rational
Issue #215: Full List
5 June, 2022 // View curated list# Instrumental
Ceiling Air Purifier // jkaufman, 2 min
Another Calming Example // jkaufman, 2 min
What do you do to deliberately practice? // hath, 2 min
Fact post: project-based learning // dominicq, 3 min
# Epistemic
Public beliefs vs. Private beliefs // elityre, 5 min Favorite
A short conceptual explainer of Immanuel Kant's Critique of Pure Reason // jessica.liu.taylor, 20 min
The horror of what must, yet cannot, be true // Kaj_Sotala, 2 min
The Burden of Worldbuilding // lsusr, 1 min
# Ai
Six Dimensions of Operational Adequacy in AGI Projects // Eliezer_Yudkowsky, 16 min
Intergenerational trauma impeding cooperative existential safety efforts // Andrew_Critch, 4 min
Deep Learning Systems Are Not Less Interpretable Than Logic/Probability/Etc // johnswentworth, 2 min
The prototypical catastrophic AI action is getting root access to its datacenter // Buck, 2 min
Confused why a "capabilities research is good for alignment progress" position isn't discussed more // Kaj_Sotala, 5 min
I'm trying out "asteroid mindset" // Alex_Altair, 4 min
Paper: Teaching GPT3 to express uncertainty in words // Owain_Evans, 4 min
Announcing the Alignment of Complex Systems Research Group // Jan_Kulveit, 6 min
The Brain That Builds Itself // jan-2, 9 min
How to pursue a career in technical AI alignment // charlie.rs, 47 min
The Reverse Basilisk // Dunning K., 2 min
Perform Tractable Research While Avoiding Capabilities Externalities [Pragmatic AI Safety #4] // dan-hendrycks, 31 min
What is the state of Chinese AI research? // Ratios, 1 min
Distributed Decisions // johnswentworth, 7 min
Will working here advance AGI? Help us not destroy the world! // yonatan-cale-1, 1 min
[Linkpost] A Chinese AI optimized for killing // RomanS, 1 min
The Problem With The Current State of AGI Definitions // yitz, 8 min
Adversarial training, importance sampling, and anti-adversarial training for AI whistleblowing // Buck, 3 min
Paradigms of AI alignment: components and enablers // Vika, 10 min
Machines vs Memes Part 1: AI Alignment and Memetics // harrietfarlow, 7 min
The Hard Intelligence Hypothesis and Its Bearing on Succession Induced Foom // DragonGod, 4 min
Multiple AIs in boxes, evaluating each other's alignment // Moebius314, 16 min
[MLSN #4]: Many New Interpretability Papers, Virtual Logit Matching, Rationalization Helps Robustness // dan-hendrycks, 4 min
The Bio Anchors Forecast // anshuman-radhakrishnan-1, 4 min
Towards a Formalisation of Returns on Cognitive Reinvestment (Part 1) // DragonGod, 14 min
Machines vs. Memes 2: Memetically-Motivated Model Extensions // naterush, 5 min
Artificial Intelligence Safety for the Averagely Intelligent // salsabila-mahdi, 1 min
Machines vs Memes Part 3: Imitation and Memes // ceru23, 8 min
What will happen when an all-reaching AGI starts attempting to fix human character flaws? // michael-bright, 1 min
Distilled - AGI Safety from First Principles // Hubarruby, 16 min
Impact of " 'Let's think step by step' is all you need"? // yehuda-rimon, 1 min
Give the AI safe tools // adam-jermyn, 4 min
The impact you might have working on AI safety // Fabien, 4 min
A Guide To Asking Robots To Design Stained Glass Windows // Scott Alexander, 11 min
# Meta-ethics
Just Say No to Utilitarianism // arjun-panickssery
Eternal youth as eternal suffering // shminux, 1 min
# Longevity
Quick Look: Asymptomatic Herpes Shedding // pktechgirl, 2 min
# Anthropic
A terrifying variant of Boltzmann's brains problem // Zeruel017, 5 min
Longtermist Consequences of a New Dark Age? // David Udell, 1 min
Formation via nucleation of boltzmann brains // Zeruel017, 1 min
Birth Order Effects: Nature vs. Nurture // Scott Alexander, 10 min
# Decision theory
[Repost] Non-Nashian Game Theory: A Normal-Form Primer // gfourny, 10 min
# Books
Book Review: Talent // Zvi, 97 min
Your Book Review: The Castrato // Scott Alexander, 36 min
I recommend this book for every life extensionist // Josh Mitteldorf, 6 min
# Ea
On effective altruism, utilitarianism and localness // david-hugh-jones, 6 min
Revisiting "Why Global Poverty" // jkaufman, 3 min
# Culture war
Rationalism in an Age of Egregores // David Udell, 2 min
Probability that the President would win election against a random adult citizen? // daniel-kokotajlo, 1 min
Storytelling: Mediocre Metamodernism // Venkatesh Rao, 13 min
# Misc
Reinventing the wheel // jasoncrawford, 2 min
Wielding civilization // dominicq, 2 min
How would you build Dath Ilan on earth? // yair-halberstadt, 1 min
On The Spectrum, On The Guest List: (iii) Etiquette // party-girl, 9 min
The Fourth Arena: What’s Up in the world these days? We’re moving to a new, a new what? // bill-benzon, 3 min
The STEM Attractor // David Udell, 2 min
Is there any formal argument that climate change needs to more extreme weather events? // ChristianKl, 1 min
Does quantum mechanics predict all the effects of relativity except gravity? // EniScien, 1 min
Finding the Right Problem // tobot, 2 min
What features should social media have (to promote good discussion)? // blackstampede, 1 min
Notion template for personal predictions // Arjun Yadav, 1 min
# Podcasts
#131 - Lewis Dartnell on getting humanity to bounce back faster in a post-apocalyptic world // , 65 min
163 – Effective Aesthetics // The Bayesian Conspiracy, 98 min
# Rational fiction
Passable Puppet // burmesetheaterwide, 3 min
# Videos of the week
Breaking down my seduction bodylanguage // Aella, 9 min