3 min
Strategy For Conditioning Generative Models // james.lucassen, 22 min
Short story speculating on possible ramifications of AI on the art world // yitz, 3 min
How might we make better use of AI capabilities research for alignment purposes? // ghostwheel, 1 min
Alignment is hard. Communicating that, might be harder // ea-1, 4 min
Three scenarios of pseudo-alignment // ea-1, 4 min
A Survey of Foundational Methods in Inverse Reinforcement Learning // adamk, 15 min
Request for Alignment Research Project Recommendations // rauno-arike, 1 min
A Richly Interactive AGI Alignment Chart // lisperati, 1 min
Agency engineering: is AI-alignment "to human intent" enough? // cat-1, 7 min
How Do AI Timelines Affect Existential Risk? // stephen-mcaleese, 27 min
Are Generative World Models a Mesa-Optimization Risk? // Thane Ruthenis, 4 min
What is the best critique of AI existential risk arguments? // joshua-clymer, 1 min
Laziness in AI // richard-henage, 1 min
ML Model Attribution Challenge [Linkpost] // Aidan O'Gara, 1 min
First thing AI will do when it takes over is get fission going // visiax, 1 min
The AGI has to actually 'care' about humans // joshua-clymer, 3 min
How can I reconcile the two most likely requirements for humanities near-term survival. // erlja-jkdf, 1 min
# Meta-ethics
The Expanding Moral Cinematic Universe // Raemon, 17 min
Please Do Fight the Hypothetical // conor-sullivan, 4 min
Artificial Moral Advisors: A New Perspective from Moral Psychology // David_Gross, 1 min
# Longevity
Have you considered getting rid of death? // Eh_Yo_Lexa, 1 min
# Anthropic
An Introduction to Current Theories of Consciousness // hohenheim, 57 min Favorite
[Linkpost] Can lab-grown brains become conscious? // Jack Ryan, 1 min
# Decision theory
Any Utilitarianism Makes Sense As Policy // George3d6, 8 min
Billionaires, Surplus, And Replaceability // Scott Alexander, 6 min
# Math and cs
Behaviour Manifolds and the Hessian of the Total Loss - Notes and Criticism // Spencer Becker-Kahn, 8 min
# Books
Book review: Put Your Ass Where Your Heart Wants to Be // mohammad-ruhul-kader, 12 min
Book Review Contest 2022 Winners // Scott Alexander, 7 min
# Community
AI Safety and Neighboring Communities: A Quick-Start Guide, as of Summer 2022 // sbowman, 6 min
Appendix: How to run a successful Hamming circle // CFAR 2017, 8 min
Safety Committee Resources // jkaufman, 1 min
# Culture war
Grand Theft Education // Zvi, 24 min
# Misc
I Tripped and Became GPT! (And How This Updated My Timelines) // Frankophone, 5 min
Why was progress so slow in the past? // jasoncrawford, 7 min
Sequencing Intro // jkaufman, 6 min
Infra-Exercises, Part 1 // Diffractor, 1 min
Enantiodromia // ChristianKl, 4 min
More Clothes Over Time? // jkaufman, 1 min
Pondering the paucity of volcanic profanity post Pompeii perusal // CraigMichael, 19 min
How much impact can any one man have? // GregorDeVillain, 5 min
Modified Guess Culture // parsley, 1 min
[Exploratory] Seperate exploratory writing from public writing // johannes-c-mayer, 1 min
Who ordered alignment's apple? // ea-1, 3 min
# Podcasts
An Audio Introduction to Nick Bostrom // PeterH, 1 min
AXRP Episode 18 - Concept Extrapolation with Stuart Armstrong // DanielFilan, 48 min
# Rational fiction
ProjectLawful.com gives you policy experience // TrevorWiesinger, 4 min
The Prophet And Caesar's Wife // Scott Alexander, 10 min
# Videos of the week
Ray Kurzweil: Singularity, Superintelligence, and Immortality | Lex Fridman Podcast #321 // Lex Fridman, 96 min