rational
Issue #220: Full List
10 July, 2022 // View curated list
# Instrumental
Babysitting as Parenting Trial? // jkaufman, 3 min
Aversion Factoring // CFAR 2017, 9 min
Predicting Parental Emotional Changes? // jkaufman, 1 min
Tarnished Guy who Puts a Num on it // Jacobian, 5 min
Trigger-Action Planning // CFAR 2017, 15 min
I’ve become a medical mystery and I don’t know how to effectively get help // CraigMichael, 2 min
Goal Factoring // CFAR 2017, 9 min
What New Desktop Should I Buy? // Zvi, 1 min
Consider Multiclassing // JustisMills, 3 min
Procedural Executive Function, Part 1 // DaystarEld, 16 min
Five routes of access to scientific literature // AllAmericanBreakfast, 7 min
In Search of Strategic Clarity // james.lucassen, 6 min
# Epistemic
ITT-passing and civility are good; "charity" is bad; steelmanning is niche // RobbBB, 7 min
A Pattern Language For Rationality // Vaniver, 18 min
Cognitive Dissonance on Cognitive Capability // niederman, 1 min
Nobody Knows How Well Homework Works // Scott Alexander, 3 min
# Ai
AI Forecasting: One Year In // jsteinhardt, 6 min
Principles for Alignment/Agency Projects // johnswentworth, 5 min
Human values & biases are inaccessible to the genome // TurnTrout, 6 min
My Most Likely Reason to Die Young is AI X-Risk // AISafetyIsNotLongtermist, 4 min
MATS Models // johnswentworth, 19 min
The curious case of Pretty Good human inner/outer alignment // PavleMiha, 4 min
Race Along Rashomon Ridge // LosPolloFowler, 10 min
New US Senate Bill on Catastrophic Risk Mitigation [Linkpost] // Evan R. Murphy, 1 min
Deep neural networks are not opaque. // jem-mosig, 3 min
Safety considerations for online generative modeling // samuel-marks, 17 min
Please help us communicate AI xrisk. It could save the world. // otto-barten, 2 min
Research Notes: What are we aligning for? // DarkSym, 2 min
A compressed take on recent disagreements // kman, 1 min
Four Societal Interventions to Improve our AGI Position // rafael-cosman-1, 6 min
Outer vs inner misalignment: three framings // ricraz, 11 min
We Need a Consolidated List of Bad AI Alignment Solutions // Double, 1 min
Train first VS prune first in neural networks. // donald-hobson, 2 min
Wonder and The Golden AI Rule // JeffreyK, 7 min
Anthropic's SoLU (Softmax Linear Unit) // joel-burget, 5 min
Reinforcement Learner Wireheading // Nate Showell, 4 min
Can we achieve AGI Alignment by balancing multiple human objectives? // ben-smith, 4 min
How humanity would respond to slow takeoff, with takeaways from the entire COVID-19 pandemic // sharmake-farah, 2 min
Which one of these two academic routes should I take to end up in AI Safety? // martinsq, 1 min
Making it harder for an AGI to "trick" us, with STVs // tor-okland-barstad, 28 min
Cooperation with and between AGI\'s // PeterMcCluskey, 13 min
When is it appropriate to use statistical models and probabilities for decision making ? // younes-kamel, 5 min
How STVs may make it harder for an AGI to "trick" us // tor-okland-barstad, 27 min
Grouped Loss may disfavor discontinuous capabilities // adam-jermyn, 4 min
A central AI alignment problem: capabilities generalization, and the sharp left turn // Nate Soares, 12 min
# Meta-ethics
Some thoughts on Animals // nitinkhanna, 2 min
# Longevity
Being a donor for Fecal Microbiota Transplants (FMT): Do good & earn easy money (up to 180k/y) // anton-rodenhauser, 10 min
# Anthropic
Our Level In the Great Filter // Robin Hanson, 5 min
# Decision theory
Decision theory and dynamic inconsistency // paulfchristiano, 11 min
Understanding updatelessness in the context of EDT and CDT // Sylvester Kollin, 8 min
Imperial Russia was doing fine without the Soviets // Davis Kedrosky, 17 min
Seeking opinions on the current and forward state of cryptocurrencies. // jmh, 1 min
# Math and cs
Assorted thoughts about abstraction // adamzerner, 8 min
# Books
Book Review: The Righteous Mind // ErnestScribbler, 42 min
Your Book Review: The Outlier // Scott Alexander, 24 min
# Ea
When Giving People Money Doesn’t Help // Zvi, 12 min
# Community
Carrying the Torch: A Response to Anna Salamon by the Guild of the Rose // moridinamael, 7 min
Changes in Community Dynamics: A Follow-Up to 'The Berkeley Community & the Rest of Us' // Evan_Gaensbauer, 4 min
# Culture war
Genders Discrimination // Jacobian, 5 min
# Fun
SOMA - A story about Consciousness // johannes-c-mayer, 1 min
# Misc
Toni Kurz and the Insanity of Climbing Mountains // GeneSmith, 12 min
My vision of a good future, part I // jeff-ladish, 10 min
User research as a barometer of software design // adamzerner, 3 min
Wealth as a source of technological stagnation? // alyssavance, 3 min
Nature abhors an immutable replicator... usually // MSRayne, 3 min
How to Become a World Historical Figure (Péladan's Dream) // rogersbacon, 36 min
Some Adventures of a Curious Richard Feynman // dalton-mabery, 3 min
New book on the psychology of belief // derrick-farnell, 1 min
Post hoc justifications as Compression Algorithm // johannes-c-mayer, 1 min
Using Ngram to estimate depression prevalence over time // David_Gross, 2 min
Outline: The Rectifying of Maps // hamnox, 2 min
Unbounded Intelligence Lottery // kman, 1 min
Should you write under a blog or your own name? // dalton-mabery, 1 min
Brand Truth Narrowly // Robin Hanson, 3 min
More/General Agents in NBER // Robin Hanson, 3 min
Artful Supporting Complaints // Robin Hanson, 3 min
Study: Ritalin Works, But School Isn't Worth Paying Attention To // Scott Alexander, 5 min
# Podcasts
EP 160 Curtis Yarvin on Monarchy in the U.S.A. // The Jim Rutt Show, 109 min
EP 159 Bobby Azarian on the Romance of Reality // The Jim Rutt Show, 121 min
# Rational fiction
Report from a civilizational observer on Earth // owencb, 6 min
# Videos of the week
Lex Fridman plays chess with Demis Hassabis // Lex Fridman, 9 min