Subagents, akrasia, and coherence in humans
Rest Days vs Recovery Days
More realistic tales of doomΩ
Alignment Research Field GuideΩ
Personalized Medicine For Real
Humans Who Are Not Concentrating Are Not General Intelligences
"Other people are wrong" vs "I am right"
Thoughts on Human ModelsΩ
Building up to an Internal Family Systems model
S-Curves for Trend Forecasting
Disentangling arguments for the importance of AI safetyΩ
Less Competition, More Meritocracy?
Book Summary: Consciousness and the Brain
The 3 Books Technique for Learning a New Skilll
[Link]Reframing Superintelligence: Comprehensive AI Services as General IntelligenceΩ
[Question]What makes people intellectually active?
The Pavlov Strategy
2018 AI Alignment Literature Review and Charity ComparisonΩ
Meditations on Momentum
Norms of Membership for Voluntary Groups
Why we need a *theory* of human valuesΩ
Is Science Slowing Down?
Act of Charity
Sam Harris and the Is–Ought Gap
Embedded Agency (full-text version)Ω
Conversational Cultures: Combat vs Nurture
Prediction-Augmented Evaluation Systems
Good Samaritans in experiments
Coordination Problems in Evolution: Eigen's Paradox
Public Positions and Private Guts
Some cruxes on impactful alternatives to AI policy work
[Link]The funnel of human experience
The Rocket Alignment ProblemΩ
[Link]Realism about rationality
Unrolling social metacognition: Three levels of meta are not enough.
Historical mathematicians exhibit a birth order effect too
Subsidizing Prediction Markets
Preliminary thoughts on moral weight
Strategies of Personal Growth
Prediction Markets: When Do They Work?
Melatonin: Much More Than You Wanted To Know
[Link]Book review: Pearl's Book of Why